diff options
Diffstat (limited to 'net')
260 files changed, 16405 insertions, 6220 deletions
diff --git a/net/802/psnap.c b/net/802/psnap.c index 34e42968b477..270b9d2cae65 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -59,10 +59,8 @@ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, proto = find_snap_client(skb->h.raw); if (proto) { /* Pass the frame on. */ - u8 *hdr = skb->data; skb->h.raw += 5; - skb_pull(skb, 5); - skb_postpull_rcsum(skb, hdr, 5); + skb_pull_rcsum(skb, 5); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } else { skb->sk = NULL; diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index fa76220708ce..3948949a609a 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -69,7 +69,7 @@ static struct packet_type vlan_packet_type = { /* Bits of netdev state that are propagated from real device to virtual */ #define VLAN_LINK_STATE_MASK \ - ((1<<__LINK_STATE_PRESENT)|(1<<__LINK_STATE_NOCARRIER)) + ((1<<__LINK_STATE_PRESENT)|(1<<__LINK_STATE_NOCARRIER)|(1<<__LINK_STATE_DORMANT)) /* End of global variables definitions. */ @@ -344,6 +344,26 @@ static void vlan_setup(struct net_device *new_dev) new_dev->do_ioctl = vlan_dev_ioctl; } +static void vlan_transfer_operstate(const struct net_device *dev, struct net_device *vlandev) +{ + /* Have to respect userspace enforced dormant state + * of real device, also must allow supplicant running + * on VLAN device + */ + if (dev->operstate == IF_OPER_DORMANT) + netif_dormant_on(vlandev); + else + netif_dormant_off(vlandev); + + if (netif_carrier_ok(dev)) { + if (!netif_carrier_ok(vlandev)) + netif_carrier_on(vlandev); + } else { + if (netif_carrier_ok(vlandev)) + netif_carrier_off(vlandev); + } +} + /* Attach a VLAN device to a mac address (ie Ethernet Card). * Returns the device that was created, or NULL if there was * an error of some kind. @@ -450,7 +470,7 @@ static struct net_device *register_vlan_device(const char *eth_IF_name, new_dev->flags = real_dev->flags; new_dev->flags &= ~IFF_UP; - new_dev->state = real_dev->state & VLAN_LINK_STATE_MASK; + new_dev->state = real_dev->state & ~(1<<__LINK_STATE_START); /* need 4 bytes for extra VLAN header info, * hope the underlying device can handle it. @@ -498,6 +518,10 @@ static struct net_device *register_vlan_device(const char *eth_IF_name, if (register_netdevice(new_dev)) goto out_free_newdev; + new_dev->iflink = real_dev->ifindex; + vlan_transfer_operstate(real_dev, new_dev); + linkwatch_fire_event(new_dev); /* _MUST_ call rfc2863_policy() */ + /* So, got the sucker initialized, now lets place * it into our local structure. */ @@ -573,25 +597,12 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, switch (event) { case NETDEV_CHANGE: /* Propagate real device state to vlan devices */ - flgs = dev->state & VLAN_LINK_STATE_MASK; for (i = 0; i < VLAN_GROUP_ARRAY_LEN; i++) { vlandev = grp->vlan_devices[i]; if (!vlandev) continue; - if (netif_carrier_ok(dev)) { - if (!netif_carrier_ok(vlandev)) - netif_carrier_on(vlandev); - } else { - if (netif_carrier_ok(vlandev)) - netif_carrier_off(vlandev); - } - - if ((vlandev->state & VLAN_LINK_STATE_MASK) != flgs) { - vlandev->state = (vlandev->state &~ VLAN_LINK_STATE_MASK) - | flgs; - netdev_state_change(vlandev); - } + vlan_transfer_operstate(dev, vlandev); } break; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 0f604d227da2..da9cfe927158 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -163,10 +163,8 @@ int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev, stats->rx_packets++; stats->rx_bytes += skb->len; - skb_pull(skb, VLAN_HLEN); /* take off the VLAN header (4 bytes currently) */ - - /* Need to correct hardware checksum */ - skb_postpull_rcsum(skb, vhdr, VLAN_HLEN); + /* Take off the VLAN header (4 bytes currently) */ + skb_pull_rcsum(skb, VLAN_HLEN); /* Ok, lets check to make sure the device (dev) we * came in on is what this VLAN is attached to. diff --git a/net/atm/clip.c b/net/atm/clip.c index 73370de97539..3ab4e7947bab 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -289,7 +289,6 @@ static void clip_neigh_error(struct neighbour *neigh,struct sk_buff *skb) static struct neigh_ops clip_neigh_ops = { .family = AF_INET, - .destructor = clip_neigh_destroy, .solicit = clip_neigh_solicit, .error_report = clip_neigh_error, .output = dev_queue_xmit, @@ -347,6 +346,7 @@ static struct neigh_table clip_tbl = { /* parameters are copied from ARP ... */ .parms = { .tbl = &clip_tbl, + .neigh_destructor = clip_neigh_destroy, .base_reachable_time = 30 * HZ, .retrans_time = 1 * HZ, .gc_staletime = 60 * HZ, diff --git a/net/atm/common.c b/net/atm/common.c index 6656b111cc05..ae002220fa99 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -451,12 +451,12 @@ int vcc_connect(struct socket *sock, int itf, short vpi, int vci) dev = try_then_request_module(atm_dev_lookup(itf), "atm-device-%d", itf); } else { dev = NULL; - down(&atm_dev_mutex); + mutex_lock(&atm_dev_mutex); if (!list_empty(&atm_devs)) { dev = list_entry(atm_devs.next, struct atm_dev, dev_list); atm_dev_hold(dev); } - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); } if (!dev) return -ENODEV; diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index eb109af7eb4a..851cfa6312af 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -18,6 +18,7 @@ #include <linux/atmmpc.h> #include <net/atmclip.h> #include <linux/atmlec.h> +#include <linux/mutex.h> #include <asm/ioctls.h> #include "resources.h" @@ -25,22 +26,22 @@ #include "common.h" -static DECLARE_MUTEX(ioctl_mutex); +static DEFINE_MUTEX(ioctl_mutex); static LIST_HEAD(ioctl_list); void register_atm_ioctl(struct atm_ioctl *ioctl) { - down(&ioctl_mutex); + mutex_lock(&ioctl_mutex); list_add_tail(&ioctl->list, &ioctl_list); - up(&ioctl_mutex); + mutex_unlock(&ioctl_mutex); } void deregister_atm_ioctl(struct atm_ioctl *ioctl) { - down(&ioctl_mutex); + mutex_lock(&ioctl_mutex); list_del(&ioctl->list); - up(&ioctl_mutex); + mutex_unlock(&ioctl_mutex); } EXPORT_SYMBOL(register_atm_ioctl); @@ -137,7 +138,7 @@ int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) error = -ENOIOCTLCMD; - down(&ioctl_mutex); + mutex_lock(&ioctl_mutex); list_for_each(pos, &ioctl_list) { struct atm_ioctl * ic = list_entry(pos, struct atm_ioctl, list); if (try_module_get(ic->owner)) { @@ -147,7 +148,7 @@ int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } } - up(&ioctl_mutex); + mutex_unlock(&ioctl_mutex); if (error != -ENOIOCTLCMD) goto done; diff --git a/net/atm/resources.c b/net/atm/resources.c index 224190537c90..18ac80698f83 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -18,6 +18,8 @@ #include <linux/bitops.h> #include <linux/capability.h> #include <linux/delay.h> +#include <linux/mutex.h> + #include <net/sock.h> /* for struct sock */ #include "common.h" @@ -26,7 +28,7 @@ LIST_HEAD(atm_devs); -DECLARE_MUTEX(atm_dev_mutex); +DEFINE_MUTEX(atm_dev_mutex); static struct atm_dev *__alloc_atm_dev(const char *type) { @@ -65,9 +67,9 @@ struct atm_dev *atm_dev_lookup(int number) { struct atm_dev *dev; - down(&atm_dev_mutex); + mutex_lock(&atm_dev_mutex); dev = __atm_dev_lookup(number); - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); return dev; } @@ -83,11 +85,11 @@ struct atm_dev *atm_dev_register(const char *type, const struct atmdev_ops *ops, type); return NULL; } - down(&atm_dev_mutex); + mutex_lock(&atm_dev_mutex); if (number != -1) { if ((inuse = __atm_dev_lookup(number))) { atm_dev_put(inuse); - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); kfree(dev); return NULL; } @@ -112,12 +114,12 @@ struct atm_dev *atm_dev_register(const char *type, const struct atmdev_ops *ops, printk(KERN_ERR "atm_dev_register: " "atm_proc_dev_register failed for dev %s\n", type); - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); kfree(dev); return NULL; } list_add_tail(&dev->dev_list, &atm_devs); - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); return dev; } @@ -133,9 +135,9 @@ void atm_dev_deregister(struct atm_dev *dev) * with same number can appear, such we need deregister proc, * release async all vccs and remove them from vccs list too */ - down(&atm_dev_mutex); + mutex_lock(&atm_dev_mutex); list_del(&dev->dev_list); - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); atm_dev_release_vccs(dev); atm_proc_dev_deregister(dev); @@ -196,16 +198,16 @@ int atm_dev_ioctl(unsigned int cmd, void __user *arg) return -EFAULT; if (get_user(len, &iobuf->length)) return -EFAULT; - down(&atm_dev_mutex); + mutex_lock(&atm_dev_mutex); list_for_each(p, &atm_devs) size += sizeof(int); if (size > len) { - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); return -E2BIG; } tmp_buf = kmalloc(size, GFP_ATOMIC); if (!tmp_buf) { - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); return -ENOMEM; } tmp_p = tmp_buf; @@ -213,7 +215,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *arg) dev = list_entry(p, struct atm_dev, dev_list); *tmp_p++ = dev->number; } - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); error = ((copy_to_user(buf, tmp_buf, size)) || put_user(size, &iobuf->length)) ? -EFAULT : 0; @@ -400,13 +402,13 @@ static __inline__ void *dev_get_idx(loff_t left) void *atm_dev_seq_start(struct seq_file *seq, loff_t *pos) { - down(&atm_dev_mutex); + mutex_lock(&atm_dev_mutex); return *pos ? dev_get_idx(*pos) : (void *) 1; } void atm_dev_seq_stop(struct seq_file *seq, void *v) { - up(&atm_dev_mutex); + mutex_unlock(&atm_dev_mutex); } void *atm_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) diff --git a/net/atm/resources.h b/net/atm/resources.h index b7fb82a93b42..ac7222fee7a8 100644 --- a/net/atm/resources.h +++ b/net/atm/resources.h @@ -8,10 +8,11 @@ #include <linux/config.h> #include <linux/atmdev.h> +#include <linux/mutex.h> extern struct list_head atm_devs; -extern struct semaphore atm_dev_mutex; +extern struct mutex atm_dev_mutex; int atm_dev_ioctl(unsigned int cmd, void __user *arg); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 5b4253c61f62..e99010ce8bb2 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -37,6 +37,8 @@ #include <linux/wait.h> #include <linux/device.h> #include <linux/net.h> +#include <linux/mutex.h> + #include <net/sock.h> #include <asm/uaccess.h> #include <asm/unaligned.h> @@ -57,9 +59,9 @@ static unsigned int l2cap_mtu = RFCOMM_MAX_L2CAP_MTU; static struct task_struct *rfcomm_thread; -static DECLARE_MUTEX(rfcomm_sem); -#define rfcomm_lock() down(&rfcomm_sem); -#define rfcomm_unlock() up(&rfcomm_sem); +static DEFINE_MUTEX(rfcomm_mutex); +#define rfcomm_lock() mutex_lock(&rfcomm_mutex) +#define rfcomm_unlock() mutex_unlock(&rfcomm_mutex) static unsigned long rfcomm_event; diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig index db23d59746cf..12265aff7099 100644 --- a/net/bridge/Kconfig +++ b/net/bridge/Kconfig @@ -4,6 +4,7 @@ config BRIDGE tristate "802.1d Ethernet Bridging" + select LLC ---help--- If you say Y here, then your Linux box will be able to act as an Ethernet bridge, which means that the different Ethernet segments it diff --git a/net/bridge/br.c b/net/bridge/br.c index 188cc1ac49eb..22d806cf40ca 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -19,13 +19,23 @@ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/init.h> +#include <linux/llc.h> +#include <net/llc.h> #include "br_private.h" int (*br_should_route_hook) (struct sk_buff **pskb) = NULL; +static struct llc_sap *br_stp_sap; + static int __init br_init(void) { + br_stp_sap = llc_sap_open(LLC_SAP_BSPAN, br_stp_rcv); + if (!br_stp_sap) { + printk(KERN_ERR "bridge: can't register sap for STP\n"); + return -EBUSY; + } + br_fdb_init(); #ifdef CONFIG_BRIDGE_NETFILTER @@ -45,6 +55,8 @@ static int __init br_init(void) static void __exit br_deinit(void) { + llc_sap_close(br_stp_sap); + #ifdef CONFIG_BRIDGE_NETFILTER br_netfilter_fini(); #endif diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 0b33a7b3a00c..0c88a2ac32c1 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -27,6 +27,7 @@ static struct net_device_stats *br_dev_get_stats(struct net_device *dev) return &br->statistics; } +/* net device transmit always called with no BH (preempt_disabled) */ int br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -39,7 +40,6 @@ int br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb->mac.raw = skb->data; skb_pull(skb, ETH_HLEN); - rcu_read_lock(); if (dest[0] & 1) br_flood_deliver(br, skb, 0); else if ((dst = __br_fdb_get(br, dest)) != NULL) @@ -47,7 +47,6 @@ int br_dev_xmit(struct sk_buff *skb, struct net_device *dev) else br_flood_deliver(br, skb, 0); - rcu_read_unlock(); return 0; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 1f08a59b51ea..3a73b8c94271 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -341,7 +341,6 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, if (hold_time(br) == 0) return; - rcu_read_lock(); fdb = fdb_find(head, addr); if (likely(fdb)) { /* attempt to update an entry for a local interface */ @@ -356,13 +355,12 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, fdb->ageing_timer = jiffies; } } else { - spin_lock_bh(&br->hash_lock); + spin_lock(&br->hash_lock); if (!fdb_find(head, addr)) fdb_create(head, source, addr, 0); /* else we lose race and someone else inserts * it first, don't bother updating */ - spin_unlock_bh(&br->hash_lock); + spin_unlock(&br->hash_lock); } - rcu_read_unlock(); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f36b35edd60c..59eef42d4a42 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -210,7 +210,8 @@ static struct net_device *new_bridge_dev(const char *name) br->bridge_id.prio[0] = 0x80; br->bridge_id.prio[1] = 0x00; - memset(br->bridge_id.addr, 0, ETH_ALEN); + + memcpy(br->group_addr, br_group_address, ETH_ALEN); br->feature_mask = dev->features; br->stp_enabled = 0; @@ -237,12 +238,11 @@ static int find_portno(struct net_bridge *br) struct net_bridge_port *p; unsigned long *inuse; - inuse = kmalloc(BITS_TO_LONGS(BR_MAX_PORTS)*sizeof(unsigned long), + inuse = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long), GFP_KERNEL); if (!inuse) return -ENOMEM; - memset(inuse, 0, BITS_TO_LONGS(BR_MAX_PORTS)*sizeof(unsigned long)); set_bit(0, inuse); /* zero is reserved */ list_for_each_entry(p, &br->port_list, list) { set_bit(p->port_no, inuse); @@ -264,11 +264,10 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, if (index < 0) return ERR_PTR(index); - p = kmalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc(sizeof(*p), GFP_KERNEL); if (p == NULL) return ERR_PTR(-ENOMEM); - memset(p, 0, sizeof(*p)); p->br = br; dev_hold(dev); p->dev = dev; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 4eef83755315..b7766562d72c 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -19,13 +19,8 @@ #include <linux/netfilter_bridge.h> #include "br_private.h" -const unsigned char bridge_ula[6] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; - -static int br_pass_frame_up_finish(struct sk_buff *skb) -{ - netif_receive_skb(skb); - return 0; -} +/* Bridge group multicast address 802.1d (pg 51). */ +const u8 br_group_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; static void br_pass_frame_up(struct net_bridge *br, struct sk_buff *skb) { @@ -38,7 +33,7 @@ static void br_pass_frame_up(struct net_bridge *br, struct sk_buff *skb) skb->dev = br->dev; NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL, - br_pass_frame_up_finish); + netif_receive_skb); } /* note: already called with rcu_read_lock (preempt_disabled) */ @@ -100,6 +95,25 @@ drop: goto out; } +/* note: already called with rcu_read_lock (preempt_disabled) */ +static int br_handle_local_finish(struct sk_buff *skb) +{ + struct net_bridge_port *p = rcu_dereference(skb->dev->br_port); + + if (p && p->state != BR_STATE_DISABLED) + br_fdb_update(p->br, p, eth_hdr(skb)->h_source); + + return 0; /* process further */ +} + +/* Does address match the link local multicast address. + * 01:80:c2:00:00:0X + */ +static inline int is_link_local(const unsigned char *dest) +{ + return memcmp(dest, br_group_address, 5) == 0 && (dest[5] & 0xf0) == 0; +} + /* * Called via br_handle_frame_hook. * Return 0 if *pskb should be processed furthur @@ -117,15 +131,10 @@ int br_handle_frame(struct net_bridge_port *p, struct sk_buff **pskb) if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) goto err; - if (p->br->stp_enabled && - !memcmp(dest, bridge_ula, 5) && - !(dest[5] & 0xF0)) { - if (!dest[5]) { - NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev, - NULL, br_stp_handle_bpdu); - return 1; - } - goto err; + if (unlikely(is_link_local(dest))) { + skb->pkt_type = PACKET_HOST; + return NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_IN, skb, skb->dev, + NULL, br_handle_local_finish) != 0; } if (p->state == BR_STATE_FORWARDING || p->state == BR_STATE_LEARNING) { diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index e060aad8624d..f29450b788be 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -61,15 +61,25 @@ static int brnf_filter_vlan_tagged = 1; #define brnf_filter_vlan_tagged 1 #endif -#define IS_VLAN_IP (skb->protocol == __constant_htons(ETH_P_8021Q) && \ - hdr->h_vlan_encapsulated_proto == __constant_htons(ETH_P_IP) && \ - brnf_filter_vlan_tagged) -#define IS_VLAN_IPV6 (skb->protocol == __constant_htons(ETH_P_8021Q) && \ - hdr->h_vlan_encapsulated_proto == __constant_htons(ETH_P_IPV6) && \ - brnf_filter_vlan_tagged) -#define IS_VLAN_ARP (skb->protocol == __constant_htons(ETH_P_8021Q) && \ - hdr->h_vlan_encapsulated_proto == __constant_htons(ETH_P_ARP) && \ - brnf_filter_vlan_tagged) +static __be16 inline vlan_proto(const struct sk_buff *skb) +{ + return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; +} + +#define IS_VLAN_IP(skb) \ + (skb->protocol == htons(ETH_P_8021Q) && \ + vlan_proto(skb) == htons(ETH_P_IP) && \ + brnf_filter_vlan_tagged) + +#define IS_VLAN_IPV6(skb) \ + (skb->protocol == htons(ETH_P_8021Q) && \ + vlan_proto(skb) == htons(ETH_P_IPV6) &&\ + brnf_filter_vlan_tagged) + +#define IS_VLAN_ARP(skb) \ + (skb->protocol == htons(ETH_P_8021Q) && \ + vlan_proto(skb) == htons(ETH_P_ARP) && \ + brnf_filter_vlan_tagged) /* We need these fake structures to make netfilter happy -- * lots of places assume that skb->dst != NULL, which isn't @@ -103,6 +113,25 @@ static inline struct net_device *bridge_parent(const struct net_device *dev) return port ? port->br->dev : NULL; } +static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) +{ + skb->nf_bridge = kzalloc(sizeof(struct nf_bridge_info), GFP_ATOMIC); + if (likely(skb->nf_bridge)) + atomic_set(&(skb->nf_bridge->use), 1); + + return skb->nf_bridge; +} + +static inline void nf_bridge_save_header(struct sk_buff *skb) +{ + int header_size = 16; + + if (skb->protocol == htons(ETH_P_8021Q)) + header_size = 18; + + memcpy(skb->nf_bridge->data, skb->data - header_size, header_size); +} + /* PF_BRIDGE/PRE_ROUTING *********************************************/ /* Undo the changes made for ip6tables PREROUTING and continue the * bridge PRE_ROUTING hook. */ @@ -120,7 +149,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) dst_hold(skb->dst); skb->dev = nf_bridge->physindev; - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + if (skb->protocol == htons(ETH_P_8021Q)) { skb_push(skb, VLAN_HLEN); skb->nh.raw -= VLAN_HLEN; } @@ -136,7 +165,7 @@ static void __br_dnat_complain(void) if (jiffies - last_complaint >= 5 * HZ) { printk(KERN_WARNING "Performing cross-bridge DNAT requires IP " - "forwarding to be enabled\n"); + "forwarding to be enabled\n"); last_complaint = jiffies; } } @@ -196,7 +225,7 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) if (!skb->dev) kfree_skb(skb); else { - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + if (skb->protocol == htons(ETH_P_8021Q)) { skb_pull(skb, VLAN_HLEN); skb->nh.raw += VLAN_HLEN; } @@ -218,12 +247,17 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb) nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; if (dnat_took_place(skb)) { - if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, - dev)) { + if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev)) { struct rtable *rt; - struct flowi fl = { .nl_u = - { .ip4_u = { .daddr = iph->daddr, .saddr = 0 , - .tos = RT_TOS(iph->tos)} }, .proto = 0}; + struct flowi fl = { + .nl_u = { + .ip4_u = { + .daddr = iph->daddr, + .saddr = 0, + .tos = RT_TOS(iph->tos) }, + }, + .proto = 0, + }; if (!ip_route_output_key(&rt, &fl)) { /* - Bridged-and-DNAT'ed traffic doesn't @@ -247,7 +281,7 @@ bridged_dnat: nf_bridge->mask |= BRNF_BRIDGED_DNAT; skb->dev = nf_bridge->physindev; if (skb->protocol == - __constant_htons(ETH_P_8021Q)) { + htons(ETH_P_8021Q)) { skb_push(skb, VLAN_HLEN); skb->nh.raw -= VLAN_HLEN; } @@ -257,8 +291,7 @@ bridged_dnat: 1); return 0; } - memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, - ETH_ALEN); + memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN); skb->pkt_type = PACKET_HOST; } } else { @@ -267,7 +300,7 @@ bridged_dnat: } skb->dev = nf_bridge->physindev; - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + if (skb->protocol == htons(ETH_P_8021Q)) { skb_push(skb, VLAN_HLEN); skb->nh.raw -= VLAN_HLEN; } @@ -297,10 +330,10 @@ static struct net_device *setup_pre_routing(struct sk_buff *skb) /* We only check the length. A bridge shouldn't do any hop-by-hop stuff anyway */ static int check_hbh_len(struct sk_buff *skb) { - unsigned char *raw = (u8*)(skb->nh.ipv6h+1); + unsigned char *raw = (u8 *) (skb->nh.ipv6h + 1); u32 pkt_len; int off = raw - skb->nh.raw; - int len = (raw[1]+1)<<3; + int len = (raw[1] + 1) << 3; if ((raw + len) - skb->data > skb_headlen(skb)) goto bad; @@ -309,7 +342,7 @@ static int check_hbh_len(struct sk_buff *skb) len -= 2; while (len > 0) { - int optlen = skb->nh.raw[off+1]+2; + int optlen = skb->nh.raw[off + 1] + 2; switch (skb->nh.raw[off]) { case IPV6_TLV_PAD0: @@ -320,16 +353,16 @@ static int check_hbh_len(struct sk_buff *skb) break; case IPV6_TLV_JUMBO: - if (skb->nh.raw[off+1] != 4 || (off&3) != 2) + if (skb->nh.raw[off + 1] != 4 || (off & 3) != 2) goto bad; - pkt_len = ntohl(*(u32*)(skb->nh.raw+off+2)); + pkt_len = ntohl(*(u32 *) (skb->nh.raw + off + 2)); if (pkt_len <= IPV6_MAXPLEN || skb->nh.ipv6h->payload_len) goto bad; if (pkt_len > skb->len - sizeof(struct ipv6hdr)) goto bad; if (pskb_trim_rcsum(skb, - pkt_len+sizeof(struct ipv6hdr))) + pkt_len + sizeof(struct ipv6hdr))) goto bad; break; default: @@ -350,12 +383,13 @@ bad: /* Replicate the checks that IPv6 does on packet reception and pass the packet * to ip6tables, which doesn't support NAT, so things are fairly simple. */ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook, - struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, int (*okfn)(struct sk_buff *)) + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct ipv6hdr *hdr; u32 pkt_len; - struct nf_bridge_info *nf_bridge; if (skb->len < sizeof(struct ipv6hdr)) goto inhdr_error; @@ -381,10 +415,10 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook, } } if (hdr->nexthdr == NEXTHDR_HOP && check_hbh_len(skb)) - goto inhdr_error; + goto inhdr_error; - nf_bridge_put(skb->nf_bridge); - if ((nf_bridge = nf_bridge_alloc(skb)) == NULL) + nf_bridge_put(skb->nf_bridge); + if (!nf_bridge_alloc(skb)) return NF_DROP; if (!setup_pre_routing(skb)) return NF_DROP; @@ -412,10 +446,8 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, struct iphdr *iph; __u32 len; struct sk_buff *skb = *pskb; - struct nf_bridge_info *nf_bridge; - struct vlan_ethhdr *hdr = vlan_eth_hdr(*pskb); - if (skb->protocol == __constant_htons(ETH_P_IPV6) || IS_VLAN_IPV6) { + if (skb->protocol == htons(ETH_P_IPV6) || IS_VLAN_IPV6(skb)) { #ifdef CONFIG_SYSCTL if (!brnf_call_ip6tables) return NF_ACCEPT; @@ -423,10 +455,8 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL) goto out; - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { - u8 *vhdr = skb->data; - skb_pull(skb, VLAN_HLEN); - skb_postpull_rcsum(skb, vhdr, VLAN_HLEN); + if (skb->protocol == htons(ETH_P_8021Q)) { + skb_pull_rcsum(skb, VLAN_HLEN); skb->nh.raw += VLAN_HLEN; } return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn); @@ -436,16 +466,14 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, return NF_ACCEPT; #endif - if (skb->protocol != __constant_htons(ETH_P_IP) && !IS_VLAN_IP) + if (skb->protocol != htons(ETH_P_IP) && !IS_VLAN_IP(skb)) return NF_ACCEPT; if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL) goto out; - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { - u8 *vhdr = skb->data; - skb_pull(skb, VLAN_HLEN); - skb_postpull_rcsum(skb, vhdr, VLAN_HLEN); + if (skb->protocol == htons(ETH_P_8021Q)) { + skb_pull_rcsum(skb, VLAN_HLEN); skb->nh.raw += VLAN_HLEN; } @@ -456,15 +484,15 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; - if (!pskb_may_pull(skb, 4*iph->ihl)) + if (!pskb_may_pull(skb, 4 * iph->ihl)) goto inhdr_error; iph = skb->nh.iph; - if (ip_fast_csum((__u8 *)iph, iph->ihl) != 0) + if (ip_fast_csum((__u8 *) iph, iph->ihl) != 0) goto inhdr_error; len = ntohs(iph->tot_len); - if (skb->len < len || len < 4*iph->ihl) + if (skb->len < len || len < 4 * iph->ihl) goto inhdr_error; if (skb->len > len) { @@ -473,8 +501,8 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, skb->ip_summed = CHECKSUM_NONE; } - nf_bridge_put(skb->nf_bridge); - if ((nf_bridge = nf_bridge_alloc(skb)) == NULL) + nf_bridge_put(skb->nf_bridge); + if (!nf_bridge_alloc(skb)) return NF_DROP; if (!setup_pre_routing(skb)) return NF_DROP; @@ -486,7 +514,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, return NF_STOLEN; inhdr_error: -// IP_INC_STATS_BH(IpInHdrErrors); +// IP_INC_STATS_BH(IpInHdrErrors); out: return NF_DROP; } @@ -500,8 +528,9 @@ out: * register an IPv4 PRE_ROUTING 'sabotage' hook that will * prevent this from happening. */ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff **pskb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct sk_buff *skb = *pskb; @@ -513,15 +542,13 @@ static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff **pskb, return NF_ACCEPT; } - /* PF_BRIDGE/FORWARD *************************************************/ static int br_nf_forward_finish(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = skb->nf_bridge; struct net_device *in; - struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); - if (skb->protocol != __constant_htons(ETH_P_ARP) && !IS_VLAN_ARP) { + if (skb->protocol != htons(ETH_P_ARP) && !IS_VLAN_ARP(skb)) { in = nf_bridge->physindev; if (nf_bridge->mask & BRNF_PKT_TYPE) { skb->pkt_type = PACKET_OTHERHOST; @@ -530,12 +557,12 @@ static int br_nf_forward_finish(struct sk_buff *skb) } else { in = *((struct net_device **)(skb->cb)); } - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + if (skb->protocol == htons(ETH_P_8021Q)) { skb_push(skb, VLAN_HLEN); skb->nh.raw -= VLAN_HLEN; } NF_HOOK_THRESH(PF_BRIDGE, NF_BR_FORWARD, skb, in, - skb->dev, br_forward_finish, 1); + skb->dev, br_forward_finish, 1); return 0; } @@ -545,12 +572,12 @@ static int br_nf_forward_finish(struct sk_buff *skb) * because of the physdev module. For ARP, indev and outdev are the * bridge ports. */ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff **pskb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct sk_buff *skb = *pskb; struct nf_bridge_info *nf_bridge; - struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); struct net_device *parent; int pf; @@ -561,12 +588,12 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff **pskb, if (!parent) return NF_DROP; - if (skb->protocol == __constant_htons(ETH_P_IP) || IS_VLAN_IP) + if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) pf = PF_INET; else pf = PF_INET6; - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + if (skb->protocol == htons(ETH_P_8021Q)) { skb_pull(*pskb, VLAN_HLEN); (*pskb)->nh.raw += VLAN_HLEN; } @@ -588,11 +615,11 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff **pskb, } static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff **pskb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct sk_buff *skb = *pskb; - struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); struct net_device **d = (struct net_device **)(skb->cb); #ifdef CONFIG_SYSCTL @@ -600,15 +627,15 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff **pskb, return NF_ACCEPT; #endif - if (skb->protocol != __constant_htons(ETH_P_ARP)) { - if (!IS_VLAN_ARP) + if (skb->protocol != htons(ETH_P_ARP)) { + if (!IS_VLAN_ARP(skb)) return NF_ACCEPT; skb_pull(*pskb, VLAN_HLEN); (*pskb)->nh.raw += VLAN_HLEN; } if (skb->nh.arph->ar_pln != 4) { - if (IS_VLAN_ARP) { + if (IS_VLAN_ARP(skb)) { skb_push(*pskb, VLAN_HLEN); (*pskb)->nh.raw -= VLAN_HLEN; } @@ -621,17 +648,16 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff **pskb, return NF_STOLEN; } - /* PF_BRIDGE/LOCAL_OUT ***********************************************/ static int br_nf_local_out_finish(struct sk_buff *skb) { - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + if (skb->protocol == htons(ETH_P_8021Q)) { skb_push(skb, VLAN_HLEN); skb->nh.raw -= VLAN_HLEN; } NF_HOOK_THRESH(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, - br_forward_finish, NF_BR_PRI_FIRST + 1); + br_forward_finish, NF_BR_PRI_FIRST + 1); return 0; } @@ -657,19 +683,19 @@ static int br_nf_local_out_finish(struct sk_buff *skb) * even routed packets that didn't arrive on a bridge interface have their * nf_bridge->physindev set. */ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct net_device *realindev, *realoutdev; struct sk_buff *skb = *pskb; struct nf_bridge_info *nf_bridge; - struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); int pf; if (!skb->nf_bridge) return NF_ACCEPT; - if (skb->protocol == __constant_htons(ETH_P_IP) || IS_VLAN_IP) + if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) pf = PF_INET; else pf = PF_INET6; @@ -695,7 +721,7 @@ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb, skb->pkt_type = PACKET_OTHERHOST; nf_bridge->mask ^= BRNF_PKT_TYPE; } - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + if (skb->protocol == htons(ETH_P_8021Q)) { skb_push(skb, VLAN_HLEN); skb->nh.raw -= VLAN_HLEN; } @@ -713,14 +739,14 @@ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb, if (nf_bridge->netoutdev) realoutdev = nf_bridge->netoutdev; #endif - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + if (skb->protocol == htons(ETH_P_8021Q)) { skb_pull(skb, VLAN_HLEN); (*pskb)->nh.raw += VLAN_HLEN; } /* IP forwarded traffic has a physindev, locally * generated traffic hasn't. */ if (realindev != NULL) { - if (!(nf_bridge->mask & BRNF_DONT_TAKE_PARENT) ) { + if (!(nf_bridge->mask & BRNF_DONT_TAKE_PARENT)) { struct net_device *parent = bridge_parent(realindev); if (parent) realindev = parent; @@ -742,12 +768,12 @@ out: /* PF_BRIDGE/POST_ROUTING ********************************************/ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct sk_buff *skb = *pskb; struct nf_bridge_info *nf_bridge = (*pskb)->nf_bridge; - struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); struct net_device *realoutdev = bridge_parent(skb->dev); int pf; @@ -756,7 +782,7 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, * keep the check just to be sure... */ if (skb->mac.raw < skb->head || skb->mac.raw + ETH_HLEN > skb->data) { printk(KERN_CRIT "br_netfilter: Argh!! br_nf_post_routing: " - "bad mac.raw pointer."); + "bad mac.raw pointer."); goto print_error; } #endif @@ -767,7 +793,7 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, if (!realoutdev) return NF_DROP; - if (skb->protocol == __constant_htons(ETH_P_IP) || IS_VLAN_IP) + if (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) pf = PF_INET; else pf = PF_INET6; @@ -786,7 +812,7 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, nf_bridge->mask |= BRNF_PKT_TYPE; } - if (skb->protocol == __constant_htons(ETH_P_8021Q)) { + if (skb->protocol == htons(ETH_P_8021Q)) { skb_pull(skb, VLAN_HLEN); skb->nh.raw += VLAN_HLEN; } @@ -798,7 +824,7 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, realoutdev = nf_bridge->netoutdev; #endif NF_HOOK(pf, NF_IP_POST_ROUTING, skb, NULL, realoutdev, - br_dev_queue_push_xmit); + br_dev_queue_push_xmit); return NF_STOLEN; @@ -810,18 +836,18 @@ print_error: printk("[%s]", realoutdev->name); } printk(" head:%p, raw:%p, data:%p\n", skb->head, skb->mac.raw, - skb->data); + skb->data); return NF_ACCEPT; #endif } - /* IP/SABOTAGE *****************************************************/ /* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING * for the second time. */ static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff **pskb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { if ((*pskb)->nf_bridge && !((*pskb)->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) { @@ -835,18 +861,18 @@ static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff **pskb, * and PF_INET(6)/POST_ROUTING until we have done the forwarding * decision in the bridge code and have determined nf_bridge->physoutdev. */ static unsigned int ip_sabotage_out(unsigned int hook, struct sk_buff **pskb, - const struct net_device *in, const struct net_device *out, - int (*okfn)(struct sk_buff *)) + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) { struct sk_buff *skb = *pskb; if ((out->hard_start_xmit == br_dev_xmit && - okfn != br_nf_forward_finish && - okfn != br_nf_local_out_finish && - okfn != br_dev_queue_push_xmit) + okfn != br_nf_forward_finish && + okfn != br_nf_local_out_finish && okfn != br_dev_queue_push_xmit) #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) || ((out->priv_flags & IFF_802_1Q_VLAN) && - VLAN_DEV_INFO(out)->real_dev->hard_start_xmit == br_dev_xmit) + VLAN_DEV_INFO(out)->real_dev->hard_start_xmit == br_dev_xmit) #endif ) { struct nf_bridge_info *nf_bridge; @@ -971,8 +997,8 @@ static struct nf_hook_ops br_nf_ops[] = { #ifdef CONFIG_SYSCTL static -int brnf_sysctl_call_tables(ctl_table *ctl, int write, struct file * filp, - void __user *buffer, size_t *lenp, loff_t *ppos) +int brnf_sysctl_call_tables(ctl_table * ctl, int write, struct file *filp, + void __user * buffer, size_t * lenp, loff_t * ppos) { int ret; @@ -1059,7 +1085,8 @@ int br_netfilter_init(void) #ifdef CONFIG_SYSCTL brnf_sysctl_header = register_sysctl_table(brnf_net_table, 0); if (brnf_sysctl_header == NULL) { - printk(KERN_WARNING "br_netfilter: can't register to sysctl.\n"); + printk(KERN_WARNING + "br_netfilter: can't register to sysctl.\n"); for (i = 0; i < ARRAY_SIZE(br_nf_ops); i++) nf_unregister_hook(&br_nf_ops[i]); return -EFAULT; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 8f10e09f251b..86ecea7ed372 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -109,6 +109,7 @@ struct net_bridge unsigned long bridge_hello_time; unsigned long bridge_forward_delay; + u8 group_addr[ETH_ALEN]; u16 root_port; unsigned char stp_enabled; unsigned char topology_change; @@ -122,7 +123,7 @@ struct net_bridge }; extern struct notifier_block br_device_notifier; -extern const unsigned char bridge_ula[6]; +extern const u8 br_group_address[ETH_ALEN]; /* called under bridge lock */ static inline int br_is_root_bridge(const struct net_bridge *br) @@ -217,7 +218,8 @@ extern void br_stp_set_path_cost(struct net_bridge_port *p, extern ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id); /* br_stp_bpdu.c */ -extern int br_stp_handle_bpdu(struct sk_buff *skb); +extern int br_stp_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev); /* br_stp_timer.c */ extern void br_stp_timer_init(struct net_bridge *br); diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 296f6a487c52..8934a54792be 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -15,158 +15,162 @@ #include <linux/kernel.h> #include <linux/netfilter_bridge.h> +#include <linux/etherdevice.h> +#include <linux/llc.h> +#include <net/llc.h> +#include <net/llc_pdu.h> #include "br_private.h" #include "br_private_stp.h" -#define JIFFIES_TO_TICKS(j) (((j) << 8) / HZ) -#define TICKS_TO_JIFFIES(j) (((j) * HZ) >> 8) +#define STP_HZ 256 -static void br_send_bpdu(struct net_bridge_port *p, unsigned char *data, int length) +#define LLC_RESERVE sizeof(struct llc_pdu_un) + +static void br_send_bpdu(struct net_bridge_port *p, + const unsigned char *data, int length) { - struct net_device *dev; struct sk_buff *skb; - int size; if (!p->br->stp_enabled) return; - size = length + 2*ETH_ALEN + 2; - if (size < 60) - size = 60; - - dev = p->dev; - - if ((skb = dev_alloc_skb(size)) == NULL) { - printk(KERN_INFO "br: memory squeeze!\n"); + skb = dev_alloc_skb(length+LLC_RESERVE); + if (!skb) return; - } - skb->dev = dev; + skb->dev = p->dev; skb->protocol = htons(ETH_P_802_2); - skb->mac.raw = skb_put(skb, size); - memcpy(skb->mac.raw, bridge_ula, ETH_ALEN); - memcpy(skb->mac.raw+ETH_ALEN, dev->dev_addr, ETH_ALEN); - skb->mac.raw[2*ETH_ALEN] = 0; - skb->mac.raw[2*ETH_ALEN+1] = length; - skb->nh.raw = skb->mac.raw + 2*ETH_ALEN + 2; - memcpy(skb->nh.raw, data, length); - memset(skb->nh.raw + length, 0xa5, size - length - 2*ETH_ALEN - 2); + + skb_reserve(skb, LLC_RESERVE); + memcpy(__skb_put(skb, length), data, length); + + llc_pdu_header_init(skb, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, + LLC_SAP_BSPAN, LLC_PDU_CMD); + llc_pdu_init_as_ui_cmd(skb); + + llc_mac_hdr_init(skb, p->dev->dev_addr, p->br->group_addr); NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, dev_queue_xmit); } -static __inline__ void br_set_ticks(unsigned char *dest, int jiff) +static inline void br_set_ticks(unsigned char *dest, int j) { - __u16 ticks; + unsigned long ticks = (STP_HZ * j)/ HZ; - ticks = JIFFIES_TO_TICKS(jiff); - dest[0] = (ticks >> 8) & 0xFF; - dest[1] = ticks & 0xFF; + *((__be16 *) dest) = htons(ticks); } -static __inline__ int br_get_ticks(unsigned char *dest) +static inline int br_get_ticks(const unsigned char *src) { - return TICKS_TO_JIFFIES((dest[0] << 8) | dest[1]); + unsigned long ticks = ntohs(*(__be16 *)src); + + return (ticks * HZ + STP_HZ - 1) / STP_HZ; } /* called under bridge lock */ void br_send_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu) { - unsigned char buf[38]; - - buf[0] = 0x42; - buf[1] = 0x42; - buf[2] = 0x03; - buf[3] = 0; - buf[4] = 0; - buf[5] = 0; - buf[6] = BPDU_TYPE_CONFIG; - buf[7] = (bpdu->topology_change ? 0x01 : 0) | + unsigned char buf[35]; + + buf[0] = 0; + buf[1] = 0; + buf[2] = 0; + buf[3] = BPDU_TYPE_CONFIG; + buf[4] = (bpdu->topology_change ? 0x01 : 0) | (bpdu->topology_change_ack ? 0x80 : 0); - buf[8] = bpdu->root.prio[0]; - buf[9] = bpdu->root.prio[1]; - buf[10] = bpdu->root.addr[0]; - buf[11] = bpdu->root.addr[1]; - buf[12] = bpdu->root.addr[2]; - buf[13] = bpdu->root.addr[3]; - buf[14] = bpdu->root.addr[4]; - buf[15] = bpdu->root.addr[5]; - buf[16] = (bpdu->root_path_cost >> 24) & 0xFF; - buf[17] = (bpdu->root_path_cost >> 16) & 0xFF; - buf[18] = (bpdu->root_path_cost >> 8) & 0xFF; - buf[19] = bpdu->root_path_cost & 0xFF; - buf[20] = bpdu->bridge_id.prio[0]; - buf[21] = bpdu->bridge_id.prio[1]; - buf[22] = bpdu->bridge_id.addr[0]; - buf[23] = bpdu->bridge_id.addr[1]; - buf[24] = bpdu->bridge_id.addr[2]; - buf[25] = bpdu->bridge_id.addr[3]; - buf[26] = bpdu->bridge_id.addr[4]; - buf[27] = bpdu->bridge_id.addr[5]; - buf[28] = (bpdu->port_id >> 8) & 0xFF; - buf[29] = bpdu->port_id & 0xFF; - - br_set_ticks(buf+30, bpdu->message_age); - br_set_ticks(buf+32, bpdu->max_age); - br_set_ticks(buf+34, bpdu->hello_time); - br_set_ticks(buf+36, bpdu->forward_delay); - - br_send_bpdu(p, buf, 38); + buf[5] = bpdu->root.prio[0]; + buf[6] = bpdu->root.prio[1]; + buf[7] = bpdu->root.addr[0]; + buf[8] = bpdu->root.addr[1]; + buf[9] = bpdu->root.addr[2]; + buf[10] = bpdu->root.addr[3]; + buf[11] = bpdu->root.addr[4]; + buf[12] = bpdu->root.addr[5]; + buf[13] = (bpdu->root_path_cost >> 24) & 0xFF; + buf[14] = (bpdu->root_path_cost >> 16) & 0xFF; + buf[15] = (bpdu->root_path_cost >> 8) & 0xFF; + buf[16] = bpdu->root_path_cost & 0xFF; + buf[17] = bpdu->bridge_id.prio[0]; + buf[18] = bpdu->bridge_id.prio[1]; + buf[19] = bpdu->bridge_id.addr[0]; + buf[20] = bpdu->bridge_id.addr[1]; + buf[21] = bpdu->bridge_id.addr[2]; + buf[22] = bpdu->bridge_id.addr[3]; + buf[23] = bpdu->bridge_id.addr[4]; + buf[24] = bpdu->bridge_id.addr[5]; + buf[25] = (bpdu->port_id >> 8) & 0xFF; + buf[26] = bpdu->port_id & 0xFF; + + br_set_ticks(buf+27, bpdu->message_age); + br_set_ticks(buf+29, bpdu->max_age); + br_set_ticks(buf+31, bpdu->hello_time); + br_set_ticks(buf+33, bpdu->forward_delay); + + br_send_bpdu(p, buf, 35); } /* called under bridge lock */ void br_send_tcn_bpdu(struct net_bridge_port *p) { - unsigned char buf[7]; - - buf[0] = 0x42; - buf[1] = 0x42; - buf[2] = 0x03; - buf[3] = 0; - buf[4] = 0; - buf[5] = 0; - buf[6] = BPDU_TYPE_TCN; + unsigned char buf[4]; + + buf[0] = 0; + buf[1] = 0; + buf[2] = 0; + buf[3] = BPDU_TYPE_TCN; br_send_bpdu(p, buf, 7); } -static const unsigned char header[6] = {0x42, 0x42, 0x03, 0x00, 0x00, 0x00}; - -/* NO locks, but rcu_read_lock (preempt_disabled) */ -int br_stp_handle_bpdu(struct sk_buff *skb) +/* + * Called from llc. + * + * NO locks, but rcu_read_lock (preempt_disabled) + */ +int br_stp_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) { - struct net_bridge_port *p = rcu_dereference(skb->dev->br_port); + const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); + const unsigned char *dest = eth_hdr(skb)->h_dest; + struct net_bridge_port *p = rcu_dereference(dev->br_port); struct net_bridge *br; - unsigned char *buf; + const unsigned char *buf; if (!p) goto err; - br = p->br; - spin_lock(&br->lock); + if (pdu->ssap != LLC_SAP_BSPAN + || pdu->dsap != LLC_SAP_BSPAN + || pdu->ctrl_1 != LLC_PDU_TYPE_U) + goto err; - if (p->state == BR_STATE_DISABLED || !(br->dev->flags & IFF_UP)) - goto out; + if (!pskb_may_pull(skb, 4)) + goto err; + + /* compare of protocol id and version */ + buf = skb->data; + if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) + goto err; - /* insert into forwarding database after filtering to avoid spoofing */ - br_fdb_update(br, p, eth_hdr(skb)->h_source); + br = p->br; + spin_lock(&br->lock); - if (!br->stp_enabled) + if (p->state == BR_STATE_DISABLED + || !br->stp_enabled + || !(br->dev->flags & IFF_UP)) goto out; - /* need at least the 802 and STP headers */ - if (!pskb_may_pull(skb, sizeof(header)+1) || - memcmp(skb->data, header, sizeof(header))) + if (compare_ether_addr(dest, br->group_addr) != 0) goto out; - buf = skb_pull(skb, sizeof(header)); + buf = skb_pull(skb, 3); if (buf[0] == BPDU_TYPE_CONFIG) { struct br_config_bpdu bpdu; if (!pskb_may_pull(skb, 32)) - goto out; + goto out; buf = skb->data; bpdu.topology_change = (buf[1] & 0x01) ? 1 : 0; diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 9bef55f56425..d0fcde82c6fc 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -39,13 +39,13 @@ static void br_hello_timer_expired(unsigned long arg) struct net_bridge *br = (struct net_bridge *)arg; pr_debug("%s: hello timer expired\n", br->dev->name); - spin_lock_bh(&br->lock); + spin_lock(&br->lock); if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); mod_timer(&br->hello_timer, jiffies + br->hello_time); } - spin_unlock_bh(&br->lock); + spin_unlock(&br->lock); } static void br_message_age_timer_expired(unsigned long arg) @@ -71,7 +71,7 @@ static void br_message_age_timer_expired(unsigned long arg) * running when we are the root bridge. So.. this was_root * check is redundant. I'm leaving it in for now, though. */ - spin_lock_bh(&br->lock); + spin_lock(&br->lock); if (p->state == BR_STATE_DISABLED) goto unlock; was_root = br_is_root_bridge(br); @@ -82,7 +82,7 @@ static void br_message_age_timer_expired(unsigned long arg) if (br_is_root_bridge(br) && !was_root) br_become_root_bridge(br); unlock: - spin_unlock_bh(&br->lock); + spin_unlock(&br->lock); } static void br_forward_delay_timer_expired(unsigned long arg) @@ -92,7 +92,7 @@ static void br_forward_delay_timer_expired(unsigned long arg) pr_debug("%s: %d(%s) forward delay timer\n", br->dev->name, p->port_no, p->dev->name); - spin_lock_bh(&br->lock); + spin_lock(&br->lock); if (p->state == BR_STATE_LISTENING) { p->state = BR_STATE_LEARNING; mod_timer(&p->forward_delay_timer, @@ -103,7 +103,7 @@ static void br_forward_delay_timer_expired(unsigned long arg) br_topology_change_detection(br); } br_log_state(p); - spin_unlock_bh(&br->lock); + spin_unlock(&br->lock); } static void br_tcn_timer_expired(unsigned long arg) @@ -111,13 +111,13 @@ static void br_tcn_timer_expired(unsigned long arg) struct net_bridge *br = (struct net_bridge *) arg; pr_debug("%s: tcn timer expired\n", br->dev->name); - spin_lock_bh(&br->lock); + spin_lock(&br->lock); if (br->dev->flags & IFF_UP) { br_transmit_tcn(br); mod_timer(&br->tcn_timer,jiffies + br->bridge_hello_time); } - spin_unlock_bh(&br->lock); + spin_unlock(&br->lock); } static void br_topology_change_timer_expired(unsigned long arg) @@ -125,10 +125,10 @@ static void br_topology_change_timer_expired(unsigned long arg) struct net_bridge *br = (struct net_bridge *) arg; pr_debug("%s: topo change timer expired\n", br->dev->name); - spin_lock_bh(&br->lock); + spin_lock(&br->lock); br->topology_change_detected = 0; br->topology_change = 0; - spin_unlock_bh(&br->lock); + spin_unlock(&br->lock); } static void br_hold_timer_expired(unsigned long arg) @@ -138,45 +138,36 @@ static void br_hold_timer_expired(unsigned long arg) pr_debug("%s: %d(%s) hold timer expired\n", p->br->dev->name, p->port_no, p->dev->name); - spin_lock_bh(&p->br->lock); + spin_lock(&p->br->lock); if (p->config_pending) br_transmit_config(p); - spin_unlock_bh(&p->br->lock); -} - -static inline void br_timer_init(struct timer_list *timer, - void (*_function)(unsigned long), - unsigned long _data) -{ - init_timer(timer); - timer->function = _function; - timer->data = _data; + spin_unlock(&p->br->lock); } void br_stp_timer_init(struct net_bridge *br) { - br_timer_init(&br->hello_timer, br_hello_timer_expired, + setup_timer(&br->hello_timer, br_hello_timer_expired, (unsigned long) br); - br_timer_init(&br->tcn_timer, br_tcn_timer_expired, + setup_timer(&br->tcn_timer, br_tcn_timer_expired, (unsigned long) br); - br_timer_init(&br->topology_change_timer, + setup_timer(&br->topology_change_timer, br_topology_change_timer_expired, (unsigned long) br); - br_timer_init(&br->gc_timer, br_fdb_cleanup, (unsigned long) br); + setup_timer(&br->gc_timer, br_fdb_cleanup, (unsigned long) br); } void br_stp_port_timer_init(struct net_bridge_port *p) { - br_timer_init(&p->message_age_timer, br_message_age_timer_expired, + setup_timer(&p->message_age_timer, br_message_age_timer_expired, (unsigned long) p); - br_timer_init(&p->forward_delay_timer, br_forward_delay_timer_expired, + setup_timer(&p->forward_delay_timer, br_forward_delay_timer_expired, (unsigned long) p); - br_timer_init(&p->hold_timer, br_hold_timer_expired, + setup_timer(&p->hold_timer, br_hold_timer_expired, (unsigned long) p); } diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 6f577f16c4c0..96bcb2ff59ab 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -242,6 +242,54 @@ static ssize_t show_gc_timer(struct class_device *cd, char *buf) } static CLASS_DEVICE_ATTR(gc_timer, S_IRUGO, show_gc_timer, NULL); +static ssize_t show_group_addr(struct class_device *cd, char *buf) +{ + struct net_bridge *br = to_bridge(cd); + return sprintf(buf, "%x:%x:%x:%x:%x:%x\n", + br->group_addr[0], br->group_addr[1], + br->group_addr[2], br->group_addr[3], + br->group_addr[4], br->group_addr[5]); +} + +static ssize_t store_group_addr(struct class_device *cd, const char *buf, + size_t len) +{ + struct net_bridge *br = to_bridge(cd); + unsigned new_addr[6]; + int i; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (sscanf(buf, "%x:%x:%x:%x:%x:%x", + &new_addr[0], &new_addr[1], &new_addr[2], + &new_addr[3], &new_addr[4], &new_addr[5]) != 6) + return -EINVAL; + + /* Must be 01:80:c2:00:00:0X */ + for (i = 0; i < 5; i++) + if (new_addr[i] != br_group_address[i]) + return -EINVAL; + + if (new_addr[5] & ~0xf) + return -EINVAL; + + if (new_addr[5] == 1 /* 802.3x Pause address */ + || new_addr[5] == 2 /* 802.3ad Slow protocols */ + || new_addr[5] == 3) /* 802.1X PAE address */ + return -EINVAL; + + spin_lock_bh(&br->lock); + for (i = 0; i < 6; i++) + br->group_addr[i] = new_addr[i]; + spin_unlock_bh(&br->lock); + return len; +} + +static CLASS_DEVICE_ATTR(group_addr, S_IRUGO | S_IWUSR, + show_group_addr, store_group_addr); + + static struct attribute *bridge_attrs[] = { &class_device_attr_forward_delay.attr, &class_device_attr_hello_time.attr, @@ -259,6 +307,7 @@ static struct attribute *bridge_attrs[] = { &class_device_attr_tcn_timer.attr, &class_device_attr_topology_change_timer.attr, &class_device_attr_gc_timer.attr, + &class_device_attr_group_addr.attr, NULL }; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index cbd4020cc84d..997953367204 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -35,6 +35,7 @@ #define ASSERT_READ_LOCK(x) #define ASSERT_WRITE_LOCK(x) #include <linux/netfilter_ipv4/listhelp.h> +#include <linux/mutex.h> #if 0 /* use this for remote debugging @@ -81,7 +82,7 @@ static void print_string(char *str) -static DECLARE_MUTEX(ebt_mutex); +static DEFINE_MUTEX(ebt_mutex); static LIST_HEAD(ebt_tables); static LIST_HEAD(ebt_targets); static LIST_HEAD(ebt_matches); @@ -296,18 +297,18 @@ letscontinue: /* If it succeeds, returns element and locks mutex */ static inline void * find_inlist_lock_noload(struct list_head *head, const char *name, int *error, - struct semaphore *mutex) + struct mutex *mutex) { void *ret; - *error = down_interruptible(mutex); + *error = mutex_lock_interruptible(mutex); if (*error != 0) return NULL; ret = list_named_find(head, name); if (!ret) { *error = -ENOENT; - up(mutex); + mutex_unlock(mutex); } return ret; } @@ -317,7 +318,7 @@ find_inlist_lock_noload(struct list_head *head, const char *name, int *error, #else static void * find_inlist_lock(struct list_head *head, const char *name, const char *prefix, - int *error, struct semaphore *mutex) + int *error, struct mutex *mutex) { void *ret; @@ -331,25 +332,25 @@ find_inlist_lock(struct list_head *head, const char *name, const char *prefix, #endif static inline struct ebt_table * -find_table_lock(const char *name, int *error, struct semaphore *mutex) +find_table_lock(const char *name, int *error, struct mutex *mutex) { return find_inlist_lock(&ebt_tables, name, "ebtable_", error, mutex); } static inline struct ebt_match * -find_match_lock(const char *name, int *error, struct semaphore *mutex) +find_match_lock(const char *name, int *error, struct mutex *mutex) { return find_inlist_lock(&ebt_matches, name, "ebt_", error, mutex); } static inline struct ebt_watcher * -find_watcher_lock(const char *name, int *error, struct semaphore *mutex) +find_watcher_lock(const char *name, int *error, struct mutex *mutex) { return find_inlist_lock(&ebt_watchers, name, "ebt_", error, mutex); } static inline struct ebt_target * -find_target_lock(const char *name, int *error, struct semaphore *mutex) +find_target_lock(const char *name, int *error, struct mutex *mutex) { return find_inlist_lock(&ebt_targets, name, "ebt_", error, mutex); } @@ -369,10 +370,10 @@ ebt_check_match(struct ebt_entry_match *m, struct ebt_entry *e, return ret; m->u.match = match; if (!try_module_get(match->me)) { - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); return -ENOENT; } - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); if (match->check && match->check(name, hookmask, e, m->data, m->match_size) != 0) { BUGPRINT("match->check failed\n"); @@ -398,10 +399,10 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct ebt_entry *e, return ret; w->u.watcher = watcher; if (!try_module_get(watcher->me)) { - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); return -ENOENT; } - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); if (watcher->check && watcher->check(name, hookmask, e, w->data, w->watcher_size) != 0) { BUGPRINT("watcher->check failed\n"); @@ -638,11 +639,11 @@ ebt_check_entry(struct ebt_entry *e, struct ebt_table_info *newinfo, if (!target) goto cleanup_watchers; if (!try_module_get(target->me)) { - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); ret = -ENOENT; goto cleanup_watchers; } - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); t->u.target = target; if (t->u.target == &ebt_standard_target) { @@ -1015,7 +1016,7 @@ static int do_replace(void __user *user, unsigned int len) t->private = newinfo; write_unlock_bh(&t->lock); - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); /* so, a user can change the chains while having messed up her counter allocation. Only reason why this is done is because this way the lock is held only once, while this doesn't bring the kernel into a @@ -1045,7 +1046,7 @@ static int do_replace(void __user *user, unsigned int len) return ret; free_unlock: - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); free_iterate: EBT_ENTRY_ITERATE(newinfo->entries, newinfo->entries_size, ebt_cleanup_entry, NULL); @@ -1068,69 +1069,69 @@ int ebt_register_target(struct ebt_target *target) { int ret; - ret = down_interruptible(&ebt_mutex); + ret = mutex_lock_interruptible(&ebt_mutex); if (ret != 0) return ret; if (!list_named_insert(&ebt_targets, target)) { - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); return -EEXIST; } - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); return 0; } void ebt_unregister_target(struct ebt_target *target) { - down(&ebt_mutex); + mutex_lock(&ebt_mutex); LIST_DELETE(&ebt_targets, target); - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); } int ebt_register_match(struct ebt_match *match) { int ret; - ret = down_interruptible(&ebt_mutex); + ret = mutex_lock_interruptible(&ebt_mutex); if (ret != 0) return ret; if (!list_named_insert(&ebt_matches, match)) { - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); return -EEXIST; } - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); return 0; } void ebt_unregister_match(struct ebt_match *match) { - down(&ebt_mutex); + mutex_lock(&ebt_mutex); LIST_DELETE(&ebt_matches, match); - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); } int ebt_register_watcher(struct ebt_watcher *watcher) { int ret; - ret = down_interruptible(&ebt_mutex); + ret = mutex_lock_interruptible(&ebt_mutex); if (ret != 0) return ret; if (!list_named_insert(&ebt_watchers, watcher)) { - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); return -EEXIST; } - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); return 0; } void ebt_unregister_watcher(struct ebt_watcher *watcher) { - down(&ebt_mutex); + mutex_lock(&ebt_mutex); LIST_DELETE(&ebt_watchers, watcher); - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); } int ebt_register_table(struct ebt_table *table) @@ -1178,7 +1179,7 @@ int ebt_register_table(struct ebt_table *table) table->private = newinfo; rwlock_init(&table->lock); - ret = down_interruptible(&ebt_mutex); + ret = mutex_lock_interruptible(&ebt_mutex); if (ret != 0) goto free_chainstack; @@ -1194,10 +1195,10 @@ int ebt_register_table(struct ebt_table *table) goto free_unlock; } list_prepend(&ebt_tables, table); - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); return 0; free_unlock: - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); free_chainstack: if (newinfo->chainstack) { for_each_cpu(i) @@ -1218,9 +1219,9 @@ void ebt_unregister_table(struct ebt_table *table) BUGPRINT("Request to unregister NULL table!!!\n"); return; } - down(&ebt_mutex); + mutex_lock(&ebt_mutex); LIST_DELETE(&ebt_tables, table); - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); vfree(table->private->entries); if (table->private->chainstack) { for_each_cpu(i) @@ -1281,7 +1282,7 @@ static int update_counters(void __user *user, unsigned int len) write_unlock_bh(&t->lock); ret = 0; unlock_mutex: - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); free_tmp: vfree(tmp); return ret; @@ -1328,7 +1329,7 @@ static inline int ebt_make_names(struct ebt_entry *e, char *base, char *ubase) return 0; } -/* called with ebt_mutex down */ +/* called with ebt_mutex locked */ static int copy_everything_to_user(struct ebt_table *t, void __user *user, int *len, int cmd) { @@ -1440,7 +1441,7 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case EBT_SO_GET_INIT_INFO: if (*len != sizeof(struct ebt_replace)){ ret = -EINVAL; - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); break; } if (cmd == EBT_SO_GET_INFO) { @@ -1452,7 +1453,7 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) tmp.entries_size = t->table->entries_size; tmp.valid_hooks = t->table->valid_hooks; } - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); if (copy_to_user(user, &tmp, *len) != 0){ BUGPRINT("c2u Didn't work\n"); ret = -EFAULT; @@ -1464,11 +1465,11 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case EBT_SO_GET_ENTRIES: case EBT_SO_GET_INIT_ENTRIES: ret = copy_everything_to_user(t, user, len, cmd); - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); break; default: - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); ret = -EINVAL; } @@ -1476,17 +1477,23 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } static struct nf_sockopt_ops ebt_sockopts = -{ { NULL, NULL }, PF_INET, EBT_BASE_CTL, EBT_SO_SET_MAX + 1, do_ebt_set_ctl, - EBT_BASE_CTL, EBT_SO_GET_MAX + 1, do_ebt_get_ctl, 0, NULL +{ + .pf = PF_INET, + .set_optmin = EBT_BASE_CTL, + .set_optmax = EBT_SO_SET_MAX + 1, + .set = do_ebt_set_ctl, + .get_optmin = EBT_BASE_CTL, + .get_optmax = EBT_SO_GET_MAX + 1, + .get = do_ebt_get_ctl, }; static int __init init(void) { int ret; - down(&ebt_mutex); + mutex_lock(&ebt_mutex); list_named_insert(&ebt_targets, &ebt_standard_target); - up(&ebt_mutex); + mutex_unlock(&ebt_mutex); if ((ret = nf_register_sockopt(&ebt_sockopts)) < 0) return ret; diff --git a/net/compat.c b/net/compat.c index e593dace2fdb..13177a1a4b39 100644 --- a/net/compat.c +++ b/net/compat.c @@ -416,7 +416,7 @@ struct compat_sock_fprog { compat_uptr_t filter; /* struct sock_filter * */ }; -static int do_set_attach_filter(int fd, int level, int optname, +static int do_set_attach_filter(struct socket *sock, int level, int optname, char __user *optval, int optlen) { struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval; @@ -432,11 +432,12 @@ static int do_set_attach_filter(int fd, int level, int optname, __put_user(compat_ptr(ptr), &kfprog->filter)) return -EFAULT; - return sys_setsockopt(fd, level, optname, (char __user *)kfprog, + return sock_setsockopt(sock, level, optname, (char __user *)kfprog, sizeof(struct sock_fprog)); } -static int do_set_sock_timeout(int fd, int level, int optname, char __user *optval, int optlen) +static int do_set_sock_timeout(struct socket *sock, int level, + int optname, char __user *optval, int optlen) { struct compat_timeval __user *up = (struct compat_timeval __user *) optval; struct timeval ktime; @@ -451,30 +452,61 @@ static int do_set_sock_timeout(int fd, int level, int optname, char __user *optv return -EFAULT; old_fs = get_fs(); set_fs(KERNEL_DS); - err = sys_setsockopt(fd, level, optname, (char *) &ktime, sizeof(ktime)); + err = sock_setsockopt(sock, level, optname, (char *) &ktime, sizeof(ktime)); set_fs(old_fs); return err; } +static int compat_sock_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, int optlen) +{ + if (optname == SO_ATTACH_FILTER) + return do_set_attach_filter(sock, level, optname, + optval, optlen); + if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) + return do_set_sock_timeout(sock, level, optname, optval, optlen); + + return sock_setsockopt(sock, level, optname, optval, optlen); +} + asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, char __user *optval, int optlen) { + int err; + struct socket *sock; + /* SO_SET_REPLACE seems to be the same in all levels */ if (optname == IPT_SO_SET_REPLACE) return do_netfilter_replace(fd, level, optname, optval, optlen); - if (level == SOL_SOCKET && optname == SO_ATTACH_FILTER) - return do_set_attach_filter(fd, level, optname, - optval, optlen); - if (level == SOL_SOCKET && - (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) - return do_set_sock_timeout(fd, level, optname, optval, optlen); - return sys_setsockopt(fd, level, optname, optval, optlen); + if (optlen < 0) + return -EINVAL; + + if ((sock = sockfd_lookup(fd, &err))!=NULL) + { + err = security_socket_setsockopt(sock,level,optname); + if (err) { + sockfd_put(sock); + return err; + } + + if (level == SOL_SOCKET) + err = compat_sock_setsockopt(sock, level, + optname, optval, optlen); + else if (sock->ops->compat_setsockopt) + err = sock->ops->compat_setsockopt(sock, level, + optname, optval, optlen); + else + err = sock->ops->setsockopt(sock, level, + optname, optval, optlen); + sockfd_put(sock); + } + return err; } -static int do_get_sock_timeout(int fd, int level, int optname, +static int do_get_sock_timeout(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct compat_timeval __user *up; @@ -490,7 +522,7 @@ static int do_get_sock_timeout(int fd, int level, int optname, len = sizeof(ktime); old_fs = get_fs(); set_fs(KERNEL_DS); - err = sys_getsockopt(fd, level, optname, (char *) &ktime, &len); + err = sock_getsockopt(sock, level, optname, (char *) &ktime, &len); set_fs(old_fs); if (!err) { @@ -503,15 +535,42 @@ static int do_get_sock_timeout(int fd, int level, int optname, return err; } -asmlinkage long compat_sys_getsockopt(int fd, int level, int optname, +static int compat_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { - if (level == SOL_SOCKET && - (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) - return do_get_sock_timeout(fd, level, optname, optval, optlen); - return sys_getsockopt(fd, level, optname, optval, optlen); + if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) + return do_get_sock_timeout(sock, level, optname, optval, optlen); + return sock_getsockopt(sock, level, optname, optval, optlen); } +asmlinkage long compat_sys_getsockopt(int fd, int level, int optname, + char __user *optval, int __user *optlen) +{ + int err; + struct socket *sock; + + if ((sock = sockfd_lookup(fd, &err))!=NULL) + { + err = security_socket_getsockopt(sock, level, + optname); + if (err) { + sockfd_put(sock); + return err; + } + + if (level == SOL_SOCKET) + err = compat_sock_getsockopt(sock, level, + optname, optval, optlen); + else if (sock->ops->compat_getsockopt) + err = sock->ops->compat_getsockopt(sock, level, + optname, optval, optlen); + else + err = sock->ops->getsockopt(sock, level, + optname, optval, optlen); + sockfd_put(sock); + } + return err; +} /* Argument list sizes for compat_sys_socketcall */ #define AL(x) ((x) * sizeof(u32)) static unsigned char nas[18]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), diff --git a/net/core/dev.c b/net/core/dev.c index ef56c035d44e..08dec6eb922b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -81,6 +81,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/mutex.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> @@ -1759,8 +1760,7 @@ static void net_rx_action(struct softirq_action *h) if (dev->quota <= 0 || dev->poll(dev, &budget)) { netpoll_poll_unlock(have); local_irq_disable(); - list_del(&dev->poll_list); - list_add_tail(&dev->poll_list, &queue->poll_list); + list_move_tail(&dev->poll_list, &queue->poll_list); if (dev->quota < 0) dev->quota += dev->weight; else @@ -2174,12 +2174,20 @@ unsigned dev_get_flags(const struct net_device *dev) flags = (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI | - IFF_RUNNING)) | + IFF_RUNNING | + IFF_LOWER_UP | + IFF_DORMANT)) | (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); - if (netif_running(dev) && netif_carrier_ok(dev)) - flags |= IFF_RUNNING; + if (netif_running(dev)) { + if (netif_oper_up(dev)) + flags |= IFF_RUNNING; + if (netif_carrier_ok(dev)) + flags |= IFF_LOWER_UP; + if (netif_dormant(dev)) + flags |= IFF_DORMANT; + } return flags; } @@ -2458,9 +2466,9 @@ int dev_ioctl(unsigned int cmd, void __user *arg) */ if (cmd == SIOCGIFCONF) { - rtnl_shlock(); + rtnl_lock(); ret = dev_ifconf((char __user *) arg); - rtnl_shunlock(); + rtnl_unlock(); return ret; } if (cmd == SIOCGIFNAME) @@ -2869,7 +2877,7 @@ static void netdev_wait_allrefs(struct net_device *dev) rebroadcast_time = warning_time = jiffies; while (atomic_read(&dev->refcnt) != 0) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { - rtnl_shlock(); + rtnl_lock(); /* Rebroadcast unregister notification */ notifier_call_chain(&netdev_chain, @@ -2886,7 +2894,7 @@ static void netdev_wait_allrefs(struct net_device *dev) linkwatch_run_queue(); } - rtnl_shunlock(); + __rtnl_unlock(); rebroadcast_time = jiffies; } @@ -2924,7 +2932,7 @@ static void netdev_wait_allrefs(struct net_device *dev) * 2) Since we run with the RTNL semaphore not held, we can sleep * safely in order to wait for the netdev refcnt to drop to zero. */ -static DECLARE_MUTEX(net_todo_run_mutex); +static DEFINE_MUTEX(net_todo_run_mutex); void netdev_run_todo(void) { struct list_head list = LIST_HEAD_INIT(list); @@ -2932,7 +2940,7 @@ void netdev_run_todo(void) /* Need to guard against multiple cpu's getting out of order. */ - down(&net_todo_run_mutex); + mutex_lock(&net_todo_run_mutex); /* Not safe to do outside the semaphore. We must not return * until all unregister events invoked by the local processor @@ -2989,7 +2997,7 @@ void netdev_run_todo(void) } out: - up(&net_todo_run_mutex); + mutex_unlock(&net_todo_run_mutex); } /** diff --git a/net/core/flow.c b/net/core/flow.c index c4f25385029f..55789f832eda 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -20,6 +20,7 @@ #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/mutex.h> #include <net/flow.h> #include <asm/atomic.h> #include <asm/semaphore.h> @@ -287,11 +288,11 @@ static void flow_cache_flush_per_cpu(void *data) void flow_cache_flush(void) { struct flow_flush_info info; - static DECLARE_MUTEX(flow_flush_sem); + static DEFINE_MUTEX(flow_flush_sem); /* Don't want cpus going down or up during this. */ lock_cpu_hotplug(); - down(&flow_flush_sem); + mutex_lock(&flow_flush_sem); atomic_set(&info.cpuleft, num_online_cpus()); init_completion(&info.completion); @@ -301,7 +302,7 @@ void flow_cache_flush(void) local_bh_enable(); wait_for_completion(&info.completion); - up(&flow_flush_sem); + mutex_unlock(&flow_flush_sem); unlock_cpu_hotplug(); } diff --git a/net/core/link_watch.c b/net/core/link_watch.c index d43d1201275c..341de44c7ed1 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -49,6 +49,45 @@ struct lw_event { /* Avoid kmalloc() for most systems */ static struct lw_event singleevent; +static unsigned char default_operstate(const struct net_device *dev) +{ + if (!netif_carrier_ok(dev)) + return (dev->ifindex != dev->iflink ? + IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN); + + if (netif_dormant(dev)) + return IF_OPER_DORMANT; + + return IF_OPER_UP; +} + + +static void rfc2863_policy(struct net_device *dev) +{ + unsigned char operstate = default_operstate(dev); + + if (operstate == dev->operstate) + return; + + write_lock_bh(&dev_base_lock); + + switch(dev->link_mode) { + case IF_LINK_MODE_DORMANT: + if (operstate == IF_OPER_UP) + operstate = IF_OPER_DORMANT; + break; + + case IF_LINK_MODE_DEFAULT: + default: + break; + }; + + dev->operstate = operstate; + + write_unlock_bh(&dev_base_lock); +} + + /* Must be called with the rtnl semaphore held */ void linkwatch_run_queue(void) { @@ -74,6 +113,7 @@ void linkwatch_run_queue(void) */ clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); + rfc2863_policy(dev); if (dev->flags & IFF_UP) { if (netif_carrier_ok(dev)) { WARN_ON(dev->qdisc_sleeping == &noop_qdisc); @@ -99,9 +139,9 @@ static void linkwatch_event(void *dummy) linkwatch_nextevent = jiffies + HZ; clear_bit(LW_RUNNING, &linkwatch_flags); - rtnl_shlock(); + rtnl_lock(); linkwatch_run_queue(); - rtnl_shunlock(); + rtnl_unlock(); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e68700f950a5..0c8666872d10 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -586,8 +586,8 @@ void neigh_destroy(struct neighbour *neigh) kfree(hh); } - if (neigh->ops && neigh->ops->destructor) - (neigh->ops->destructor)(neigh); + if (neigh->parms->neigh_destructor) + (neigh->parms->neigh_destructor)(neigh); skb_queue_purge(&neigh->arp_queue); @@ -750,11 +750,13 @@ static void neigh_timer_handler(unsigned long arg) neigh->used + neigh->parms->delay_probe_time)) { NEIGH_PRINTK2("neigh %p is delayed.\n", neigh); neigh->nud_state = NUD_DELAY; + neigh->updated = jiffies; neigh_suspect(neigh); next = now + neigh->parms->delay_probe_time; } else { NEIGH_PRINTK2("neigh %p is suspected.\n", neigh); neigh->nud_state = NUD_STALE; + neigh->updated = jiffies; neigh_suspect(neigh); } } else if (state & NUD_DELAY) { @@ -762,11 +764,13 @@ static void neigh_timer_handler(unsigned long arg) neigh->confirmed + neigh->parms->delay_probe_time)) { NEIGH_PRINTK2("neigh %p is now reachable.\n", neigh); neigh->nud_state = NUD_REACHABLE; + neigh->updated = jiffies; neigh_connect(neigh); next = neigh->confirmed + neigh->parms->reachable_time; } else { NEIGH_PRINTK2("neigh %p is probed.\n", neigh); neigh->nud_state = NUD_PROBE; + neigh->updated = jiffies; atomic_set(&neigh->probes, 0); next = now + neigh->parms->retrans_time; } @@ -780,6 +784,7 @@ static void neigh_timer_handler(unsigned long arg) struct sk_buff *skb; neigh->nud_state = NUD_FAILED; + neigh->updated = jiffies; notify = 1; NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); NEIGH_PRINTK2("neigh %p is failed.\n", neigh); @@ -843,10 +848,12 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) if (neigh->parms->mcast_probes + neigh->parms->app_probes) { atomic_set(&neigh->probes, neigh->parms->ucast_probes); neigh->nud_state = NUD_INCOMPLETE; + neigh->updated = jiffies; neigh_hold(neigh); neigh_add_timer(neigh, now + 1); } else { neigh->nud_state = NUD_FAILED; + neigh->updated = jiffies; write_unlock_bh(&neigh->lock); if (skb) @@ -857,6 +864,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) NEIGH_PRINTK2("neigh %p is delayed.\n", neigh); neigh_hold(neigh); neigh->nud_state = NUD_DELAY; + neigh->updated = jiffies; neigh_add_timer(neigh, jiffies + neigh->parms->delay_probe_time); } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e8b2acbc8ea2..21b68464cabb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -91,6 +91,7 @@ NETDEVICE_SHOW(iflink, fmt_dec); NETDEVICE_SHOW(ifindex, fmt_dec); NETDEVICE_SHOW(features, fmt_long_hex); NETDEVICE_SHOW(type, fmt_dec); +NETDEVICE_SHOW(link_mode, fmt_dec); /* use same locking rules as GIFHWADDR ioctl's */ static ssize_t format_addr(char *buf, const unsigned char *addr, int len) @@ -133,6 +134,43 @@ static ssize_t show_carrier(struct class_device *dev, char *buf) return -EINVAL; } +static ssize_t show_dormant(struct class_device *dev, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + + if (netif_running(netdev)) + return sprintf(buf, fmt_dec, !!netif_dormant(netdev)); + + return -EINVAL; +} + +static const char *operstates[] = { + "unknown", + "notpresent", /* currently unused */ + "down", + "lowerlayerdown", + "testing", /* currently unused */ + "dormant", + "up" +}; + +static ssize_t show_operstate(struct class_device *dev, char *buf) +{ + const struct net_device *netdev = to_net_dev(dev); + unsigned char operstate; + + read_lock(&dev_base_lock); + operstate = netdev->operstate; + if (!netif_running(netdev)) + operstate = IF_OPER_DOWN; + read_unlock(&dev_base_lock); + + if (operstate >= sizeof(operstates)) + return -EINVAL; /* should not happen */ + + return sprintf(buf, "%s\n", operstates[operstate]); +} + /* read-write attributes */ NETDEVICE_SHOW(mtu, fmt_dec); @@ -190,9 +228,12 @@ static struct class_device_attribute net_class_attributes[] = { __ATTR(ifindex, S_IRUGO, show_ifindex, NULL), __ATTR(features, S_IRUGO, show_features, NULL), __ATTR(type, S_IRUGO, show_type, NULL), + __ATTR(link_mode, S_IRUGO, show_link_mode, NULL), __ATTR(address, S_IRUGO, show_address, NULL), __ATTR(broadcast, S_IRUGO, show_broadcast, NULL), __ATTR(carrier, S_IRUGO, show_carrier, NULL), + __ATTR(dormant, S_IRUGO, show_dormant, NULL), + __ATTR(operstate, S_IRUGO, show_operstate, NULL), __ATTR(mtu, S_IRUGO | S_IWUSR, show_mtu, store_mtu), __ATTR(flags, S_IRUGO | S_IWUSR, show_flags, store_flags), __ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len, diff --git a/net/core/netpoll.c b/net/core/netpoll.c index ea51f8d02eb8..e8e05cebd95a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -669,14 +669,14 @@ int netpoll_setup(struct netpoll *np) printk(KERN_INFO "%s: device %s not up yet, forcing it\n", np->name, np->dev_name); - rtnl_shlock(); + rtnl_lock(); if (dev_change_flags(ndev, ndev->flags | IFF_UP) < 0) { printk(KERN_ERR "%s: failed to open %s\n", np->name, np->dev_name); - rtnl_shunlock(); + rtnl_unlock(); goto release; } - rtnl_shunlock(); + rtnl_unlock(); atleast = jiffies + HZ/10; atmost = jiffies + 4*HZ; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index da16f8fd1494..8eedaedba743 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -113,6 +113,7 @@ #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/smp_lock.h> +#include <linux/mutex.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -125,6 +126,7 @@ #include <linux/capability.h> #include <linux/delay.h> #include <linux/timer.h> +#include <linux/list.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/netdevice.h> @@ -149,38 +151,34 @@ #include <asm/io.h> #include <asm/dma.h> #include <asm/uaccess.h> -#include <asm/div64.h> /* do_div */ +#include <asm/div64.h> /* do_div */ #include <asm/timex.h> - -#define VERSION "pktgen v2.63: Packet Generator for packet performance testing.\n" +#define VERSION "pktgen v2.66: Packet Generator for packet performance testing.\n" /* #define PG_DEBUG(a) a */ -#define PG_DEBUG(a) +#define PG_DEBUG(a) /* The buckets are exponential in 'width' */ #define LAT_BUCKETS_MAX 32 #define IP_NAME_SZ 32 /* Device flag bits */ -#define F_IPSRC_RND (1<<0) /* IP-Src Random */ -#define F_IPDST_RND (1<<1) /* IP-Dst Random */ -#define F_UDPSRC_RND (1<<2) /* UDP-Src Random */ -#define F_UDPDST_RND (1<<3) /* UDP-Dst Random */ -#define F_MACSRC_RND (1<<4) /* MAC-Src Random */ -#define F_MACDST_RND (1<<5) /* MAC-Dst Random */ -#define F_TXSIZE_RND (1<<6) /* Transmit size is random */ -#define F_IPV6 (1<<7) /* Interface in IPV6 Mode */ +#define F_IPSRC_RND (1<<0) /* IP-Src Random */ +#define F_IPDST_RND (1<<1) /* IP-Dst Random */ +#define F_UDPSRC_RND (1<<2) /* UDP-Src Random */ +#define F_UDPDST_RND (1<<3) /* UDP-Dst Random */ +#define F_MACSRC_RND (1<<4) /* MAC-Src Random */ +#define F_MACDST_RND (1<<5) /* MAC-Dst Random */ +#define F_TXSIZE_RND (1<<6) /* Transmit size is random */ +#define F_IPV6 (1<<7) /* Interface in IPV6 Mode */ /* Thread control flag bits */ -#define T_TERMINATE (1<<0) -#define T_STOP (1<<1) /* Stop run */ -#define T_RUN (1<<2) /* Start run */ -#define T_REMDEV (1<<3) /* Remove all devs */ - -/* Locks */ -#define thread_lock() down(&pktgen_sem) -#define thread_unlock() up(&pktgen_sem) +#define T_TERMINATE (1<<0) +#define T_STOP (1<<1) /* Stop run */ +#define T_RUN (1<<2) /* Start run */ +#define T_REMDEVALL (1<<3) /* Remove all devs */ +#define T_REMDEV (1<<4) /* Remove one dev */ /* If lock -- can be removed after some work */ #define if_lock(t) spin_lock(&(t->if_lock)); @@ -194,10 +192,9 @@ static struct proc_dir_entry *pg_proc_dir = NULL; #define MAX_CFLOWS 65536 -struct flow_state -{ - __u32 cur_daddr; - int count; +struct flow_state { + __u32 cur_daddr; + int count; }; struct pktgen_dev { @@ -206,141 +203,144 @@ struct pktgen_dev { * Try to keep frequent/infrequent used vars. separated. */ - char ifname[IFNAMSIZ]; - char result[512]; - - struct pktgen_thread* pg_thread; /* the owner */ - struct pktgen_dev *next; /* Used for chaining in the thread's run-queue */ - - int running; /* if this changes to false, the test will stop */ - - /* If min != max, then we will either do a linear iteration, or - * we will do a random selection from within the range. - */ - __u32 flags; - - int min_pkt_size; /* = ETH_ZLEN; */ - int max_pkt_size; /* = ETH_ZLEN; */ - int nfrags; - __u32 delay_us; /* Default delay */ - __u32 delay_ns; - __u64 count; /* Default No packets to send */ - __u64 sofar; /* How many pkts we've sent so far */ - __u64 tx_bytes; /* How many bytes we've transmitted */ - __u64 errors; /* Errors when trying to transmit, pkts will be re-sent */ - - /* runtime counters relating to clone_skb */ - __u64 next_tx_us; /* timestamp of when to tx next */ - __u32 next_tx_ns; - - __u64 allocated_skbs; - __u32 clone_count; - int last_ok; /* Was last skb sent? - * Or a failed transmit of some sort? This will keep - * sequence numbers in order, for example. - */ - __u64 started_at; /* micro-seconds */ - __u64 stopped_at; /* micro-seconds */ - __u64 idle_acc; /* micro-seconds */ - __u32 seq_num; - - int clone_skb; /* Use multiple SKBs during packet gen. If this number - * is greater than 1, then that many copies of the same - * packet will be sent before a new packet is allocated. - * For instance, if you want to send 1024 identical packets - * before creating a new packet, set clone_skb to 1024. - */ - - char dst_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ - char dst_max[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ - char src_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ - char src_max[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ - - struct in6_addr in6_saddr; - struct in6_addr in6_daddr; - struct in6_addr cur_in6_daddr; - struct in6_addr cur_in6_saddr; + char ifname[IFNAMSIZ]; + char result[512]; + + struct pktgen_thread *pg_thread; /* the owner */ + struct list_head list; /* Used for chaining in the thread's run-queue */ + + int running; /* if this changes to false, the test will stop */ + + /* If min != max, then we will either do a linear iteration, or + * we will do a random selection from within the range. + */ + __u32 flags; + int removal_mark; /* non-zero => the device is marked for + * removal by worker thread */ + + int min_pkt_size; /* = ETH_ZLEN; */ + int max_pkt_size; /* = ETH_ZLEN; */ + int nfrags; + __u32 delay_us; /* Default delay */ + __u32 delay_ns; + __u64 count; /* Default No packets to send */ + __u64 sofar; /* How many pkts we've sent so far */ + __u64 tx_bytes; /* How many bytes we've transmitted */ + __u64 errors; /* Errors when trying to transmit, pkts will be re-sent */ + + /* runtime counters relating to clone_skb */ + __u64 next_tx_us; /* timestamp of when to tx next */ + __u32 next_tx_ns; + + __u64 allocated_skbs; + __u32 clone_count; + int last_ok; /* Was last skb sent? + * Or a failed transmit of some sort? This will keep + * sequence numbers in order, for example. + */ + __u64 started_at; /* micro-seconds */ + __u64 stopped_at; /* micro-seconds */ + __u64 idle_acc; /* micro-seconds */ + __u32 seq_num; + + int clone_skb; /* Use multiple SKBs during packet gen. If this number + * is greater than 1, then that many copies of the same + * packet will be sent before a new packet is allocated. + * For instance, if you want to send 1024 identical packets + * before creating a new packet, set clone_skb to 1024. + */ + + char dst_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ + char dst_max[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ + char src_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ + char src_max[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ + + struct in6_addr in6_saddr; + struct in6_addr in6_daddr; + struct in6_addr cur_in6_daddr; + struct in6_addr cur_in6_saddr; /* For ranges */ - struct in6_addr min_in6_daddr; - struct in6_addr max_in6_daddr; - struct in6_addr min_in6_saddr; - struct in6_addr max_in6_saddr; - - /* If we're doing ranges, random or incremental, then this - * defines the min/max for those ranges. - */ - __u32 saddr_min; /* inclusive, source IP address */ - __u32 saddr_max; /* exclusive, source IP address */ - __u32 daddr_min; /* inclusive, dest IP address */ - __u32 daddr_max; /* exclusive, dest IP address */ - - __u16 udp_src_min; /* inclusive, source UDP port */ - __u16 udp_src_max; /* exclusive, source UDP port */ - __u16 udp_dst_min; /* inclusive, dest UDP port */ - __u16 udp_dst_max; /* exclusive, dest UDP port */ - - __u32 src_mac_count; /* How many MACs to iterate through */ - __u32 dst_mac_count; /* How many MACs to iterate through */ - - unsigned char dst_mac[ETH_ALEN]; - unsigned char src_mac[ETH_ALEN]; - - __u32 cur_dst_mac_offset; - __u32 cur_src_mac_offset; - __u32 cur_saddr; - __u32 cur_daddr; - __u16 cur_udp_dst; - __u16 cur_udp_src; - __u32 cur_pkt_size; - - __u8 hh[14]; - /* = { - 0x00, 0x80, 0xC8, 0x79, 0xB3, 0xCB, - - We fill in SRC address later - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x08, 0x00 - }; - */ - __u16 pad; /* pad out the hh struct to an even 16 bytes */ - - struct sk_buff* skb; /* skb we are to transmit next, mainly used for when we - * are transmitting the same one multiple times - */ - struct net_device* odev; /* The out-going device. Note that the device should - * have it's pg_info pointer pointing back to this - * device. This will be set when the user specifies - * the out-going device name (not when the inject is - * started as it used to do.) - */ + struct in6_addr min_in6_daddr; + struct in6_addr max_in6_daddr; + struct in6_addr min_in6_saddr; + struct in6_addr max_in6_saddr; + + /* If we're doing ranges, random or incremental, then this + * defines the min/max for those ranges. + */ + __u32 saddr_min; /* inclusive, source IP address */ + __u32 saddr_max; /* exclusive, source IP address */ + __u32 daddr_min; /* inclusive, dest IP address */ + __u32 daddr_max; /* exclusive, dest IP address */ + + __u16 udp_src_min; /* inclusive, source UDP port */ + __u16 udp_src_max; /* exclusive, source UDP port */ + __u16 udp_dst_min; /* inclusive, dest UDP port */ + __u16 udp_dst_max; /* exclusive, dest UDP port */ + + __u32 src_mac_count; /* How many MACs to iterate through */ + __u32 dst_mac_count; /* How many MACs to iterate through */ + + unsigned char dst_mac[ETH_ALEN]; + unsigned char src_mac[ETH_ALEN]; + + __u32 cur_dst_mac_offset; + __u32 cur_src_mac_offset; + __u32 cur_saddr; + __u32 cur_daddr; + __u16 cur_udp_dst; + __u16 cur_udp_src; + __u32 cur_pkt_size; + + __u8 hh[14]; + /* = { + 0x00, 0x80, 0xC8, 0x79, 0xB3, 0xCB, + + We fill in SRC address later + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x08, 0x00 + }; + */ + __u16 pad; /* pad out the hh struct to an even 16 bytes */ + + struct sk_buff *skb; /* skb we are to transmit next, mainly used for when we + * are transmitting the same one multiple times + */ + struct net_device *odev; /* The out-going device. Note that the device should + * have it's pg_info pointer pointing back to this + * device. This will be set when the user specifies + * the out-going device name (not when the inject is + * started as it used to do.) + */ struct flow_state *flows; - unsigned cflows; /* Concurrent flows (config) */ - unsigned lflow; /* Flow length (config) */ - unsigned nflows; /* accumulated flows (stats) */ + unsigned cflows; /* Concurrent flows (config) */ + unsigned lflow; /* Flow length (config) */ + unsigned nflows; /* accumulated flows (stats) */ }; struct pktgen_hdr { - __u32 pgh_magic; - __u32 seq_num; + __u32 pgh_magic; + __u32 seq_num; __u32 tv_sec; __u32 tv_usec; }; struct pktgen_thread { - spinlock_t if_lock; - struct pktgen_dev *if_list; /* All device here */ - struct pktgen_thread* next; - char name[32]; - char result[512]; - u32 max_before_softirq; /* We'll call do_softirq to prevent starvation. */ - - /* Field for thread to receive "posted" events terminate, stop ifs etc.*/ - - u32 control; + spinlock_t if_lock; + struct list_head if_list; /* All device here */ + struct list_head th_list; + int removed; + char name[32]; + char result[512]; + u32 max_before_softirq; /* We'll call do_softirq to prevent starvation. */ + + /* Field for thread to receive "posted" events terminate, stop ifs etc. */ + + u32 control; int pid; int cpu; - wait_queue_head_t queue; + wait_queue_head_t queue; }; #define REMOVE 1 @@ -364,77 +364,76 @@ struct pktgen_thread { */ static inline s64 divremdi3(s64 x, s64 y, int type) { - u64 a = (x < 0) ? -x : x; - u64 b = (y < 0) ? -y : y; - u64 res = 0, d = 1; - - if (b > 0) { - while (b < a) { - b <<= 1; - d <<= 1; - } - } - - do { - if ( a >= b ) { - a -= b; - res += d; - } - b >>= 1; - d >>= 1; - } - while (d); - - if (PG_DIV == type) { - return (((x ^ y) & (1ll<<63)) == 0) ? res : -(s64)res; - } - else { - return ((x & (1ll<<63)) == 0) ? a : -(s64)a; - } + u64 a = (x < 0) ? -x : x; + u64 b = (y < 0) ? -y : y; + u64 res = 0, d = 1; + + if (b > 0) { + while (b < a) { + b <<= 1; + d <<= 1; + } + } + + do { + if (a >= b) { + a -= b; + res += d; + } + b >>= 1; + d >>= 1; + } + while (d); + + if (PG_DIV == type) { + return (((x ^ y) & (1ll << 63)) == 0) ? res : -(s64) res; + } else { + return ((x & (1ll << 63)) == 0) ? a : -(s64) a; + } } /* End of hacks to deal with 64-bit math on x86 */ /** Convert to milliseconds */ -static inline __u64 tv_to_ms(const struct timeval* tv) +static inline __u64 tv_to_ms(const struct timeval *tv) { - __u64 ms = tv->tv_usec / 1000; - ms += (__u64)tv->tv_sec * (__u64)1000; - return ms; + __u64 ms = tv->tv_usec / 1000; + ms += (__u64) tv->tv_sec * (__u64) 1000; + return ms; } - /** Convert to micro-seconds */ -static inline __u64 tv_to_us(const struct timeval* tv) +static inline __u64 tv_to_us(const struct timeval *tv) { - __u64 us = tv->tv_usec; - us += (__u64)tv->tv_sec * (__u64)1000000; - return us; + __u64 us = tv->tv_usec; + us += (__u64) tv->tv_sec * (__u64) 1000000; + return us; } -static inline __u64 pg_div(__u64 n, __u32 base) { - __u64 tmp = n; - do_div(tmp, base); - /* printk("pktgen: pg_div, n: %llu base: %d rv: %llu\n", - n, base, tmp); */ - return tmp; +static inline __u64 pg_div(__u64 n, __u32 base) +{ + __u64 tmp = n; + do_div(tmp, base); + /* printk("pktgen: pg_div, n: %llu base: %d rv: %llu\n", + n, base, tmp); */ + return tmp; } -static inline __u64 pg_div64(__u64 n, __u64 base) +static inline __u64 pg_div64(__u64 n, __u64 base) { - __u64 tmp = n; + __u64 tmp = n; /* * How do we know if the architecture we are running on * supports division with 64 bit base? * */ -#if defined(__sparc_v9__) || defined(__powerpc64__) || defined(__alpha__) || defined(__x86_64__) || defined(__ia64__) +#if defined(__sparc_v9__) || defined(__powerpc64__) || defined(__alpha__) || defined(__x86_64__) || defined(__ia64__) - do_div(tmp, base); + do_div(tmp, base); #else - tmp = divremdi3(n, base, PG_DIV); + tmp = divremdi3(n, base, PG_DIV); #endif - return tmp; + return tmp; } static inline u32 pktgen_random(void) @@ -448,51 +447,51 @@ static inline u32 pktgen_random(void) #endif } -static inline __u64 getCurMs(void) +static inline __u64 getCurMs(void) { - struct timeval tv; - do_gettimeofday(&tv); - return tv_to_ms(&tv); + struct timeval tv; + do_gettimeofday(&tv); + return tv_to_ms(&tv); } -static inline __u64 getCurUs(void) +static inline __u64 getCurUs(void) { - struct timeval tv; - do_gettimeofday(&tv); - return tv_to_us(&tv); + struct timeval tv; + do_gettimeofday(&tv); + return tv_to_us(&tv); } -static inline __u64 tv_diff(const struct timeval* a, const struct timeval* b) +static inline __u64 tv_diff(const struct timeval *a, const struct timeval *b) { - return tv_to_us(a) - tv_to_us(b); + return tv_to_us(a) - tv_to_us(b); } - /* old include end */ static char version[] __initdata = VERSION; -static int pktgen_remove_device(struct pktgen_thread* t, struct pktgen_dev *i); -static int pktgen_add_device(struct pktgen_thread* t, const char* ifname); -static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread* t, const char* ifname); +static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i); +static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); +static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, + const char *ifname); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); static void pktgen_run_all_threads(void); static void pktgen_stop_all_threads_ifs(void); static int pktgen_stop_device(struct pktgen_dev *pkt_dev); -static void pktgen_stop(struct pktgen_thread* t); +static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); -static struct pktgen_dev *pktgen_NN_threads(const char* dev_name, int remove); -static unsigned int scan_ip6(const char *s,char ip[16]); -static unsigned int fmt_ip6(char *s,const char ip[16]); +static int pktgen_mark_device(const char *ifname); +static unsigned int scan_ip6(const char *s, char ip[16]); +static unsigned int fmt_ip6(char *s, const char ip[16]); /* Module parameters, defaults. */ -static int pg_count_d = 1000; /* 1000 pkts by default */ +static int pg_count_d = 1000; /* 1000 pkts by default */ static int pg_delay_d; static int pg_clone_skb_d; static int debug; -static DECLARE_MUTEX(pktgen_sem); -static struct pktgen_thread *pktgen_threads = NULL; +static DEFINE_MUTEX(pktgen_thread_lock); +static LIST_HEAD(pktgen_threads); static struct notifier_block pktgen_notifier_block = { .notifier_call = pktgen_device_event, @@ -504,21 +503,21 @@ static struct notifier_block pktgen_notifier_block = { */ static int pgctrl_show(struct seq_file *seq, void *v) -{ +{ seq_puts(seq, VERSION); return 0; } -static ssize_t pgctrl_write(struct file* file,const char __user * buf, - size_t count, loff_t *ppos) +static ssize_t pgctrl_write(struct file *file, const char __user * buf, + size_t count, loff_t * ppos) { int err = 0; char data[128]; - if (!capable(CAP_NET_ADMIN)){ - err = -EPERM; + if (!capable(CAP_NET_ADMIN)) { + err = -EPERM; goto out; - } + } if (count > sizeof(data)) count = sizeof(data); @@ -526,22 +525,22 @@ static ssize_t pgctrl_write(struct file* file,const char __user * buf, if (copy_from_user(data, buf, count)) { err = -EFAULT; goto out; - } - data[count-1] = 0; /* Make string */ + } + data[count - 1] = 0; /* Make string */ - if (!strcmp(data, "stop")) + if (!strcmp(data, "stop")) pktgen_stop_all_threads_ifs(); - else if (!strcmp(data, "start")) + else if (!strcmp(data, "start")) pktgen_run_all_threads(); - else + else printk("pktgen: Unknown command: %s\n", data); err = count; - out: - return err; +out: + return err; } static int pgctrl_open(struct inode *inode, struct file *file) @@ -550,147 +549,158 @@ static int pgctrl_open(struct inode *inode, struct file *file) } static struct file_operations pktgen_fops = { - .owner = THIS_MODULE, - .open = pgctrl_open, - .read = seq_read, - .llseek = seq_lseek, - .write = pgctrl_write, - .release = single_release, + .owner = THIS_MODULE, + .open = pgctrl_open, + .read = seq_read, + .llseek = seq_lseek, + .write = pgctrl_write, + .release = single_release, }; static int pktgen_if_show(struct seq_file *seq, void *v) { int i; - struct pktgen_dev *pkt_dev = seq->private; - __u64 sa; - __u64 stopped; - __u64 now = getCurUs(); - - seq_printf(seq, "Params: count %llu min_pkt_size: %u max_pkt_size: %u\n", - (unsigned long long) pkt_dev->count, - pkt_dev->min_pkt_size, pkt_dev->max_pkt_size); + struct pktgen_dev *pkt_dev = seq->private; + __u64 sa; + __u64 stopped; + __u64 now = getCurUs(); + + seq_printf(seq, + "Params: count %llu min_pkt_size: %u max_pkt_size: %u\n", + (unsigned long long)pkt_dev->count, pkt_dev->min_pkt_size, + pkt_dev->max_pkt_size); + + seq_printf(seq, + " frags: %d delay: %u clone_skb: %d ifname: %s\n", + pkt_dev->nfrags, + 1000 * pkt_dev->delay_us + pkt_dev->delay_ns, + pkt_dev->clone_skb, pkt_dev->ifname); + + seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, + pkt_dev->lflow); + + if (pkt_dev->flags & F_IPV6) { + char b1[128], b2[128], b3[128]; + fmt_ip6(b1, pkt_dev->in6_saddr.s6_addr); + fmt_ip6(b2, pkt_dev->min_in6_saddr.s6_addr); + fmt_ip6(b3, pkt_dev->max_in6_saddr.s6_addr); + seq_printf(seq, + " saddr: %s min_saddr: %s max_saddr: %s\n", b1, + b2, b3); + + fmt_ip6(b1, pkt_dev->in6_daddr.s6_addr); + fmt_ip6(b2, pkt_dev->min_in6_daddr.s6_addr); + fmt_ip6(b3, pkt_dev->max_in6_daddr.s6_addr); + seq_printf(seq, + " daddr: %s min_daddr: %s max_daddr: %s\n", b1, + b2, b3); + + } else + seq_printf(seq, + " dst_min: %s dst_max: %s\n src_min: %s src_max: %s\n", + pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min, + pkt_dev->src_max); - seq_printf(seq, " frags: %d delay: %u clone_skb: %d ifname: %s\n", - pkt_dev->nfrags, 1000*pkt_dev->delay_us+pkt_dev->delay_ns, pkt_dev->clone_skb, pkt_dev->ifname); + seq_puts(seq, " src_mac: "); - seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); + if (is_zero_ether_addr(pkt_dev->src_mac)) + for (i = 0; i < 6; i++) + seq_printf(seq, "%02X%s", pkt_dev->odev->dev_addr[i], + i == 5 ? " " : ":"); + else + for (i = 0; i < 6; i++) + seq_printf(seq, "%02X%s", pkt_dev->src_mac[i], + i == 5 ? " " : ":"); + + seq_printf(seq, "dst_mac: "); + for (i = 0; i < 6; i++) + seq_printf(seq, "%02X%s", pkt_dev->dst_mac[i], + i == 5 ? "\n" : ":"); + + seq_printf(seq, + " udp_src_min: %d udp_src_max: %d udp_dst_min: %d udp_dst_max: %d\n", + pkt_dev->udp_src_min, pkt_dev->udp_src_max, + pkt_dev->udp_dst_min, pkt_dev->udp_dst_max); + + seq_printf(seq, + " src_mac_count: %d dst_mac_count: %d \n Flags: ", + pkt_dev->src_mac_count, pkt_dev->dst_mac_count); + if (pkt_dev->flags & F_IPV6) + seq_printf(seq, "IPV6 "); - if(pkt_dev->flags & F_IPV6) { - char b1[128], b2[128], b3[128]; - fmt_ip6(b1, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_saddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_saddr.s6_addr); - seq_printf(seq, " saddr: %s min_saddr: %s max_saddr: %s\n", b1, b2, b3); + if (pkt_dev->flags & F_IPSRC_RND) + seq_printf(seq, "IPSRC_RND "); - fmt_ip6(b1, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_daddr.s6_addr); - seq_printf(seq, " daddr: %s min_daddr: %s max_daddr: %s\n", b1, b2, b3); + if (pkt_dev->flags & F_IPDST_RND) + seq_printf(seq, "IPDST_RND "); - } - else - seq_printf(seq," dst_min: %s dst_max: %s\n src_min: %s src_max: %s\n", - pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min, pkt_dev->src_max); + if (pkt_dev->flags & F_TXSIZE_RND) + seq_printf(seq, "TXSIZE_RND "); - seq_puts(seq, " src_mac: "); + if (pkt_dev->flags & F_UDPSRC_RND) + seq_printf(seq, "UDPSRC_RND "); - if (is_zero_ether_addr(pkt_dev->src_mac)) - for (i = 0; i < 6; i++) - seq_printf(seq, "%02X%s", pkt_dev->odev->dev_addr[i], i == 5 ? " " : ":"); - else - for (i = 0; i < 6; i++) - seq_printf(seq, "%02X%s", pkt_dev->src_mac[i], i == 5 ? " " : ":"); + if (pkt_dev->flags & F_UDPDST_RND) + seq_printf(seq, "UDPDST_RND "); - seq_printf(seq, "dst_mac: "); - for (i = 0; i < 6; i++) - seq_printf(seq, "%02X%s", pkt_dev->dst_mac[i], i == 5 ? "\n" : ":"); + if (pkt_dev->flags & F_MACSRC_RND) + seq_printf(seq, "MACSRC_RND "); - seq_printf(seq, " udp_src_min: %d udp_src_max: %d udp_dst_min: %d udp_dst_max: %d\n", - pkt_dev->udp_src_min, pkt_dev->udp_src_max, pkt_dev->udp_dst_min, - pkt_dev->udp_dst_max); + if (pkt_dev->flags & F_MACDST_RND) + seq_printf(seq, "MACDST_RND "); - seq_printf(seq, " src_mac_count: %d dst_mac_count: %d \n Flags: ", - pkt_dev->src_mac_count, pkt_dev->dst_mac_count); + seq_puts(seq, "\n"); + + sa = pkt_dev->started_at; + stopped = pkt_dev->stopped_at; + if (pkt_dev->running) + stopped = now; /* not really stopped, more like last-running-at */ + seq_printf(seq, + "Current:\n pkts-sofar: %llu errors: %llu\n started: %lluus stopped: %lluus idle: %lluus\n", + (unsigned long long)pkt_dev->sofar, + (unsigned long long)pkt_dev->errors, (unsigned long long)sa, + (unsigned long long)stopped, + (unsigned long long)pkt_dev->idle_acc); - if (pkt_dev->flags & F_IPV6) - seq_printf(seq, "IPV6 "); - - if (pkt_dev->flags & F_IPSRC_RND) - seq_printf(seq, "IPSRC_RND "); - - if (pkt_dev->flags & F_IPDST_RND) - seq_printf(seq, "IPDST_RND "); - - if (pkt_dev->flags & F_TXSIZE_RND) - seq_printf(seq, "TXSIZE_RND "); - - if (pkt_dev->flags & F_UDPSRC_RND) - seq_printf(seq, "UDPSRC_RND "); - - if (pkt_dev->flags & F_UDPDST_RND) - seq_printf(seq, "UDPDST_RND "); - - if (pkt_dev->flags & F_MACSRC_RND) - seq_printf(seq, "MACSRC_RND "); - - if (pkt_dev->flags & F_MACDST_RND) - seq_printf(seq, "MACDST_RND "); - - - seq_puts(seq, "\n"); - - sa = pkt_dev->started_at; - stopped = pkt_dev->stopped_at; - if (pkt_dev->running) - stopped = now; /* not really stopped, more like last-running-at */ - - seq_printf(seq, "Current:\n pkts-sofar: %llu errors: %llu\n started: %lluus stopped: %lluus idle: %lluus\n", - (unsigned long long) pkt_dev->sofar, - (unsigned long long) pkt_dev->errors, - (unsigned long long) sa, - (unsigned long long) stopped, - (unsigned long long) pkt_dev->idle_acc); - - seq_printf(seq, " seq_num: %d cur_dst_mac_offset: %d cur_src_mac_offset: %d\n", + seq_printf(seq, + " seq_num: %d cur_dst_mac_offset: %d cur_src_mac_offset: %d\n", pkt_dev->seq_num, pkt_dev->cur_dst_mac_offset, pkt_dev->cur_src_mac_offset); - if(pkt_dev->flags & F_IPV6) { + if (pkt_dev->flags & F_IPV6) { char b1[128], b2[128]; - fmt_ip6(b1, pkt_dev->cur_in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->cur_in6_saddr.s6_addr); - seq_printf(seq, " cur_saddr: %s cur_daddr: %s\n", b2, b1); - } - else - seq_printf(seq, " cur_saddr: 0x%x cur_daddr: 0x%x\n", + fmt_ip6(b1, pkt_dev->cur_in6_daddr.s6_addr); + fmt_ip6(b2, pkt_dev->cur_in6_saddr.s6_addr); + seq_printf(seq, " cur_saddr: %s cur_daddr: %s\n", b2, b1); + } else + seq_printf(seq, " cur_saddr: 0x%x cur_daddr: 0x%x\n", pkt_dev->cur_saddr, pkt_dev->cur_daddr); - - seq_printf(seq, " cur_udp_dst: %d cur_udp_src: %d\n", + seq_printf(seq, " cur_udp_dst: %d cur_udp_src: %d\n", pkt_dev->cur_udp_dst, pkt_dev->cur_udp_src); - seq_printf(seq, " flows: %u\n", pkt_dev->nflows); + seq_printf(seq, " flows: %u\n", pkt_dev->nflows); if (pkt_dev->result[0]) - seq_printf(seq, "Result: %s\n", pkt_dev->result); + seq_printf(seq, "Result: %s\n", pkt_dev->result); else - seq_printf(seq, "Result: Idle\n"); + seq_printf(seq, "Result: Idle\n"); return 0; } - -static int count_trail_chars(const char __user *user_buffer, unsigned int maxlen) +static int count_trail_chars(const char __user * user_buffer, + unsigned int maxlen) { int i; for (i = 0; i < maxlen; i++) { - char c; - if (get_user(c, &user_buffer[i])) - return -EFAULT; - switch (c) { + char c; + if (get_user(c, &user_buffer[i])) + return -EFAULT; + switch (c) { case '\"': case '\n': case '\r': @@ -706,34 +716,34 @@ done: return i; } -static unsigned long num_arg(const char __user *user_buffer, unsigned long maxlen, - unsigned long *num) +static unsigned long num_arg(const char __user * user_buffer, + unsigned long maxlen, unsigned long *num) { int i = 0; *num = 0; - - for(; i < maxlen; i++) { - char c; - if (get_user(c, &user_buffer[i])) - return -EFAULT; - if ((c >= '0') && (c <= '9')) { + + for (; i < maxlen; i++) { + char c; + if (get_user(c, &user_buffer[i])) + return -EFAULT; + if ((c >= '0') && (c <= '9')) { *num *= 10; - *num += c -'0'; + *num += c - '0'; } else break; } return i; } -static int strn_len(const char __user *user_buffer, unsigned int maxlen) +static int strn_len(const char __user * user_buffer, unsigned int maxlen) { int i = 0; - for(; i < maxlen; i++) { - char c; - if (get_user(c, &user_buffer[i])) - return -EFAULT; - switch (c) { + for (; i < maxlen; i++) { + char c; + if (get_user(c, &user_buffer[i])) + return -EFAULT; + switch (c) { case '\"': case '\n': case '\r': @@ -746,119 +756,133 @@ static int strn_len(const char __user *user_buffer, unsigned int maxlen) }; } done_str: - return i; } -static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer, - size_t count, loff_t *offset) +static ssize_t pktgen_if_write(struct file *file, + const char __user * user_buffer, size_t count, + loff_t * offset) { - struct seq_file *seq = (struct seq_file *) file->private_data; - struct pktgen_dev *pkt_dev = seq->private; + struct seq_file *seq = (struct seq_file *)file->private_data; + struct pktgen_dev *pkt_dev = seq->private; int i = 0, max, len; char name[16], valstr[32]; unsigned long value = 0; - char* pg_result = NULL; - int tmp = 0; + char *pg_result = NULL; + int tmp = 0; char buf[128]; - - pg_result = &(pkt_dev->result[0]); - + + pg_result = &(pkt_dev->result[0]); + if (count < 1) { printk("pktgen: wrong command format\n"); return -EINVAL; } - + max = count - i; tmp = count_trail_chars(&user_buffer[i], max); - if (tmp < 0) { + if (tmp < 0) { printk("pktgen: illegal format\n"); - return tmp; + return tmp; } - i += tmp; - + i += tmp; + /* Read variable name */ len = strn_len(&user_buffer[i], sizeof(name) - 1); - if (len < 0) { return len; } + if (len < 0) { + return len; + } memset(name, 0, sizeof(name)); - if (copy_from_user(name, &user_buffer[i], len) ) + if (copy_from_user(name, &user_buffer[i], len)) return -EFAULT; i += len; - - max = count -i; + + max = count - i; len = count_trail_chars(&user_buffer[i], max); - if (len < 0) - return len; - + if (len < 0) + return len; + i += len; if (debug) { - char tb[count + 1]; - if (copy_from_user(tb, user_buffer, count)) + char tb[count + 1]; + if (copy_from_user(tb, user_buffer, count)) return -EFAULT; - tb[count] = 0; + tb[count] = 0; printk("pktgen: %s,%lu buffer -:%s:-\n", name, - (unsigned long) count, tb); - } + (unsigned long)count, tb); + } if (!strcmp(name, "min_pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; - if (value < 14+20+8) - value = 14+20+8; - if (value != pkt_dev->min_pkt_size) { - pkt_dev->min_pkt_size = value; - pkt_dev->cur_pkt_size = value; - } - sprintf(pg_result, "OK: min_pkt_size=%u", pkt_dev->min_pkt_size); + if (value < 14 + 20 + 8) + value = 14 + 20 + 8; + if (value != pkt_dev->min_pkt_size) { + pkt_dev->min_pkt_size = value; + pkt_dev->cur_pkt_size = value; + } + sprintf(pg_result, "OK: min_pkt_size=%u", + pkt_dev->min_pkt_size); return count; } - if (!strcmp(name, "max_pkt_size")) { + if (!strcmp(name, "max_pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; - if (value < 14+20+8) - value = 14+20+8; - if (value != pkt_dev->max_pkt_size) { - pkt_dev->max_pkt_size = value; - pkt_dev->cur_pkt_size = value; - } - sprintf(pg_result, "OK: max_pkt_size=%u", pkt_dev->max_pkt_size); + if (value < 14 + 20 + 8) + value = 14 + 20 + 8; + if (value != pkt_dev->max_pkt_size) { + pkt_dev->max_pkt_size = value; + pkt_dev->cur_pkt_size = value; + } + sprintf(pg_result, "OK: max_pkt_size=%u", + pkt_dev->max_pkt_size); return count; } - /* Shortcut for min = max */ + /* Shortcut for min = max */ if (!strcmp(name, "pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; - if (value < 14+20+8) - value = 14+20+8; - if (value != pkt_dev->min_pkt_size) { - pkt_dev->min_pkt_size = value; - pkt_dev->max_pkt_size = value; - pkt_dev->cur_pkt_size = value; - } + if (value < 14 + 20 + 8) + value = 14 + 20 + 8; + if (value != pkt_dev->min_pkt_size) { + pkt_dev->min_pkt_size = value; + pkt_dev->max_pkt_size = value; + pkt_dev->cur_pkt_size = value; + } sprintf(pg_result, "OK: pkt_size=%u", pkt_dev->min_pkt_size); return count; } - if (!strcmp(name, "debug")) { + if (!strcmp(name, "debug")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; - debug = value; + debug = value; sprintf(pg_result, "OK: debug=%u", debug); return count; } - if (!strcmp(name, "frags")) { + if (!strcmp(name, "frags")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; pkt_dev->nfrags = value; sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags); @@ -866,7 +890,9 @@ static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer } if (!strcmp(name, "delay")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; if (value == 0x7FFFFFFF) { pkt_dev->delay_us = 0x7FFFFFFF; @@ -875,308 +901,347 @@ static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer pkt_dev->delay_us = value / 1000; pkt_dev->delay_ns = value % 1000; } - sprintf(pg_result, "OK: delay=%u", 1000*pkt_dev->delay_us+pkt_dev->delay_ns); + sprintf(pg_result, "OK: delay=%u", + 1000 * pkt_dev->delay_us + pkt_dev->delay_ns); return count; } - if (!strcmp(name, "udp_src_min")) { + if (!strcmp(name, "udp_src_min")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; - if (value != pkt_dev->udp_src_min) { - pkt_dev->udp_src_min = value; - pkt_dev->cur_udp_src = value; - } + if (value != pkt_dev->udp_src_min) { + pkt_dev->udp_src_min = value; + pkt_dev->cur_udp_src = value; + } sprintf(pg_result, "OK: udp_src_min=%u", pkt_dev->udp_src_min); return count; } - if (!strcmp(name, "udp_dst_min")) { + if (!strcmp(name, "udp_dst_min")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; - if (value != pkt_dev->udp_dst_min) { - pkt_dev->udp_dst_min = value; - pkt_dev->cur_udp_dst = value; - } + if (value != pkt_dev->udp_dst_min) { + pkt_dev->udp_dst_min = value; + pkt_dev->cur_udp_dst = value; + } sprintf(pg_result, "OK: udp_dst_min=%u", pkt_dev->udp_dst_min); return count; } - if (!strcmp(name, "udp_src_max")) { + if (!strcmp(name, "udp_src_max")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; - if (value != pkt_dev->udp_src_max) { - pkt_dev->udp_src_max = value; - pkt_dev->cur_udp_src = value; - } + if (value != pkt_dev->udp_src_max) { + pkt_dev->udp_src_max = value; + pkt_dev->cur_udp_src = value; + } sprintf(pg_result, "OK: udp_src_max=%u", pkt_dev->udp_src_max); return count; } - if (!strcmp(name, "udp_dst_max")) { + if (!strcmp(name, "udp_dst_max")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; - if (value != pkt_dev->udp_dst_max) { - pkt_dev->udp_dst_max = value; - pkt_dev->cur_udp_dst = value; - } + if (value != pkt_dev->udp_dst_max) { + pkt_dev->udp_dst_max = value; + pkt_dev->cur_udp_dst = value; + } sprintf(pg_result, "OK: udp_dst_max=%u", pkt_dev->udp_dst_max); return count; } if (!strcmp(name, "clone_skb")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; - pkt_dev->clone_skb = value; - + pkt_dev->clone_skb = value; + sprintf(pg_result, "OK: clone_skb=%d", pkt_dev->clone_skb); return count; } if (!strcmp(name, "count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; pkt_dev->count = value; sprintf(pg_result, "OK: count=%llu", - (unsigned long long) pkt_dev->count); + (unsigned long long)pkt_dev->count); return count; } if (!strcmp(name, "src_mac_count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; if (pkt_dev->src_mac_count != value) { - pkt_dev->src_mac_count = value; - pkt_dev->cur_src_mac_offset = 0; - } - sprintf(pg_result, "OK: src_mac_count=%d", pkt_dev->src_mac_count); + pkt_dev->src_mac_count = value; + pkt_dev->cur_src_mac_offset = 0; + } + sprintf(pg_result, "OK: src_mac_count=%d", + pkt_dev->src_mac_count); return count; } if (!strcmp(name, "dst_mac_count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; if (pkt_dev->dst_mac_count != value) { - pkt_dev->dst_mac_count = value; - pkt_dev->cur_dst_mac_offset = 0; - } - sprintf(pg_result, "OK: dst_mac_count=%d", pkt_dev->dst_mac_count); + pkt_dev->dst_mac_count = value; + pkt_dev->cur_dst_mac_offset = 0; + } + sprintf(pg_result, "OK: dst_mac_count=%d", + pkt_dev->dst_mac_count); return count; } if (!strcmp(name, "flag")) { - char f[32]; - memset(f, 0, 32); + char f[32]; + memset(f, 0, 32); len = strn_len(&user_buffer[i], sizeof(f) - 1); - if (len < 0) { return len; } + if (len < 0) { + return len; + } if (copy_from_user(f, &user_buffer[i], len)) return -EFAULT; i += len; - if (strcmp(f, "IPSRC_RND") == 0) - pkt_dev->flags |= F_IPSRC_RND; - - else if (strcmp(f, "!IPSRC_RND") == 0) - pkt_dev->flags &= ~F_IPSRC_RND; - - else if (strcmp(f, "TXSIZE_RND") == 0) - pkt_dev->flags |= F_TXSIZE_RND; - - else if (strcmp(f, "!TXSIZE_RND") == 0) - pkt_dev->flags &= ~F_TXSIZE_RND; - - else if (strcmp(f, "IPDST_RND") == 0) - pkt_dev->flags |= F_IPDST_RND; - - else if (strcmp(f, "!IPDST_RND") == 0) - pkt_dev->flags &= ~F_IPDST_RND; - - else if (strcmp(f, "UDPSRC_RND") == 0) - pkt_dev->flags |= F_UDPSRC_RND; - - else if (strcmp(f, "!UDPSRC_RND") == 0) - pkt_dev->flags &= ~F_UDPSRC_RND; - - else if (strcmp(f, "UDPDST_RND") == 0) - pkt_dev->flags |= F_UDPDST_RND; - - else if (strcmp(f, "!UDPDST_RND") == 0) - pkt_dev->flags &= ~F_UDPDST_RND; - - else if (strcmp(f, "MACSRC_RND") == 0) - pkt_dev->flags |= F_MACSRC_RND; - - else if (strcmp(f, "!MACSRC_RND") == 0) - pkt_dev->flags &= ~F_MACSRC_RND; - - else if (strcmp(f, "MACDST_RND") == 0) - pkt_dev->flags |= F_MACDST_RND; - - else if (strcmp(f, "!MACDST_RND") == 0) - pkt_dev->flags &= ~F_MACDST_RND; - - else { - sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", - f, - "IPSRC_RND, IPDST_RND, TXSIZE_RND, UDPSRC_RND, UDPDST_RND, MACSRC_RND, MACDST_RND\n"); - return count; - } + if (strcmp(f, "IPSRC_RND") == 0) + pkt_dev->flags |= F_IPSRC_RND; + + else if (strcmp(f, "!IPSRC_RND") == 0) + pkt_dev->flags &= ~F_IPSRC_RND; + + else if (strcmp(f, "TXSIZE_RND") == 0) + pkt_dev->flags |= F_TXSIZE_RND; + + else if (strcmp(f, "!TXSIZE_RND") == 0) + pkt_dev->flags &= ~F_TXSIZE_RND; + + else if (strcmp(f, "IPDST_RND") == 0) + pkt_dev->flags |= F_IPDST_RND; + + else if (strcmp(f, "!IPDST_RND") == 0) + pkt_dev->flags &= ~F_IPDST_RND; + + else if (strcmp(f, "UDPSRC_RND") == 0) + pkt_dev->flags |= F_UDPSRC_RND; + + else if (strcmp(f, "!UDPSRC_RND") == 0) + pkt_dev->flags &= ~F_UDPSRC_RND; + + else if (strcmp(f, "UDPDST_RND") == 0) + pkt_dev->flags |= F_UDPDST_RND; + + else if (strcmp(f, "!UDPDST_RND") == 0) + pkt_dev->flags &= ~F_UDPDST_RND; + + else if (strcmp(f, "MACSRC_RND") == 0) + pkt_dev->flags |= F_MACSRC_RND; + + else if (strcmp(f, "!MACSRC_RND") == 0) + pkt_dev->flags &= ~F_MACSRC_RND; + + else if (strcmp(f, "MACDST_RND") == 0) + pkt_dev->flags |= F_MACDST_RND; + + else if (strcmp(f, "!MACDST_RND") == 0) + pkt_dev->flags &= ~F_MACDST_RND; + + else { + sprintf(pg_result, + "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", + f, + "IPSRC_RND, IPDST_RND, TXSIZE_RND, UDPSRC_RND, UDPDST_RND, MACSRC_RND, MACDST_RND\n"); + return count; + } sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags); return count; } if (!strcmp(name, "dst_min") || !strcmp(name, "dst")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_min) - 1); - if (len < 0) { return len; } + if (len < 0) { + return len; + } - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; - if (strcmp(buf, pkt_dev->dst_min) != 0) { - memset(pkt_dev->dst_min, 0, sizeof(pkt_dev->dst_min)); - strncpy(pkt_dev->dst_min, buf, len); - pkt_dev->daddr_min = in_aton(pkt_dev->dst_min); - pkt_dev->cur_daddr = pkt_dev->daddr_min; - } - if(debug) - printk("pktgen: dst_min set to: %s\n", pkt_dev->dst_min); - i += len; + buf[len] = 0; + if (strcmp(buf, pkt_dev->dst_min) != 0) { + memset(pkt_dev->dst_min, 0, sizeof(pkt_dev->dst_min)); + strncpy(pkt_dev->dst_min, buf, len); + pkt_dev->daddr_min = in_aton(pkt_dev->dst_min); + pkt_dev->cur_daddr = pkt_dev->daddr_min; + } + if (debug) + printk("pktgen: dst_min set to: %s\n", + pkt_dev->dst_min); + i += len; sprintf(pg_result, "OK: dst_min=%s", pkt_dev->dst_min); return count; } if (!strcmp(name, "dst_max")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_max) - 1); - if (len < 0) { return len; } + if (len < 0) { + return len; + } - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; - if (strcmp(buf, pkt_dev->dst_max) != 0) { - memset(pkt_dev->dst_max, 0, sizeof(pkt_dev->dst_max)); - strncpy(pkt_dev->dst_max, buf, len); - pkt_dev->daddr_max = in_aton(pkt_dev->dst_max); - pkt_dev->cur_daddr = pkt_dev->daddr_max; - } - if(debug) - printk("pktgen: dst_max set to: %s\n", pkt_dev->dst_max); + buf[len] = 0; + if (strcmp(buf, pkt_dev->dst_max) != 0) { + memset(pkt_dev->dst_max, 0, sizeof(pkt_dev->dst_max)); + strncpy(pkt_dev->dst_max, buf, len); + pkt_dev->daddr_max = in_aton(pkt_dev->dst_max); + pkt_dev->cur_daddr = pkt_dev->daddr_max; + } + if (debug) + printk("pktgen: dst_max set to: %s\n", + pkt_dev->dst_max); i += len; sprintf(pg_result, "OK: dst_max=%s", pkt_dev->dst_max); return count; } if (!strcmp(name, "dst6")) { len = strn_len(&user_buffer[i], sizeof(buf) - 1); - if (len < 0) return len; + if (len < 0) + return len; pkt_dev->flags |= F_IPV6; - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; + buf[len] = 0; scan_ip6(buf, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_daddr.s6_addr); + fmt_ip6(buf, pkt_dev->in6_daddr.s6_addr); ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->in6_daddr); - if(debug) + if (debug) printk("pktgen: dst6 set to: %s\n", buf); - i += len; + i += len; sprintf(pg_result, "OK: dst6=%s", buf); return count; } if (!strcmp(name, "dst6_min")) { len = strn_len(&user_buffer[i], sizeof(buf) - 1); - if (len < 0) return len; + if (len < 0) + return len; pkt_dev->flags |= F_IPV6; - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; + buf[len] = 0; scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); + fmt_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->min_in6_daddr); - if(debug) + ipv6_addr_copy(&pkt_dev->cur_in6_daddr, + &pkt_dev->min_in6_daddr); + if (debug) printk("pktgen: dst6_min set to: %s\n", buf); - i += len; + i += len; sprintf(pg_result, "OK: dst6_min=%s", buf); return count; } if (!strcmp(name, "dst6_max")) { len = strn_len(&user_buffer[i], sizeof(buf) - 1); - if (len < 0) return len; + if (len < 0) + return len; pkt_dev->flags |= F_IPV6; - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; + buf[len] = 0; scan_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); + fmt_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); - if(debug) + if (debug) printk("pktgen: dst6_max set to: %s\n", buf); - i += len; + i += len; sprintf(pg_result, "OK: dst6_max=%s", buf); return count; } if (!strcmp(name, "src6")) { len = strn_len(&user_buffer[i], sizeof(buf) - 1); - if (len < 0) return len; + if (len < 0) + return len; pkt_dev->flags |= F_IPV6; - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; + buf[len] = 0; scan_ip6(buf, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_saddr.s6_addr); + fmt_ip6(buf, pkt_dev->in6_saddr.s6_addr); ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &pkt_dev->in6_saddr); - if(debug) + if (debug) printk("pktgen: src6 set to: %s\n", buf); - - i += len; + + i += len; sprintf(pg_result, "OK: src6=%s", buf); return count; } if (!strcmp(name, "src_min")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_min) - 1); - if (len < 0) { return len; } - if (copy_from_user(buf, &user_buffer[i], len)) + if (len < 0) { + return len; + } + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; - if (strcmp(buf, pkt_dev->src_min) != 0) { - memset(pkt_dev->src_min, 0, sizeof(pkt_dev->src_min)); - strncpy(pkt_dev->src_min, buf, len); - pkt_dev->saddr_min = in_aton(pkt_dev->src_min); - pkt_dev->cur_saddr = pkt_dev->saddr_min; - } - if(debug) - printk("pktgen: src_min set to: %s\n", pkt_dev->src_min); + buf[len] = 0; + if (strcmp(buf, pkt_dev->src_min) != 0) { + memset(pkt_dev->src_min, 0, sizeof(pkt_dev->src_min)); + strncpy(pkt_dev->src_min, buf, len); + pkt_dev->saddr_min = in_aton(pkt_dev->src_min); + pkt_dev->cur_saddr = pkt_dev->saddr_min; + } + if (debug) + printk("pktgen: src_min set to: %s\n", + pkt_dev->src_min); i += len; sprintf(pg_result, "OK: src_min=%s", pkt_dev->src_min); return count; } if (!strcmp(name, "src_max")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_max) - 1); - if (len < 0) { return len; } - if (copy_from_user(buf, &user_buffer[i], len)) + if (len < 0) { + return len; + } + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; - if (strcmp(buf, pkt_dev->src_max) != 0) { - memset(pkt_dev->src_max, 0, sizeof(pkt_dev->src_max)); - strncpy(pkt_dev->src_max, buf, len); - pkt_dev->saddr_max = in_aton(pkt_dev->src_max); - pkt_dev->cur_saddr = pkt_dev->saddr_max; - } - if(debug) - printk("pktgen: src_max set to: %s\n", pkt_dev->src_max); + buf[len] = 0; + if (strcmp(buf, pkt_dev->src_max) != 0) { + memset(pkt_dev->src_max, 0, sizeof(pkt_dev->src_max)); + strncpy(pkt_dev->src_max, buf, len); + pkt_dev->saddr_max = in_aton(pkt_dev->src_max); + pkt_dev->cur_saddr = pkt_dev->saddr_max; + } + if (debug) + printk("pktgen: src_max set to: %s\n", + pkt_dev->src_max); i += len; sprintf(pg_result, "OK: src_max=%s", pkt_dev->src_max); return count; @@ -1186,15 +1251,17 @@ static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer unsigned char old_dmac[ETH_ALEN]; unsigned char *m = pkt_dev->dst_mac; memcpy(old_dmac, pkt_dev->dst_mac, ETH_ALEN); - + len = strn_len(&user_buffer[i], sizeof(valstr) - 1); - if (len < 0) { return len; } + if (len < 0) { + return len; + } memset(valstr, 0, sizeof(valstr)); - if( copy_from_user(valstr, &user_buffer[i], len)) + if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; i += len; - for(*m = 0;*v && m < pkt_dev->dst_mac + 6; v++) { + for (*m = 0; *v && m < pkt_dev->dst_mac + 6; v++) { if (*v >= '0' && *v <= '9') { *m *= 16; *m += *v - '0'; @@ -1216,7 +1283,7 @@ static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer /* Set up Dest MAC */ if (compare_ether_addr(old_dmac, pkt_dev->dst_mac)) memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); - + sprintf(pg_result, "OK: dstmac"); return count; } @@ -1225,13 +1292,15 @@ static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer unsigned char *m = pkt_dev->src_mac; len = strn_len(&user_buffer[i], sizeof(valstr) - 1); - if (len < 0) { return len; } + if (len < 0) { + return len; + } memset(valstr, 0, sizeof(valstr)); - if( copy_from_user(valstr, &user_buffer[i], len)) + if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; i += len; - for(*m = 0;*v && m < pkt_dev->src_mac + 6; v++) { + for (*m = 0; *v && m < pkt_dev->src_mac + 6; v++) { if (*v >= '0' && *v <= '9') { *m *= 16; *m += *v - '0'; @@ -1248,21 +1317,23 @@ static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer m++; *m = 0; } - } + } - sprintf(pg_result, "OK: srcmac"); + sprintf(pg_result, "OK: srcmac"); return count; } - if (!strcmp(name, "clear_counters")) { - pktgen_clear_counters(pkt_dev); - sprintf(pg_result, "OK: Clearing counters.\n"); - return count; - } + if (!strcmp(name, "clear_counters")) { + pktgen_clear_counters(pkt_dev); + sprintf(pg_result, "OK: Clearing counters.\n"); + return count; + } if (!strcmp(name, "flows")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; if (value > MAX_CFLOWS) value = MAX_CFLOWS; @@ -1274,13 +1345,15 @@ static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer if (!strcmp(name, "flowlen")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) { + return len; + } i += len; pkt_dev->lflow = value; sprintf(pg_result, "OK: flowlen=%u", pkt_dev->lflow); return count; } - + sprintf(pkt_dev->result, "No such parameter \"%s\"", name); return -EINVAL; } @@ -1291,35 +1364,35 @@ static int pktgen_if_open(struct inode *inode, struct file *file) } static struct file_operations pktgen_if_fops = { - .owner = THIS_MODULE, - .open = pktgen_if_open, - .read = seq_read, - .llseek = seq_lseek, - .write = pktgen_if_write, - .release = single_release, + .owner = THIS_MODULE, + .open = pktgen_if_open, + .read = seq_read, + .llseek = seq_lseek, + .write = pktgen_if_write, + .release = single_release, }; static int pktgen_thread_show(struct seq_file *seq, void *v) { - struct pktgen_thread *t = seq->private; - struct pktgen_dev *pkt_dev = NULL; + struct pktgen_thread *t = seq->private; + struct pktgen_dev *pkt_dev; BUG_ON(!t); seq_printf(seq, "Name: %s max_before_softirq: %d\n", - t->name, t->max_before_softirq); + t->name, t->max_before_softirq); + + seq_printf(seq, "Running: "); - seq_printf(seq, "Running: "); - - if_lock(t); - for(pkt_dev = t->if_list;pkt_dev; pkt_dev = pkt_dev->next) - if(pkt_dev->running) + if_lock(t); + list_for_each_entry(pkt_dev, &t->if_list, list) + if (pkt_dev->running) seq_printf(seq, "%s ", pkt_dev->ifname); - - seq_printf(seq, "\nStopped: "); - for(pkt_dev = t->if_list;pkt_dev; pkt_dev = pkt_dev->next) - if(!pkt_dev->running) + seq_printf(seq, "\nStopped: "); + + list_for_each_entry(pkt_dev, &t->if_list, list) + if (!pkt_dev->running) seq_printf(seq, "%s ", pkt_dev->ifname); if (t->result[0]) @@ -1327,30 +1400,30 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) else seq_printf(seq, "\nResult: NA\n"); - if_unlock(t); + if_unlock(t); return 0; } static ssize_t pktgen_thread_write(struct file *file, - const char __user *user_buffer, - size_t count, loff_t *offset) + const char __user * user_buffer, + size_t count, loff_t * offset) { - struct seq_file *seq = (struct seq_file *) file->private_data; - struct pktgen_thread *t = seq->private; + struct seq_file *seq = (struct seq_file *)file->private_data; + struct pktgen_thread *t = seq->private; int i = 0, max, len, ret; char name[40]; - char *pg_result; - unsigned long value = 0; + char *pg_result; + unsigned long value = 0; if (count < 1) { - // sprintf(pg_result, "Wrong command format"); + // sprintf(pg_result, "Wrong command format"); return -EINVAL; } max = count - i; - len = count_trail_chars(&user_buffer[i], max); - if (len < 0) + len = count_trail_chars(&user_buffer[i], max); + if (len < 0) return len; i += len; @@ -1358,26 +1431,25 @@ static ssize_t pktgen_thread_write(struct file *file, /* Read variable name */ len = strn_len(&user_buffer[i], sizeof(name) - 1); - if (len < 0) + if (len < 0) return len; - + memset(name, 0, sizeof(name)); if (copy_from_user(name, &user_buffer[i], len)) return -EFAULT; i += len; - max = count -i; + max = count - i; len = count_trail_chars(&user_buffer[i], max); - if (len < 0) + if (len < 0) return len; i += len; if (debug) - printk("pktgen: t=%s, count=%lu\n", name, - (unsigned long) count); + printk("pktgen: t=%s, count=%lu\n", name, (unsigned long)count); - if(!t) { + if (!t) { printk("pktgen: ERROR: No thread\n"); ret = -EINVAL; goto out; @@ -1385,48 +1457,47 @@ static ssize_t pktgen_thread_write(struct file *file, pg_result = &(t->result[0]); - if (!strcmp(name, "add_device")) { - char f[32]; - memset(f, 0, 32); + if (!strcmp(name, "add_device")) { + char f[32]; + memset(f, 0, 32); len = strn_len(&user_buffer[i], sizeof(f) - 1); - if (len < 0) { - ret = len; + if (len < 0) { + ret = len; goto out; } - if( copy_from_user(f, &user_buffer[i], len) ) + if (copy_from_user(f, &user_buffer[i], len)) return -EFAULT; i += len; - thread_lock(); - pktgen_add_device(t, f); - thread_unlock(); - ret = count; - sprintf(pg_result, "OK: add_device=%s", f); + mutex_lock(&pktgen_thread_lock); + pktgen_add_device(t, f); + mutex_unlock(&pktgen_thread_lock); + ret = count; + sprintf(pg_result, "OK: add_device=%s", f); goto out; } - if (!strcmp(name, "rem_device_all")) { - thread_lock(); - t->control |= T_REMDEV; - thread_unlock(); - schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ + if (!strcmp(name, "rem_device_all")) { + mutex_lock(&pktgen_thread_lock); + t->control |= T_REMDEVALL; + mutex_unlock(&pktgen_thread_lock); + schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ ret = count; - sprintf(pg_result, "OK: rem_device_all"); + sprintf(pg_result, "OK: rem_device_all"); goto out; } - if (!strcmp(name, "max_before_softirq")) { - len = num_arg(&user_buffer[i], 10, &value); - thread_lock(); - t->max_before_softirq = value; - thread_unlock(); - ret = count; - sprintf(pg_result, "OK: max_before_softirq=%lu", value); + if (!strcmp(name, "max_before_softirq")) { + len = num_arg(&user_buffer[i], 10, &value); + mutex_lock(&pktgen_thread_lock); + t->max_before_softirq = value; + mutex_unlock(&pktgen_thread_lock); + ret = count; + sprintf(pg_result, "OK: max_before_softirq=%lu", value); goto out; } ret = -EINVAL; - out: - +out: return ret; } @@ -1436,47 +1507,78 @@ static int pktgen_thread_open(struct inode *inode, struct file *file) } static struct file_operations pktgen_thread_fops = { - .owner = THIS_MODULE, - .open = pktgen_thread_open, - .read = seq_read, - .llseek = seq_lseek, - .write = pktgen_thread_write, - .release = single_release, + .owner = THIS_MODULE, + .open = pktgen_thread_open, + .read = seq_read, + .llseek = seq_lseek, + .write = pktgen_thread_write, + .release = single_release, }; /* Think find or remove for NN */ -static struct pktgen_dev *__pktgen_NN_threads(const char* ifname, int remove) +static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; - t = pktgen_threads; - - while (t) { + list_for_each_entry(t, &pktgen_threads, th_list) { pkt_dev = pktgen_find_dev(t, ifname); if (pkt_dev) { - if(remove) { - if_lock(t); - pktgen_remove_device(t, pkt_dev); - if_unlock(t); - } + if (remove) { + if_lock(t); + pkt_dev->removal_mark = 1; + t->control |= T_REMDEV; + if_unlock(t); + } break; } - t = t->next; } - return pkt_dev; + return pkt_dev; } -static struct pktgen_dev *pktgen_NN_threads(const char* ifname, int remove) +/* + * mark a device for removal + */ +static int pktgen_mark_device(const char *ifname) { struct pktgen_dev *pkt_dev = NULL; - thread_lock(); - pkt_dev = __pktgen_NN_threads(ifname, remove); - thread_unlock(); - return pkt_dev; + const int max_tries = 10, msec_per_try = 125; + int i = 0; + int ret = 0; + + mutex_lock(&pktgen_thread_lock); + PG_DEBUG(printk("pktgen: pktgen_mark_device marking %s for removal\n", + ifname)); + + while (1) { + + pkt_dev = __pktgen_NN_threads(ifname, REMOVE); + if (pkt_dev == NULL) + break; /* success */ + + mutex_unlock(&pktgen_thread_lock); + PG_DEBUG(printk("pktgen: pktgen_mark_device waiting for %s " + "to disappear....\n", ifname)); + schedule_timeout_interruptible(msecs_to_jiffies(msec_per_try)); + mutex_lock(&pktgen_thread_lock); + + if (++i >= max_tries) { + printk("pktgen_mark_device: timed out after waiting " + "%d msec for device %s to be removed\n", + msec_per_try * i, ifname); + ret = 1; + break; + } + + } + + mutex_unlock(&pktgen_thread_lock); + + return ret; } -static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) +static int pktgen_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) { struct net_device *dev = (struct net_device *)(ptr); @@ -1491,9 +1593,9 @@ static int pktgen_device_event(struct notifier_block *unused, unsigned long even case NETDEV_UP: /* Ignore for now */ break; - + case NETDEV_UNREGISTER: - pktgen_NN_threads(dev->name, REMOVE); + pktgen_mark_device(dev->name); break; }; @@ -1502,15 +1604,16 @@ static int pktgen_device_event(struct notifier_block *unused, unsigned long even /* Associate pktgen_dev with a device. */ -static struct net_device* pktgen_setup_dev(struct pktgen_dev *pkt_dev) { +static struct net_device *pktgen_setup_dev(struct pktgen_dev *pkt_dev) +{ struct net_device *odev; /* Clean old setups */ if (pkt_dev->odev) { dev_put(pkt_dev->odev); - pkt_dev->odev = NULL; - } + pkt_dev->odev = NULL; + } odev = dev_get_by_name(pkt_dev->ifname); @@ -1519,7 +1622,8 @@ static struct net_device* pktgen_setup_dev(struct pktgen_dev *pkt_dev) { goto out; } if (odev->type != ARPHRD_ETHER) { - printk("pktgen: not an ethernet device: \"%s\"\n", pkt_dev->ifname); + printk("pktgen: not an ethernet device: \"%s\"\n", + pkt_dev->ifname); goto out_put; } if (!netif_running(odev)) { @@ -1527,13 +1631,13 @@ static struct net_device* pktgen_setup_dev(struct pktgen_dev *pkt_dev) { goto out_put; } pkt_dev->odev = odev; - - return pkt_dev->odev; + + return pkt_dev->odev; out_put: dev_put(odev); out: - return NULL; + return NULL; } @@ -1543,59 +1647,64 @@ out: static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) { /* Try once more, just in case it works now. */ - if (!pkt_dev->odev) - pktgen_setup_dev(pkt_dev); - - if (!pkt_dev->odev) { - printk("pktgen: ERROR: pkt_dev->odev == NULL in setup_inject.\n"); - sprintf(pkt_dev->result, "ERROR: pkt_dev->odev == NULL in setup_inject.\n"); - return; - } - - /* Default to the interface's mac if not explicitly set. */ + if (!pkt_dev->odev) + pktgen_setup_dev(pkt_dev); + + if (!pkt_dev->odev) { + printk("pktgen: ERROR: pkt_dev->odev == NULL in setup_inject.\n"); + sprintf(pkt_dev->result, + "ERROR: pkt_dev->odev == NULL in setup_inject.\n"); + return; + } + + /* Default to the interface's mac if not explicitly set. */ if (is_zero_ether_addr(pkt_dev->src_mac)) - memcpy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr, ETH_ALEN); + memcpy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr, ETH_ALEN); - /* Set up Dest MAC */ + /* Set up Dest MAC */ memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); - /* Set up pkt size */ - pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size; - - if(pkt_dev->flags & F_IPV6) { + /* Set up pkt size */ + pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size; + + if (pkt_dev->flags & F_IPV6) { /* * Skip this automatic address setting until locks or functions * gets exported */ #ifdef NOTNOW - int i, set = 0, err=1; + int i, set = 0, err = 1; struct inet6_dev *idev; - for(i=0; i< IN6_ADDR_HSIZE; i++) - if(pkt_dev->cur_in6_saddr.s6_addr[i]) { + for (i = 0; i < IN6_ADDR_HSIZE; i++) + if (pkt_dev->cur_in6_saddr.s6_addr[i]) { set = 1; break; } - if(!set) { - + if (!set) { + /* * Use linklevel address if unconfigured. * * use ipv6_get_lladdr if/when it's get exported */ - read_lock(&addrconf_lock); if ((idev = __in6_dev_get(pkt_dev->odev)) != NULL) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { - if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) { - ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &ifp->addr); + for (ifp = idev->addr_list; ifp; + ifp = ifp->if_next) { + if (ifp->scope == IFA_LINK + && !(ifp-> + flags & IFA_F_TENTATIVE)) { + ipv6_addr_copy(&pkt_dev-> + cur_in6_saddr, + &ifp->addr); err = 0; break; } @@ -1603,28 +1712,28 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) read_unlock_bh(&idev->lock); } read_unlock(&addrconf_lock); - if(err) printk("pktgen: ERROR: IPv6 link address not availble.\n"); + if (err) + printk("pktgen: ERROR: IPv6 link address not availble.\n"); } #endif - } - else { + } else { pkt_dev->saddr_min = 0; pkt_dev->saddr_max = 0; if (strlen(pkt_dev->src_min) == 0) { - - struct in_device *in_dev; + + struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(pkt_dev->odev); if (in_dev) { if (in_dev->ifa_list) { - pkt_dev->saddr_min = in_dev->ifa_list->ifa_address; + pkt_dev->saddr_min = + in_dev->ifa_list->ifa_address; pkt_dev->saddr_max = pkt_dev->saddr_min; } } rcu_read_unlock(); - } - else { + } else { pkt_dev->saddr_min = in_aton(pkt_dev->src_min); pkt_dev->saddr_max = in_aton(pkt_dev->src_max); } @@ -1632,13 +1741,13 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) pkt_dev->daddr_min = in_aton(pkt_dev->dst_min); pkt_dev->daddr_max = in_aton(pkt_dev->dst_max); } - /* Initialize current values. */ - pkt_dev->cur_dst_mac_offset = 0; - pkt_dev->cur_src_mac_offset = 0; - pkt_dev->cur_saddr = pkt_dev->saddr_min; - pkt_dev->cur_daddr = pkt_dev->daddr_min; - pkt_dev->cur_udp_dst = pkt_dev->udp_dst_min; - pkt_dev->cur_udp_src = pkt_dev->udp_src_min; + /* Initialize current values. */ + pkt_dev->cur_dst_mac_offset = 0; + pkt_dev->cur_src_mac_offset = 0; + pkt_dev->cur_saddr = pkt_dev->saddr_min; + pkt_dev->cur_daddr = pkt_dev->daddr_min; + pkt_dev->cur_udp_dst = pkt_dev->udp_dst_min; + pkt_dev->cur_udp_src = pkt_dev->udp_src_min; pkt_dev->nflows = 0; } @@ -1651,7 +1760,7 @@ static void spin(struct pktgen_dev *pkt_dev, __u64 spin_until_us) printk(KERN_INFO "sleeping for %d\n", (int)(spin_until_us - now)); while (now < spin_until_us) { /* TODO: optimize sleeping behavior */ - if (spin_until_us - now > jiffies_to_usecs(1)+1) + if (spin_until_us - now > jiffies_to_usecs(1) + 1) schedule_timeout_interruptible(1); else if (spin_until_us - now > 100) { do_softirq(); @@ -1667,102 +1776,110 @@ static void spin(struct pktgen_dev *pkt_dev, __u64 spin_until_us) pkt_dev->idle_acc += now - start; } - /* Increment/randomize headers according to flags and current values * for IP src/dest, UDP src/dst port, MAC-Addr src/dst */ -static void mod_cur_headers(struct pktgen_dev *pkt_dev) { - __u32 imn; - __u32 imx; - int flow = 0; +static void mod_cur_headers(struct pktgen_dev *pkt_dev) +{ + __u32 imn; + __u32 imx; + int flow = 0; - if(pkt_dev->cflows) { + if (pkt_dev->cflows) { flow = pktgen_random() % pkt_dev->cflows; - + if (pkt_dev->flows[flow].count > pkt_dev->lflow) pkt_dev->flows[flow].count = 0; - } - + } /* Deal with source MAC */ - if (pkt_dev->src_mac_count > 1) { - __u32 mc; - __u32 tmp; - - if (pkt_dev->flags & F_MACSRC_RND) - mc = pktgen_random() % (pkt_dev->src_mac_count); - else { - mc = pkt_dev->cur_src_mac_offset++; - if (pkt_dev->cur_src_mac_offset > pkt_dev->src_mac_count) - pkt_dev->cur_src_mac_offset = 0; - } - - tmp = pkt_dev->src_mac[5] + (mc & 0xFF); - pkt_dev->hh[11] = tmp; - tmp = (pkt_dev->src_mac[4] + ((mc >> 8) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[10] = tmp; - tmp = (pkt_dev->src_mac[3] + ((mc >> 16) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[9] = tmp; - tmp = (pkt_dev->src_mac[2] + ((mc >> 24) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[8] = tmp; - tmp = (pkt_dev->src_mac[1] + (tmp >> 8)); - pkt_dev->hh[7] = tmp; - } - - /* Deal with Destination MAC */ - if (pkt_dev->dst_mac_count > 1) { - __u32 mc; - __u32 tmp; - - if (pkt_dev->flags & F_MACDST_RND) - mc = pktgen_random() % (pkt_dev->dst_mac_count); - - else { - mc = pkt_dev->cur_dst_mac_offset++; - if (pkt_dev->cur_dst_mac_offset > pkt_dev->dst_mac_count) { - pkt_dev->cur_dst_mac_offset = 0; - } - } - - tmp = pkt_dev->dst_mac[5] + (mc & 0xFF); - pkt_dev->hh[5] = tmp; - tmp = (pkt_dev->dst_mac[4] + ((mc >> 8) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[4] = tmp; - tmp = (pkt_dev->dst_mac[3] + ((mc >> 16) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[3] = tmp; - tmp = (pkt_dev->dst_mac[2] + ((mc >> 24) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[2] = tmp; - tmp = (pkt_dev->dst_mac[1] + (tmp >> 8)); - pkt_dev->hh[1] = tmp; - } - - if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { - if (pkt_dev->flags & F_UDPSRC_RND) - pkt_dev->cur_udp_src = ((pktgen_random() % (pkt_dev->udp_src_max - pkt_dev->udp_src_min)) + pkt_dev->udp_src_min); - - else { + if (pkt_dev->src_mac_count > 1) { + __u32 mc; + __u32 tmp; + + if (pkt_dev->flags & F_MACSRC_RND) + mc = pktgen_random() % (pkt_dev->src_mac_count); + else { + mc = pkt_dev->cur_src_mac_offset++; + if (pkt_dev->cur_src_mac_offset > + pkt_dev->src_mac_count) + pkt_dev->cur_src_mac_offset = 0; + } + + tmp = pkt_dev->src_mac[5] + (mc & 0xFF); + pkt_dev->hh[11] = tmp; + tmp = (pkt_dev->src_mac[4] + ((mc >> 8) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[10] = tmp; + tmp = (pkt_dev->src_mac[3] + ((mc >> 16) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[9] = tmp; + tmp = (pkt_dev->src_mac[2] + ((mc >> 24) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[8] = tmp; + tmp = (pkt_dev->src_mac[1] + (tmp >> 8)); + pkt_dev->hh[7] = tmp; + } + + /* Deal with Destination MAC */ + if (pkt_dev->dst_mac_count > 1) { + __u32 mc; + __u32 tmp; + + if (pkt_dev->flags & F_MACDST_RND) + mc = pktgen_random() % (pkt_dev->dst_mac_count); + + else { + mc = pkt_dev->cur_dst_mac_offset++; + if (pkt_dev->cur_dst_mac_offset > + pkt_dev->dst_mac_count) { + pkt_dev->cur_dst_mac_offset = 0; + } + } + + tmp = pkt_dev->dst_mac[5] + (mc & 0xFF); + pkt_dev->hh[5] = tmp; + tmp = (pkt_dev->dst_mac[4] + ((mc >> 8) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[4] = tmp; + tmp = (pkt_dev->dst_mac[3] + ((mc >> 16) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[3] = tmp; + tmp = (pkt_dev->dst_mac[2] + ((mc >> 24) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[2] = tmp; + tmp = (pkt_dev->dst_mac[1] + (tmp >> 8)); + pkt_dev->hh[1] = tmp; + } + + if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { + if (pkt_dev->flags & F_UDPSRC_RND) + pkt_dev->cur_udp_src = + ((pktgen_random() % + (pkt_dev->udp_src_max - pkt_dev->udp_src_min)) + + pkt_dev->udp_src_min); + + else { pkt_dev->cur_udp_src++; if (pkt_dev->cur_udp_src >= pkt_dev->udp_src_max) pkt_dev->cur_udp_src = pkt_dev->udp_src_min; - } - } - - if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) { - if (pkt_dev->flags & F_UDPDST_RND) { - pkt_dev->cur_udp_dst = ((pktgen_random() % (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min)) + pkt_dev->udp_dst_min); - } - else { + } + } + + if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) { + if (pkt_dev->flags & F_UDPDST_RND) { + pkt_dev->cur_udp_dst = + ((pktgen_random() % + (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min)) + + pkt_dev->udp_dst_min); + } else { pkt_dev->cur_udp_dst++; - if (pkt_dev->cur_udp_dst >= pkt_dev->udp_dst_max) + if (pkt_dev->cur_udp_dst >= pkt_dev->udp_dst_max) pkt_dev->cur_udp_dst = pkt_dev->udp_dst_min; - } - } + } + } if (!(pkt_dev->flags & F_IPV6)) { - if ((imn = ntohl(pkt_dev->saddr_min)) < (imx = ntohl(pkt_dev->saddr_max))) { + if ((imn = ntohl(pkt_dev->saddr_min)) < (imx = + ntohl(pkt_dev-> + saddr_max))) { __u32 t; - if (pkt_dev->flags & F_IPSRC_RND) + if (pkt_dev->flags & F_IPSRC_RND) t = ((pktgen_random() % (imx - imn)) + imn); else { t = ntohl(pkt_dev->cur_saddr); @@ -1773,25 +1890,32 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) { } pkt_dev->cur_saddr = htonl(t); } - + if (pkt_dev->cflows && pkt_dev->flows[flow].count != 0) { pkt_dev->cur_daddr = pkt_dev->flows[flow].cur_daddr; } else { - if ((imn = ntohl(pkt_dev->daddr_min)) < (imx = ntohl(pkt_dev->daddr_max))) { + if ((imn = ntohl(pkt_dev->daddr_min)) < (imx = + ntohl(pkt_dev-> + daddr_max))) + { __u32 t; if (pkt_dev->flags & F_IPDST_RND) { - t = ((pktgen_random() % (imx - imn)) + imn); + t = ((pktgen_random() % (imx - imn)) + + imn); t = htonl(t); - while( LOOPBACK(t) || MULTICAST(t) || BADCLASS(t) || ZERONET(t) || LOCAL_MCAST(t) ) { - t = ((pktgen_random() % (imx - imn)) + imn); + while (LOOPBACK(t) || MULTICAST(t) + || BADCLASS(t) || ZERONET(t) + || LOCAL_MCAST(t)) { + t = ((pktgen_random() % + (imx - imn)) + imn); t = htonl(t); } pkt_dev->cur_daddr = t; } - + else { t = ntohl(pkt_dev->cur_daddr); t++; @@ -1801,60 +1925,59 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) { pkt_dev->cur_daddr = htonl(t); } } - if(pkt_dev->cflows) { - pkt_dev->flows[flow].cur_daddr = pkt_dev->cur_daddr; + if (pkt_dev->cflows) { + pkt_dev->flows[flow].cur_daddr = + pkt_dev->cur_daddr; pkt_dev->nflows++; } } - } - else /* IPV6 * */ - { - if(pkt_dev->min_in6_daddr.s6_addr32[0] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[1] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[2] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[3] == 0); + } else { /* IPV6 * */ + + if (pkt_dev->min_in6_daddr.s6_addr32[0] == 0 && + pkt_dev->min_in6_daddr.s6_addr32[1] == 0 && + pkt_dev->min_in6_daddr.s6_addr32[2] == 0 && + pkt_dev->min_in6_daddr.s6_addr32[3] == 0) ; else { int i; /* Only random destinations yet */ - for(i=0; i < 4; i++) { + for (i = 0; i < 4; i++) { pkt_dev->cur_in6_daddr.s6_addr32[i] = - ((pktgen_random() | - pkt_dev->min_in6_daddr.s6_addr32[i]) & - pkt_dev->max_in6_daddr.s6_addr32[i]); + ((pktgen_random() | + pkt_dev->min_in6_daddr.s6_addr32[i]) & + pkt_dev->max_in6_daddr.s6_addr32[i]); } - } + } } - if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) { - __u32 t; - if (pkt_dev->flags & F_TXSIZE_RND) { - t = ((pktgen_random() % (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size)) - + pkt_dev->min_pkt_size); - } - else { + if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) { + __u32 t; + if (pkt_dev->flags & F_TXSIZE_RND) { + t = ((pktgen_random() % + (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size)) + + pkt_dev->min_pkt_size); + } else { t = pkt_dev->cur_pkt_size + 1; - if (t > pkt_dev->max_pkt_size) + if (t > pkt_dev->max_pkt_size) t = pkt_dev->min_pkt_size; - } - pkt_dev->cur_pkt_size = t; - } + } + pkt_dev->cur_pkt_size = t; + } pkt_dev->flows[flow].count++; } - -static struct sk_buff *fill_packet_ipv4(struct net_device *odev, - struct pktgen_dev *pkt_dev) +static struct sk_buff *fill_packet_ipv4(struct net_device *odev, + struct pktgen_dev *pkt_dev) { struct sk_buff *skb = NULL; __u8 *eth; struct udphdr *udph; int datalen, iplen; struct iphdr *iph; - struct pktgen_hdr *pgh = NULL; - + struct pktgen_hdr *pgh = NULL; + /* Update any of the values, used when we're incrementing various * fields. */ @@ -1875,47 +1998,47 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); memcpy(eth, pkt_dev->hh, 12); - *(u16*)ð[12] = __constant_htons(ETH_P_IP); + *(u16 *) & eth[12] = __constant_htons(ETH_P_IP); - datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8; /* Eth + IPh + UDPh */ - if (datalen < sizeof(struct pktgen_hdr)) + datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8; /* Eth + IPh + UDPh */ + if (datalen < sizeof(struct pktgen_hdr)) datalen = sizeof(struct pktgen_hdr); - + udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); - udph->len = htons(datalen + 8); /* DATA + udphdr */ - udph->check = 0; /* No checksum */ + udph->len = htons(datalen + 8); /* DATA + udphdr */ + udph->check = 0; /* No checksum */ iph->ihl = 5; iph->version = 4; iph->ttl = 32; iph->tos = 0; - iph->protocol = IPPROTO_UDP; /* UDP */ + iph->protocol = IPPROTO_UDP; /* UDP */ iph->saddr = pkt_dev->cur_saddr; iph->daddr = pkt_dev->cur_daddr; iph->frag_off = 0; iplen = 20 + 8 + datalen; iph->tot_len = htons(iplen); iph->check = 0; - iph->check = ip_fast_csum((void *) iph, iph->ihl); + iph->check = ip_fast_csum((void *)iph, iph->ihl); skb->protocol = __constant_htons(ETH_P_IP); - skb->mac.raw = ((u8 *)iph) - 14; + skb->mac.raw = ((u8 *) iph) - 14; skb->dev = odev; skb->pkt_type = PACKET_HOST; - if (pkt_dev->nfrags <= 0) - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); + if (pkt_dev->nfrags <= 0) + pgh = (struct pktgen_hdr *)skb_put(skb, datalen); else { int frags = pkt_dev->nfrags; int i; - pgh = (struct pktgen_hdr*)(((char*)(udph)) + 8); - + pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); + if (frags > MAX_SKB_FRAGS) frags = MAX_SKB_FRAGS; - if (datalen > frags*PAGE_SIZE) { - skb_put(skb, datalen-frags*PAGE_SIZE); - datalen = frags*PAGE_SIZE; + if (datalen > frags * PAGE_SIZE) { + skb_put(skb, datalen - frags * PAGE_SIZE); + datalen = frags * PAGE_SIZE; } i = 0; @@ -1924,7 +2047,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, skb_shinfo(skb)->frags[i].page = page; skb_shinfo(skb)->frags[i].page_offset = 0; skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); datalen -= skb_shinfo(skb)->frags[i].size; skb->len += skb_shinfo(skb)->frags[i].size; skb->data_len += skb_shinfo(skb)->frags[i].size; @@ -1944,30 +2067,33 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, skb_shinfo(skb)->frags[i - 1].size -= rem; - skb_shinfo(skb)->frags[i] = skb_shinfo(skb)->frags[i - 1]; + skb_shinfo(skb)->frags[i] = + skb_shinfo(skb)->frags[i - 1]; get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += skb_shinfo(skb)->frags[i - 1].size; + skb_shinfo(skb)->frags[i].page = + skb_shinfo(skb)->frags[i - 1].page; + skb_shinfo(skb)->frags[i].page_offset += + skb_shinfo(skb)->frags[i - 1].size; skb_shinfo(skb)->frags[i].size = rem; i++; skb_shinfo(skb)->nr_frags = i; } } - /* Stamp the time, and sequence number, convert them to network byte order */ + /* Stamp the time, and sequence number, convert them to network byte order */ + + if (pgh) { + struct timeval timestamp; + + pgh->pgh_magic = htonl(PKTGEN_MAGIC); + pgh->seq_num = htonl(pkt_dev->seq_num); + + do_gettimeofday(×tamp); + pgh->tv_sec = htonl(timestamp.tv_sec); + pgh->tv_usec = htonl(timestamp.tv_usec); + } + pkt_dev->seq_num++; - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } - pkt_dev->seq_num++; - return skb; } @@ -1980,23 +2106,24 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, * --ro */ -static unsigned int scan_ip6(const char *s,char ip[16]) +static unsigned int scan_ip6(const char *s, char ip[16]) { unsigned int i; - unsigned int len=0; + unsigned int len = 0; unsigned long u; char suffix[16]; - unsigned int prefixlen=0; - unsigned int suffixlen=0; + unsigned int prefixlen = 0; + unsigned int suffixlen = 0; __u32 tmp; - for (i=0; i<16; i++) ip[i]=0; + for (i = 0; i < 16; i++) + ip[i] = 0; for (;;) { if (*s == ':') { len++; - if (s[1] == ':') { /* Found "::", skip to part 2 */ - s+=2; + if (s[1] == ':') { /* Found "::", skip to part 2 */ + s += 2; len++; break; } @@ -2004,129 +2131,149 @@ static unsigned int scan_ip6(const char *s,char ip[16]) } { char *tmp; - u=simple_strtoul(s,&tmp,16); - i=tmp-s; + u = simple_strtoul(s, &tmp, 16); + i = tmp - s; } - if (!i) return 0; - if (prefixlen==12 && s[i]=='.') { + if (!i) + return 0; + if (prefixlen == 12 && s[i] == '.') { /* the last 4 bytes may be written as IPv4 address */ tmp = in_aton(s); - memcpy((struct in_addr*)(ip+12), &tmp, sizeof(tmp)); - return i+len; + memcpy((struct in_addr *)(ip + 12), &tmp, sizeof(tmp)); + return i + len; } ip[prefixlen++] = (u >> 8); ip[prefixlen++] = (u & 255); - s += i; len += i; - if (prefixlen==16) + s += i; + len += i; + if (prefixlen == 16) return len; } /* part 2, after "::" */ for (;;) { if (*s == ':') { - if (suffixlen==0) + if (suffixlen == 0) break; s++; len++; - } else if (suffixlen!=0) + } else if (suffixlen != 0) break; { char *tmp; - u=simple_strtol(s,&tmp,16); - i=tmp-s; + u = simple_strtol(s, &tmp, 16); + i = tmp - s; } if (!i) { - if (*s) len--; + if (*s) + len--; break; } - if (suffixlen+prefixlen<=12 && s[i]=='.') { + if (suffixlen + prefixlen <= 12 && s[i] == '.') { tmp = in_aton(s); - memcpy((struct in_addr*)(suffix+suffixlen), &tmp, sizeof(tmp)); - suffixlen+=4; - len+=strlen(s); + memcpy((struct in_addr *)(suffix + suffixlen), &tmp, + sizeof(tmp)); + suffixlen += 4; + len += strlen(s); break; } suffix[suffixlen++] = (u >> 8); suffix[suffixlen++] = (u & 255); - s += i; len += i; - if (prefixlen+suffixlen==16) + s += i; + len += i; + if (prefixlen + suffixlen == 16) break; } - for (i=0; i<suffixlen; i++) - ip[16-suffixlen+i] = suffix[i]; + for (i = 0; i < suffixlen; i++) + ip[16 - suffixlen + i] = suffix[i]; return len; } -static char tohex(char hexdigit) { - return hexdigit>9?hexdigit+'a'-10:hexdigit+'0'; +static char tohex(char hexdigit) +{ + return hexdigit > 9 ? hexdigit + 'a' - 10 : hexdigit + '0'; } -static int fmt_xlong(char* s,unsigned int i) { - char* bak=s; - *s=tohex((i>>12)&0xf); if (s!=bak || *s!='0') ++s; - *s=tohex((i>>8)&0xf); if (s!=bak || *s!='0') ++s; - *s=tohex((i>>4)&0xf); if (s!=bak || *s!='0') ++s; - *s=tohex(i&0xf); - return s-bak+1; +static int fmt_xlong(char *s, unsigned int i) +{ + char *bak = s; + *s = tohex((i >> 12) & 0xf); + if (s != bak || *s != '0') + ++s; + *s = tohex((i >> 8) & 0xf); + if (s != bak || *s != '0') + ++s; + *s = tohex((i >> 4) & 0xf); + if (s != bak || *s != '0') + ++s; + *s = tohex(i & 0xf); + return s - bak + 1; } -static unsigned int fmt_ip6(char *s,const char ip[16]) { +static unsigned int fmt_ip6(char *s, const char ip[16]) +{ unsigned int len; unsigned int i; unsigned int temp; unsigned int compressing; int j; - len = 0; compressing = 0; - for (j=0; j<16; j+=2) { + len = 0; + compressing = 0; + for (j = 0; j < 16; j += 2) { #ifdef V4MAPPEDPREFIX - if (j==12 && !memcmp(ip,V4mappedprefix,12)) { - inet_ntoa_r(*(struct in_addr*)(ip+12),s); - temp=strlen(s); - return len+temp; + if (j == 12 && !memcmp(ip, V4mappedprefix, 12)) { + inet_ntoa_r(*(struct in_addr *)(ip + 12), s); + temp = strlen(s); + return len + temp; } #endif - temp = ((unsigned long) (unsigned char) ip[j] << 8) + - (unsigned long) (unsigned char) ip[j+1]; + temp = ((unsigned long)(unsigned char)ip[j] << 8) + + (unsigned long)(unsigned char)ip[j + 1]; if (temp == 0) { if (!compressing) { - compressing=1; - if (j==0) { - *s++=':'; ++len; + compressing = 1; + if (j == 0) { + *s++ = ':'; + ++len; } } } else { if (compressing) { - compressing=0; - *s++=':'; ++len; + compressing = 0; + *s++ = ':'; + ++len; } - i = fmt_xlong(s,temp); len += i; s += i; - if (j<14) { + i = fmt_xlong(s, temp); + len += i; + s += i; + if (j < 14) { *s++ = ':'; ++len; } } } if (compressing) { - *s++=':'; ++len; + *s++ = ':'; + ++len; } - *s=0; + *s = 0; return len; } -static struct sk_buff *fill_packet_ipv6(struct net_device *odev, - struct pktgen_dev *pkt_dev) +static struct sk_buff *fill_packet_ipv6(struct net_device *odev, + struct pktgen_dev *pkt_dev) { struct sk_buff *skb = NULL; __u8 *eth; struct udphdr *udph; int datalen; struct ipv6hdr *iph; - struct pktgen_hdr *pgh = NULL; + struct pktgen_hdr *pgh = NULL; /* Update any of the values, used when we're incrementing various * fields. @@ -2147,23 +2294,23 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); memcpy(eth, pkt_dev->hh, 12); - *(u16*)ð[12] = __constant_htons(ETH_P_IPV6); + *(u16 *) & eth[12] = __constant_htons(ETH_P_IPV6); - datalen = pkt_dev->cur_pkt_size-14- - sizeof(struct ipv6hdr)-sizeof(struct udphdr); /* Eth + IPh + UDPh */ + datalen = pkt_dev->cur_pkt_size - 14 - sizeof(struct ipv6hdr) - sizeof(struct udphdr); /* Eth + IPh + UDPh */ - if (datalen < sizeof(struct pktgen_hdr)) { + if (datalen < sizeof(struct pktgen_hdr)) { datalen = sizeof(struct pktgen_hdr); if (net_ratelimit()) - printk(KERN_INFO "pktgen: increased datalen to %d\n", datalen); + printk(KERN_INFO "pktgen: increased datalen to %d\n", + datalen); } udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); - udph->len = htons(datalen + sizeof(struct udphdr)); - udph->check = 0; /* No checksum */ + udph->len = htons(datalen + sizeof(struct udphdr)); + udph->check = 0; /* No checksum */ - *(u32*)iph = __constant_htonl(0x60000000); /* Version + flow */ + *(u32 *) iph = __constant_htonl(0x60000000); /* Version + flow */ iph->hop_limit = 32; @@ -2173,24 +2320,24 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr); ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr); - skb->mac.raw = ((u8 *)iph) - 14; + skb->mac.raw = ((u8 *) iph) - 14; skb->protocol = __constant_htons(ETH_P_IPV6); skb->dev = odev; skb->pkt_type = PACKET_HOST; - if (pkt_dev->nfrags <= 0) - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); + if (pkt_dev->nfrags <= 0) + pgh = (struct pktgen_hdr *)skb_put(skb, datalen); else { int frags = pkt_dev->nfrags; int i; - pgh = (struct pktgen_hdr*)(((char*)(udph)) + 8); - + pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); + if (frags > MAX_SKB_FRAGS) frags = MAX_SKB_FRAGS; - if (datalen > frags*PAGE_SIZE) { - skb_put(skb, datalen-frags*PAGE_SIZE); - datalen = frags*PAGE_SIZE; + if (datalen > frags * PAGE_SIZE) { + skb_put(skb, datalen - frags * PAGE_SIZE); + datalen = frags * PAGE_SIZE; } i = 0; @@ -2199,7 +2346,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb_shinfo(skb)->frags[i].page = page; skb_shinfo(skb)->frags[i].page_offset = 0; skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); datalen -= skb_shinfo(skb)->frags[i].size; skb->len += skb_shinfo(skb)->frags[i].size; skb->data_len += skb_shinfo(skb)->frags[i].size; @@ -2219,305 +2366,333 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb_shinfo(skb)->frags[i - 1].size -= rem; - skb_shinfo(skb)->frags[i] = skb_shinfo(skb)->frags[i - 1]; + skb_shinfo(skb)->frags[i] = + skb_shinfo(skb)->frags[i - 1]; get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += skb_shinfo(skb)->frags[i - 1].size; + skb_shinfo(skb)->frags[i].page = + skb_shinfo(skb)->frags[i - 1].page; + skb_shinfo(skb)->frags[i].page_offset += + skb_shinfo(skb)->frags[i - 1].size; skb_shinfo(skb)->frags[i].size = rem; i++; skb_shinfo(skb)->nr_frags = i; } } - /* Stamp the time, and sequence number, convert them to network byte order */ + /* Stamp the time, and sequence number, convert them to network byte order */ /* should we update cloned packets too ? */ - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } - pkt_dev->seq_num++; - + if (pgh) { + struct timeval timestamp; + + pgh->pgh_magic = htonl(PKTGEN_MAGIC); + pgh->seq_num = htonl(pkt_dev->seq_num); + + do_gettimeofday(×tamp); + pgh->tv_sec = htonl(timestamp.tv_sec); + pgh->tv_usec = htonl(timestamp.tv_usec); + } + pkt_dev->seq_num++; + return skb; } -static inline struct sk_buff *fill_packet(struct net_device *odev, - struct pktgen_dev *pkt_dev) +static inline struct sk_buff *fill_packet(struct net_device *odev, + struct pktgen_dev *pkt_dev) { - if(pkt_dev->flags & F_IPV6) + if (pkt_dev->flags & F_IPV6) return fill_packet_ipv6(odev, pkt_dev); else return fill_packet_ipv4(odev, pkt_dev); } -static void pktgen_clear_counters(struct pktgen_dev *pkt_dev) +static void pktgen_clear_counters(struct pktgen_dev *pkt_dev) { - pkt_dev->seq_num = 1; - pkt_dev->idle_acc = 0; + pkt_dev->seq_num = 1; + pkt_dev->idle_acc = 0; pkt_dev->sofar = 0; - pkt_dev->tx_bytes = 0; - pkt_dev->errors = 0; + pkt_dev->tx_bytes = 0; + pkt_dev->errors = 0; } /* Set up structure for sending pkts, clear counters */ static void pktgen_run(struct pktgen_thread *t) { - struct pktgen_dev *pkt_dev = NULL; + struct pktgen_dev *pkt_dev; int started = 0; PG_DEBUG(printk("pktgen: entering pktgen_run. %p\n", t)); if_lock(t); - for (pkt_dev = t->if_list; pkt_dev; pkt_dev = pkt_dev->next ) { + list_for_each_entry(pkt_dev, &t->if_list, list) { /* * setup odev and create initial packet. */ pktgen_setup_inject(pkt_dev); - if(pkt_dev->odev) { + if (pkt_dev->odev) { pktgen_clear_counters(pkt_dev); - pkt_dev->running = 1; /* Cranke yeself! */ + pkt_dev->running = 1; /* Cranke yeself! */ pkt_dev->skb = NULL; pkt_dev->started_at = getCurUs(); - pkt_dev->next_tx_us = getCurUs(); /* Transmit immediately */ + pkt_dev->next_tx_us = getCurUs(); /* Transmit immediately */ pkt_dev->next_tx_ns = 0; - + strcpy(pkt_dev->result, "Starting"); started++; - } - else + } else strcpy(pkt_dev->result, "Error starting"); } if_unlock(t); - if(started) t->control &= ~(T_STOP); + if (started) + t->control &= ~(T_STOP); } static void pktgen_stop_all_threads_ifs(void) { - struct pktgen_thread *t = pktgen_threads; + struct pktgen_thread *t; - PG_DEBUG(printk("pktgen: entering pktgen_stop_all_threads.\n")); + PG_DEBUG(printk("pktgen: entering pktgen_stop_all_threads_ifs.\n")); - thread_lock(); - while(t) { - pktgen_stop(t); - t = t->next; - } - thread_unlock(); + mutex_lock(&pktgen_thread_lock); + + list_for_each_entry(t, &pktgen_threads, th_list) + t->control |= T_STOP; + + mutex_unlock(&pktgen_thread_lock); } -static int thread_is_running(struct pktgen_thread *t ) +static int thread_is_running(struct pktgen_thread *t) { - struct pktgen_dev *next; - int res = 0; + struct pktgen_dev *pkt_dev; + int res = 0; - for(next=t->if_list; next; next=next->next) { - if(next->running) { + list_for_each_entry(pkt_dev, &t->if_list, list) + if (pkt_dev->running) { res = 1; break; } - } - return res; + return res; } -static int pktgen_wait_thread_run(struct pktgen_thread *t ) +static int pktgen_wait_thread_run(struct pktgen_thread *t) { - if_lock(t); + if_lock(t); - while(thread_is_running(t)) { + while (thread_is_running(t)) { - if_unlock(t); + if_unlock(t); - msleep_interruptible(100); + msleep_interruptible(100); - if (signal_pending(current)) - goto signal; - if_lock(t); - } - if_unlock(t); - return 1; - signal: - return 0; + if (signal_pending(current)) + goto signal; + if_lock(t); + } + if_unlock(t); + return 1; +signal: + return 0; } static int pktgen_wait_all_threads_run(void) { - struct pktgen_thread *t = pktgen_threads; + struct pktgen_thread *t; int sig = 1; - - while (t) { + + mutex_lock(&pktgen_thread_lock); + + list_for_each_entry(t, &pktgen_threads, th_list) { sig = pktgen_wait_thread_run(t); - if( sig == 0 ) break; - thread_lock(); - t=t->next; - thread_unlock(); - } - if(sig == 0) { - thread_lock(); - while (t) { - t->control |= (T_STOP); - t=t->next; - } - thread_unlock(); + if (sig == 0) + break; } + + if (sig == 0) + list_for_each_entry(t, &pktgen_threads, th_list) + t->control |= (T_STOP); + + mutex_unlock(&pktgen_thread_lock); return sig; } static void pktgen_run_all_threads(void) { - struct pktgen_thread *t = pktgen_threads; + struct pktgen_thread *t; PG_DEBUG(printk("pktgen: entering pktgen_run_all_threads.\n")); - thread_lock(); + mutex_lock(&pktgen_thread_lock); - while(t) { + list_for_each_entry(t, &pktgen_threads, th_list) t->control |= (T_RUN); - t = t->next; - } - thread_unlock(); - schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ - + mutex_unlock(&pktgen_thread_lock); + + schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ + pktgen_wait_all_threads_run(); } - static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) { - __u64 total_us, bps, mbps, pps, idle; - char *p = pkt_dev->result; - - total_us = pkt_dev->stopped_at - pkt_dev->started_at; - - idle = pkt_dev->idle_acc; - - p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n", - (unsigned long long) total_us, - (unsigned long long)(total_us - idle), - (unsigned long long) idle, - (unsigned long long) pkt_dev->sofar, - pkt_dev->cur_pkt_size, nr_frags); - - pps = pkt_dev->sofar * USEC_PER_SEC; - - while ((total_us >> 32) != 0) { - pps >>= 1; - total_us >>= 1; - } - - do_div(pps, total_us); - - bps = pps * 8 * pkt_dev->cur_pkt_size; - - mbps = bps; - do_div(mbps, 1000000); - p += sprintf(p, " %llupps %lluMb/sec (%llubps) errors: %llu", - (unsigned long long) pps, - (unsigned long long) mbps, - (unsigned long long) bps, - (unsigned long long) pkt_dev->errors); + __u64 total_us, bps, mbps, pps, idle; + char *p = pkt_dev->result; + + total_us = pkt_dev->stopped_at - pkt_dev->started_at; + + idle = pkt_dev->idle_acc; + + p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n", + (unsigned long long)total_us, + (unsigned long long)(total_us - idle), + (unsigned long long)idle, + (unsigned long long)pkt_dev->sofar, + pkt_dev->cur_pkt_size, nr_frags); + + pps = pkt_dev->sofar * USEC_PER_SEC; + + while ((total_us >> 32) != 0) { + pps >>= 1; + total_us >>= 1; + } + + do_div(pps, total_us); + + bps = pps * 8 * pkt_dev->cur_pkt_size; + + mbps = bps; + do_div(mbps, 1000000); + p += sprintf(p, " %llupps %lluMb/sec (%llubps) errors: %llu", + (unsigned long long)pps, + (unsigned long long)mbps, + (unsigned long long)bps, + (unsigned long long)pkt_dev->errors); } - /* Set stopped-at timer, remove from running list, do counters & statistics */ -static int pktgen_stop_device(struct pktgen_dev *pkt_dev) +static int pktgen_stop_device(struct pktgen_dev *pkt_dev) { - - if (!pkt_dev->running) { - printk("pktgen: interface: %s is already stopped\n", pkt_dev->ifname); - return -EINVAL; - } + int nr_frags = pkt_dev->skb ? skb_shinfo(pkt_dev->skb)->nr_frags : -1; - pkt_dev->stopped_at = getCurUs(); - pkt_dev->running = 0; + if (!pkt_dev->running) { + printk("pktgen: interface: %s is already stopped\n", + pkt_dev->ifname); + return -EINVAL; + } - show_results(pkt_dev, skb_shinfo(pkt_dev->skb)->nr_frags); + pkt_dev->stopped_at = getCurUs(); + pkt_dev->running = 0; - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); + show_results(pkt_dev, nr_frags); - pkt_dev->skb = NULL; - - return 0; + return 0; } -static struct pktgen_dev *next_to_run(struct pktgen_thread *t ) +static struct pktgen_dev *next_to_run(struct pktgen_thread *t) { - struct pktgen_dev *next, *best = NULL; - + struct pktgen_dev *pkt_dev, *best = NULL; + if_lock(t); - for(next=t->if_list; next ; next=next->next) { - if(!next->running) continue; - if(best == NULL) best=next; - else if ( next->next_tx_us < best->next_tx_us) - best = next; + list_for_each_entry(pkt_dev, &t->if_list, list) { + if (!pkt_dev->running) + continue; + if (best == NULL) + best = pkt_dev; + else if (pkt_dev->next_tx_us < best->next_tx_us) + best = pkt_dev; } if_unlock(t); - return best; + return best; } -static void pktgen_stop(struct pktgen_thread *t) { - struct pktgen_dev *next = NULL; +static void pktgen_stop(struct pktgen_thread *t) +{ + struct pktgen_dev *pkt_dev; - PG_DEBUG(printk("pktgen: entering pktgen_stop.\n")); + PG_DEBUG(printk("pktgen: entering pktgen_stop\n")); - if_lock(t); + if_lock(t); - for(next=t->if_list; next; next=next->next) - pktgen_stop_device(next); + list_for_each_entry(pkt_dev, &t->if_list, list) { + pktgen_stop_device(pkt_dev); + if (pkt_dev->skb) + kfree_skb(pkt_dev->skb); - if_unlock(t); + pkt_dev->skb = NULL; + } + + if_unlock(t); } -static void pktgen_rem_all_ifs(struct pktgen_thread *t) +/* + * one of our devices needs to be removed - find it + * and remove it + */ +static void pktgen_rem_one_if(struct pktgen_thread *t) { - struct pktgen_dev *cur, *next = NULL; - - /* Remove all devices, free mem */ - - if_lock(t); - - for(cur=t->if_list; cur; cur=next) { - next = cur->next; + struct list_head *q, *n; + struct pktgen_dev *cur; + + PG_DEBUG(printk("pktgen: entering pktgen_rem_one_if\n")); + + if_lock(t); + + list_for_each_safe(q, n, &t->if_list) { + cur = list_entry(q, struct pktgen_dev, list); + + if (!cur->removal_mark) + continue; + + if (cur->skb) + kfree_skb(cur->skb); + cur->skb = NULL; + pktgen_remove_device(t, cur); + + break; } - if_unlock(t); + if_unlock(t); } -static void pktgen_rem_thread(struct pktgen_thread *t) +static void pktgen_rem_all_ifs(struct pktgen_thread *t) { - /* Remove from the thread list */ + struct list_head *q, *n; + struct pktgen_dev *cur; - struct pktgen_thread *tmp = pktgen_threads; + /* Remove all devices, free mem */ - remove_proc_entry(t->name, pg_proc_dir); + PG_DEBUG(printk("pktgen: entering pktgen_rem_all_ifs\n")); + if_lock(t); - thread_lock(); + list_for_each_safe(q, n, &t->if_list) { + cur = list_entry(q, struct pktgen_dev, list); - if (tmp == t) - pktgen_threads = tmp->next; - else { - while (tmp) { - if (tmp->next == t) { - tmp->next = t->next; - t->next = NULL; - break; - } - tmp = tmp->next; - } + if (cur->skb) + kfree_skb(cur->skb); + cur->skb = NULL; + + pktgen_remove_device(t, cur); } - thread_unlock(); + + if_unlock(t); +} + +static void pktgen_rem_thread(struct pktgen_thread *t) +{ + /* Remove from the thread list */ + + remove_proc_entry(t->name, pg_proc_dir); + + mutex_lock(&pktgen_thread_lock); + + list_del(&t->th_list); + + mutex_unlock(&pktgen_thread_lock); } static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) @@ -2527,7 +2702,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) int ret; odev = pkt_dev->odev; - + if (pkt_dev->delay_us || pkt_dev->delay_ns) { u64 now; @@ -2544,67 +2719,71 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) goto out; } } - + if (netif_queue_stopped(odev) || need_resched()) { idle_start = getCurUs(); - + if (!netif_running(odev)) { pktgen_stop_device(pkt_dev); + if (pkt_dev->skb) + kfree_skb(pkt_dev->skb); + pkt_dev->skb = NULL; goto out; } - if (need_resched()) + if (need_resched()) schedule(); - + pkt_dev->idle_acc += getCurUs() - idle_start; - + if (netif_queue_stopped(odev)) { - pkt_dev->next_tx_us = getCurUs(); /* TODO */ + pkt_dev->next_tx_us = getCurUs(); /* TODO */ pkt_dev->next_tx_ns = 0; - goto out; /* Try the next interface */ + goto out; /* Try the next interface */ } } - + if (pkt_dev->last_ok || !pkt_dev->skb) { - if ((++pkt_dev->clone_count >= pkt_dev->clone_skb ) || (!pkt_dev->skb)) { + if ((++pkt_dev->clone_count >= pkt_dev->clone_skb) + || (!pkt_dev->skb)) { /* build a new pkt */ - if (pkt_dev->skb) + if (pkt_dev->skb) kfree_skb(pkt_dev->skb); - + pkt_dev->skb = fill_packet(odev, pkt_dev); if (pkt_dev->skb == NULL) { printk("pktgen: ERROR: couldn't allocate skb in fill_packet.\n"); schedule(); - pkt_dev->clone_count--; /* back out increment, OOM */ + pkt_dev->clone_count--; /* back out increment, OOM */ goto out; } pkt_dev->allocated_skbs++; - pkt_dev->clone_count = 0; /* reset counter */ + pkt_dev->clone_count = 0; /* reset counter */ } } - + spin_lock_bh(&odev->xmit_lock); if (!netif_queue_stopped(odev)) { atomic_inc(&(pkt_dev->skb->users)); -retry_now: + retry_now: ret = odev->hard_start_xmit(pkt_dev->skb, odev); if (likely(ret == NETDEV_TX_OK)) { - pkt_dev->last_ok = 1; + pkt_dev->last_ok = 1; pkt_dev->sofar++; pkt_dev->seq_num++; pkt_dev->tx_bytes += pkt_dev->cur_pkt_size; - - } else if (ret == NETDEV_TX_LOCKED + + } else if (ret == NETDEV_TX_LOCKED && (odev->features & NETIF_F_LLTX)) { cpu_relax(); goto retry_now; - } else { /* Retry it next time */ - + } else { /* Retry it next time */ + atomic_dec(&(pkt_dev->skb->users)); - + if (debug && net_ratelimit()) printk(KERN_INFO "pktgen: Hard xmit error\n"); - + pkt_dev->errors++; pkt_dev->last_ok = 0; } @@ -2619,16 +2798,16 @@ retry_now: pkt_dev->next_tx_us++; pkt_dev->next_tx_ns -= 1000; } - } + } - else { /* Retry it next time */ - pkt_dev->last_ok = 0; - pkt_dev->next_tx_us = getCurUs(); /* TODO */ + else { /* Retry it next time */ + pkt_dev->last_ok = 0; + pkt_dev->next_tx_us = getCurUs(); /* TODO */ pkt_dev->next_tx_ns = 0; - } + } spin_unlock_bh(&odev->xmit_lock); - + /* If pkt_dev->count is zero, then run forever */ if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) { if (atomic_read(&(pkt_dev->skb->users)) != 1) { @@ -2641,72 +2820,74 @@ retry_now: } pkt_dev->idle_acc += getCurUs() - idle_start; } - + /* Done with this */ pktgen_stop_device(pkt_dev); - } - out:; - } + if (pkt_dev->skb) + kfree_skb(pkt_dev->skb); + pkt_dev->skb = NULL; + } +out:; +} /* * Main loop of the thread goes here */ -static void pktgen_thread_worker(struct pktgen_thread *t) +static void pktgen_thread_worker(struct pktgen_thread *t) { DEFINE_WAIT(wait); - struct pktgen_dev *pkt_dev = NULL; + struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; sigset_t tmpsig; u32 max_before_softirq; - u32 tx_since_softirq = 0; + u32 tx_since_softirq = 0; daemonize("pktgen/%d", cpu); - /* Block all signals except SIGKILL, SIGSTOP and SIGTERM */ + /* Block all signals except SIGKILL, SIGSTOP and SIGTERM */ - spin_lock_irq(¤t->sighand->siglock); - tmpsig = current->blocked; - siginitsetinv(¤t->blocked, - sigmask(SIGKILL) | - sigmask(SIGSTOP)| - sigmask(SIGTERM)); + spin_lock_irq(¤t->sighand->siglock); + tmpsig = current->blocked; + siginitsetinv(¤t->blocked, + sigmask(SIGKILL) | sigmask(SIGSTOP) | sigmask(SIGTERM)); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); /* Migrate to the right CPU */ set_cpus_allowed(current, cpumask_of_cpu(cpu)); - if (smp_processor_id() != cpu) - BUG(); + if (smp_processor_id() != cpu) + BUG(); init_waitqueue_head(&t->queue); t->control &= ~(T_TERMINATE); t->control &= ~(T_RUN); t->control &= ~(T_STOP); + t->control &= ~(T_REMDEVALL); t->control &= ~(T_REMDEV); - t->pid = current->pid; + t->pid = current->pid; - PG_DEBUG(printk("pktgen: starting pktgen/%d: pid=%d\n", cpu, current->pid)); + PG_DEBUG(printk("pktgen: starting pktgen/%d: pid=%d\n", cpu, current->pid)); max_before_softirq = t->max_before_softirq; - - __set_current_state(TASK_INTERRUPTIBLE); - mb(); - while (1) { - + __set_current_state(TASK_INTERRUPTIBLE); + mb(); + + while (1) { + __set_current_state(TASK_RUNNING); /* * Get next dev to xmit -- if any. */ - pkt_dev = next_to_run(t); - - if (pkt_dev) { + pkt_dev = next_to_run(t); + + if (pkt_dev) { pktgen_xmit(pkt_dev); @@ -2724,115 +2905,125 @@ static void pktgen_thread_worker(struct pktgen_thread *t) } } else { prepare_to_wait(&(t->queue), &wait, TASK_INTERRUPTIBLE); - schedule_timeout(HZ/10); + schedule_timeout(HZ / 10); finish_wait(&(t->queue), &wait); } - /* + /* * Back from sleep, either due to the timeout or signal. * We check if we have any "posted" work for us. */ - if (t->control & T_TERMINATE || signal_pending(current)) - /* we received a request to terminate ourself */ - break; - + if (t->control & T_TERMINATE || signal_pending(current)) + /* we received a request to terminate ourself */ + break; - if(t->control & T_STOP) { + if (t->control & T_STOP) { pktgen_stop(t); t->control &= ~(T_STOP); } - if(t->control & T_RUN) { + if (t->control & T_RUN) { pktgen_run(t); t->control &= ~(T_RUN); } - if(t->control & T_REMDEV) { + if (t->control & T_REMDEVALL) { pktgen_rem_all_ifs(t); + t->control &= ~(T_REMDEVALL); + } + + if (t->control & T_REMDEV) { + pktgen_rem_one_if(t); t->control &= ~(T_REMDEV); } - if (need_resched()) + if (need_resched()) schedule(); - } + } + + PG_DEBUG(printk("pktgen: %s stopping all device\n", t->name)); + pktgen_stop(t); - PG_DEBUG(printk("pktgen: %s stopping all device\n", t->name)); - pktgen_stop(t); + PG_DEBUG(printk("pktgen: %s removing all device\n", t->name)); + pktgen_rem_all_ifs(t); - PG_DEBUG(printk("pktgen: %s removing all device\n", t->name)); - pktgen_rem_all_ifs(t); + PG_DEBUG(printk("pktgen: %s removing thread.\n", t->name)); + pktgen_rem_thread(t); - PG_DEBUG(printk("pktgen: %s removing thread.\n", t->name)); - pktgen_rem_thread(t); + t->removed = 1; } -static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, const char* ifname) +static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, + const char *ifname) { - struct pktgen_dev *pkt_dev = NULL; - if_lock(t); - - for(pkt_dev=t->if_list; pkt_dev; pkt_dev = pkt_dev->next ) { - if (strncmp(pkt_dev->ifname, ifname, IFNAMSIZ) == 0) { - break; - } - } - - if_unlock(t); - PG_DEBUG(printk("pktgen: find_dev(%s) returning %p\n", ifname,pkt_dev)); - return pkt_dev; + struct pktgen_dev *p, *pkt_dev = NULL; + if_lock(t); + + list_for_each_entry(p, &t->if_list, list) + if (strncmp(p->ifname, ifname, IFNAMSIZ) == 0) { + pkt_dev = p; + break; + } + + if_unlock(t); + PG_DEBUG(printk("pktgen: find_dev(%s) returning %p\n", ifname, pkt_dev)); + return pkt_dev; } /* * Adds a dev at front of if_list. */ -static int add_dev_to_thread(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) +static int add_dev_to_thread(struct pktgen_thread *t, + struct pktgen_dev *pkt_dev) { int rv = 0; - - if_lock(t); - - if (pkt_dev->pg_thread) { - printk("pktgen: ERROR: already assigned to a thread.\n"); - rv = -EBUSY; - goto out; - } - pkt_dev->next =t->if_list; t->if_list=pkt_dev; - pkt_dev->pg_thread = t; + + if_lock(t); + + if (pkt_dev->pg_thread) { + printk("pktgen: ERROR: already assigned to a thread.\n"); + rv = -EBUSY; + goto out; + } + + list_add(&pkt_dev->list, &t->if_list); + pkt_dev->pg_thread = t; pkt_dev->running = 0; - out: - if_unlock(t); - return rv; +out: + if_unlock(t); + return rv; } /* Called under thread lock */ -static int pktgen_add_device(struct pktgen_thread *t, const char* ifname) +static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) { - struct pktgen_dev *pkt_dev; + struct pktgen_dev *pkt_dev; struct proc_dir_entry *pe; - + /* We don't allow a device to be on several threads */ pkt_dev = __pktgen_NN_threads(ifname, FIND); if (pkt_dev) { - printk("pktgen: ERROR: interface already used.\n"); - return -EBUSY; - } + printk("pktgen: ERROR: interface already used.\n"); + return -EBUSY; + } pkt_dev = kzalloc(sizeof(struct pktgen_dev), GFP_KERNEL); if (!pkt_dev) return -ENOMEM; - pkt_dev->flows = vmalloc(MAX_CFLOWS*sizeof(struct flow_state)); + pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state)); if (pkt_dev->flows == NULL) { kfree(pkt_dev); return -ENOMEM; } - memset(pkt_dev->flows, 0, MAX_CFLOWS*sizeof(struct flow_state)); + memset(pkt_dev->flows, 0, MAX_CFLOWS * sizeof(struct flow_state)); + pkt_dev->removal_mark = 0; pkt_dev->min_pkt_size = ETH_ZLEN; pkt_dev->max_pkt_size = ETH_ZLEN; pkt_dev->nfrags = 0; @@ -2841,14 +3032,14 @@ static int pktgen_add_device(struct pktgen_thread *t, const char* ifname) pkt_dev->delay_ns = pg_delay_d % 1000; pkt_dev->count = pg_count_d; pkt_dev->sofar = 0; - pkt_dev->udp_src_min = 9; /* sink port */ + pkt_dev->udp_src_min = 9; /* sink port */ pkt_dev->udp_src_max = 9; pkt_dev->udp_dst_min = 9; pkt_dev->udp_dst_max = 9; strncpy(pkt_dev->ifname, ifname, IFNAMSIZ); - if (! pktgen_setup_dev(pkt_dev)) { + if (!pktgen_setup_dev(pkt_dev)) { printk("pktgen: ERROR: pktgen_setup_dev failed.\n"); if (pkt_dev->flows) vfree(pkt_dev->flows); @@ -2871,65 +3062,74 @@ static int pktgen_add_device(struct pktgen_thread *t, const char* ifname) return add_dev_to_thread(t, pkt_dev); } -static struct pktgen_thread * __init pktgen_find_thread(const char* name) +static struct pktgen_thread *__init pktgen_find_thread(const char *name) { - struct pktgen_thread *t = NULL; + struct pktgen_thread *t; - thread_lock(); + mutex_lock(&pktgen_thread_lock); - t = pktgen_threads; - while (t) { - if (strcmp(t->name, name) == 0) - break; + list_for_each_entry(t, &pktgen_threads, th_list) + if (strcmp(t->name, name) == 0) { + mutex_unlock(&pktgen_thread_lock); + return t; + } - t = t->next; - } - thread_unlock(); - return t; + mutex_unlock(&pktgen_thread_lock); + return NULL; } -static int __init pktgen_create_thread(const char* name, int cpu) +static int __init pktgen_create_thread(const char *name, int cpu) { - struct pktgen_thread *t = NULL; + int err; + struct pktgen_thread *t = NULL; struct proc_dir_entry *pe; - if (strlen(name) > 31) { - printk("pktgen: ERROR: Thread name cannot be more than 31 characters.\n"); - return -EINVAL; - } - - if (pktgen_find_thread(name)) { - printk("pktgen: ERROR: thread: %s already exists\n", name); - return -EINVAL; - } - - t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL); - if (!t) { - printk("pktgen: ERROR: out of memory, can't create new thread.\n"); - return -ENOMEM; - } - - strcpy(t->name, name); - spin_lock_init(&t->if_lock); + if (strlen(name) > 31) { + printk("pktgen: ERROR: Thread name cannot be more than 31 characters.\n"); + return -EINVAL; + } + + if (pktgen_find_thread(name)) { + printk("pktgen: ERROR: thread: %s already exists\n", name); + return -EINVAL; + } + + t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL); + if (!t) { + printk("pktgen: ERROR: out of memory, can't create new thread.\n"); + return -ENOMEM; + } + + strcpy(t->name, name); + spin_lock_init(&t->if_lock); t->cpu = cpu; - - pe = create_proc_entry(t->name, 0600, pg_proc_dir); - if (!pe) { - printk("pktgen: cannot create %s/%s procfs entry.\n", + + pe = create_proc_entry(t->name, 0600, pg_proc_dir); + if (!pe) { + printk("pktgen: cannot create %s/%s procfs entry.\n", PG_PROC_DIR, t->name); - kfree(t); - return -EINVAL; - } + kfree(t); + return -EINVAL; + } pe->proc_fops = &pktgen_thread_fops; pe->data = t; - t->next = pktgen_threads; - pktgen_threads = t; + INIT_LIST_HEAD(&t->if_list); - if (kernel_thread((void *) pktgen_thread_worker, (void *) t, - CLONE_FS | CLONE_FILES | CLONE_SIGHAND) < 0) + list_add_tail(&t->th_list, &pktgen_threads); + + t->removed = 0; + + err = kernel_thread((void *)pktgen_thread_worker, (void *)t, + CLONE_FS | CLONE_FILES | CLONE_SIGHAND); + if (err < 0) { printk("pktgen: kernel_thread() failed for cpu %d\n", t->cpu); + remove_proc_entry(t->name, pg_proc_dir); + list_del(&t->th_list); + kfree(t); + return err; + } return 0; } @@ -2937,55 +3137,52 @@ static int __init pktgen_create_thread(const char* name, int cpu) /* * Removes a device from the thread if_list. */ -static void _rem_dev_from_if_list(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) +static void _rem_dev_from_if_list(struct pktgen_thread *t, + struct pktgen_dev *pkt_dev) { - struct pktgen_dev *i, *prev = NULL; - - i = t->if_list; + struct list_head *q, *n; + struct pktgen_dev *p; - while(i) { - if(i == pkt_dev) { - if(prev) prev->next = i->next; - else t->if_list = NULL; - break; - } - prev = i; - i=i->next; + list_for_each_safe(q, n, &t->if_list) { + p = list_entry(q, struct pktgen_dev, list); + if (p == pkt_dev) + list_del(&p->list); } } -static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) +static int pktgen_remove_device(struct pktgen_thread *t, + struct pktgen_dev *pkt_dev) { PG_DEBUG(printk("pktgen: remove_device pkt_dev=%p\n", pkt_dev)); - if (pkt_dev->running) { - printk("pktgen:WARNING: trying to remove a running interface, stopping it now.\n"); - pktgen_stop_device(pkt_dev); - } - - /* Dis-associate from the interface */ + if (pkt_dev->running) { + printk("pktgen:WARNING: trying to remove a running interface, stopping it now.\n"); + pktgen_stop_device(pkt_dev); + } + + /* Dis-associate from the interface */ if (pkt_dev->odev) { dev_put(pkt_dev->odev); - pkt_dev->odev = NULL; - } - + pkt_dev->odev = NULL; + } + /* And update the thread if_list */ _rem_dev_from_if_list(t, pkt_dev); - /* Clean up proc file system */ + /* Clean up proc file system */ remove_proc_entry(pkt_dev->ifname, pg_proc_dir); if (pkt_dev->flows) vfree(pkt_dev->flows); kfree(pkt_dev); - return 0; + return 0; } -static int __init pg_init(void) +static int __init pg_init(void) { int cpu; struct proc_dir_entry *pe; @@ -2998,50 +3195,65 @@ static int __init pg_init(void) pg_proc_dir->owner = THIS_MODULE; pe = create_proc_entry(PGCTRL, 0600, pg_proc_dir); - if (pe == NULL) { - printk("pktgen: ERROR: cannot create %s procfs entry.\n", PGCTRL); + if (pe == NULL) { + printk("pktgen: ERROR: cannot create %s procfs entry.\n", + PGCTRL); proc_net_remove(PG_PROC_DIR); - return -EINVAL; - } + return -EINVAL; + } - pe->proc_fops = &pktgen_fops; - pe->data = NULL; + pe->proc_fops = &pktgen_fops; + pe->data = NULL; /* Register us to receive netdevice events */ register_netdevice_notifier(&pktgen_notifier_block); - + for_each_online_cpu(cpu) { + int err; char buf[30]; - sprintf(buf, "kpktgend_%i", cpu); - pktgen_create_thread(buf, cpu); - } - return 0; + sprintf(buf, "kpktgend_%i", cpu); + err = pktgen_create_thread(buf, cpu); + if (err) + printk("pktgen: WARNING: Cannot create thread for cpu %d (%d)\n", + cpu, err); + } + + if (list_empty(&pktgen_threads)) { + printk("pktgen: ERROR: Initialization failed for all threads\n"); + unregister_netdevice_notifier(&pktgen_notifier_block); + remove_proc_entry(PGCTRL, pg_proc_dir); + proc_net_remove(PG_PROC_DIR); + return -ENODEV; + } + + return 0; } static void __exit pg_cleanup(void) { + struct pktgen_thread *t; + struct list_head *q, *n; wait_queue_head_t queue; init_waitqueue_head(&queue); - /* Stop all interfaces & threads */ + /* Stop all interfaces & threads */ - while (pktgen_threads) { - struct pktgen_thread *t = pktgen_threads; - pktgen_threads->control |= (T_TERMINATE); + list_for_each_safe(q, n, &pktgen_threads) { + t = list_entry(q, struct pktgen_thread, th_list); + t->control |= (T_TERMINATE); - wait_event_interruptible_timeout(queue, (t != pktgen_threads), HZ); - } + wait_event_interruptible_timeout(queue, (t->removed == 1), HZ); + } - /* Un-register us from receiving netdevice events */ + /* Un-register us from receiving netdevice events */ unregister_netdevice_notifier(&pktgen_notifier_block); - /* Clean up proc file system */ + /* Clean up proc file system */ remove_proc_entry(PGCTRL, pg_proc_dir); proc_net_remove(PG_PROC_DIR); } - module_init(pg_init); module_exit(pg_cleanup); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eca2976abb25..ae10d3740faa 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -35,6 +35,7 @@ #include <linux/skbuff.h> #include <linux/init.h> #include <linux/security.h> +#include <linux/mutex.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -51,25 +52,31 @@ #include <net/pkt_sched.h> #include <net/netlink.h> -DECLARE_MUTEX(rtnl_sem); +static DEFINE_MUTEX(rtnl_mutex); void rtnl_lock(void) { - rtnl_shlock(); + mutex_lock(&rtnl_mutex); } -int rtnl_lock_interruptible(void) +void __rtnl_unlock(void) { - return down_interruptible(&rtnl_sem); + mutex_unlock(&rtnl_mutex); } - + void rtnl_unlock(void) { - rtnl_shunlock(); - + mutex_unlock(&rtnl_mutex); + if (rtnl && rtnl->sk_receive_queue.qlen) + rtnl->sk_data_ready(rtnl, 0); netdev_run_todo(); } +int rtnl_trylock(void) +{ + return mutex_trylock(&rtnl_mutex); +} + int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len) { memset(tb, 0, sizeof(struct rtattr*)*maxattr); @@ -179,6 +186,33 @@ rtattr_failure: } +static void set_operstate(struct net_device *dev, unsigned char transition) +{ + unsigned char operstate = dev->operstate; + + switch(transition) { + case IF_OPER_UP: + if ((operstate == IF_OPER_DORMANT || + operstate == IF_OPER_UNKNOWN) && + !netif_dormant(dev)) + operstate = IF_OPER_UP; + break; + + case IF_OPER_DORMANT: + if (operstate == IF_OPER_UP || + operstate == IF_OPER_UNKNOWN) + operstate = IF_OPER_DORMANT; + break; + }; + + if (dev->operstate != operstate) { + write_lock_bh(&dev_base_lock); + dev->operstate = operstate; + write_unlock_bh(&dev_base_lock); + netdev_state_change(dev); + } +} + static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags) @@ -209,6 +243,13 @@ static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, } if (1) { + u8 operstate = netif_running(dev)?dev->operstate:IF_OPER_DOWN; + u8 link_mode = dev->link_mode; + RTA_PUT(skb, IFLA_OPERSTATE, sizeof(operstate), &operstate); + RTA_PUT(skb, IFLA_LINKMODE, sizeof(link_mode), &link_mode); + } + + if (1) { struct rtnl_link_ifmap map = { .mem_start = dev->mem_start, .mem_end = dev->mem_end, @@ -399,6 +440,22 @@ static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) dev->weight = *((u32 *) RTA_DATA(ida[IFLA_WEIGHT - 1])); } + if (ida[IFLA_OPERSTATE - 1]) { + if (ida[IFLA_OPERSTATE - 1]->rta_len != RTA_LENGTH(sizeof(u8))) + goto out; + + set_operstate(dev, *((u8 *) RTA_DATA(ida[IFLA_OPERSTATE - 1]))); + } + + if (ida[IFLA_LINKMODE - 1]) { + if (ida[IFLA_LINKMODE - 1]->rta_len != RTA_LENGTH(sizeof(u8))) + goto out; + + write_lock_bh(&dev_base_lock); + dev->link_mode = *((u8 *) RTA_DATA(ida[IFLA_LINKMODE - 1])); + write_unlock_bh(&dev_base_lock); + } + if (ifm->ifi_index >= 0 && ida[IFLA_IFNAME - 1]) { char ifname[IFNAMSIZ]; @@ -575,9 +632,9 @@ static void rtnetlink_rcv(struct sock *sk, int len) unsigned int qlen = 0; do { - rtnl_lock(); + mutex_lock(&rtnl_mutex); netlink_run_queue(sk, &qlen, &rtnetlink_rcv_msg); - up(&rtnl_sem); + mutex_unlock(&rtnl_mutex); netdev_run_todo(); } while (qlen); @@ -654,6 +711,5 @@ EXPORT_SYMBOL(rtnetlink_links); EXPORT_SYMBOL(rtnetlink_put_metrics); EXPORT_SYMBOL(rtnl); EXPORT_SYMBOL(rtnl_lock); -EXPORT_SYMBOL(rtnl_lock_interruptible); -EXPORT_SYMBOL(rtnl_sem); +EXPORT_SYMBOL(rtnl_trylock); EXPORT_SYMBOL(rtnl_unlock); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2144952d1c6c..c9f878454531 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -356,6 +356,24 @@ void __kfree_skb(struct sk_buff *skb) } /** + * kfree_skb - free an sk_buff + * @skb: buffer to free + * + * Drop a reference to the buffer and free it if the usage count has + * hit zero. + */ +void kfree_skb(struct sk_buff *skb) +{ + if (unlikely(!skb)) + return; + if (likely(atomic_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!atomic_dec_and_test(&skb->users))) + return; + __kfree_skb(skb); +} + +/** * skb_clone - duplicate an sk_buff * @skb: buffer to clone * @gfp_mask: allocation priority @@ -1777,6 +1795,29 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, return 0; } +/** + * skb_pull_rcsum - pull skb and update receive checksum + * @skb: buffer to update + * @start: start of data before pull + * @len: length of data pulled + * + * This function performs an skb_pull on the packet and updates + * update the CHECKSUM_HW checksum. It should be used on receive + * path processing instead of skb_pull unless you know that the + * checksum difference is zero (e.g., a valid IP header) or you + * are setting ip_summed to CHECKSUM_NONE. + */ +unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) +{ + BUG_ON(len > skb->len); + skb->len -= len; + BUG_ON(skb->len < skb->data_len); + skb_postpull_rcsum(skb, skb->data, len); + return skb->data += len; +} + +EXPORT_SYMBOL_GPL(skb_pull_rcsum); + void __init skb_init(void) { skbuff_head_cache = kmem_cache_create("skbuff_head_cache", @@ -1799,6 +1840,7 @@ void __init skb_init(void) EXPORT_SYMBOL(___pskb_trim); EXPORT_SYMBOL(__kfree_skb); +EXPORT_SYMBOL(kfree_skb); EXPORT_SYMBOL(__pskb_pull_tail); EXPORT_SYMBOL(__alloc_skb); EXPORT_SYMBOL(pskb_copy); diff --git a/net/core/sock.c b/net/core/sock.c index 6e00811d44bc..1a7e6eac90b0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -616,7 +616,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PEERSEC: - return security_socket_getpeersec(sock, optval, optlen, len); + return security_socket_getpeersec_stream(sock, optval, optlen, len); default: return(-ENOPROTOOPT); @@ -1385,6 +1385,20 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname, EXPORT_SYMBOL(sock_common_getsockopt); +#ifdef CONFIG_COMPAT +int compat_sock_common_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct sock *sk = sock->sk; + + if (sk->sk_prot->compat_setsockopt != NULL) + return sk->sk_prot->compat_getsockopt(sk, level, optname, + optval, optlen); + return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen); +} +EXPORT_SYMBOL(compat_sock_common_getsockopt); +#endif + int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { @@ -1414,6 +1428,20 @@ int sock_common_setsockopt(struct socket *sock, int level, int optname, EXPORT_SYMBOL(sock_common_setsockopt); +#ifdef CONFIG_COMPAT +int compat_sock_common_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, int optlen) +{ + struct sock *sk = sock->sk; + + if (sk->sk_prot->compat_setsockopt != NULL) + return sk->sk_prot->compat_setsockopt(sk, level, optname, + optval, optlen); + return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen); +} +EXPORT_SYMBOL(compat_sock_common_setsockopt); +#endif + void sk_common_release(struct sock *sk) { if (sk->sk_prot->destroy) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 2f278c8e4743..710453656721 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -26,6 +26,11 @@ extern int sysctl_core_destroy_delay; extern char sysctl_divert_version[]; #endif /* CONFIG_NET_DIVERT */ +#ifdef CONFIG_XFRM +extern u32 sysctl_xfrm_aevent_etime; +extern u32 sysctl_xfrm_aevent_rseqth; +#endif + ctl_table core_table[] = { #ifdef CONFIG_NET { @@ -111,6 +116,24 @@ ctl_table core_table[] = { .proc_handler = &proc_dostring }, #endif /* CONFIG_NET_DIVERT */ +#ifdef CONFIG_XFRM + { + .ctl_name = NET_CORE_AEVENT_ETIME, + .procname = "xfrm_aevent_etime", + .data = &sysctl_xfrm_aevent_etime, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = &proc_dointvec + }, + { + .ctl_name = NET_CORE_AEVENT_RSEQTH, + .procname = "xfrm_aevent_rseqth", + .data = &sysctl_xfrm_aevent_rseqth, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = &proc_dointvec + }, +#endif /* CONFIG_XFRM */ #endif /* CONFIG_NET */ { .ctl_name = NET_CORE_SOMAXCONN, diff --git a/net/dccp/Kconfig b/net/dccp/Kconfig index 187ac182e24b..7e096ba8454f 100644 --- a/net/dccp/Kconfig +++ b/net/dccp/Kconfig @@ -24,6 +24,10 @@ config INET_DCCP_DIAG def_tristate y if (IP_DCCP = y && INET_DIAG = y) def_tristate m +config IP_DCCP_ACKVEC + depends on IP_DCCP + def_bool N + source "net/dccp/ccids/Kconfig" menu "DCCP Kernel Hacking" @@ -36,15 +40,6 @@ config IP_DCCP_DEBUG Just say N. -config IP_DCCP_UNLOAD_HACK - depends on IP_DCCP=m && IP_DCCP_CCID3=m - bool "DCCP control sock unload hack" - ---help--- - Enable this to be able to unload the dccp module when the it - has only one refcount held, the control sock one. Just execute - "rmmod dccp_ccid3 dccp" - - Just say N. endmenu endmenu diff --git a/net/dccp/Makefile b/net/dccp/Makefile index 87b27fff6e3b..7696e219b05d 100644 --- a/net/dccp/Makefile +++ b/net/dccp/Makefile @@ -2,15 +2,18 @@ obj-$(CONFIG_IPV6) += dccp_ipv6.o dccp_ipv6-y := ipv6.o -obj-$(CONFIG_IP_DCCP) += dccp.o +obj-$(CONFIG_IP_DCCP) += dccp.o dccp_ipv4.o -dccp-y := ccid.o input.o ipv4.o minisocks.o options.o output.o proto.o \ - timer.o +dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o + +dccp_ipv4-y := ipv4.o dccp-$(CONFIG_IP_DCCP_ACKVEC) += ackvec.o obj-$(CONFIG_INET_DCCP_DIAG) += dccp_diag.o +dccp-$(CONFIG_SYSCTL) += sysctl.o + dccp_diag-y := diag.o obj-y += ccids/ diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 2c77dafbd091..b5981e5f6b00 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -13,36 +13,83 @@ #include "dccp.h" #include <linux/dccp.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/kernel.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <net/sock.h> +static kmem_cache_t *dccp_ackvec_slab; +static kmem_cache_t *dccp_ackvec_record_slab; + +static struct dccp_ackvec_record *dccp_ackvec_record_new(void) +{ + struct dccp_ackvec_record *avr = + kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC); + + if (avr != NULL) + INIT_LIST_HEAD(&avr->dccpavr_node); + + return avr; +} + +static void dccp_ackvec_record_delete(struct dccp_ackvec_record *avr) +{ + if (unlikely(avr == NULL)) + return; + /* Check if deleting a linked record */ + WARN_ON(!list_empty(&avr->dccpavr_node)); + kmem_cache_free(dccp_ackvec_record_slab, avr); +} + +static void dccp_ackvec_insert_avr(struct dccp_ackvec *av, + struct dccp_ackvec_record *avr) +{ + /* + * AVRs are sorted by seqno. Since we are sending them in order, we + * just add the AVR at the head of the list. + * -sorbo. + */ + if (!list_empty(&av->dccpav_records)) { + const struct dccp_ackvec_record *head = + list_entry(av->dccpav_records.next, + struct dccp_ackvec_record, + dccpavr_node); + BUG_ON(before48(avr->dccpavr_ack_seqno, + head->dccpavr_ack_seqno)); + } + + list_add(&avr->dccpavr_node, &av->dccpav_records); +} + int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); +#ifdef CONFIG_IP_DCCP_DEBUG + const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? + "CLIENT tx: " : "server tx: "; +#endif struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; int len = av->dccpav_vec_len + 2; struct timeval now; u32 elapsed_time; unsigned char *to, *from; + struct dccp_ackvec_record *avr; + + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + return -1; dccp_timestamp(sk, &now); elapsed_time = timeval_delta(&now, &av->dccpav_time) / 10; - if (elapsed_time != 0) - dccp_insert_option_elapsed_time(sk, skb, elapsed_time); - - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + if (elapsed_time != 0 && + dccp_insert_option_elapsed_time(sk, skb, elapsed_time)) return -1; - /* - * XXX: now we have just one ack vector sent record, so - * we have to wait for it to be cleared. - * - * Of course this is not acceptable, but this is just for - * basic testing now. - */ - if (av->dccpav_ack_seqno != DCCP_MAX_SEQNO + 1) + avr = dccp_ackvec_record_new(); + if (avr == NULL) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; @@ -55,8 +102,8 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) from = av->dccpav_buf + av->dccpav_buf_head; /* Check if buf_head wraps */ - if ((int)av->dccpav_buf_head + len > av->dccpav_vec_len) { - const u32 tailsize = av->dccpav_vec_len - av->dccpav_buf_head; + if ((int)av->dccpav_buf_head + len > DCCP_MAX_ACKVEC_LEN) { + const u32 tailsize = DCCP_MAX_ACKVEC_LEN - av->dccpav_buf_head; memcpy(to, from, tailsize); to += tailsize; @@ -73,45 +120,37 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) * sequence number it used for the ack packet; ack_ptr will equal * buf_head; ack_ackno will equal buf_ackno; and ack_nonce will * equal buf_nonce. - * - * This implemention uses just one ack record for now. */ - av->dccpav_ack_seqno = DCCP_SKB_CB(skb)->dccpd_seq; - av->dccpav_ack_ptr = av->dccpav_buf_head; - av->dccpav_ack_ackno = av->dccpav_buf_ackno; - av->dccpav_ack_nonce = av->dccpav_buf_nonce; - av->dccpav_sent_len = av->dccpav_vec_len; + avr->dccpavr_ack_seqno = DCCP_SKB_CB(skb)->dccpd_seq; + avr->dccpavr_ack_ptr = av->dccpav_buf_head; + avr->dccpavr_ack_ackno = av->dccpav_buf_ackno; + avr->dccpavr_ack_nonce = av->dccpav_buf_nonce; + avr->dccpavr_sent_len = av->dccpav_vec_len; + + dccp_ackvec_insert_avr(av, avr); dccp_pr_debug("%sACK Vector 0, len=%d, ack_seqno=%llu, " "ack_ackno=%llu\n", - debug_prefix, av->dccpav_sent_len, - (unsigned long long)av->dccpav_ack_seqno, - (unsigned long long)av->dccpav_ack_ackno); - return -1; + debug_prefix, avr->dccpavr_sent_len, + (unsigned long long)avr->dccpavr_ack_seqno, + (unsigned long long)avr->dccpavr_ack_ackno); + return 0; } -struct dccp_ackvec *dccp_ackvec_alloc(const unsigned int len, - const gfp_t priority) +struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) { - struct dccp_ackvec *av; - - BUG_ON(len == 0); + struct dccp_ackvec *av = kmem_cache_alloc(dccp_ackvec_slab, priority); - if (len > DCCP_MAX_ACKVEC_LEN) - return NULL; - - av = kmalloc(sizeof(*av) + len, priority); if (av != NULL) { - av->dccpav_buf_len = len; av->dccpav_buf_head = - av->dccpav_buf_tail = av->dccpav_buf_len - 1; - av->dccpav_buf_ackno = - av->dccpav_ack_ackno = av->dccpav_ack_seqno = ~0LLU; + av->dccpav_buf_tail = DCCP_MAX_ACKVEC_LEN - 1; + av->dccpav_buf_ackno = DCCP_MAX_SEQNO + 1; av->dccpav_buf_nonce = av->dccpav_buf_nonce = 0; av->dccpav_ack_ptr = 0; av->dccpav_time.tv_sec = 0; av->dccpav_time.tv_usec = 0; av->dccpav_sent_len = av->dccpav_vec_len = 0; + INIT_LIST_HEAD(&av->dccpav_records); } return av; @@ -119,7 +158,20 @@ struct dccp_ackvec *dccp_ackvec_alloc(const unsigned int len, void dccp_ackvec_free(struct dccp_ackvec *av) { - kfree(av); + if (unlikely(av == NULL)) + return; + + if (!list_empty(&av->dccpav_records)) { + struct dccp_ackvec_record *avr, *next; + + list_for_each_entry_safe(avr, next, &av->dccpav_records, + dccpavr_node) { + list_del_init(&avr->dccpavr_node); + dccp_ackvec_record_delete(avr); + } + } + + kmem_cache_free(dccp_ackvec_slab, av); } static inline u8 dccp_ackvec_state(const struct dccp_ackvec *av, @@ -146,7 +198,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, unsigned int gap; long new_head; - if (av->dccpav_vec_len + packets > av->dccpav_buf_len) + if (av->dccpav_vec_len + packets > DCCP_MAX_ACKVEC_LEN) return -ENOBUFS; gap = packets - 1; @@ -158,7 +210,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, gap + new_head + 1); gap = -new_head; } - new_head += av->dccpav_buf_len; + new_head += DCCP_MAX_ACKVEC_LEN; } av->dccpav_buf_head = new_head; @@ -251,7 +303,7 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, goto out_duplicate; delta -= len + 1; - if (++index == av->dccpav_buf_len) + if (++index == DCCP_MAX_ACKVEC_LEN) index = 0; } } @@ -259,7 +311,6 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, av->dccpav_buf_ackno = ackno; dccp_timestamp(sk, &av->dccpav_time); out: - dccp_pr_debug(""); return 0; out_duplicate: @@ -297,44 +348,50 @@ void dccp_ackvec_print(const struct dccp_ackvec *av) } #endif -static void dccp_ackvec_throw_away_ack_record(struct dccp_ackvec *av) +static void dccp_ackvec_throw_record(struct dccp_ackvec *av, + struct dccp_ackvec_record *avr) { - /* - * As we're keeping track of the ack vector size (dccpav_vec_len) and - * the sent ack vector size (dccpav_sent_len) we don't need - * dccpav_buf_tail at all, but keep this code here as in the future - * we'll implement a vector of ack records, as suggested in - * draft-ietf-dccp-spec-11.txt Appendix A. -acme - */ -#if 0 - u32 new_buf_tail = av->dccpav_ack_ptr + 1; - if (new_buf_tail >= av->dccpav_vec_len) - new_buf_tail -= av->dccpav_vec_len; - av->dccpav_buf_tail = new_buf_tail; -#endif - av->dccpav_vec_len -= av->dccpav_sent_len; + struct dccp_ackvec_record *next; + + av->dccpav_buf_tail = avr->dccpavr_ack_ptr - 1; + if (av->dccpav_buf_tail == 0) + av->dccpav_buf_tail = DCCP_MAX_ACKVEC_LEN - 1; + + av->dccpav_vec_len -= avr->dccpavr_sent_len; + + /* free records */ + list_for_each_entry_safe_from(avr, next, &av->dccpav_records, + dccpavr_node) { + list_del_init(&avr->dccpavr_node); + dccp_ackvec_record_delete(avr); + } } void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, const u64 ackno) { - /* Check if we actually sent an ACK vector */ - if (av->dccpav_ack_seqno == DCCP_MAX_SEQNO + 1) - return; + struct dccp_ackvec_record *avr; - if (ackno == av->dccpav_ack_seqno) { + /* + * If we traverse backwards, it should be faster when we have large + * windows. We will be receiving ACKs for stuff we sent a while back + * -sorbo. + */ + list_for_each_entry_reverse(avr, &av->dccpav_records, dccpavr_node) { + if (ackno == avr->dccpavr_ack_seqno) { #ifdef CONFIG_IP_DCCP_DEBUG - struct dccp_sock *dp = dccp_sk(sk); - const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? - "CLIENT rx ack: " : "server rx ack: "; + struct dccp_sock *dp = dccp_sk(sk); + const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? + "CLIENT rx ack: " : "server rx ack: "; #endif - dccp_pr_debug("%sACK packet 0, len=%d, ack_seqno=%llu, " - "ack_ackno=%llu, ACKED!\n", - debug_prefix, 1, - (unsigned long long)av->dccpav_ack_seqno, - (unsigned long long)av->dccpav_ack_ackno); - dccp_ackvec_throw_away_ack_record(av); - av->dccpav_ack_seqno = DCCP_MAX_SEQNO + 1; + dccp_pr_debug("%sACK packet 0, len=%d, ack_seqno=%llu, " + "ack_ackno=%llu, ACKED!\n", + debug_prefix, 1, + (unsigned long long)avr->dccpavr_ack_seqno, + (unsigned long long)avr->dccpavr_ack_ackno); + dccp_ackvec_throw_record(av, avr); + break; + } } } @@ -344,28 +401,20 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, const unsigned char *vector) { unsigned char i; + struct dccp_ackvec_record *avr; /* Check if we actually sent an ACK vector */ - if (av->dccpav_ack_seqno == DCCP_MAX_SEQNO + 1) - return; - /* - * We're in the receiver half connection, so if the received an ACK - * vector ackno (e.g. 50) before dccpav_ack_seqno (e.g. 52), we're - * not interested. - * - * Extra explanation with example: - * - * if we received an ACK vector with ackno 50, it can only be acking - * 50, 49, 48, etc, not 52 (the seqno for the ACK vector we sent). - */ - /* dccp_pr_debug("is %llu < %llu? ", ackno, av->dccpav_ack_seqno); */ - if (before48(ackno, av->dccpav_ack_seqno)) { - /* dccp_pr_debug_cat("yes\n"); */ + if (list_empty(&av->dccpav_records)) return; - } - /* dccp_pr_debug_cat("no\n"); */ i = len; + /* + * XXX + * I think it might be more efficient to work backwards. See comment on + * rcv_ackno. -sorbo. + */ + avr = list_entry(av->dccpav_records.next, struct dccp_ackvec_record, + dccpavr_node); while (i--) { const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; u64 ackno_end_rl; @@ -373,14 +422,20 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, dccp_set_seqno(&ackno_end_rl, ackno - rl); /* - * dccp_pr_debug("is %llu <= %llu <= %llu? ", ackno_end_rl, - * av->dccpav_ack_seqno, ackno); + * If our AVR sequence number is greater than the ack, go + * forward in the AVR list until it is not so. */ - if (between48(av->dccpav_ack_seqno, ackno_end_rl, ackno)) { + list_for_each_entry_from(avr, &av->dccpav_records, + dccpavr_node) { + if (!after48(avr->dccpavr_ack_seqno, ackno)) + goto found; + } + /* End of the dccpav_records list, not found, exit */ + break; +found: + if (between48(avr->dccpavr_ack_seqno, ackno_end_rl, ackno)) { const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6; - /* dccp_pr_debug_cat("yes\n"); */ - if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED) { #ifdef CONFIG_IP_DCCP_DEBUG struct dccp_sock *dp = dccp_sk(sk); @@ -393,19 +448,16 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, "ACKED!\n", debug_prefix, len, (unsigned long long) - av->dccpav_ack_seqno, + avr->dccpavr_ack_seqno, (unsigned long long) - av->dccpav_ack_ackno); - dccp_ackvec_throw_away_ack_record(av); + avr->dccpavr_ack_ackno); + dccp_ackvec_throw_record(av, avr); } /* - * If dccpav_ack_seqno was not received, no problem - * we'll send another ACK vector. + * If it wasn't received, continue scanning... we might + * find another one. */ - av->dccpav_ack_seqno = DCCP_MAX_SEQNO + 1; - break; } - /* dccp_pr_debug_cat("no\n"); */ dccp_set_seqno(&ackno, ackno_end_rl - 1); ++vector; @@ -424,3 +476,43 @@ int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, len, value); return 0; } + +static char dccp_ackvec_slab_msg[] __initdata = + KERN_CRIT "DCCP: Unable to create ack vectors slab caches\n"; + +int __init dccp_ackvec_init(void) +{ + dccp_ackvec_slab = kmem_cache_create("dccp_ackvec", + sizeof(struct dccp_ackvec), 0, + SLAB_HWCACHE_ALIGN, NULL, NULL); + if (dccp_ackvec_slab == NULL) + goto out_err; + + dccp_ackvec_record_slab = + kmem_cache_create("dccp_ackvec_record", + sizeof(struct dccp_ackvec_record), + 0, SLAB_HWCACHE_ALIGN, NULL, NULL); + if (dccp_ackvec_record_slab == NULL) + goto out_destroy_slab; + + return 0; + +out_destroy_slab: + kmem_cache_destroy(dccp_ackvec_slab); + dccp_ackvec_slab = NULL; +out_err: + printk(dccp_ackvec_slab_msg); + return -ENOBUFS; +} + +void dccp_ackvec_exit(void) +{ + if (dccp_ackvec_slab != NULL) { + kmem_cache_destroy(dccp_ackvec_slab); + dccp_ackvec_slab = NULL; + } + if (dccp_ackvec_record_slab != NULL) { + kmem_cache_destroy(dccp_ackvec_record_slab); + dccp_ackvec_record_slab = NULL; + } +} diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index f7dfb5f67b87..ec7a89bb7b39 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -13,6 +13,7 @@ #include <linux/config.h> #include <linux/compiler.h> +#include <linux/list.h> #include <linux/time.h> #include <linux/types.h> @@ -42,39 +43,57 @@ * Ack Vectors it has recently sent. For each packet sent carrying an * Ack Vector, it remembers four variables: * - * @dccpav_ack_seqno - the Sequence Number used for the packet - * (HC-Receiver seqno) * @dccpav_ack_ptr - the value of buf_head at the time of acknowledgement. - * @dccpav_ack_ackno - the Acknowledgement Number used for the packet - * (HC-Sender seqno) + * @dccpav_records - list of dccp_ackvec_record * @dccpav_ack_nonce - the one-bit sum of the ECN Nonces for all State 0. * - * @dccpav_buf_len - circular buffer length * @dccpav_time - the time in usecs * @dccpav_buf - circular buffer of acknowledgeable packets */ struct dccp_ackvec { u64 dccpav_buf_ackno; - u64 dccpav_ack_seqno; - u64 dccpav_ack_ackno; + struct list_head dccpav_records; struct timeval dccpav_time; u8 dccpav_buf_head; u8 dccpav_buf_tail; u8 dccpav_ack_ptr; u8 dccpav_sent_len; u8 dccpav_vec_len; - u8 dccpav_buf_len; u8 dccpav_buf_nonce; u8 dccpav_ack_nonce; - u8 dccpav_buf[0]; + u8 dccpav_buf[DCCP_MAX_ACKVEC_LEN]; +}; + +/** struct dccp_ackvec_record - ack vector record + * + * ACK vector record as defined in Appendix A of spec. + * + * The list is sorted by dccpavr_ack_seqno + * + * @dccpavr_node - node in dccpav_records + * @dccpavr_ack_seqno - sequence number of the packet this record was sent on + * @dccpavr_ack_ackno - sequence number being acknowledged + * @dccpavr_ack_ptr - pointer into dccpav_buf where this record starts + * @dccpavr_ack_nonce - dccpav_ack_nonce at the time this record was sent + * @dccpavr_sent_len - lenght of the record in dccpav_buf + */ +struct dccp_ackvec_record { + struct list_head dccpavr_node; + u64 dccpavr_ack_seqno; + u64 dccpavr_ack_ackno; + u8 dccpavr_ack_ptr; + u8 dccpavr_ack_nonce; + u8 dccpavr_sent_len; }; struct sock; struct sk_buff; #ifdef CONFIG_IP_DCCP_ACKVEC -extern struct dccp_ackvec *dccp_ackvec_alloc(unsigned int len, - const gfp_t priority); +extern int dccp_ackvec_init(void); +extern void dccp_ackvec_exit(void); + +extern struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority); extern void dccp_ackvec_free(struct dccp_ackvec *av); extern int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, @@ -92,8 +111,16 @@ static inline int dccp_ackvec_pending(const struct dccp_ackvec *av) return av->dccpav_sent_len != av->dccpav_vec_len; } #else /* CONFIG_IP_DCCP_ACKVEC */ -static inline struct dccp_ackvec *dccp_ackvec_alloc(unsigned int len, - const gfp_t priority) +static inline int dccp_ackvec_init(void) +{ + return 0; +} + +static inline void dccp_ackvec_exit(void) +{ +} + +static inline struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) { return NULL; } diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 9d8fc0e289ea..ff05e59043cd 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -13,7 +13,7 @@ #include "ccid.h" -static struct ccid *ccids[CCID_MAX]; +static struct ccid_operations *ccids[CCID_MAX]; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) static atomic_t ccids_lockct = ATOMIC_INIT(0); static DEFINE_SPINLOCK(ccids_lock); @@ -55,85 +55,202 @@ static inline void ccids_read_unlock(void) #define ccids_read_unlock() do { } while(0) #endif -int ccid_register(struct ccid *ccid) +static kmem_cache_t *ccid_kmem_cache_create(int obj_size, const char *fmt,...) { - int err; + kmem_cache_t *slab; + char slab_name_fmt[32], *slab_name; + va_list args; - if (ccid->ccid_init == NULL) - return -1; + va_start(args, fmt); + vsnprintf(slab_name_fmt, sizeof(slab_name_fmt), fmt, args); + va_end(args); + + slab_name = kstrdup(slab_name_fmt, GFP_KERNEL); + if (slab_name == NULL) + return NULL; + slab = kmem_cache_create(slab_name, sizeof(struct ccid) + obj_size, 0, + SLAB_HWCACHE_ALIGN, NULL, NULL); + if (slab == NULL) + kfree(slab_name); + return slab; +} + +static void ccid_kmem_cache_destroy(kmem_cache_t *slab) +{ + if (slab != NULL) { + const char *name = kmem_cache_name(slab); + + kmem_cache_destroy(slab); + kfree(name); + } +} + +int ccid_register(struct ccid_operations *ccid_ops) +{ + int err = -ENOBUFS; + + ccid_ops->ccid_hc_rx_slab = + ccid_kmem_cache_create(ccid_ops->ccid_hc_rx_obj_size, + "%s_hc_rx_sock", + ccid_ops->ccid_name); + if (ccid_ops->ccid_hc_rx_slab == NULL) + goto out; + + ccid_ops->ccid_hc_tx_slab = + ccid_kmem_cache_create(ccid_ops->ccid_hc_tx_obj_size, + "%s_hc_tx_sock", + ccid_ops->ccid_name); + if (ccid_ops->ccid_hc_tx_slab == NULL) + goto out_free_rx_slab; ccids_write_lock(); err = -EEXIST; - if (ccids[ccid->ccid_id] == NULL) { - ccids[ccid->ccid_id] = ccid; + if (ccids[ccid_ops->ccid_id] == NULL) { + ccids[ccid_ops->ccid_id] = ccid_ops; err = 0; } ccids_write_unlock(); - if (err == 0) - pr_info("CCID: Registered CCID %d (%s)\n", - ccid->ccid_id, ccid->ccid_name); + if (err != 0) + goto out_free_tx_slab; + + pr_info("CCID: Registered CCID %d (%s)\n", + ccid_ops->ccid_id, ccid_ops->ccid_name); +out: return err; +out_free_tx_slab: + ccid_kmem_cache_destroy(ccid_ops->ccid_hc_tx_slab); + ccid_ops->ccid_hc_tx_slab = NULL; + goto out; +out_free_rx_slab: + ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab); + ccid_ops->ccid_hc_rx_slab = NULL; + goto out; } EXPORT_SYMBOL_GPL(ccid_register); -int ccid_unregister(struct ccid *ccid) +int ccid_unregister(struct ccid_operations *ccid_ops) { ccids_write_lock(); - ccids[ccid->ccid_id] = NULL; + ccids[ccid_ops->ccid_id] = NULL; ccids_write_unlock(); + + ccid_kmem_cache_destroy(ccid_ops->ccid_hc_tx_slab); + ccid_ops->ccid_hc_tx_slab = NULL; + ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab); + ccid_ops->ccid_hc_rx_slab = NULL; + pr_info("CCID: Unregistered CCID %d (%s)\n", - ccid->ccid_id, ccid->ccid_name); + ccid_ops->ccid_id, ccid_ops->ccid_name); return 0; } EXPORT_SYMBOL_GPL(ccid_unregister); -struct ccid *ccid_init(unsigned char id, struct sock *sk) +struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx, gfp_t gfp) { - struct ccid *ccid; + struct ccid_operations *ccid_ops; + struct ccid *ccid = NULL; + ccids_read_lock(); #ifdef CONFIG_KMOD - if (ccids[id] == NULL) + if (ccids[id] == NULL) { + /* We only try to load if in process context */ + ccids_read_unlock(); + if (gfp & GFP_ATOMIC) + goto out; request_module("net-dccp-ccid-%d", id); + ccids_read_lock(); + } #endif - ccids_read_lock(); + ccid_ops = ccids[id]; + if (ccid_ops == NULL) + goto out_unlock; - ccid = ccids[id]; - if (ccid == NULL) - goto out; + if (!try_module_get(ccid_ops->ccid_owner)) + goto out_unlock; - if (!try_module_get(ccid->ccid_owner)) - goto out_err; + ccids_read_unlock(); - if (ccid->ccid_init(sk) != 0) + ccid = kmem_cache_alloc(rx ? ccid_ops->ccid_hc_rx_slab : + ccid_ops->ccid_hc_tx_slab, gfp); + if (ccid == NULL) goto out_module_put; + ccid->ccid_ops = ccid_ops; + if (rx) { + memset(ccid + 1, 0, ccid_ops->ccid_hc_rx_obj_size); + if (ccid->ccid_ops->ccid_hc_rx_init != NULL && + ccid->ccid_ops->ccid_hc_rx_init(ccid, sk) != 0) + goto out_free_ccid; + } else { + memset(ccid + 1, 0, ccid_ops->ccid_hc_tx_obj_size); + if (ccid->ccid_ops->ccid_hc_tx_init != NULL && + ccid->ccid_ops->ccid_hc_tx_init(ccid, sk) != 0) + goto out_free_ccid; + } out: - ccids_read_unlock(); return ccid; -out_module_put: - module_put(ccid->ccid_owner); -out_err: +out_unlock: + ccids_read_unlock(); + goto out; +out_free_ccid: + kmem_cache_free(rx ? ccid_ops->ccid_hc_rx_slab : + ccid_ops->ccid_hc_tx_slab, ccid); ccid = NULL; +out_module_put: + module_put(ccid_ops->ccid_owner); goto out; } -EXPORT_SYMBOL_GPL(ccid_init); +EXPORT_SYMBOL_GPL(ccid_new); + +struct ccid *ccid_hc_rx_new(unsigned char id, struct sock *sk, gfp_t gfp) +{ + return ccid_new(id, sk, 1, gfp); +} + +EXPORT_SYMBOL_GPL(ccid_hc_rx_new); + +struct ccid *ccid_hc_tx_new(unsigned char id,struct sock *sk, gfp_t gfp) +{ + return ccid_new(id, sk, 0, gfp); +} + +EXPORT_SYMBOL_GPL(ccid_hc_tx_new); -void ccid_exit(struct ccid *ccid, struct sock *sk) +static void ccid_delete(struct ccid *ccid, struct sock *sk, int rx) { + struct ccid_operations *ccid_ops; + if (ccid == NULL) return; + ccid_ops = ccid->ccid_ops; + if (rx) { + if (ccid_ops->ccid_hc_rx_exit != NULL) + ccid_ops->ccid_hc_rx_exit(sk); + kmem_cache_free(ccid_ops->ccid_hc_rx_slab, ccid); + } else { + if (ccid_ops->ccid_hc_tx_exit != NULL) + ccid_ops->ccid_hc_tx_exit(sk); + kmem_cache_free(ccid_ops->ccid_hc_tx_slab, ccid); + } ccids_read_lock(); + if (ccids[ccid_ops->ccid_id] != NULL) + module_put(ccid_ops->ccid_owner); + ccids_read_unlock(); +} - if (ccids[ccid->ccid_id] != NULL) { - if (ccid->ccid_exit != NULL) - ccid->ccid_exit(sk); - module_put(ccid->ccid_owner); - } +void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk) +{ + ccid_delete(ccid, sk, 1); +} - ccids_read_unlock(); +EXPORT_SYMBOL_GPL(ccid_hc_rx_delete); + +void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk) +{ + ccid_delete(ccid, sk, 0); } -EXPORT_SYMBOL_GPL(ccid_exit); +EXPORT_SYMBOL_GPL(ccid_hc_tx_delete); diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index de681c6ad081..f7eb6c613414 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -23,14 +23,16 @@ struct tcp_info; -struct ccid { +struct ccid_operations { unsigned char ccid_id; const char *ccid_name; struct module *ccid_owner; - int (*ccid_init)(struct sock *sk); - void (*ccid_exit)(struct sock *sk); - int (*ccid_hc_rx_init)(struct sock *sk); - int (*ccid_hc_tx_init)(struct sock *sk); + kmem_cache_t *ccid_hc_rx_slab; + __u32 ccid_hc_rx_obj_size; + kmem_cache_t *ccid_hc_tx_slab; + __u32 ccid_hc_tx_obj_size; + int (*ccid_hc_rx_init)(struct ccid *ccid, struct sock *sk); + int (*ccid_hc_tx_init)(struct ccid *ccid, struct sock *sk); void (*ccid_hc_rx_exit)(struct sock *sk); void (*ccid_hc_tx_exit)(struct sock *sk); void (*ccid_hc_rx_packet_recv)(struct sock *sk, @@ -39,9 +41,9 @@ struct ccid { unsigned char option, unsigned char len, u16 idx, unsigned char* value); - void (*ccid_hc_rx_insert_options)(struct sock *sk, + int (*ccid_hc_rx_insert_options)(struct sock *sk, struct sk_buff *skb); - void (*ccid_hc_tx_insert_options)(struct sock *sk, + int (*ccid_hc_tx_insert_options)(struct sock *sk, struct sk_buff *skb); void (*ccid_hc_tx_packet_recv)(struct sock *sk, struct sk_buff *skb); @@ -67,75 +69,58 @@ struct ccid { int __user *optlen); }; -extern int ccid_register(struct ccid *ccid); -extern int ccid_unregister(struct ccid *ccid); +extern int ccid_register(struct ccid_operations *ccid_ops); +extern int ccid_unregister(struct ccid_operations *ccid_ops); -extern struct ccid *ccid_init(unsigned char id, struct sock *sk); -extern void ccid_exit(struct ccid *ccid, struct sock *sk); +struct ccid { + struct ccid_operations *ccid_ops; + char ccid_priv[0]; +}; -static inline void __ccid_get(struct ccid *ccid) +static inline void *ccid_priv(const struct ccid *ccid) { - __module_get(ccid->ccid_owner); + return (void *)ccid->ccid_priv; } +extern struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx, + gfp_t gfp); + +extern struct ccid *ccid_hc_rx_new(unsigned char id, struct sock *sk, + gfp_t gfp); +extern struct ccid *ccid_hc_tx_new(unsigned char id, struct sock *sk, + gfp_t gfp); + +extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk); +extern void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk); + static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk, struct sk_buff *skb, int len) { int rc = 0; - if (ccid->ccid_hc_tx_send_packet != NULL) - rc = ccid->ccid_hc_tx_send_packet(sk, skb, len); + if (ccid->ccid_ops->ccid_hc_tx_send_packet != NULL) + rc = ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb, len); return rc; } static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk, int more, int len) { - if (ccid->ccid_hc_tx_packet_sent != NULL) - ccid->ccid_hc_tx_packet_sent(sk, more, len); -} - -static inline int ccid_hc_rx_init(struct ccid *ccid, struct sock *sk) -{ - int rc = 0; - if (ccid->ccid_hc_rx_init != NULL) - rc = ccid->ccid_hc_rx_init(sk); - return rc; -} - -static inline int ccid_hc_tx_init(struct ccid *ccid, struct sock *sk) -{ - int rc = 0; - if (ccid->ccid_hc_tx_init != NULL) - rc = ccid->ccid_hc_tx_init(sk); - return rc; -} - -static inline void ccid_hc_rx_exit(struct ccid *ccid, struct sock *sk) -{ - if (ccid != NULL && ccid->ccid_hc_rx_exit != NULL && - dccp_sk(sk)->dccps_hc_rx_ccid_private != NULL) - ccid->ccid_hc_rx_exit(sk); -} - -static inline void ccid_hc_tx_exit(struct ccid *ccid, struct sock *sk) -{ - if (ccid != NULL && ccid->ccid_hc_tx_exit != NULL && - dccp_sk(sk)->dccps_hc_tx_ccid_private != NULL) - ccid->ccid_hc_tx_exit(sk); + if (ccid->ccid_ops->ccid_hc_tx_packet_sent != NULL) + ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, more, len); } static inline void ccid_hc_rx_packet_recv(struct ccid *ccid, struct sock *sk, struct sk_buff *skb) { - if (ccid->ccid_hc_rx_packet_recv != NULL) - ccid->ccid_hc_rx_packet_recv(sk, skb); + if (ccid->ccid_ops->ccid_hc_rx_packet_recv != NULL) + ccid->ccid_ops->ccid_hc_rx_packet_recv(sk, skb); } static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, struct sk_buff *skb) { - if (ccid->ccid_hc_tx_packet_recv != NULL) - ccid->ccid_hc_tx_packet_recv(sk, skb); + if (ccid->ccid_ops->ccid_hc_tx_packet_recv != NULL) + ccid->ccid_ops->ccid_hc_tx_packet_recv(sk, skb); } static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, @@ -144,8 +129,8 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, unsigned char* value) { int rc = 0; - if (ccid->ccid_hc_tx_parse_options != NULL) - rc = ccid->ccid_hc_tx_parse_options(sk, option, len, idx, + if (ccid->ccid_ops->ccid_hc_tx_parse_options != NULL) + rc = ccid->ccid_ops->ccid_hc_tx_parse_options(sk, option, len, idx, value); return rc; } @@ -156,37 +141,39 @@ static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, unsigned char* value) { int rc = 0; - if (ccid->ccid_hc_rx_parse_options != NULL) - rc = ccid->ccid_hc_rx_parse_options(sk, option, len, idx, value); + if (ccid->ccid_ops->ccid_hc_rx_parse_options != NULL) + rc = ccid->ccid_ops->ccid_hc_rx_parse_options(sk, option, len, idx, value); return rc; } -static inline void ccid_hc_tx_insert_options(struct ccid *ccid, struct sock *sk, - struct sk_buff *skb) +static inline int ccid_hc_tx_insert_options(struct ccid *ccid, struct sock *sk, + struct sk_buff *skb) { - if (ccid->ccid_hc_tx_insert_options != NULL) - ccid->ccid_hc_tx_insert_options(sk, skb); + if (ccid->ccid_ops->ccid_hc_tx_insert_options != NULL) + return ccid->ccid_ops->ccid_hc_tx_insert_options(sk, skb); + return 0; } -static inline void ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk, - struct sk_buff *skb) +static inline int ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk, + struct sk_buff *skb) { - if (ccid->ccid_hc_rx_insert_options != NULL) - ccid->ccid_hc_rx_insert_options(sk, skb); + if (ccid->ccid_ops->ccid_hc_rx_insert_options != NULL) + return ccid->ccid_ops->ccid_hc_rx_insert_options(sk, skb); + return 0; } static inline void ccid_hc_rx_get_info(struct ccid *ccid, struct sock *sk, struct tcp_info *info) { - if (ccid->ccid_hc_rx_get_info != NULL) - ccid->ccid_hc_rx_get_info(sk, info); + if (ccid->ccid_ops->ccid_hc_rx_get_info != NULL) + ccid->ccid_ops->ccid_hc_rx_get_info(sk, info); } static inline void ccid_hc_tx_get_info(struct ccid *ccid, struct sock *sk, struct tcp_info *info) { - if (ccid->ccid_hc_tx_get_info != NULL) - ccid->ccid_hc_tx_get_info(sk, info); + if (ccid->ccid_ops->ccid_hc_tx_get_info != NULL) + ccid->ccid_ops->ccid_hc_tx_get_info(sk, info); } static inline int ccid_hc_rx_getsockopt(struct ccid *ccid, struct sock *sk, @@ -194,8 +181,8 @@ static inline int ccid_hc_rx_getsockopt(struct ccid *ccid, struct sock *sk, u32 __user *optval, int __user *optlen) { int rc = -ENOPROTOOPT; - if (ccid->ccid_hc_rx_getsockopt != NULL) - rc = ccid->ccid_hc_rx_getsockopt(sk, optname, len, + if (ccid->ccid_ops->ccid_hc_rx_getsockopt != NULL) + rc = ccid->ccid_ops->ccid_hc_rx_getsockopt(sk, optname, len, optval, optlen); return rc; } @@ -205,8 +192,8 @@ static inline int ccid_hc_tx_getsockopt(struct ccid *ccid, struct sock *sk, u32 __user *optval, int __user *optlen) { int rc = -ENOPROTOOPT; - if (ccid->ccid_hc_tx_getsockopt != NULL) - rc = ccid->ccid_hc_tx_getsockopt(sk, optname, len, + if (ccid->ccid_ops->ccid_hc_tx_getsockopt != NULL) + rc = ccid->ccid_ops->ccid_hc_tx_getsockopt(sk, optname, len, optval, optlen); return rc; } diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig index 7684d83946a4..ca00191628f7 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -1,9 +1,39 @@ menu "DCCP CCIDs Configuration (EXPERIMENTAL)" depends on IP_DCCP && EXPERIMENTAL +config IP_DCCP_CCID2 + tristate "CCID2 (TCP-Like) (EXPERIMENTAL)" + depends on IP_DCCP + def_tristate IP_DCCP + select IP_DCCP_ACKVEC + ---help--- + CCID 2, TCP-like Congestion Control, denotes Additive Increase, + Multiplicative Decrease (AIMD) congestion control with behavior + modelled directly on TCP, including congestion window, slow start, + timeouts, and so forth [RFC 2581]. CCID 2 achieves maximum + bandwidth over the long term, consistent with the use of end-to-end + congestion control, but halves its congestion window in response to + each congestion event. This leads to the abrupt rate changes + typical of TCP. Applications should use CCID 2 if they prefer + maximum bandwidth utilization to steadiness of rate. This is often + the case for applications that are not playing their data directly + to the user. For example, a hypothetical application that + transferred files over DCCP, using application-level retransmissions + for lost packets, would prefer CCID 2 to CCID 3. On-line games may + also prefer CCID 2. + + CCID 2 is further described in: + http://www.icir.org/kohler/dccp/draft-ietf-dccp-ccid2-10.txt + + This text was extracted from: + http://www.icir.org/kohler/dccp/draft-ietf-dccp-spec-13.txt + + If in doubt, say M. + config IP_DCCP_CCID3 - tristate "CCID3 (TFRC) (EXPERIMENTAL)" + tristate "CCID3 (TCP-Friendly) (EXPERIMENTAL)" depends on IP_DCCP + def_tristate IP_DCCP ---help--- CCID 3 denotes TCP-Friendly Rate Control (TFRC), an equation-based rate-controlled congestion control mechanism. TFRC is designed to @@ -15,10 +45,15 @@ config IP_DCCP_CCID3 suitable than CCID 2 for applications such streaming media where a relatively smooth sending rate is of importance. - CCID 3 is further described in [CCID 3 PROFILE]. The TFRC - congestion control algorithms were initially described in RFC 3448. + CCID 3 is further described in: + + http://www.icir.org/kohler/dccp/draft-ietf-dccp-ccid3-11.txt. + + The TFRC congestion control algorithms were initially described in + RFC 3448. - This text was extracted from draft-ietf-dccp-spec-11.txt. + This text was extracted from: + http://www.icir.org/kohler/dccp/draft-ietf-dccp-spec-13.txt If in doubt, say M. diff --git a/net/dccp/ccids/Makefile b/net/dccp/ccids/Makefile index 956f79f50743..438f20bccff7 100644 --- a/net/dccp/ccids/Makefile +++ b/net/dccp/ccids/Makefile @@ -2,4 +2,8 @@ obj-$(CONFIG_IP_DCCP_CCID3) += dccp_ccid3.o dccp_ccid3-y := ccid3.o +obj-$(CONFIG_IP_DCCP_CCID2) += dccp_ccid2.o + +dccp_ccid2-y := ccid2.o + obj-y += lib/ diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c new file mode 100644 index 000000000000..d4f9e2d33453 --- /dev/null +++ b/net/dccp/ccids/ccid2.c @@ -0,0 +1,779 @@ +/* + * net/dccp/ccids/ccid2.c + * + * Copyright (c) 2005, 2006 Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * + * Changes to meet Linux coding standards, and DCCP infrastructure fixes. + * + * Copyright (c) 2006 Arnaldo Carvalho de Melo <acme@conectiva.com.br> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +/* + * This implementation should follow: draft-ietf-dccp-ccid2-10.txt + * + * BUGS: + * - sequence number wrapping + * - jiffies wrapping + */ + +#include <linux/config.h> +#include "../ccid.h" +#include "../dccp.h" +#include "ccid2.h" + +static int ccid2_debug; + +#undef CCID2_DEBUG +#ifdef CCID2_DEBUG +#define ccid2_pr_debug(format, a...) \ + do { if (ccid2_debug) \ + printk(KERN_DEBUG "%s: " format, __FUNCTION__, ##a); \ + } while (0) +#else +#define ccid2_pr_debug(format, a...) +#endif + +static const int ccid2_seq_len = 128; + +#ifdef CCID2_DEBUG +static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) +{ + int len = 0; + int pipe = 0; + struct ccid2_seq *seqp = hctx->ccid2hctx_seqh; + + /* there is data in the chain */ + if (seqp != hctx->ccid2hctx_seqt) { + seqp = seqp->ccid2s_prev; + len++; + if (!seqp->ccid2s_acked) + pipe++; + + while (seqp != hctx->ccid2hctx_seqt) { + struct ccid2_seq *prev = seqp->ccid2s_prev; + + len++; + if (!prev->ccid2s_acked) + pipe++; + + /* packets are sent sequentially */ + BUG_ON(seqp->ccid2s_seq <= prev->ccid2s_seq); + BUG_ON(seqp->ccid2s_sent < prev->ccid2s_sent); + BUG_ON(len > ccid2_seq_len); + + seqp = prev; + } + } + + BUG_ON(pipe != hctx->ccid2hctx_pipe); + ccid2_pr_debug("len of chain=%d\n", len); + + do { + seqp = seqp->ccid2s_prev; + len++; + BUG_ON(len > ccid2_seq_len); + } while (seqp != hctx->ccid2hctx_seqh); + + BUG_ON(len != ccid2_seq_len); + ccid2_pr_debug("total len=%d\n", len); +} +#else +#define ccid2_hc_tx_check_sanity(hctx) do {} while (0) +#endif + +static int ccid2_hc_tx_send_packet(struct sock *sk, + struct sk_buff *skb, int len) +{ + struct ccid2_hc_tx_sock *hctx; + + switch (DCCP_SKB_CB(skb)->dccpd_type) { + case 0: /* XXX data packets from userland come through like this */ + case DCCP_PKT_DATA: + case DCCP_PKT_DATAACK: + break; + /* No congestion control on other packets */ + default: + return 0; + } + + hctx = ccid2_hc_tx_sk(sk); + + ccid2_pr_debug("pipe=%d cwnd=%d\n", hctx->ccid2hctx_pipe, + hctx->ccid2hctx_cwnd); + + if (hctx->ccid2hctx_pipe < hctx->ccid2hctx_cwnd) { + /* OK we can send... make sure previous packet was sent off */ + if (!hctx->ccid2hctx_sendwait) { + hctx->ccid2hctx_sendwait = 1; + return 0; + } + } + + return 100; /* XXX */ +} + +static void ccid2_change_l_ack_ratio(struct sock *sk, int val) +{ + struct dccp_sock *dp = dccp_sk(sk); + /* + * XXX I don't really agree with val != 2. If cwnd is 1, ack ratio + * should be 1... it shouldn't be allowed to become 2. + * -sorbo. + */ + if (val != 2) { + const struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + int max = hctx->ccid2hctx_cwnd / 2; + + /* round up */ + if (hctx->ccid2hctx_cwnd & 1) + max++; + + if (val > max) + val = max; + } + + ccid2_pr_debug("changing local ack ratio to %d\n", val); + WARN_ON(val <= 0); + dp->dccps_l_ack_ratio = val; +} + +static void ccid2_change_cwnd(struct sock *sk, int val) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + if (val == 0) + val = 1; + + /* XXX do we need to change ack ratio? */ + ccid2_pr_debug("change cwnd to %d\n", val); + + BUG_ON(val < 1); + hctx->ccid2hctx_cwnd = val; +} + +static void ccid2_start_rto_timer(struct sock *sk); + +static void ccid2_hc_tx_rto_expire(unsigned long data) +{ + struct sock *sk = (struct sock *)data; + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + long s; + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer, + jiffies + HZ / 5); + goto out; + } + + ccid2_pr_debug("RTO_EXPIRE\n"); + + ccid2_hc_tx_check_sanity(hctx); + + /* back-off timer */ + hctx->ccid2hctx_rto <<= 1; + + s = hctx->ccid2hctx_rto / HZ; + if (s > 60) + hctx->ccid2hctx_rto = 60 * HZ; + + ccid2_start_rto_timer(sk); + + /* adjust pipe, cwnd etc */ + hctx->ccid2hctx_pipe = 0; + hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd >> 1; + if (hctx->ccid2hctx_ssthresh < 2) + hctx->ccid2hctx_ssthresh = 2; + ccid2_change_cwnd(sk, 1); + + /* clear state about stuff we sent */ + hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh; + hctx->ccid2hctx_ssacks = 0; + hctx->ccid2hctx_acks = 0; + hctx->ccid2hctx_sent = 0; + + /* clear ack ratio state. */ + hctx->ccid2hctx_arsent = 0; + hctx->ccid2hctx_ackloss = 0; + hctx->ccid2hctx_rpseq = 0; + hctx->ccid2hctx_rpdupack = -1; + ccid2_change_l_ack_ratio(sk, 1); + ccid2_hc_tx_check_sanity(hctx); +out: + bh_unlock_sock(sk); + sock_put(sk); +} + +static void ccid2_start_rto_timer(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + ccid2_pr_debug("setting RTO timeout=%ld\n", hctx->ccid2hctx_rto); + + BUG_ON(timer_pending(&hctx->ccid2hctx_rtotimer)); + sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer, + jiffies + hctx->ccid2hctx_rto); +} + +static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + u64 seq; + + ccid2_hc_tx_check_sanity(hctx); + + BUG_ON(!hctx->ccid2hctx_sendwait); + hctx->ccid2hctx_sendwait = 0; + hctx->ccid2hctx_pipe++; + BUG_ON(hctx->ccid2hctx_pipe < 0); + + /* There is an issue. What if another packet is sent between + * packet_send() and packet_sent(). Then the sequence number would be + * wrong. + * -sorbo. + */ + seq = dp->dccps_gss; + + hctx->ccid2hctx_seqh->ccid2s_seq = seq; + hctx->ccid2hctx_seqh->ccid2s_acked = 0; + hctx->ccid2hctx_seqh->ccid2s_sent = jiffies; + hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqh->ccid2s_next; + + ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd, + hctx->ccid2hctx_pipe); + + if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt) { + /* XXX allocate more space */ + WARN_ON(1); + } + + hctx->ccid2hctx_sent++; + + /* Ack Ratio. Need to maintain a concept of how many windows we sent */ + hctx->ccid2hctx_arsent++; + /* We had an ack loss in this window... */ + if (hctx->ccid2hctx_ackloss) { + if (hctx->ccid2hctx_arsent >= hctx->ccid2hctx_cwnd) { + hctx->ccid2hctx_arsent = 0; + hctx->ccid2hctx_ackloss = 0; + } + } else { + /* No acks lost up to now... */ + /* decrease ack ratio if enough packets were sent */ + if (dp->dccps_l_ack_ratio > 1) { + /* XXX don't calculate denominator each time */ + int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio - + dp->dccps_l_ack_ratio; + + denom = hctx->ccid2hctx_cwnd * hctx->ccid2hctx_cwnd / denom; + + if (hctx->ccid2hctx_arsent >= denom) { + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1); + hctx->ccid2hctx_arsent = 0; + } + } else { + /* we can't increase ack ratio further [1] */ + hctx->ccid2hctx_arsent = 0; /* or maybe set it to cwnd*/ + } + } + + /* setup RTO timer */ + if (!timer_pending(&hctx->ccid2hctx_rtotimer)) + ccid2_start_rto_timer(sk); + +#ifdef CCID2_DEBUG + ccid2_pr_debug("pipe=%d\n", hctx->ccid2hctx_pipe); + ccid2_pr_debug("Sent: seq=%llu\n", seq); + do { + struct ccid2_seq *seqp = hctx->ccid2hctx_seqt; + + while (seqp != hctx->ccid2hctx_seqh) { + ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n", + seqp->ccid2s_seq, seqp->ccid2s_acked, + seqp->ccid2s_sent); + seqp = seqp->ccid2s_next; + } + } while (0); + ccid2_pr_debug("=========\n"); + ccid2_hc_tx_check_sanity(hctx); +#endif +} + +/* XXX Lame code duplication! + * returns -1 if none was found. + * else returns the next offset to use in the function call. + */ +static int ccid2_ackvector(struct sock *sk, struct sk_buff *skb, int offset, + unsigned char **vec, unsigned char *veclen) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); + unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb); + unsigned char *opt_ptr; + const unsigned char *opt_end = (unsigned char *)dh + + (dh->dccph_doff * 4); + unsigned char opt, len; + unsigned char *value; + + BUG_ON(offset < 0); + options += offset; + opt_ptr = options; + if (opt_ptr >= opt_end) + return -1; + + while (opt_ptr != opt_end) { + opt = *opt_ptr++; + len = 0; + value = NULL; + + /* Check if this isn't a single byte option */ + if (opt > DCCPO_MAX_RESERVED) { + if (opt_ptr == opt_end) + goto out_invalid_option; + + len = *opt_ptr++; + if (len < 3) + goto out_invalid_option; + /* + * Remove the type and len fields, leaving + * just the value size + */ + len -= 2; + value = opt_ptr; + opt_ptr += len; + + if (opt_ptr > opt_end) + goto out_invalid_option; + } + + switch (opt) { + case DCCPO_ACK_VECTOR_0: + case DCCPO_ACK_VECTOR_1: + *vec = value; + *veclen = len; + return offset + (opt_ptr - options); + } + } + + return -1; + +out_invalid_option: + BUG_ON(1); /* should never happen... options were previously parsed ! */ + return -1; +} + +static void ccid2_hc_tx_kill_rto_timer(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + sk_stop_timer(sk, &hctx->ccid2hctx_rtotimer); + ccid2_pr_debug("deleted RTO timer\n"); +} + +static inline void ccid2_new_ack(struct sock *sk, + struct ccid2_seq *seqp, + unsigned int *maxincr) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + /* slow start */ + if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh) { + hctx->ccid2hctx_acks = 0; + + /* We can increase cwnd at most maxincr [ack_ratio/2] */ + if (*maxincr) { + /* increase every 2 acks */ + hctx->ccid2hctx_ssacks++; + if (hctx->ccid2hctx_ssacks == 2) { + ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1); + hctx->ccid2hctx_ssacks = 0; + *maxincr = *maxincr - 1; + } + } else { + /* increased cwnd enough for this single ack */ + hctx->ccid2hctx_ssacks = 0; + } + } else { + hctx->ccid2hctx_ssacks = 0; + hctx->ccid2hctx_acks++; + + if (hctx->ccid2hctx_acks >= hctx->ccid2hctx_cwnd) { + ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1); + hctx->ccid2hctx_acks = 0; + } + } + + /* update RTO */ + if (hctx->ccid2hctx_srtt == -1 || + (jiffies - hctx->ccid2hctx_lastrtt) >= hctx->ccid2hctx_srtt) { + unsigned long r = jiffies - seqp->ccid2s_sent; + int s; + + /* first measurement */ + if (hctx->ccid2hctx_srtt == -1) { + ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n", + r, jiffies, seqp->ccid2s_seq); + hctx->ccid2hctx_srtt = r; + hctx->ccid2hctx_rttvar = r >> 1; + } else { + /* RTTVAR */ + long tmp = hctx->ccid2hctx_srtt - r; + if (tmp < 0) + tmp *= -1; + + tmp >>= 2; + hctx->ccid2hctx_rttvar *= 3; + hctx->ccid2hctx_rttvar >>= 2; + hctx->ccid2hctx_rttvar += tmp; + + /* SRTT */ + hctx->ccid2hctx_srtt *= 7; + hctx->ccid2hctx_srtt >>= 3; + tmp = r >> 3; + hctx->ccid2hctx_srtt += tmp; + } + s = hctx->ccid2hctx_rttvar << 2; + /* clock granularity is 1 when based on jiffies */ + if (!s) + s = 1; + hctx->ccid2hctx_rto = hctx->ccid2hctx_srtt + s; + + /* must be at least a second */ + s = hctx->ccid2hctx_rto / HZ; + /* DCCP doesn't require this [but I like it cuz my code sux] */ +#if 1 + if (s < 1) + hctx->ccid2hctx_rto = HZ; +#endif + /* max 60 seconds */ + if (s > 60) + hctx->ccid2hctx_rto = HZ * 60; + + hctx->ccid2hctx_lastrtt = jiffies; + + ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n", + hctx->ccid2hctx_srtt, hctx->ccid2hctx_rttvar, + hctx->ccid2hctx_rto, HZ, r); + hctx->ccid2hctx_sent = 0; + } + + /* we got a new ack, so re-start RTO timer */ + ccid2_hc_tx_kill_rto_timer(sk); + ccid2_start_rto_timer(sk); +} + +static void ccid2_hc_tx_dec_pipe(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + hctx->ccid2hctx_pipe--; + BUG_ON(hctx->ccid2hctx_pipe < 0); + + if (hctx->ccid2hctx_pipe == 0) + ccid2_hc_tx_kill_rto_timer(sk); +} + +static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + u64 ackno, seqno; + struct ccid2_seq *seqp; + unsigned char *vector; + unsigned char veclen; + int offset = 0; + int done = 0; + int loss = 0; + unsigned int maxincr = 0; + + ccid2_hc_tx_check_sanity(hctx); + /* check reverse path congestion */ + seqno = DCCP_SKB_CB(skb)->dccpd_seq; + + /* XXX this whole "algorithm" is broken. Need to fix it to keep track + * of the seqnos of the dupacks so that rpseq and rpdupack are correct + * -sorbo. + */ + /* need to bootstrap */ + if (hctx->ccid2hctx_rpdupack == -1) { + hctx->ccid2hctx_rpdupack = 0; + hctx->ccid2hctx_rpseq = seqno; + } else { + /* check if packet is consecutive */ + if ((hctx->ccid2hctx_rpseq + 1) == seqno) + hctx->ccid2hctx_rpseq++; + /* it's a later packet */ + else if (after48(seqno, hctx->ccid2hctx_rpseq)) { + hctx->ccid2hctx_rpdupack++; + + /* check if we got enough dupacks */ + if (hctx->ccid2hctx_rpdupack >= + hctx->ccid2hctx_numdupack) { + hctx->ccid2hctx_rpdupack = -1; /* XXX lame */ + hctx->ccid2hctx_rpseq = 0; + + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio << 1); + } + } + } + + /* check forward path congestion */ + /* still didn't send out new data packets */ + if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt) + return; + + switch (DCCP_SKB_CB(skb)->dccpd_type) { + case DCCP_PKT_ACK: + case DCCP_PKT_DATAACK: + break; + default: + return; + } + + ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq; + seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + + /* If in slow-start, cwnd can increase at most Ack Ratio / 2 packets for + * this single ack. I round up. + * -sorbo. + */ + maxincr = dp->dccps_l_ack_ratio >> 1; + maxincr++; + + /* go through all ack vectors */ + while ((offset = ccid2_ackvector(sk, skb, offset, + &vector, &veclen)) != -1) { + /* go through this ack vector */ + while (veclen--) { + const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; + u64 ackno_end_rl; + + dccp_set_seqno(&ackno_end_rl, ackno - rl); + ccid2_pr_debug("ackvec start:%llu end:%llu\n", ackno, + ackno_end_rl); + /* if the seqno we are analyzing is larger than the + * current ackno, then move towards the tail of our + * seqnos. + */ + while (after48(seqp->ccid2s_seq, ackno)) { + if (seqp == hctx->ccid2hctx_seqt) { + done = 1; + break; + } + seqp = seqp->ccid2s_prev; + } + if (done) + break; + + /* check all seqnos in the range of the vector + * run length + */ + while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) { + const u8 state = (*vector & + DCCP_ACKVEC_STATE_MASK) >> 6; + + /* new packet received or marked */ + if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED && + !seqp->ccid2s_acked) { + if (state == + DCCP_ACKVEC_STATE_ECN_MARKED) { + loss = 1; + } else + ccid2_new_ack(sk, seqp, + &maxincr); + + seqp->ccid2s_acked = 1; + ccid2_pr_debug("Got ack for %llu\n", + seqp->ccid2s_seq); + ccid2_hc_tx_dec_pipe(sk); + } + if (seqp == hctx->ccid2hctx_seqt) { + done = 1; + break; + } + seqp = seqp->ccid2s_next; + } + if (done) + break; + + + dccp_set_seqno(&ackno, ackno_end_rl - 1); + vector++; + } + if (done) + break; + } + + /* The state about what is acked should be correct now + * Check for NUMDUPACK + */ + seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + done = 0; + while (1) { + if (seqp->ccid2s_acked) { + done++; + if (done == hctx->ccid2hctx_numdupack) + break; + } + if (seqp == hctx->ccid2hctx_seqt) + break; + seqp = seqp->ccid2s_prev; + } + + /* If there are at least 3 acknowledgements, anything unacknowledged + * below the last sequence number is considered lost + */ + if (done == hctx->ccid2hctx_numdupack) { + struct ccid2_seq *last_acked = seqp; + + /* check for lost packets */ + while (1) { + if (!seqp->ccid2s_acked) { + loss = 1; + ccid2_hc_tx_dec_pipe(sk); + } + if (seqp == hctx->ccid2hctx_seqt) + break; + seqp = seqp->ccid2s_prev; + } + + hctx->ccid2hctx_seqt = last_acked; + } + + /* trim acked packets in tail */ + while (hctx->ccid2hctx_seqt != hctx->ccid2hctx_seqh) { + if (!hctx->ccid2hctx_seqt->ccid2s_acked) + break; + + hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqt->ccid2s_next; + } + + if (loss) { + /* XXX do bit shifts guarantee a 0 as the new bit? */ + ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd >> 1); + hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd; + if (hctx->ccid2hctx_ssthresh < 2) + hctx->ccid2hctx_ssthresh = 2; + } + + ccid2_hc_tx_check_sanity(hctx); +} + +static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid_priv(ccid); + int seqcount = ccid2_seq_len; + int i; + + /* XXX init variables with proper values */ + hctx->ccid2hctx_cwnd = 1; + hctx->ccid2hctx_ssthresh = 10; + hctx->ccid2hctx_numdupack = 3; + + /* XXX init ~ to window size... */ + hctx->ccid2hctx_seqbuf = kmalloc(sizeof(*hctx->ccid2hctx_seqbuf) * + seqcount, gfp_any()); + if (hctx->ccid2hctx_seqbuf == NULL) + return -ENOMEM; + + for (i = 0; i < (seqcount - 1); i++) { + hctx->ccid2hctx_seqbuf[i].ccid2s_next = + &hctx->ccid2hctx_seqbuf[i + 1]; + hctx->ccid2hctx_seqbuf[i + 1].ccid2s_prev = + &hctx->ccid2hctx_seqbuf[i]; + } + hctx->ccid2hctx_seqbuf[seqcount - 1].ccid2s_next = + hctx->ccid2hctx_seqbuf; + hctx->ccid2hctx_seqbuf->ccid2s_prev = + &hctx->ccid2hctx_seqbuf[seqcount - 1]; + + hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqbuf; + hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh; + hctx->ccid2hctx_sent = 0; + hctx->ccid2hctx_rto = 3 * HZ; + hctx->ccid2hctx_srtt = -1; + hctx->ccid2hctx_rttvar = -1; + hctx->ccid2hctx_lastrtt = 0; + hctx->ccid2hctx_rpdupack = -1; + + hctx->ccid2hctx_rtotimer.function = &ccid2_hc_tx_rto_expire; + hctx->ccid2hctx_rtotimer.data = (unsigned long)sk; + init_timer(&hctx->ccid2hctx_rtotimer); + + ccid2_hc_tx_check_sanity(hctx); + return 0; +} + +static void ccid2_hc_tx_exit(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + + ccid2_hc_tx_kill_rto_timer(sk); + kfree(hctx->ccid2hctx_seqbuf); + hctx->ccid2hctx_seqbuf = NULL; +} + +static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) +{ + const struct dccp_sock *dp = dccp_sk(sk); + struct ccid2_hc_rx_sock *hcrx = ccid2_hc_rx_sk(sk); + + switch (DCCP_SKB_CB(skb)->dccpd_type) { + case DCCP_PKT_DATA: + case DCCP_PKT_DATAACK: + hcrx->ccid2hcrx_data++; + if (hcrx->ccid2hcrx_data >= dp->dccps_r_ack_ratio) { + dccp_send_ack(sk); + hcrx->ccid2hcrx_data = 0; + } + break; + } +} + +static struct ccid_operations ccid2 = { + .ccid_id = 2, + .ccid_name = "ccid2", + .ccid_owner = THIS_MODULE, + .ccid_hc_tx_obj_size = sizeof(struct ccid2_hc_tx_sock), + .ccid_hc_tx_init = ccid2_hc_tx_init, + .ccid_hc_tx_exit = ccid2_hc_tx_exit, + .ccid_hc_tx_send_packet = ccid2_hc_tx_send_packet, + .ccid_hc_tx_packet_sent = ccid2_hc_tx_packet_sent, + .ccid_hc_tx_packet_recv = ccid2_hc_tx_packet_recv, + .ccid_hc_rx_obj_size = sizeof(struct ccid2_hc_rx_sock), + .ccid_hc_rx_packet_recv = ccid2_hc_rx_packet_recv, +}; + +module_param(ccid2_debug, int, 0444); +MODULE_PARM_DESC(ccid2_debug, "Enable debug messages"); + +static __init int ccid2_module_init(void) +{ + return ccid_register(&ccid2); +} +module_init(ccid2_module_init); + +static __exit void ccid2_module_exit(void) +{ + ccid_unregister(&ccid2); +} +module_exit(ccid2_module_exit); + +MODULE_AUTHOR("Andrea Bittau <a.bittau@cs.ucl.ac.uk>"); +MODULE_DESCRIPTION("DCCP TCP-Like (CCID2) CCID"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("net-dccp-ccid-2"); diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h new file mode 100644 index 000000000000..451a87464fa5 --- /dev/null +++ b/net/dccp/ccids/ccid2.h @@ -0,0 +1,85 @@ +/* + * net/dccp/ccids/ccid2.h + * + * Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ +#ifndef _DCCP_CCID2_H_ +#define _DCCP_CCID2_H_ + +#include <linux/dccp.h> +#include <linux/timer.h> +#include <linux/types.h> +#include "../ccid.h" + +struct sock; + +struct ccid2_seq { + u64 ccid2s_seq; + unsigned long ccid2s_sent; + int ccid2s_acked; + struct ccid2_seq *ccid2s_prev; + struct ccid2_seq *ccid2s_next; +}; + +/** struct ccid2_hc_tx_sock - CCID2 TX half connection + * + * @ccid2hctx_ssacks - ACKs recv in slow start + * @ccid2hctx_acks - ACKS recv in AI phase + * @ccid2hctx_sent - packets sent in this window + * @ccid2hctx_lastrtt -time RTT was last measured + * @ccid2hctx_arsent - packets sent [ack ratio] + * @ccid2hctx_ackloss - ack was lost in this win + * @ccid2hctx_rpseq - last consecutive seqno + * @ccid2hctx_rpdupack - dupacks since rpseq +*/ +struct ccid2_hc_tx_sock { + int ccid2hctx_cwnd; + int ccid2hctx_ssacks; + int ccid2hctx_acks; + int ccid2hctx_ssthresh; + int ccid2hctx_pipe; + int ccid2hctx_numdupack; + struct ccid2_seq *ccid2hctx_seqbuf; + struct ccid2_seq *ccid2hctx_seqh; + struct ccid2_seq *ccid2hctx_seqt; + long ccid2hctx_rto; + long ccid2hctx_srtt; + long ccid2hctx_rttvar; + int ccid2hctx_sent; + unsigned long ccid2hctx_lastrtt; + struct timer_list ccid2hctx_rtotimer; + unsigned long ccid2hctx_arsent; + int ccid2hctx_ackloss; + u64 ccid2hctx_rpseq; + int ccid2hctx_rpdupack; + int ccid2hctx_sendwait; +}; + +struct ccid2_hc_rx_sock { + int ccid2hcrx_data; +}; + +static inline struct ccid2_hc_tx_sock *ccid2_hc_tx_sk(const struct sock *sk) +{ + return ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid); +} + +static inline struct ccid2_hc_rx_sock *ccid2_hc_rx_sk(const struct sock *sk) +{ + return ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid); +} +#endif /* _DCCP_CCID2_H_ */ diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 35d1d347541c..b4a51d0355a5 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -46,7 +46,7 @@ * Reason for maths here is to avoid 32 bit overflow when a is big. * With this we get close to the limit. */ -static inline u32 usecs_div(const u32 a, const u32 b) +static u32 usecs_div(const u32 a, const u32 b) { const u32 div = a < (UINT_MAX / (USEC_PER_SEC / 10)) ? 10 : a < (UINT_MAX / (USEC_PER_SEC / 50)) ? 50 : @@ -76,15 +76,6 @@ static struct dccp_tx_hist *ccid3_tx_hist; static struct dccp_rx_hist *ccid3_rx_hist; static struct dccp_li_hist *ccid3_li_hist; -static int ccid3_init(struct sock *sk) -{ - return 0; -} - -static void ccid3_exit(struct sock *sk) -{ -} - /* TFRC sender states */ enum ccid3_hc_tx_states { TFRC_SSTATE_NO_SENT = 1, @@ -107,8 +98,8 @@ static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) } #endif -static inline void ccid3_hc_tx_set_state(struct sock *sk, - enum ccid3_hc_tx_states state) +static void ccid3_hc_tx_set_state(struct sock *sk, + enum ccid3_hc_tx_states state) { struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); enum ccid3_hc_tx_states oldstate = hctx->ccid3hctx_state; @@ -316,8 +307,6 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, switch (hctx->ccid3hctx_state) { case TFRC_SSTATE_NO_SENT: - hctx->ccid3hctx_no_feedback_timer.function = ccid3_hc_tx_no_feedback_timer; - hctx->ccid3hctx_no_feedback_timer.data = (unsigned long)sk; sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer, jiffies + usecs_to_jiffies(TFRC_INITIAL_TIMEOUT)); hctx->ccid3hctx_last_win_count = 0; @@ -585,16 +574,15 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) } } -static void ccid3_hc_tx_insert_options(struct sock *sk, struct sk_buff *skb) +static int ccid3_hc_tx_insert_options(struct sock *sk, struct sk_buff *skb) { const struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); BUG_ON(hctx == NULL); - if (!(sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN)) - return; - - DCCP_SKB_CB(skb)->dccpd_ccval = hctx->ccid3hctx_last_win_count; + if (sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN) + DCCP_SKB_CB(skb)->dccpd_ccval = hctx->ccid3hctx_last_win_count; + return 0; } static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, @@ -626,7 +614,7 @@ static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, __FUNCTION__, dccp_role(sk), sk); rc = -EINVAL; } else { - opt_recv->ccid3or_loss_event_rate = ntohl(*(u32 *)value); + opt_recv->ccid3or_loss_event_rate = ntohl(*(__be32 *)value); ccid3_pr_debug("%s, sk=%p, LOSS_EVENT_RATE=%u\n", dccp_role(sk), sk, opt_recv->ccid3or_loss_event_rate); @@ -647,7 +635,7 @@ static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, __FUNCTION__, dccp_role(sk), sk); rc = -EINVAL; } else { - opt_recv->ccid3or_receive_rate = ntohl(*(u32 *)value); + opt_recv->ccid3or_receive_rate = ntohl(*(__be32 *)value); ccid3_pr_debug("%s, sk=%p, RECEIVE_RATE=%u\n", dccp_role(sk), sk, opt_recv->ccid3or_receive_rate); @@ -658,17 +646,10 @@ static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, return rc; } -static int ccid3_hc_tx_init(struct sock *sk) +static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_tx_sock *hctx; - - dp->dccps_hc_tx_ccid_private = kmalloc(sizeof(*hctx), gfp_any()); - if (dp->dccps_hc_tx_ccid_private == NULL) - return -ENOMEM; - - hctx = ccid3_hc_tx_sk(sk); - memset(hctx, 0, sizeof(*hctx)); + struct ccid3_hc_tx_sock *hctx = ccid_priv(ccid); if (dp->dccps_packet_size >= TFRC_MIN_PACKET_SIZE && dp->dccps_packet_size <= TFRC_MAX_PACKET_SIZE) @@ -681,6 +662,9 @@ static int ccid3_hc_tx_init(struct sock *sk) hctx->ccid3hctx_t_rto = USEC_PER_SEC; hctx->ccid3hctx_state = TFRC_SSTATE_NO_SENT; INIT_LIST_HEAD(&hctx->ccid3hctx_hist); + + hctx->ccid3hctx_no_feedback_timer.function = ccid3_hc_tx_no_feedback_timer; + hctx->ccid3hctx_no_feedback_timer.data = (unsigned long)sk; init_timer(&hctx->ccid3hctx_no_feedback_timer); return 0; @@ -688,7 +672,6 @@ static int ccid3_hc_tx_init(struct sock *sk) static void ccid3_hc_tx_exit(struct sock *sk) { - struct dccp_sock *dp = dccp_sk(sk); struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); BUG_ON(hctx == NULL); @@ -698,9 +681,6 @@ static void ccid3_hc_tx_exit(struct sock *sk) /* Empty packet history */ dccp_tx_hist_purge(ccid3_tx_hist, &hctx->ccid3hctx_hist); - - kfree(dp->dccps_hc_tx_ccid_private); - dp->dccps_hc_tx_ccid_private = NULL; } /* @@ -727,8 +707,8 @@ static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) } #endif -static inline void ccid3_hc_rx_set_state(struct sock *sk, - enum ccid3_hc_rx_states state) +static void ccid3_hc_rx_set_state(struct sock *sk, + enum ccid3_hc_rx_states state) { struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); enum ccid3_hc_rx_states oldstate = hcrx->ccid3hcrx_state; @@ -793,31 +773,35 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk) dccp_send_ack(sk); } -static void ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) +static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) { const struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); - u32 x_recv, pinv; + __be32 x_recv, pinv; BUG_ON(hcrx == NULL); if (!(sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN)) - return; + return 0; DCCP_SKB_CB(skb)->dccpd_ccval = hcrx->ccid3hcrx_last_counter; if (dccp_packet_without_ack(skb)) - return; - - if (hcrx->ccid3hcrx_elapsed_time != 0) - dccp_insert_option_elapsed_time(sk, skb, - hcrx->ccid3hcrx_elapsed_time); - dccp_insert_option_timestamp(sk, skb); + return 0; + x_recv = htonl(hcrx->ccid3hcrx_x_recv); pinv = htonl(hcrx->ccid3hcrx_pinv); - dccp_insert_option(sk, skb, TFRC_OPT_LOSS_EVENT_RATE, - &pinv, sizeof(pinv)); - dccp_insert_option(sk, skb, TFRC_OPT_RECEIVE_RATE, - &x_recv, sizeof(x_recv)); + + if ((hcrx->ccid3hcrx_elapsed_time != 0 && + dccp_insert_option_elapsed_time(sk, skb, + hcrx->ccid3hcrx_elapsed_time)) || + dccp_insert_option_timestamp(sk, skb) || + dccp_insert_option(sk, skb, TFRC_OPT_LOSS_EVENT_RATE, + &pinv, sizeof(pinv)) || + dccp_insert_option(sk, skb, TFRC_OPT_RECEIVE_RATE, + &x_recv, sizeof(x_recv))) + return -1; + + return 0; } /* calculate first loss interval @@ -1047,20 +1031,13 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) } } -static int ccid3_hc_rx_init(struct sock *sk) +static int ccid3_hc_rx_init(struct ccid *ccid, struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_rx_sock *hcrx; + struct ccid3_hc_rx_sock *hcrx = ccid_priv(ccid); ccid3_pr_debug("%s, sk=%p\n", dccp_role(sk), sk); - dp->dccps_hc_rx_ccid_private = kmalloc(sizeof(*hcrx), gfp_any()); - if (dp->dccps_hc_rx_ccid_private == NULL) - return -ENOMEM; - - hcrx = ccid3_hc_rx_sk(sk); - memset(hcrx, 0, sizeof(*hcrx)); - if (dp->dccps_packet_size >= TFRC_MIN_PACKET_SIZE && dp->dccps_packet_size <= TFRC_MAX_PACKET_SIZE) hcrx->ccid3hcrx_s = dp->dccps_packet_size; @@ -1079,7 +1056,6 @@ static int ccid3_hc_rx_init(struct sock *sk) static void ccid3_hc_rx_exit(struct sock *sk) { struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); - struct dccp_sock *dp = dccp_sk(sk); BUG_ON(hcrx == NULL); @@ -1090,9 +1066,6 @@ static void ccid3_hc_rx_exit(struct sock *sk) /* Empty loss interval history */ dccp_li_hist_purge(ccid3_li_hist, &hcrx->ccid3hcrx_li_hist); - - kfree(dp->dccps_hc_rx_ccid_private); - dp->dccps_hc_rx_ccid_private = NULL; } static void ccid3_hc_rx_get_info(struct sock *sk, struct tcp_info *info) @@ -1178,12 +1151,11 @@ static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len, return 0; } -static struct ccid ccid3 = { +static struct ccid_operations ccid3 = { .ccid_id = 3, .ccid_name = "ccid3", .ccid_owner = THIS_MODULE, - .ccid_init = ccid3_init, - .ccid_exit = ccid3_exit, + .ccid_hc_tx_obj_size = sizeof(struct ccid3_hc_tx_sock), .ccid_hc_tx_init = ccid3_hc_tx_init, .ccid_hc_tx_exit = ccid3_hc_tx_exit, .ccid_hc_tx_send_packet = ccid3_hc_tx_send_packet, @@ -1191,6 +1163,7 @@ static struct ccid ccid3 = { .ccid_hc_tx_packet_recv = ccid3_hc_tx_packet_recv, .ccid_hc_tx_insert_options = ccid3_hc_tx_insert_options, .ccid_hc_tx_parse_options = ccid3_hc_tx_parse_options, + .ccid_hc_rx_obj_size = sizeof(struct ccid3_hc_rx_sock), .ccid_hc_rx_init = ccid3_hc_rx_init, .ccid_hc_rx_exit = ccid3_hc_rx_exit, .ccid_hc_rx_insert_options = ccid3_hc_rx_insert_options, @@ -1241,15 +1214,6 @@ module_init(ccid3_module_init); static __exit void ccid3_module_exit(void) { -#ifdef CONFIG_IP_DCCP_UNLOAD_HACK - /* - * Hack to use while developing, so that we get rid of the control - * sock, that is what keeps a refcount on dccp.ko -acme - */ - extern void dccp_ctl_sock_exit(void); - - dccp_ctl_sock_exit(); -#endif ccid_unregister(&ccid3); if (ccid3_tx_hist != NULL) { diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index 0bde4583d091..f18b96d4e5a2 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -41,6 +41,7 @@ #include <linux/time.h> #include <linux/types.h> #include <linux/tfrc.h> +#include "../ccid.h" #define TFRC_MIN_PACKET_SIZE 16 #define TFRC_STD_PACKET_SIZE 256 @@ -135,12 +136,12 @@ struct ccid3_hc_rx_sock { static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) { - return dccp_sk(sk)->dccps_hc_tx_ccid_private; + return ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid); } static inline struct ccid3_hc_rx_sock *ccid3_hc_rx_sk(const struct sock *sk) { - return dccp_sk(sk)->dccps_hc_rx_ccid_private; + return ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid); } #endif /* _DCCP_CCID3_H_ */ diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 93f26dd6e6cb..1fe509148689 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -59,8 +59,6 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo); #define DCCP_RTO_MAX ((unsigned)(120 * HZ)) /* FIXME: using TCP value */ -extern struct proto dccp_prot; - /* is seq1 < seq2 ? */ static inline int before48(const u64 seq1, const u64 seq2) { @@ -120,7 +118,6 @@ DECLARE_SNMP_STAT(struct dccp_mib, dccp_statistics); extern int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb); -extern int dccp_send_response(struct sock *sk); extern void dccp_send_ack(struct sock *sk); extern void dccp_send_delayed_ack(struct sock *sk); extern void dccp_send_sync(struct sock *sk, const u64 seq, @@ -140,53 +137,8 @@ extern unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu); extern const char *dccp_packet_name(const int type); extern const char *dccp_state_name(const int state); -static inline void dccp_set_state(struct sock *sk, const int state) -{ - const int oldstate = sk->sk_state; - - dccp_pr_debug("%s(%p) %-10.10s -> %s\n", - dccp_role(sk), sk, - dccp_state_name(oldstate), dccp_state_name(state)); - WARN_ON(state == oldstate); - - switch (state) { - case DCCP_OPEN: - if (oldstate != DCCP_OPEN) - DCCP_INC_STATS(DCCP_MIB_CURRESTAB); - break; - - case DCCP_CLOSED: - if (oldstate == DCCP_CLOSING || oldstate == DCCP_OPEN) - DCCP_INC_STATS(DCCP_MIB_ESTABRESETS); - - sk->sk_prot->unhash(sk); - if (inet_csk(sk)->icsk_bind_hash != NULL && - !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) - inet_put_port(&dccp_hashinfo, sk); - /* fall through */ - default: - if (oldstate == DCCP_OPEN) - DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); - } - - /* Change state AFTER socket is unhashed to avoid closed - * socket sitting in hash tables. - */ - sk->sk_state = state; -} - -static inline void dccp_done(struct sock *sk) -{ - dccp_set_state(sk, DCCP_CLOSED); - dccp_clear_xmit_timers(sk); - - sk->sk_shutdown = SHUTDOWN_MASK; - - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - else - inet_csk_destroy_sock(sk); -} +extern void dccp_set_state(struct sock *sk, const int state); +extern void dccp_done(struct sock *sk); static inline void dccp_openreq_init(struct request_sock *req, struct dccp_sock *dp, @@ -209,10 +161,6 @@ extern struct sock *dccp_create_openreq_child(struct sock *sk, extern int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); -extern void dccp_v4_err(struct sk_buff *skb, u32); - -extern int dccp_v4_rcv(struct sk_buff *skb); - extern struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -228,24 +176,30 @@ extern int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, extern int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, const unsigned len); -extern int dccp_v4_init_sock(struct sock *sk); -extern int dccp_v4_destroy_sock(struct sock *sk); +extern int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); +extern int dccp_destroy_sock(struct sock *sk); extern void dccp_close(struct sock *sk, long timeout); extern struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, struct request_sock *req); -extern struct sk_buff *dccp_make_reset(struct sock *sk, - struct dst_entry *dst, - enum dccp_reset_codes code); extern int dccp_connect(struct sock *sk); extern int dccp_disconnect(struct sock *sk, int flags); +extern void dccp_hash(struct sock *sk); extern void dccp_unhash(struct sock *sk); extern int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int dccp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen); +#ifdef CONFIG_COMPAT +extern int compat_dccp_getsockopt(struct sock *sk, + int level, int optname, + char __user *optval, int __user *optlen); +extern int compat_dccp_setsockopt(struct sock *sk, + int level, int optname, + char __user *optval, int optlen); +#endif extern int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size); @@ -262,15 +216,14 @@ extern int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); extern int dccp_v4_checksum(const struct sk_buff *skb, - const u32 saddr, const u32 daddr); + const __be32 saddr, const __be32 daddr); -extern int dccp_v4_send_reset(struct sock *sk, - enum dccp_reset_codes code); +extern int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code); extern void dccp_send_close(struct sock *sk, const int active); extern int dccp_invalid_packet(struct sk_buff *skb); static inline int dccp_bad_service_code(const struct sock *sk, - const __u32 service) + const __be32 service) { const struct dccp_sock *dp = dccp_sk(sk); @@ -334,41 +287,29 @@ static inline void dccp_hdr_set_seq(struct dccp_hdr *dh, const u64 gss) { struct dccp_hdr_ext *dhx = (struct dccp_hdr_ext *)((void *)dh + sizeof(*dh)); - -#if defined(__LITTLE_ENDIAN_BITFIELD) - dh->dccph_seq = htonl((gss >> 32)) >> 8; -#elif defined(__BIG_ENDIAN_BITFIELD) - dh->dccph_seq = htonl((gss >> 32)); -#else -#error "Adjust your <asm/byteorder.h> defines" -#endif + dh->dccph_seq2 = 0; + dh->dccph_seq = htons((gss >> 32) & 0xfffff); dhx->dccph_seq_low = htonl(gss & 0xffffffff); } static inline void dccp_hdr_set_ack(struct dccp_hdr_ack_bits *dhack, const u64 gsr) { -#if defined(__LITTLE_ENDIAN_BITFIELD) - dhack->dccph_ack_nr_high = htonl((gsr >> 32)) >> 8; -#elif defined(__BIG_ENDIAN_BITFIELD) - dhack->dccph_ack_nr_high = htonl((gsr >> 32)); -#else -#error "Adjust your <asm/byteorder.h> defines" -#endif + dhack->dccph_reserved1 = 0; + dhack->dccph_ack_nr_high = htons(gsr >> 32); dhack->dccph_ack_nr_low = htonl(gsr & 0xffffffff); } static inline void dccp_update_gsr(struct sock *sk, u64 seq) { struct dccp_sock *dp = dccp_sk(sk); + const struct dccp_minisock *dmsk = dccp_msk(sk); dp->dccps_gsr = seq; dccp_set_seqno(&dp->dccps_swl, - (dp->dccps_gsr + 1 - - (dp->dccps_options.dccpo_sequence_window / 4))); + dp->dccps_gsr + 1 - (dmsk->dccpms_sequence_window / 4)); dccp_set_seqno(&dp->dccps_swh, - (dp->dccps_gsr + - (3 * dp->dccps_options.dccpo_sequence_window) / 4)); + dp->dccps_gsr + (3 * dmsk->dccpms_sequence_window) / 4); } static inline void dccp_update_gss(struct sock *sk, u64 seq) @@ -378,7 +319,7 @@ static inline void dccp_update_gss(struct sock *sk, u64 seq) dp->dccps_awh = dp->dccps_gss = seq; dccp_set_seqno(&dp->dccps_awl, (dp->dccps_gss - - dp->dccps_options.dccpo_sequence_window + 1)); + dccp_msk(sk)->dccpms_sequence_window + 1)); } static inline int dccp_ack_pending(const struct sock *sk) @@ -386,24 +327,22 @@ static inline int dccp_ack_pending(const struct sock *sk) const struct dccp_sock *dp = dccp_sk(sk); return dp->dccps_timestamp_echo != 0 || #ifdef CONFIG_IP_DCCP_ACKVEC - (dp->dccps_options.dccpo_send_ack_vector && + (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) || #endif inet_csk_ack_scheduled(sk); } -extern void dccp_insert_options(struct sock *sk, struct sk_buff *skb); -extern void dccp_insert_option_elapsed_time(struct sock *sk, +extern int dccp_insert_options(struct sock *sk, struct sk_buff *skb); +extern int dccp_insert_option_elapsed_time(struct sock *sk, struct sk_buff *skb, u32 elapsed_time); -extern void dccp_insert_option_timestamp(struct sock *sk, +extern int dccp_insert_option_timestamp(struct sock *sk, struct sk_buff *skb); -extern void dccp_insert_option(struct sock *sk, struct sk_buff *skb, +extern int dccp_insert_option(struct sock *sk, struct sk_buff *skb, unsigned char option, const void *value, unsigned char len); -extern struct socket *dccp_ctl_socket; - extern void dccp_timestamp(const struct sock *sk, struct timeval *tv); static inline suseconds_t timeval_usecs(const struct timeval *tv) @@ -444,4 +383,18 @@ static inline void timeval_sub_usecs(struct timeval *tv, } } +#ifdef CONFIG_SYSCTL +extern int dccp_sysctl_init(void); +extern void dccp_sysctl_exit(void); +#else +static inline int dccp_sysctl_init(void) +{ + return 0; +} + +static inline void dccp_sysctl_exit(void) +{ +} +#endif + #endif /* _DCCP_H */ diff --git a/net/dccp/diag.c b/net/dccp/diag.c index 3f78c00e3822..0f25dc395967 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -30,7 +30,7 @@ static void dccp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_backoff = icsk->icsk_backoff; info->tcpi_pmtu = icsk->icsk_pmtu_cookie; - if (dp->dccps_options.dccpo_send_ack_vector) + if (dccp_msk(sk)->dccpms_send_ack_vector) info->tcpi_options |= TCPI_OPT_SACK; ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info); diff --git a/net/dccp/feat.c b/net/dccp/feat.c new file mode 100644 index 000000000000..e3dd30d36c8a --- /dev/null +++ b/net/dccp/feat.c @@ -0,0 +1,586 @@ +/* + * net/dccp/feat.c + * + * An implementation of the DCCP protocol + * Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/config.h> +#include <linux/module.h> + +#include "dccp.h" +#include "ccid.h" +#include "feat.h" + +#define DCCP_FEAT_SP_NOAGREE (-123) + +int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature, + u8 *val, u8 len, gfp_t gfp) +{ + struct dccp_opt_pend *opt; + + dccp_pr_debug("feat change type=%d feat=%d\n", type, feature); + + /* XXX sanity check feat change request */ + + /* check if that feature is already being negotiated */ + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + /* ok we found a negotiation for this option already */ + if (opt->dccpop_feat == feature && opt->dccpop_type == type) { + dccp_pr_debug("Replacing old\n"); + /* replace */ + BUG_ON(opt->dccpop_val == NULL); + kfree(opt->dccpop_val); + opt->dccpop_val = val; + opt->dccpop_len = len; + opt->dccpop_conf = 0; + return 0; + } + } + + /* negotiation for a new feature */ + opt = kmalloc(sizeof(*opt), gfp); + if (opt == NULL) + return -ENOMEM; + + opt->dccpop_type = type; + opt->dccpop_feat = feature; + opt->dccpop_len = len; + opt->dccpop_val = val; + opt->dccpop_conf = 0; + opt->dccpop_sc = NULL; + + BUG_ON(opt->dccpop_val == NULL); + + list_add_tail(&opt->dccpop_node, &dmsk->dccpms_pending); + return 0; +} + +EXPORT_SYMBOL_GPL(dccp_feat_change); + +static int dccp_feat_update_ccid(struct sock *sk, u8 type, u8 new_ccid_nr) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); + /* figure out if we are changing our CCID or the peer's */ + const int rx = type == DCCPO_CHANGE_R; + const u8 ccid_nr = rx ? dmsk->dccpms_rx_ccid : dmsk->dccpms_tx_ccid; + struct ccid *new_ccid; + + /* Check if nothing is being changed. */ + if (ccid_nr == new_ccid_nr) + return 0; + + new_ccid = ccid_new(new_ccid_nr, sk, rx, GFP_ATOMIC); + if (new_ccid == NULL) + return -ENOMEM; + + if (rx) { + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + dp->dccps_hc_rx_ccid = new_ccid; + dmsk->dccpms_rx_ccid = new_ccid_nr; + } else { + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + dp->dccps_hc_tx_ccid = new_ccid; + dmsk->dccpms_tx_ccid = new_ccid_nr; + } + + return 0; +} + +/* XXX taking only u8 vals */ +static int dccp_feat_update(struct sock *sk, u8 type, u8 feat, u8 val) +{ + dccp_pr_debug("changing [%d] feat %d to %d\n", type, feat, val); + + switch (feat) { + case DCCPF_CCID: + return dccp_feat_update_ccid(sk, type, val); + default: + dccp_pr_debug("IMPLEMENT changing [%d] feat %d to %d\n", + type, feat, val); + break; + } + return 0; +} + +static int dccp_feat_reconcile(struct sock *sk, struct dccp_opt_pend *opt, + u8 *rpref, u8 rlen) +{ + struct dccp_sock *dp = dccp_sk(sk); + u8 *spref, slen, *res = NULL; + int i, j, rc, agree = 1; + + BUG_ON(rpref == NULL); + + /* check if we are the black sheep */ + if (dp->dccps_role == DCCP_ROLE_CLIENT) { + spref = rpref; + slen = rlen; + rpref = opt->dccpop_val; + rlen = opt->dccpop_len; + } else { + spref = opt->dccpop_val; + slen = opt->dccpop_len; + } + /* + * Now we have server preference list in spref and client preference in + * rpref + */ + BUG_ON(spref == NULL); + BUG_ON(rpref == NULL); + + /* FIXME sanity check vals */ + + /* Are values in any order? XXX Lame "algorithm" here */ + /* XXX assume values are 1 byte */ + for (i = 0; i < slen; i++) { + for (j = 0; j < rlen; j++) { + if (spref[i] == rpref[j]) { + res = &spref[i]; + break; + } + } + if (res) + break; + } + + /* we didn't agree on anything */ + if (res == NULL) { + /* confirm previous value */ + switch (opt->dccpop_feat) { + case DCCPF_CCID: + /* XXX did i get this right? =P */ + if (opt->dccpop_type == DCCPO_CHANGE_L) + res = &dccp_msk(sk)->dccpms_tx_ccid; + else + res = &dccp_msk(sk)->dccpms_rx_ccid; + break; + + default: + WARN_ON(1); /* XXX implement res */ + return -EFAULT; + } + + dccp_pr_debug("Don't agree... reconfirming %d\n", *res); + agree = 0; /* this is used for mandatory options... */ + } + + /* need to put result and our preference list */ + /* XXX assume 1 byte vals */ + rlen = 1 + opt->dccpop_len; + rpref = kmalloc(rlen, GFP_ATOMIC); + if (rpref == NULL) + return -ENOMEM; + + *rpref = *res; + memcpy(&rpref[1], opt->dccpop_val, opt->dccpop_len); + + /* put it in the "confirm queue" */ + if (opt->dccpop_sc == NULL) { + opt->dccpop_sc = kmalloc(sizeof(*opt->dccpop_sc), GFP_ATOMIC); + if (opt->dccpop_sc == NULL) { + kfree(rpref); + return -ENOMEM; + } + } else { + /* recycle the confirm slot */ + BUG_ON(opt->dccpop_sc->dccpoc_val == NULL); + kfree(opt->dccpop_sc->dccpoc_val); + dccp_pr_debug("recycling confirm slot\n"); + } + memset(opt->dccpop_sc, 0, sizeof(*opt->dccpop_sc)); + + opt->dccpop_sc->dccpoc_val = rpref; + opt->dccpop_sc->dccpoc_len = rlen; + + /* update the option on our side [we are about to send the confirm] */ + rc = dccp_feat_update(sk, opt->dccpop_type, opt->dccpop_feat, *res); + if (rc) { + kfree(opt->dccpop_sc->dccpoc_val); + kfree(opt->dccpop_sc); + opt->dccpop_sc = 0; + return rc; + } + + dccp_pr_debug("Will confirm %d\n", *rpref); + + /* say we want to change to X but we just got a confirm X, suppress our + * change + */ + if (!opt->dccpop_conf) { + if (*opt->dccpop_val == *res) + opt->dccpop_conf = 1; + dccp_pr_debug("won't ask for change of same feature\n"); + } + + return agree ? 0 : DCCP_FEAT_SP_NOAGREE; /* used for mandatory opts */ +} + +static int dccp_feat_sp(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len) +{ + struct dccp_minisock *dmsk = dccp_msk(sk); + struct dccp_opt_pend *opt; + int rc = 1; + u8 t; + + /* + * We received a CHANGE. We gotta match it against our own preference + * list. If we got a CHANGE_R it means it's a change for us, so we need + * to compare our CHANGE_L list. + */ + if (type == DCCPO_CHANGE_L) + t = DCCPO_CHANGE_R; + else + t = DCCPO_CHANGE_L; + + /* find our preference list for this feature */ + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + if (opt->dccpop_type != t || opt->dccpop_feat != feature) + continue; + + /* find the winner from the two preference lists */ + rc = dccp_feat_reconcile(sk, opt, val, len); + break; + } + + /* We didn't deal with the change. This can happen if we have no + * preference list for the feature. In fact, it just shouldn't + * happen---if we understand a feature, we should have a preference list + * with at least the default value. + */ + BUG_ON(rc == 1); + + return rc; +} + +static int dccp_feat_nn(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len) +{ + struct dccp_opt_pend *opt; + struct dccp_minisock *dmsk = dccp_msk(sk); + u8 *copy; + int rc; + + /* NN features must be change L */ + if (type == DCCPO_CHANGE_R) { + dccp_pr_debug("received CHANGE_R %d for NN feat %d\n", + type, feature); + return -EFAULT; + } + + /* XXX sanity check opt val */ + + /* copy option so we can confirm it */ + opt = kzalloc(sizeof(*opt), GFP_ATOMIC); + if (opt == NULL) + return -ENOMEM; + + copy = kmalloc(len, GFP_ATOMIC); + if (copy == NULL) { + kfree(opt); + return -ENOMEM; + } + memcpy(copy, val, len); + + opt->dccpop_type = DCCPO_CONFIRM_R; /* NN can only confirm R */ + opt->dccpop_feat = feature; + opt->dccpop_val = copy; + opt->dccpop_len = len; + + /* change feature */ + rc = dccp_feat_update(sk, type, feature, *val); + if (rc) { + kfree(opt->dccpop_val); + kfree(opt); + return rc; + } + + dccp_pr_debug("Confirming NN feature %d (val=%d)\n", feature, *copy); + list_add_tail(&opt->dccpop_node, &dmsk->dccpms_conf); + + return 0; +} + +static void dccp_feat_empty_confirm(struct dccp_minisock *dmsk, + u8 type, u8 feature) +{ + /* XXX check if other confirms for that are queued and recycle slot */ + struct dccp_opt_pend *opt = kzalloc(sizeof(*opt), GFP_ATOMIC); + + if (opt == NULL) { + /* XXX what do we do? Ignoring should be fine. It's a change + * after all =P + */ + return; + } + + opt->dccpop_type = type == DCCPO_CHANGE_L ? DCCPO_CONFIRM_R : + DCCPO_CONFIRM_L; + opt->dccpop_feat = feature; + opt->dccpop_val = 0; + opt->dccpop_len = 0; + + /* change feature */ + dccp_pr_debug("Empty confirm feature %d type %d\n", feature, type); + list_add_tail(&opt->dccpop_node, &dmsk->dccpms_conf); +} + +static void dccp_feat_flush_confirm(struct sock *sk) +{ + struct dccp_minisock *dmsk = dccp_msk(sk); + /* Check if there is anything to confirm in the first place */ + int yes = !list_empty(&dmsk->dccpms_conf); + + if (!yes) { + struct dccp_opt_pend *opt; + + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + if (opt->dccpop_conf) { + yes = 1; + break; + } + } + } + + if (!yes) + return; + + /* OK there is something to confirm... */ + /* XXX check if packet is in flight? Send delayed ack?? */ + if (sk->sk_state == DCCP_OPEN) + dccp_send_ack(sk); +} + +int dccp_feat_change_recv(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len) +{ + int rc; + + dccp_pr_debug("got feat change type=%d feat=%d\n", type, feature); + + /* figure out if it's SP or NN feature */ + switch (feature) { + /* deal with SP features */ + case DCCPF_CCID: + rc = dccp_feat_sp(sk, type, feature, val, len); + break; + + /* deal with NN features */ + case DCCPF_ACK_RATIO: + rc = dccp_feat_nn(sk, type, feature, val, len); + break; + + /* XXX implement other features */ + default: + rc = -EFAULT; + break; + } + + /* check if there were problems changing features */ + if (rc) { + /* If we don't agree on SP, we sent a confirm for old value. + * However we propagate rc to caller in case option was + * mandatory + */ + if (rc != DCCP_FEAT_SP_NOAGREE) + dccp_feat_empty_confirm(dccp_msk(sk), type, feature); + } + + /* generate the confirm [if required] */ + dccp_feat_flush_confirm(sk); + + return rc; +} + +EXPORT_SYMBOL_GPL(dccp_feat_change_recv); + +int dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature, + u8 *val, u8 len) +{ + u8 t; + struct dccp_opt_pend *opt; + struct dccp_minisock *dmsk = dccp_msk(sk); + int rc = 1; + int all_confirmed = 1; + + dccp_pr_debug("got feat confirm type=%d feat=%d\n", type, feature); + + /* XXX sanity check type & feat */ + + /* locate our change request */ + t = type == DCCPO_CONFIRM_L ? DCCPO_CHANGE_R : DCCPO_CHANGE_L; + + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + if (!opt->dccpop_conf && opt->dccpop_type == t && + opt->dccpop_feat == feature) { + /* we found it */ + /* XXX do sanity check */ + + opt->dccpop_conf = 1; + + /* We got a confirmation---change the option */ + dccp_feat_update(sk, opt->dccpop_type, + opt->dccpop_feat, *val); + + dccp_pr_debug("feat %d type %d confirmed %d\n", + feature, type, *val); + rc = 0; + break; + } + + if (!opt->dccpop_conf) + all_confirmed = 0; + } + + /* fix re-transmit timer */ + /* XXX gotta make sure that no option negotiation occurs during + * connection shutdown. Consider that the CLOSEREQ is sent and timer is + * on. if all options are confirmed it might kill timer which should + * remain alive until close is received. + */ + if (all_confirmed) { + dccp_pr_debug("clear feat negotiation timer %p\n", sk); + inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); + } + + if (rc) + dccp_pr_debug("feat %d type %d never requested\n", + feature, type); + return 0; +} + +EXPORT_SYMBOL_GPL(dccp_feat_confirm_recv); + +void dccp_feat_clean(struct dccp_minisock *dmsk) +{ + struct dccp_opt_pend *opt, *next; + + list_for_each_entry_safe(opt, next, &dmsk->dccpms_pending, + dccpop_node) { + BUG_ON(opt->dccpop_val == NULL); + kfree(opt->dccpop_val); + + if (opt->dccpop_sc != NULL) { + BUG_ON(opt->dccpop_sc->dccpoc_val == NULL); + kfree(opt->dccpop_sc->dccpoc_val); + kfree(opt->dccpop_sc); + } + + kfree(opt); + } + INIT_LIST_HEAD(&dmsk->dccpms_pending); + + list_for_each_entry_safe(opt, next, &dmsk->dccpms_conf, dccpop_node) { + BUG_ON(opt == NULL); + if (opt->dccpop_val != NULL) + kfree(opt->dccpop_val); + kfree(opt); + } + INIT_LIST_HEAD(&dmsk->dccpms_conf); +} + +EXPORT_SYMBOL_GPL(dccp_feat_clean); + +/* this is to be called only when a listening sock creates its child. It is + * assumed by the function---the confirm is not duplicated, but rather it is + * "passed on". + */ +int dccp_feat_clone(struct sock *oldsk, struct sock *newsk) +{ + struct dccp_minisock *olddmsk = dccp_msk(oldsk); + struct dccp_minisock *newdmsk = dccp_msk(newsk); + struct dccp_opt_pend *opt; + int rc = 0; + + INIT_LIST_HEAD(&newdmsk->dccpms_pending); + INIT_LIST_HEAD(&newdmsk->dccpms_conf); + + list_for_each_entry(opt, &olddmsk->dccpms_pending, dccpop_node) { + struct dccp_opt_pend *newopt; + /* copy the value of the option */ + u8 *val = kmalloc(opt->dccpop_len, GFP_ATOMIC); + + if (val == NULL) + goto out_clean; + memcpy(val, opt->dccpop_val, opt->dccpop_len); + + newopt = kmalloc(sizeof(*newopt), GFP_ATOMIC); + if (newopt == NULL) { + kfree(val); + goto out_clean; + } + + /* insert the option */ + memcpy(newopt, opt, sizeof(*newopt)); + newopt->dccpop_val = val; + list_add_tail(&newopt->dccpop_node, &newdmsk->dccpms_pending); + + /* XXX what happens with backlogs and multiple connections at + * once... + */ + /* the master socket no longer needs to worry about confirms */ + opt->dccpop_sc = 0; /* it's not a memleak---new socket has it */ + + /* reset state for a new socket */ + opt->dccpop_conf = 0; + } + + /* XXX not doing anything about the conf queue */ + +out: + return rc; + +out_clean: + dccp_feat_clean(newdmsk); + rc = -ENOMEM; + goto out; +} + +EXPORT_SYMBOL_GPL(dccp_feat_clone); + +static int __dccp_feat_init(struct dccp_minisock *dmsk, u8 type, u8 feat, + u8 *val, u8 len) +{ + int rc = -ENOMEM; + u8 *copy = kmalloc(len, GFP_KERNEL); + + if (copy != NULL) { + memcpy(copy, val, len); + rc = dccp_feat_change(dmsk, type, feat, copy, len, GFP_KERNEL); + if (rc) + kfree(copy); + } + return rc; +} + +int dccp_feat_init(struct dccp_minisock *dmsk) +{ + int rc; + + INIT_LIST_HEAD(&dmsk->dccpms_pending); + INIT_LIST_HEAD(&dmsk->dccpms_conf); + + /* CCID L */ + rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_L, DCCPF_CCID, + &dmsk->dccpms_tx_ccid, 1); + if (rc) + goto out; + + /* CCID R */ + rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_R, DCCPF_CCID, + &dmsk->dccpms_rx_ccid, 1); + if (rc) + goto out; + + /* Ack ratio */ + rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_L, DCCPF_ACK_RATIO, + &dmsk->dccpms_ack_ratio, 1); +out: + return rc; +} + +EXPORT_SYMBOL_GPL(dccp_feat_init); diff --git a/net/dccp/feat.h b/net/dccp/feat.h new file mode 100644 index 000000000000..6048373c7186 --- /dev/null +++ b/net/dccp/feat.h @@ -0,0 +1,29 @@ +#ifndef _DCCP_FEAT_H +#define _DCCP_FEAT_H +/* + * net/dccp/feat.h + * + * An implementation of the DCCP protocol + * Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/types.h> + +struct sock; +struct dccp_minisock; + +extern int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature, + u8 *val, u8 len, gfp_t gfp); +extern int dccp_feat_change_recv(struct sock *sk, u8 type, u8 feature, + u8 *val, u8 len); +extern int dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature, + u8 *val, u8 len); +extern void dccp_feat_clean(struct dccp_minisock *dmsk); +extern int dccp_feat_clone(struct sock *oldsk, struct sock *newsk); +extern int dccp_feat_init(struct dccp_minisock *dmsk); + +#endif /* _DCCP_FEAT_H */ diff --git a/net/dccp/input.c b/net/dccp/input.c index b6cba72b44e8..bfc53665516b 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -32,7 +32,7 @@ static void dccp_fin(struct sock *sk, struct sk_buff *skb) static void dccp_rcv_close(struct sock *sk, struct sk_buff *skb) { - dccp_v4_send_reset(sk, DCCP_RESET_CODE_CLOSED); + dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED); dccp_fin(sk, skb); dccp_set_state(sk, DCCP_CLOSED); sk_wake_async(sk, 1, POLL_HUP); @@ -56,11 +56,11 @@ static void dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) dccp_send_close(sk, 0); } -static inline void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb) +static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - if (dp->dccps_options.dccpo_send_ack_vector) + if (dccp_msk(sk)->dccpms_send_ack_vector) dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_ack_seq); } @@ -151,9 +151,8 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) return 0; } -static inline int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct dccp_hdr *dh, - const unsigned len) +static int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb, + const struct dccp_hdr *dh, const unsigned len) { struct dccp_sock *dp = dccp_sk(sk); @@ -247,7 +246,7 @@ int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); - if (dp->dccps_options.dccpo_send_ack_vector && + if (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) @@ -300,7 +299,10 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, goto out_invalid_packet; } - if (dp->dccps_options.dccpo_send_ack_vector && + if (dccp_parse_options(sk, skb)) + goto out_invalid_packet; + + if (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) @@ -321,14 +323,6 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, dccp_set_seqno(&dp->dccps_swl, max48(dp->dccps_swl, dp->dccps_isr)); - if (ccid_hc_rx_init(dp->dccps_hc_rx_ccid, sk) != 0 || - ccid_hc_tx_init(dp->dccps_hc_tx_ccid, sk) != 0) { - ccid_hc_rx_exit(dp->dccps_hc_rx_ccid, sk); - ccid_hc_tx_exit(dp->dccps_hc_tx_ccid, sk); - /* FIXME: send appropriate RESET code */ - goto out_invalid_packet; - } - dccp_sync_mss(sk, icsk->icsk_pmtu_cookie); /* @@ -492,7 +486,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); - if (dp->dccps_options.dccpo_send_ack_vector && + if (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index dc0487b5bace..29047995c695 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -18,8 +18,10 @@ #include <linux/random.h> #include <net/icmp.h> +#include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/inet_sock.h> +#include <net/protocol.h> #include <net/sock.h> #include <net/timewait_sock.h> #include <net/tcp_states.h> @@ -28,14 +30,14 @@ #include "ackvec.h" #include "ccid.h" #include "dccp.h" +#include "feat.h" -struct inet_hashinfo __cacheline_aligned dccp_hashinfo = { - .lhash_lock = RW_LOCK_UNLOCKED, - .lhash_users = ATOMIC_INIT(0), - .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait), -}; - -EXPORT_SYMBOL_GPL(dccp_hashinfo); +/* + * This is the global socket data structure used for responding to + * the Out-of-the-blue (OOTB) packets. A control sock will be created + * for this socket at the initialization time. + */ +static struct socket *dccp_v4_ctl_socket; static int dccp_v4_get_port(struct sock *sk, const unsigned short snum) { @@ -43,18 +45,6 @@ static int dccp_v4_get_port(struct sock *sk, const unsigned short snum) inet_csk_bind_conflict); } -static void dccp_v4_hash(struct sock *sk) -{ - inet_hash(&dccp_hashinfo, sk); -} - -void dccp_unhash(struct sock *sk) -{ - inet_unhash(&dccp_hashinfo, sk); -} - -EXPORT_SYMBOL_GPL(dccp_unhash); - int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); @@ -207,11 +197,12 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, } /* else let the usual retransmit timer handle it */ } -static void dccp_v4_ctl_send_ack(struct sk_buff *rxskb) +static void dccp_v4_reqsk_send_ack(struct sk_buff *rxskb, + struct request_sock *req) { int err; struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; - const int dccp_hdr_ack_len = sizeof(struct dccp_hdr) + + const u32 dccp_hdr_ack_len = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_ack_bits); struct sk_buff *skb; @@ -219,12 +210,12 @@ static void dccp_v4_ctl_send_ack(struct sk_buff *rxskb) if (((struct rtable *)rxskb->dst)->rt_type != RTN_LOCAL) return; - skb = alloc_skb(MAX_DCCP_HEADER + 15, GFP_ATOMIC); + skb = alloc_skb(dccp_v4_ctl_socket->sk->sk_prot->max_header, GFP_ATOMIC); if (skb == NULL) return; /* Reserve space for headers. */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, dccp_v4_ctl_socket->sk->sk_prot->max_header); skb->dst = dst_clone(rxskb->dst); @@ -243,11 +234,11 @@ static void dccp_v4_ctl_send_ack(struct sk_buff *rxskb) dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), DCCP_SKB_CB(rxskb)->dccpd_seq); - bh_lock_sock(dccp_ctl_socket->sk); - err = ip_build_and_send_pkt(skb, dccp_ctl_socket->sk, + bh_lock_sock(dccp_v4_ctl_socket->sk); + err = ip_build_and_send_pkt(skb, dccp_v4_ctl_socket->sk, rxskb->nh.iph->daddr, rxskb->nh.iph->saddr, NULL); - bh_unlock_sock(dccp_ctl_socket->sk); + bh_unlock_sock(dccp_v4_ctl_socket->sk); if (err == NET_XMIT_CN || err == 0) { DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); @@ -255,12 +246,6 @@ static void dccp_v4_ctl_send_ack(struct sk_buff *rxskb) } } -static void dccp_v4_reqsk_send_ack(struct sk_buff *skb, - struct request_sock *req) -{ - dccp_v4_ctl_send_ack(skb); -} - static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, struct dst_entry *dst) { @@ -275,7 +260,10 @@ static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, skb = dccp_make_response(sk, dst, req); if (skb != NULL) { const struct inet_request_sock *ireq = inet_rsk(req); + struct dccp_hdr *dh = dccp_hdr(skb); + dh->dccph_checksum = dccp_v4_checksum(skb, ireq->loc_addr, + ireq->rmt_addr); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, ireq->rmt_addr, @@ -301,7 +289,7 @@ out: * check at all. A more general error queue to queue errors for later handling * is probably better. */ -void dccp_v4_err(struct sk_buff *skb, u32 info) +static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + @@ -456,32 +444,6 @@ void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) EXPORT_SYMBOL_GPL(dccp_v4_send_check); -int dccp_v4_send_reset(struct sock *sk, enum dccp_reset_codes code) -{ - struct sk_buff *skb; - /* - * FIXME: what if rebuild_header fails? - * Should we be doing a rebuild_header here? - */ - int err = inet_sk_rebuild_header(sk); - - if (err != 0) - return err; - - skb = dccp_make_reset(sk, sk->sk_dst_cache, code); - if (skb != NULL) { - const struct inet_sock *inet = inet_sk(sk); - - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - err = ip_build_and_send_pkt(skb, sk, - inet->saddr, inet->daddr, NULL); - if (err == NET_XMIT_CN) - err = 0; - } - - return err; -} - static inline u64 dccp_v4_init_sequence(const struct sock *sk, const struct sk_buff *skb) { @@ -497,9 +459,9 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) struct dccp_sock dp; struct request_sock *req; struct dccp_request_sock *dreq; - const __u32 saddr = skb->nh.iph->saddr; - const __u32 daddr = skb->nh.iph->daddr; - const __u32 service = dccp_hdr_request(skb)->dccph_req_service; + const __be32 saddr = skb->nh.iph->saddr; + const __be32 daddr = skb->nh.iph->daddr; + const __be32 service = dccp_hdr_request(skb)->dccph_req_service; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); __u8 reset_code = DCCP_RESET_CODE_TOO_BUSY; @@ -535,7 +497,8 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (req == NULL) goto drop; - /* FIXME: process options */ + if (dccp_parse_options(sk, skb)) + goto drop; dccp_openreq_init(req, &dp, skb); @@ -660,8 +623,8 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) return sk; } -int dccp_v4_checksum(const struct sk_buff *skb, const u32 saddr, - const u32 daddr) +int dccp_v4_checksum(const struct sk_buff *skb, const __be32 saddr, + const __be32 daddr) { const struct dccp_hdr* dh = dccp_hdr(skb); int checksum_len; @@ -680,8 +643,10 @@ int dccp_v4_checksum(const struct sk_buff *skb, const u32 saddr, IPPROTO_DCCP, tmp); } +EXPORT_SYMBOL_GPL(dccp_v4_checksum); + static int dccp_v4_verify_checksum(struct sk_buff *skb, - const u32 saddr, const u32 daddr) + const __be32 saddr, const __be32 daddr) { struct dccp_hdr *dh = dccp_hdr(skb); int checksum_len; @@ -741,16 +706,17 @@ static void dccp_v4_ctl_send_reset(struct sk_buff *rxskb) if (((struct rtable *)rxskb->dst)->rt_type != RTN_LOCAL) return; - dst = dccp_v4_route_skb(dccp_ctl_socket->sk, rxskb); + dst = dccp_v4_route_skb(dccp_v4_ctl_socket->sk, rxskb); if (dst == NULL) return; - skb = alloc_skb(MAX_DCCP_HEADER + 15, GFP_ATOMIC); + skb = alloc_skb(dccp_v4_ctl_socket->sk->sk_prot->max_header, + GFP_ATOMIC); if (skb == NULL) goto out; /* Reserve space for headers. */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, dccp_v4_ctl_socket->sk->sk_prot->max_header); skb->dst = dst_clone(dst); skb->h.raw = skb_push(skb, dccp_hdr_reset_len); @@ -778,11 +744,11 @@ static void dccp_v4_ctl_send_reset(struct sk_buff *rxskb) dh->dccph_checksum = dccp_v4_checksum(skb, rxskb->nh.iph->saddr, rxskb->nh.iph->daddr); - bh_lock_sock(dccp_ctl_socket->sk); - err = ip_build_and_send_pkt(skb, dccp_ctl_socket->sk, + bh_lock_sock(dccp_v4_ctl_socket->sk); + err = ip_build_and_send_pkt(skb, dccp_v4_ctl_socket->sk, rxskb->nh.iph->daddr, rxskb->nh.iph->saddr, NULL); - bh_unlock_sock(dccp_ctl_socket->sk); + bh_unlock_sock(dccp_v4_ctl_socket->sk); if (err == NET_XMIT_CN || err == 0) { DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); @@ -912,7 +878,7 @@ int dccp_invalid_packet(struct sk_buff *skb) EXPORT_SYMBOL_GPL(dccp_invalid_packet); /* this is called when real data arrives */ -int dccp_v4_rcv(struct sk_buff *skb) +static int dccp_v4_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; struct sock *sk; @@ -1019,111 +985,37 @@ do_time_wait: goto no_dccp_socket; } -struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { - .queue_xmit = ip_queue_xmit, - .send_check = dccp_v4_send_check, - .rebuild_header = inet_sk_rebuild_header, - .conn_request = dccp_v4_conn_request, - .syn_recv_sock = dccp_v4_request_recv_sock, - .net_header_len = sizeof(struct iphdr), - .setsockopt = ip_setsockopt, - .getsockopt = ip_getsockopt, - .addr2sockaddr = inet_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in), +static struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { + .queue_xmit = ip_queue_xmit, + .send_check = dccp_v4_send_check, + .rebuild_header = inet_sk_rebuild_header, + .conn_request = dccp_v4_conn_request, + .syn_recv_sock = dccp_v4_request_recv_sock, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ip_setsockopt, + .getsockopt = ip_getsockopt, + .addr2sockaddr = inet_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ip_setsockopt, + .compat_getsockopt = compat_ip_getsockopt, +#endif }; -int dccp_v4_init_sock(struct sock *sk) -{ - struct dccp_sock *dp = dccp_sk(sk); - struct inet_connection_sock *icsk = inet_csk(sk); - static int dccp_ctl_socket_init = 1; - - dccp_options_init(&dp->dccps_options); - do_gettimeofday(&dp->dccps_epoch); - - if (dp->dccps_options.dccpo_send_ack_vector) { - dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(DCCP_MAX_ACKVEC_LEN, - GFP_KERNEL); - if (dp->dccps_hc_rx_ackvec == NULL) - return -ENOMEM; - } - - /* - * FIXME: We're hardcoding the CCID, and doing this at this point makes - * the listening (master) sock get CCID control blocks, which is not - * necessary, but for now, to not mess with the test userspace apps, - * lets leave it here, later the real solution is to do this in a - * setsockopt(CCIDs-I-want/accept). -acme - */ - if (likely(!dccp_ctl_socket_init)) { - dp->dccps_hc_rx_ccid = ccid_init(dp->dccps_options.dccpo_rx_ccid, - sk); - dp->dccps_hc_tx_ccid = ccid_init(dp->dccps_options.dccpo_tx_ccid, - sk); - if (dp->dccps_hc_rx_ccid == NULL || - dp->dccps_hc_tx_ccid == NULL) { - ccid_exit(dp->dccps_hc_rx_ccid, sk); - ccid_exit(dp->dccps_hc_tx_ccid, sk); - if (dp->dccps_options.dccpo_send_ack_vector) { - dccp_ackvec_free(dp->dccps_hc_rx_ackvec); - dp->dccps_hc_rx_ackvec = NULL; - } - dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; - return -ENOMEM; - } - } else - dccp_ctl_socket_init = 0; - - dccp_init_xmit_timers(sk); - icsk->icsk_rto = DCCP_TIMEOUT_INIT; - sk->sk_state = DCCP_CLOSED; - sk->sk_write_space = dccp_write_space; - icsk->icsk_af_ops = &dccp_ipv4_af_ops; - icsk->icsk_sync_mss = dccp_sync_mss; - dp->dccps_mss_cache = 536; - dp->dccps_role = DCCP_ROLE_UNDEFINED; - dp->dccps_service = DCCP_SERVICE_INVALID_VALUE; - - return 0; -} - -EXPORT_SYMBOL_GPL(dccp_v4_init_sock); - -int dccp_v4_destroy_sock(struct sock *sk) +static int dccp_v4_init_sock(struct sock *sk) { - struct dccp_sock *dp = dccp_sk(sk); + static __u8 dccp_v4_ctl_sock_initialized; + int err = dccp_init_sock(sk, dccp_v4_ctl_sock_initialized); - /* - * DCCP doesn't use sk_write_queue, just sk_send_head - * for retransmissions - */ - if (sk->sk_send_head != NULL) { - kfree_skb(sk->sk_send_head); - sk->sk_send_head = NULL; + if (err == 0) { + if (unlikely(!dccp_v4_ctl_sock_initialized)) + dccp_v4_ctl_sock_initialized = 1; + inet_csk(sk)->icsk_af_ops = &dccp_ipv4_af_ops; } - /* Clean up a referenced DCCP bind bucket. */ - if (inet_csk(sk)->icsk_bind_hash != NULL) - inet_put_port(&dccp_hashinfo, sk); - - kfree(dp->dccps_service_list); - dp->dccps_service_list = NULL; - - ccid_hc_rx_exit(dp->dccps_hc_rx_ccid, sk); - ccid_hc_tx_exit(dp->dccps_hc_tx_ccid, sk); - if (dp->dccps_options.dccpo_send_ack_vector) { - dccp_ackvec_free(dp->dccps_hc_rx_ackvec); - dp->dccps_hc_rx_ackvec = NULL; - } - ccid_exit(dp->dccps_hc_rx_ccid, sk); - ccid_exit(dp->dccps_hc_tx_ccid, sk); - dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; - - return 0; + return err; } -EXPORT_SYMBOL_GPL(dccp_v4_destroy_sock); - static void dccp_v4_reqsk_destructor(struct request_sock *req) { kfree(inet_rsk(req)->opt); @@ -1142,7 +1034,7 @@ static struct timewait_sock_ops dccp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct inet_timewait_sock), }; -struct proto dccp_prot = { +static struct proto dccp_v4_prot = { .name = "DCCP", .owner = THIS_MODULE, .close = dccp_close, @@ -1155,17 +1047,110 @@ struct proto dccp_prot = { .sendmsg = dccp_sendmsg, .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v4_do_rcv, - .hash = dccp_v4_hash, + .hash = dccp_hash, .unhash = dccp_unhash, .accept = inet_csk_accept, .get_port = dccp_v4_get_port, .shutdown = dccp_shutdown, - .destroy = dccp_v4_destroy_sock, + .destroy = dccp_destroy_sock, .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp_sock), .rsk_prot = &dccp_request_sock_ops, .twsk_prot = &dccp_timewait_sock_ops, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_dccp_setsockopt, + .compat_getsockopt = compat_dccp_getsockopt, +#endif +}; + +static struct net_protocol dccp_v4_protocol = { + .handler = dccp_v4_rcv, + .err_handler = dccp_v4_err, + .no_policy = 1, +}; + +static const struct proto_ops inet_dccp_ops = { + .family = PF_INET, + .owner = THIS_MODULE, + .release = inet_release, + .bind = inet_bind, + .connect = inet_stream_connect, + .socketpair = sock_no_socketpair, + .accept = inet_accept, + .getname = inet_getname, + /* FIXME: work on tcp_poll to rename it to inet_csk_poll */ + .poll = dccp_poll, + .ioctl = inet_ioctl, + /* FIXME: work on inet_listen to rename it to sock_common_listen */ + .listen = inet_dccp_listen, + .shutdown = inet_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; -EXPORT_SYMBOL_GPL(dccp_prot); +static struct inet_protosw dccp_v4_protosw = { + .type = SOCK_DCCP, + .protocol = IPPROTO_DCCP, + .prot = &dccp_v4_prot, + .ops = &inet_dccp_ops, + .capability = -1, + .no_check = 0, + .flags = INET_PROTOSW_ICSK, +}; + +static int __init dccp_v4_init(void) +{ + int err = proto_register(&dccp_v4_prot, 1); + + if (err != 0) + goto out; + + err = inet_add_protocol(&dccp_v4_protocol, IPPROTO_DCCP); + if (err != 0) + goto out_proto_unregister; + + inet_register_protosw(&dccp_v4_protosw); + + err = inet_csk_ctl_sock_create(&dccp_v4_ctl_socket, PF_INET, + SOCK_DCCP, IPPROTO_DCCP); + if (err) + goto out_unregister_protosw; +out: + return err; +out_unregister_protosw: + inet_unregister_protosw(&dccp_v4_protosw); + inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); +out_proto_unregister: + proto_unregister(&dccp_v4_prot); + goto out; +} + +static void __exit dccp_v4_exit(void) +{ + inet_unregister_protosw(&dccp_v4_protosw); + inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); + proto_unregister(&dccp_v4_prot); +} + +module_init(dccp_v4_init); +module_exit(dccp_v4_exit); + +/* + * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33) + * values directly, Also cover the case where the protocol is not specified, + * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP + */ +MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-33-type-6"); +MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-0-type-6"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); +MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol"); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 80c4d048869e..65e2ab0886e6 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1,6 +1,6 @@ /* * DCCP over IPv6 - * Linux INET6 implementation + * Linux INET6 implementation * * Based on net/dccp6/ipv6.c * @@ -33,6 +33,9 @@ #include "dccp.h" #include "ipv6.h" +/* Socket used for sending RSTs and ACKs */ +static struct socket *dccp_v6_ctl_socket; + static void dccp_v6_ctl_send_reset(struct sk_buff *skb); static void dccp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req); @@ -53,7 +56,7 @@ static void dccp_v6_hash(struct sock *sk) { if (sk->sk_state != DCCP_CLOSED) { if (inet_csk(sk)->icsk_af_ops == &dccp_ipv6_mapped) { - dccp_prot.hash(sk); + dccp_hash(sk); return; } local_bh_disable(); @@ -63,8 +66,8 @@ static void dccp_v6_hash(struct sock *sk) } static inline u16 dccp_v6_check(struct dccp_hdr *dh, int len, - struct in6_addr *saddr, - struct in6_addr *daddr, + struct in6_addr *saddr, + struct in6_addr *daddr, unsigned long base) { return csum_ipv6_magic(saddr, daddr, len, IPPROTO_DCCP, base); @@ -79,17 +82,17 @@ static __u32 dccp_v6_init_sequence(struct sock *sk, struct sk_buff *skb) skb->nh.ipv6h->saddr.s6_addr32, dh->dccph_dport, dh->dccph_sport); - else - return secure_dccp_sequence_number(skb->nh.iph->daddr, - skb->nh.iph->saddr, - dh->dccph_dport, - dh->dccph_sport); + + return secure_dccp_sequence_number(skb->nh.iph->daddr, + skb->nh.iph->saddr, + dh->dccph_dport, + dh->dccph_sport); } -static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, +static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; + struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr; struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -102,10 +105,10 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, dp->dccps_role = DCCP_ROLE_CLIENT; - if (addr_len < SIN6_LEN_RFC2133) + if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; - if (usin->sin6_family != AF_INET6) + if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; memset(&fl, 0, sizeof(fl)); @@ -122,17 +125,15 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6_sock_release(flowlabel); } } - /* - * connect() to INADDR_ANY means loopback (BSD'ism). - */ - - if (ipv6_addr_any(&usin->sin6_addr)) - usin->sin6_addr.s6_addr[15] = 0x1; + * connect() to INADDR_ANY means loopback (BSD'ism). + */ + if (ipv6_addr_any(&usin->sin6_addr)) + usin->sin6_addr.s6_addr[15] = 1; addr_type = ipv6_addr_type(&usin->sin6_addr); - if(addr_type & IPV6_ADDR_MULTICAST) + if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type & IPV6_ADDR_LINKLOCAL) { @@ -157,9 +158,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, np->flow_label = fl.fl6_flowlabel; /* - * DCCP over IPv4 + * DCCP over IPv4 */ - if (addr_type == IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; @@ -177,7 +177,6 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_backlog_rcv = dccp_v4_do_rcv; err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); - if (err) { icsk->icsk_ext_hdr_len = exthdrlen; icsk->icsk_af_ops = &dccp_ipv6_af_ops; @@ -203,8 +202,9 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl.fl_ip_dport = usin->sin6_port; fl.fl_ip_sport = inet->sport; - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; + if (np->opt != NULL && np->opt->srcrt != NULL) { + const struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; @@ -213,10 +213,12 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, err = ip6_dst_lookup(sk, &dst, &fl); if (err) goto failure; + if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + err = xfrm_lookup(&dst, &fl, sk, 0); + if (err < 0) goto failure; if (saddr == NULL) { @@ -231,7 +233,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, ip6_dst_store(sk, dst, NULL); icsk->icsk_ext_hdr_len = 0; - if (np->opt) + if (np->opt != NULL) icsk->icsk_ext_hdr_len = (np->opt->opt_flen + np->opt->opt_nflen); @@ -264,7 +266,7 @@ failure: } static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __u32 info) + int type, int code, int offset, __be32 info) { struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); @@ -305,7 +307,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* icmp should have updated the destination cache entry */ dst = __sk_dst_check(sk, np->dst_cookie); - if (dst == NULL) { struct inet_sock *inet = inet_sk(sk); struct flowi fl; @@ -322,16 +323,17 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; - if ((err = ip6_dst_lookup(sk, &dst, &fl))) { + err = ip6_dst_lookup(sk, &dst, &fl); + if (err) { sk->sk_err_soft = -err; goto out; } - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + err = xfrm_lookup(&dst, &fl, sk, 0); + if (err < 0) { sk->sk_err_soft = -err; goto out; } - } else dst_hold(dst); @@ -355,11 +357,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, &hdr->daddr, &hdr->saddr, inet6_iif(skb)); - if (!req) + if (req == NULL) goto out; - /* ICMPs are not backlogged, hence we cannot get - * an established socket here. + /* + * ICMPs are not backlogged, hence we cannot get an established + * socket here. */ BUG_TRAP(req->sk == NULL); @@ -373,7 +376,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. - It can, it SYNs are crossed. --ANK */ + It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; @@ -382,7 +385,6 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, * (see connect in sock.c) */ sk->sk_error_report(sk); - dccp_done(sk); } else sk->sk_err_soft = err; @@ -428,14 +430,16 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, ireq6->pktopts) { struct sk_buff *pktopts = ireq6->pktopts; struct inet6_skb_parm *rxopt = IP6CB(pktopts); + if (rxopt->srcrt) opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(pktopts->nh.raw + rxopt->srcrt)); } - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; + if (opt != NULL && opt->srcrt != NULL) { + const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; @@ -444,15 +448,19 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, err = ip6_dst_lookup(sk, &dst, &fl); if (err) goto done; + if (final_p) ipv6_addr_copy(&fl.fl6_dst, final_p); - if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + + err = xfrm_lookup(&dst, &fl, sk, 0); + if (err < 0) goto done; } skb = dccp_make_response(sk, dst, req); if (skb != NULL) { struct dccp_hdr *dh = dccp_hdr(skb); + dh->dccph_checksum = dccp_v6_check(dh, skb->len, &ireq6->loc_addr, &ireq6->rmt_addr, @@ -466,7 +474,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, } done: - if (opt && opt != np->opt) + if (opt != NULL && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); return err; @@ -497,7 +505,7 @@ static void dccp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) struct dccp_hdr *dh = dccp_hdr(skb); dh->dccph_checksum = csum_ipv6_magic(&np->saddr, &np->daddr, - len, IPPROTO_DCCP, + len, IPPROTO_DCCP, csum_partial((char *)dh, dh->dccph_doff << 2, skb->csum)); @@ -505,8 +513,8 @@ static void dccp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) { - struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; - const int dccp_hdr_reset_len = sizeof(struct dccp_hdr) + + struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; + const u32 dccp_hdr_reset_len = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_reset); struct sk_buff *skb; @@ -517,20 +525,14 @@ static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) return; if (!ipv6_unicast_destination(rxskb)) - return; - - /* - * We need to grab some memory, and put together an RST, - * and then put it into the queue to be sent. - */ + return; - skb = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + - dccp_hdr_reset_len, GFP_ATOMIC); - if (skb == NULL) + skb = alloc_skb(dccp_v6_ctl_socket->sk->sk_prot->max_header, + GFP_ATOMIC); + if (skb == NULL) return; - skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr) + - dccp_hdr_reset_len); + skb_reserve(skb, dccp_v6_ctl_socket->sk->sk_prot->max_header); skb->h.raw = skb_push(skb, dccp_hdr_reset_len); dh = dccp_hdr(skb); @@ -568,7 +570,7 @@ static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) /* sk = NULL, but it is safe for now. RST socket required. */ if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { - ip6_xmit(NULL, skb, &fl, NULL, 0); + ip6_xmit(dccp_v6_ctl_socket->sk, skb, &fl, NULL, 0); DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); return; @@ -578,22 +580,22 @@ static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) kfree_skb(skb); } -static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) +static void dccp_v6_reqsk_send_ack(struct sk_buff *rxskb, + struct request_sock *req) { struct flowi fl; struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; - const int dccp_hdr_ack_len = sizeof(struct dccp_hdr) + + const u32 dccp_hdr_ack_len = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_ack_bits); struct sk_buff *skb; - skb = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + - dccp_hdr_ack_len, GFP_ATOMIC); + skb = alloc_skb(dccp_v6_ctl_socket->sk->sk_prot->max_header, + GFP_ATOMIC); if (skb == NULL) return; - skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr) + - dccp_hdr_ack_len); + skb_reserve(skb, dccp_v6_ctl_socket->sk->sk_prot->max_header); skb->h.raw = skb_push(skb, dccp_hdr_ack_len); dh = dccp_hdr(skb); @@ -605,7 +607,7 @@ static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) dh->dccph_dport = rxdh->dccph_sport; dh->dccph_doff = dccp_hdr_ack_len / 4; dh->dccph_x = 1; - + dccp_hdr_set_seq(dh, DCCP_SKB_CB(rxskb)->dccpd_ack_seq); dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), DCCP_SKB_CB(rxskb)->dccpd_seq); @@ -623,7 +625,7 @@ static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { - ip6_xmit(NULL, skb, &fl, NULL, 0); + ip6_xmit(dccp_v6_ctl_socket->sk, skb, &fl, NULL, 0); DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); return; } @@ -632,12 +634,6 @@ static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) kfree_skb(skb); } -static void dccp_v6_reqsk_send_ack(struct sk_buff *skb, - struct request_sock *req) -{ - dccp_v6_ctl_send_ack(skb); -} - static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) { const struct dccp_hdr *dh = dccp_hdr(skb); @@ -657,7 +653,6 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) &iph->saddr, dh->dccph_sport, &iph->daddr, ntohs(dh->dccph_dport), inet6_iif(skb)); - if (nsk != NULL) { if (nsk->sk_state != DCCP_TIME_WAIT) { bh_lock_sock(nsk); @@ -678,7 +673,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct dccp_request_sock *dreq; struct inet6_request_sock *ireq6; struct ipv6_pinfo *np = inet6_sk(sk); - const __u32 service = dccp_hdr_request(skb)->dccph_req_service; + const __be32 service = dccp_hdr_request(skb)->dccph_req_service; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); __u8 reset_code = DCCP_RESET_CODE_TOO_BUSY; @@ -686,17 +681,17 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) return dccp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) - goto drop; + goto drop; if (dccp_bad_service_code(sk, service)) { reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; goto drop; } /* - * There are no SYN attacks on IPv6, yet... + * There are no SYN attacks on IPv6, yet... */ if (inet_csk_reqsk_queue_is_full(sk)) - goto drop; + goto drop; if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; @@ -730,7 +725,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq6->iif = inet6_iif(skb); - /* + /* * Step 3: Process LISTEN state * * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie @@ -774,9 +769,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, /* * v6 mapped */ - newsk = dccp_v4_request_recv_sock(sk, skb, req, dst); - if (newsk == NULL) + if (newsk == NULL) return NULL; newdp6 = (struct dccp6_sock *)newsk; @@ -822,9 +816,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, if (sk_acceptq_is_full(sk)) goto out_overflow; - if (np->rxopt.bits.osrcrt == 2 && - opt == NULL && ireq6->pktopts) { - struct inet6_skb_parm *rxopt = IP6CB(ireq6->pktopts); + if (np->rxopt.bits.osrcrt == 2 && opt == NULL && ireq6->pktopts) { + const struct inet6_skb_parm *rxopt = IP6CB(ireq6->pktopts); + if (rxopt->srcrt) opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(ireq6->pktopts->nh.raw + @@ -838,8 +832,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_DCCP; ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; + if (opt != NULL && opt->srcrt != NULL) { + const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; @@ -857,7 +852,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) goto out; - } + } newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) @@ -870,9 +865,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, */ ip6_dst_store(newsk, dst, NULL); - newsk->sk_route_caps = dst->dev->features & - ~(NETIF_F_IP_CSUM | NETIF_F_TSO); - + newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | + NETIF_F_TSO); newdp6 = (struct dccp6_sock *)newsk; newinet = inet_sk(newsk); newinet->pinet6 = &newdp6->inet6; @@ -886,7 +880,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr); newsk->sk_bound_dev_if = ireq6->iif; - /* Now IPv6 options... + /* Now IPv6 options... First: no IPv4 options. */ @@ -908,20 +902,20 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = skb->nh.ipv6h->hop_limit; - /* Clone native IPv6 options from listening socket (if any) - - Yes, keeping reference count would be much more clever, - but we make one more one thing there: reattach optmem - to newsk. + /* + * Clone native IPv6 options from listening socket (if any) + * + * Yes, keeping reference count would be much more clever, but we make + * one more one thing there: reattach optmem to newsk. */ - if (opt) { + if (opt != NULL) { newnp->opt = ipv6_dup_options(newsk, opt); if (opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); } inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newnp->opt) + if (newnp->opt != NULL) inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + newnp->opt->opt_flen); @@ -938,7 +932,7 @@ out_overflow: NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS); out: NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS); - if (opt && opt != np->opt) + if (opt != NULL && opt != np->opt) sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); return NULL; @@ -972,8 +966,8 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; /* - * socket locking is here for SMP purposes as backlog rcv - * is currently called with bh processing disabled. + * socket locking is here for SMP purposes as backlog rcv is currently + * called with bh processing disabled. */ /* Do Stevens' IPV6_PKTOPTIONS. @@ -998,20 +992,20 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } - if (sk->sk_state == DCCP_LISTEN) { + if (sk->sk_state == DCCP_LISTEN) { struct sock *nsk = dccp_v6_hnd_req(sk, skb); - if (!nsk) - goto discard; + if (nsk == NULL) + goto discard; /* * Queue it on the new socket if the new socket is active, * otherwise we just shortcircuit this and continue with * the new socket.. */ - if(nsk != sk) { + if (nsk != sk) { if (dccp_child_process(sk, nsk, skb)) goto reset; - if (opt_skb) + if (opt_skb != NULL) __kfree_skb(opt_skb); return 0; } @@ -1024,7 +1018,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) reset: dccp_v6_ctl_send_reset(skb); discard: - if (opt_skb) + if (opt_skb != NULL) __kfree_skb(opt_skb); kfree_skb(skb); return 0; @@ -1057,7 +1051,7 @@ static int dccp_v6_rcv(struct sk_buff **pskb) dh->dccph_sport, &skb->nh.ipv6h->daddr, ntohs(dh->dccph_dport), inet6_iif(skb)); - /* + /* * Step 2: * If no socket ... * Generate Reset(No Connection) unless P.type == Reset @@ -1066,15 +1060,14 @@ static int dccp_v6_rcv(struct sk_buff **pskb) if (sk == NULL) goto no_dccp_socket; - /* + /* * Step 2: * ... or S.state == TIMEWAIT, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ - if (sk->sk_state == DCCP_TIME_WAIT) - goto do_time_wait; + goto do_time_wait; if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; @@ -1113,32 +1106,40 @@ do_time_wait: } static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { - .queue_xmit = inet6_csk_xmit, - .send_check = dccp_v6_send_check, - .rebuild_header = inet6_sk_rebuild_header, - .conn_request = dccp_v6_conn_request, - .syn_recv_sock = dccp_v6_request_recv_sock, - .net_header_len = sizeof(struct ipv6hdr), - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .addr2sockaddr = inet6_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in6) + .queue_xmit = inet6_csk_xmit, + .send_check = dccp_v6_send_check, + .rebuild_header = inet6_sk_rebuild_header, + .conn_request = dccp_v6_conn_request, + .syn_recv_sock = dccp_v6_request_recv_sock, + .net_header_len = sizeof(struct ipv6hdr), + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .addr2sockaddr = inet6_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in6), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ipv6_setsockopt, + .compat_getsockopt = compat_ipv6_getsockopt, +#endif }; /* * DCCP over IPv4 via INET6 API */ static struct inet_connection_sock_af_ops dccp_ipv6_mapped = { - .queue_xmit = ip_queue_xmit, - .send_check = dccp_v4_send_check, - .rebuild_header = inet_sk_rebuild_header, - .conn_request = dccp_v6_conn_request, - .syn_recv_sock = dccp_v6_request_recv_sock, - .net_header_len = sizeof(struct iphdr), - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .addr2sockaddr = inet6_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in6) + .queue_xmit = ip_queue_xmit, + .send_check = dccp_v4_send_check, + .rebuild_header = inet_sk_rebuild_header, + .conn_request = dccp_v6_conn_request, + .syn_recv_sock = dccp_v6_request_recv_sock, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .addr2sockaddr = inet6_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in6), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ipv6_setsockopt, + .compat_getsockopt = compat_ipv6_getsockopt, +#endif }; /* NOTE: A lot of things set to zero explicitly by call to @@ -1146,71 +1147,83 @@ static struct inet_connection_sock_af_ops dccp_ipv6_mapped = { */ static int dccp_v6_init_sock(struct sock *sk) { - int err = dccp_v4_init_sock(sk); + static __u8 dccp_v6_ctl_sock_initialized; + int err = dccp_init_sock(sk, dccp_v6_ctl_sock_initialized); - if (err == 0) + if (err == 0) { + if (unlikely(!dccp_v6_ctl_sock_initialized)) + dccp_v6_ctl_sock_initialized = 1; inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; + } return err; } static int dccp_v6_destroy_sock(struct sock *sk) { - dccp_v4_destroy_sock(sk); + dccp_destroy_sock(sk); return inet6_destroy_sock(sk); } static struct proto dccp_v6_prot = { - .name = "DCCPv6", - .owner = THIS_MODULE, - .close = dccp_close, - .connect = dccp_v6_connect, - .disconnect = dccp_disconnect, - .ioctl = dccp_ioctl, - .init = dccp_v6_init_sock, - .setsockopt = dccp_setsockopt, - .getsockopt = dccp_getsockopt, - .sendmsg = dccp_sendmsg, - .recvmsg = dccp_recvmsg, - .backlog_rcv = dccp_v6_do_rcv, - .hash = dccp_v6_hash, - .unhash = dccp_unhash, - .accept = inet_csk_accept, - .get_port = dccp_v6_get_port, - .shutdown = dccp_shutdown, - .destroy = dccp_v6_destroy_sock, - .orphan_count = &dccp_orphan_count, - .max_header = MAX_DCCP_HEADER, - .obj_size = sizeof(struct dccp6_sock), - .rsk_prot = &dccp6_request_sock_ops, - .twsk_prot = &dccp6_timewait_sock_ops, + .name = "DCCPv6", + .owner = THIS_MODULE, + .close = dccp_close, + .connect = dccp_v6_connect, + .disconnect = dccp_disconnect, + .ioctl = dccp_ioctl, + .init = dccp_v6_init_sock, + .setsockopt = dccp_setsockopt, + .getsockopt = dccp_getsockopt, + .sendmsg = dccp_sendmsg, + .recvmsg = dccp_recvmsg, + .backlog_rcv = dccp_v6_do_rcv, + .hash = dccp_v6_hash, + .unhash = dccp_unhash, + .accept = inet_csk_accept, + .get_port = dccp_v6_get_port, + .shutdown = dccp_shutdown, + .destroy = dccp_v6_destroy_sock, + .orphan_count = &dccp_orphan_count, + .max_header = MAX_DCCP_HEADER, + .obj_size = sizeof(struct dccp6_sock), + .rsk_prot = &dccp6_request_sock_ops, + .twsk_prot = &dccp6_timewait_sock_ops, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_dccp_setsockopt, + .compat_getsockopt = compat_dccp_getsockopt, +#endif }; static struct inet6_protocol dccp_v6_protocol = { - .handler = dccp_v6_rcv, - .err_handler = dccp_v6_err, - .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + .handler = dccp_v6_rcv, + .err_handler = dccp_v6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; static struct proto_ops inet6_dccp_ops = { - .family = PF_INET6, - .owner = THIS_MODULE, - .release = inet6_release, - .bind = inet6_bind, - .connect = inet_stream_connect, - .socketpair = sock_no_socketpair, - .accept = inet_accept, - .getname = inet6_getname, - .poll = dccp_poll, - .ioctl = inet6_ioctl, - .listen = inet_dccp_listen, - .shutdown = inet_shutdown, - .setsockopt = sock_common_setsockopt, - .getsockopt = sock_common_getsockopt, - .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_stream_connect, + .socketpair = sock_no_socketpair, + .accept = inet_accept, + .getname = inet6_getname, + .poll = dccp_poll, + .ioctl = inet6_ioctl, + .listen = inet_dccp_listen, + .shutdown = inet_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; static struct inet_protosw dccp_v6_protosw = { @@ -1234,8 +1247,16 @@ static int __init dccp_v6_init(void) goto out_unregister_proto; inet6_register_protosw(&dccp_v6_protosw); + + err = inet_csk_ctl_sock_create(&dccp_v6_ctl_socket, PF_INET6, + SOCK_DCCP, IPPROTO_DCCP); + if (err != 0) + goto out_unregister_protosw; out: return err; +out_unregister_protosw: + inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); + inet6_unregister_protosw(&dccp_v6_protosw); out_unregister_proto: proto_unregister(&dccp_v6_prot); goto out; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 29261fc198e7..c0349e5b0551 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -22,6 +22,7 @@ #include "ackvec.h" #include "ccid.h" #include "dccp.h" +#include "feat.h" struct inet_timewait_death_row dccp_death_row = { .sysctl_max_tw_buckets = NR_FILE * 2, @@ -106,6 +107,7 @@ struct sock *dccp_create_openreq_child(struct sock *sk, const struct dccp_request_sock *dreq = dccp_rsk(req); struct inet_connection_sock *newicsk = inet_csk(sk); struct dccp_sock *newdp = dccp_sk(newsk); + struct dccp_minisock *newdmsk = dccp_msk(newsk); newdp->dccps_role = DCCP_ROLE_SERVER; newdp->dccps_hc_rx_ackvec = NULL; @@ -114,27 +116,27 @@ struct sock *dccp_create_openreq_child(struct sock *sk, newicsk->icsk_rto = DCCP_TIMEOUT_INIT; do_gettimeofday(&newdp->dccps_epoch); - if (newdp->dccps_options.dccpo_send_ack_vector) { + if (dccp_feat_clone(sk, newsk)) + goto out_free; + + if (newdmsk->dccpms_send_ack_vector) { newdp->dccps_hc_rx_ackvec = - dccp_ackvec_alloc(DCCP_MAX_ACKVEC_LEN, - GFP_ATOMIC); - /* - * XXX: We're using the same CCIDs set on the parent, - * i.e. sk_clone copied the master sock and left the - * CCID pointers for this child, that is why we do the - * __ccid_get calls. - */ + dccp_ackvec_alloc(GFP_ATOMIC); if (unlikely(newdp->dccps_hc_rx_ackvec == NULL)) goto out_free; } - if (unlikely(ccid_hc_rx_init(newdp->dccps_hc_rx_ccid, - newsk) != 0 || - ccid_hc_tx_init(newdp->dccps_hc_tx_ccid, - newsk) != 0)) { + newdp->dccps_hc_rx_ccid = + ccid_hc_rx_new(newdmsk->dccpms_rx_ccid, + newsk, GFP_ATOMIC); + newdp->dccps_hc_tx_ccid = + ccid_hc_tx_new(newdmsk->dccpms_tx_ccid, + newsk, GFP_ATOMIC); + if (unlikely(newdp->dccps_hc_rx_ccid == NULL || + newdp->dccps_hc_tx_ccid == NULL)) { dccp_ackvec_free(newdp->dccps_hc_rx_ackvec); - ccid_hc_rx_exit(newdp->dccps_hc_rx_ccid, newsk); - ccid_hc_tx_exit(newdp->dccps_hc_tx_ccid, newsk); + ccid_hc_rx_delete(newdp->dccps_hc_rx_ccid, newsk); + ccid_hc_tx_delete(newdp->dccps_hc_tx_ccid, newsk); out_free: /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ @@ -143,9 +145,6 @@ out_free: return NULL; } - __ccid_get(newdp->dccps_hc_rx_ccid); - __ccid_get(newdp->dccps_hc_tx_ccid); - /* * Step 3: Process LISTEN state * @@ -155,7 +154,7 @@ out_free: */ /* See dccp_v4_conn_request */ - newdp->dccps_options.dccpo_sequence_window = req->rcv_wnd; + newdmsk->dccpms_sequence_window = req->rcv_wnd; newdp->dccps_gar = newdp->dccps_isr = dreq->dreq_isr; dccp_update_gsr(newsk, dreq->dreq_isr); diff --git a/net/dccp/options.c b/net/dccp/options.c index 0a76426c9aea..e9feb2a0c770 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -21,19 +21,23 @@ #include "ackvec.h" #include "ccid.h" #include "dccp.h" +#include "feat.h" -/* stores the default values for new connection. may be changed with sysctl */ -static const struct dccp_options dccpo_default_values = { - .dccpo_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW, - .dccpo_rx_ccid = DCCPF_INITIAL_CCID, - .dccpo_tx_ccid = DCCPF_INITIAL_CCID, - .dccpo_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR, - .dccpo_send_ndp_count = DCCPF_INITIAL_SEND_NDP_COUNT, -}; +int dccp_feat_default_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW; +int dccp_feat_default_rx_ccid = DCCPF_INITIAL_CCID; +int dccp_feat_default_tx_ccid = DCCPF_INITIAL_CCID; +int dccp_feat_default_ack_ratio = DCCPF_INITIAL_ACK_RATIO; +int dccp_feat_default_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR; +int dccp_feat_default_send_ndp_count = DCCPF_INITIAL_SEND_NDP_COUNT; -void dccp_options_init(struct dccp_options *dccpo) +void dccp_minisock_init(struct dccp_minisock *dmsk) { - memcpy(dccpo, &dccpo_default_values, sizeof(*dccpo)); + dmsk->dccpms_sequence_window = dccp_feat_default_sequence_window; + dmsk->dccpms_rx_ccid = dccp_feat_default_rx_ccid; + dmsk->dccpms_tx_ccid = dccp_feat_default_tx_ccid; + dmsk->dccpms_ack_ratio = dccp_feat_default_ack_ratio; + dmsk->dccpms_send_ack_vector = dccp_feat_default_send_ack_vector; + dmsk->dccpms_send_ndp_count = dccp_feat_default_send_ndp_count; } static u32 dccp_decode_value_var(const unsigned char *bf, const u8 len) @@ -69,9 +73,12 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) unsigned char opt, len; unsigned char *value; u32 elapsed_time; + int rc; + int mandatory = 0; memset(opt_recv, 0, sizeof(*opt_recv)); + opt = len = 0; while (opt_ptr != opt_end) { opt = *opt_ptr++; len = 0; @@ -100,6 +107,12 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) switch (opt) { case DCCPO_PADDING: break; + case DCCPO_MANDATORY: + if (mandatory) + goto out_invalid_option; + if (pkt_type != DCCP_PKT_DATA) + mandatory = 1; + break; case DCCPO_NDP_COUNT: if (len > 3) goto out_invalid_option; @@ -108,12 +121,37 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) dccp_pr_debug("%sNDP count=%d\n", debug_prefix, opt_recv->dccpor_ndp); break; + case DCCPO_CHANGE_L: + /* fall through */ + case DCCPO_CHANGE_R: + if (len < 2) + goto out_invalid_option; + rc = dccp_feat_change_recv(sk, opt, *value, value + 1, + len - 1); + /* + * When there is a change error, change_recv is + * responsible for dealing with it. i.e. reply with an + * empty confirm. + * If the change was mandatory, then we need to die. + */ + if (rc && mandatory) + goto out_invalid_option; + break; + case DCCPO_CONFIRM_L: + /* fall through */ + case DCCPO_CONFIRM_R: + if (len < 2) + goto out_invalid_option; + if (dccp_feat_confirm_recv(sk, opt, *value, + value + 1, len - 1)) + goto out_invalid_option; + break; case DCCPO_ACK_VECTOR_0: case DCCPO_ACK_VECTOR_1: if (pkt_type == DCCP_PKT_DATA) - continue; + break; - if (dp->dccps_options.dccpo_send_ack_vector && + if (dccp_msk(sk)->dccpms_send_ack_vector && dccp_ackvec_parse(sk, skb, opt, value, len)) goto out_invalid_option; break; @@ -121,7 +159,7 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) if (len != 4) goto out_invalid_option; - opt_recv->dccpor_timestamp = ntohl(*(u32 *)value); + opt_recv->dccpor_timestamp = ntohl(*(__be32 *)value); dp->dccps_timestamp_echo = opt_recv->dccpor_timestamp; dccp_timestamp(sk, &dp->dccps_timestamp_time); @@ -135,7 +173,7 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) if (len != 4 && len != 6 && len != 8) goto out_invalid_option; - opt_recv->dccpor_timestamp_echo = ntohl(*(u32 *)value); + opt_recv->dccpor_timestamp_echo = ntohl(*(__be32 *)value); dccp_pr_debug("%sTIMESTAMP_ECHO=%u, len=%d, ackno=%llu, ", debug_prefix, @@ -149,9 +187,9 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) break; if (len == 6) - elapsed_time = ntohs(*(u16 *)(value + 4)); + elapsed_time = ntohs(*(__be16 *)(value + 4)); else - elapsed_time = ntohl(*(u32 *)(value + 4)); + elapsed_time = ntohl(*(__be32 *)(value + 4)); /* Give precedence to the biggest ELAPSED_TIME */ if (elapsed_time > opt_recv->dccpor_elapsed_time) @@ -165,9 +203,9 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) continue; if (len == 2) - elapsed_time = ntohs(*(u16 *)value); + elapsed_time = ntohs(*(__be16 *)value); else - elapsed_time = ntohl(*(u32 *)value); + elapsed_time = ntohl(*(__be32 *)value); if (elapsed_time > opt_recv->dccpor_elapsed_time) opt_recv->dccpor_elapsed_time = elapsed_time; @@ -208,8 +246,15 @@ int dccp_parse_options(struct sock *sk, struct sk_buff *skb) sk, opt, len); break; } + + if (opt != DCCPO_MANDATORY) + mandatory = 0; } + /* mandatory was the last byte in option list -> reset connection */ + if (mandatory) + goto out_invalid_option; + return 0; out_invalid_option: @@ -219,6 +264,8 @@ out_invalid_option: return -1; } +EXPORT_SYMBOL_GPL(dccp_parse_options); + static void dccp_encode_value_var(const u32 value, unsigned char *to, const unsigned int len) { @@ -237,17 +284,14 @@ static inline int dccp_ndp_len(const int ndp) return likely(ndp <= 0xFF) ? 1 : ndp <= 0xFFFF ? 2 : 3; } -void dccp_insert_option(struct sock *sk, struct sk_buff *skb, +int dccp_insert_option(struct sock *sk, struct sk_buff *skb, const unsigned char option, const void *value, const unsigned char len) { unsigned char *to; - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN) { - LIMIT_NETDEBUG(KERN_INFO "DCCP: packet too small to insert " - "%d option!\n", option); - return; - } + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN) + return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len + 2; @@ -256,11 +300,12 @@ void dccp_insert_option(struct sock *sk, struct sk_buff *skb, *to++ = len + 2; memcpy(to, value, len); + return 0; } EXPORT_SYMBOL_GPL(dccp_insert_option); -static void dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) +static int dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); int ndp = dp->dccps_ndp_count; @@ -276,7 +321,7 @@ static void dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) const int len = ndp_len + 2; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) - return; + return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; @@ -285,6 +330,8 @@ static void dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) *ptr++ = len; dccp_encode_value_var(ndp, ptr, ndp_len); } + + return 0; } static inline int dccp_elapsed_time_len(const u32 elapsed_time) @@ -292,27 +339,18 @@ static inline int dccp_elapsed_time_len(const u32 elapsed_time) return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4; } -void dccp_insert_option_elapsed_time(struct sock *sk, - struct sk_buff *skb, - u32 elapsed_time) +int dccp_insert_option_elapsed_time(struct sock *sk, struct sk_buff *skb, + u32 elapsed_time) { -#ifdef CONFIG_IP_DCCP_DEBUG - struct dccp_sock *dp = dccp_sk(sk); - const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? - "CLIENT TX opt: " : "server TX opt: "; -#endif const int elapsed_time_len = dccp_elapsed_time_len(elapsed_time); const int len = 2 + elapsed_time_len; unsigned char *to; if (elapsed_time_len == 0) - return; + return 0; - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) { - LIMIT_NETDEBUG(KERN_INFO "DCCP: packet too small to " - "insert elapsed time!\n"); - return; - } + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; @@ -321,17 +359,14 @@ void dccp_insert_option_elapsed_time(struct sock *sk, *to++ = len; if (elapsed_time_len == 2) { - const u16 var16 = htons((u16)elapsed_time); + const __be16 var16 = htons((u16)elapsed_time); memcpy(to, &var16, 2); } else { - const u32 var32 = htonl(elapsed_time); + const __be32 var32 = htonl(elapsed_time); memcpy(to, &var32, 4); } - dccp_pr_debug("%sELAPSED_TIME=%u, len=%d, seqno=%llu\n", - debug_prefix, elapsed_time, - len, - (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq); + return 0; } EXPORT_SYMBOL_GPL(dccp_insert_option_elapsed_time); @@ -352,32 +387,27 @@ void dccp_timestamp(const struct sock *sk, struct timeval *tv) EXPORT_SYMBOL_GPL(dccp_timestamp); -void dccp_insert_option_timestamp(struct sock *sk, struct sk_buff *skb) +int dccp_insert_option_timestamp(struct sock *sk, struct sk_buff *skb) { struct timeval tv; - u32 now; - + __be32 now; + dccp_timestamp(sk, &tv); - now = timeval_usecs(&tv) / 10; + now = htonl(timeval_usecs(&tv) / 10); /* yes this will overflow but that is the point as we want a * 10 usec 32 bit timer which mean it wraps every 11.9 hours */ - now = htonl(now); - dccp_insert_option(sk, skb, DCCPO_TIMESTAMP, &now, sizeof(now)); + return dccp_insert_option(sk, skb, DCCPO_TIMESTAMP, &now, sizeof(now)); } EXPORT_SYMBOL_GPL(dccp_insert_option_timestamp); -static void dccp_insert_option_timestamp_echo(struct sock *sk, - struct sk_buff *skb) +static int dccp_insert_option_timestamp_echo(struct sock *sk, + struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); -#ifdef CONFIG_IP_DCCP_DEBUG - const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? - "CLIENT TX opt: " : "server TX opt: "; -#endif struct timeval now; - u32 tstamp_echo; + __be32 tstamp_echo; u32 elapsed_time; int len, elapsed_time_len; unsigned char *to; @@ -387,11 +417,8 @@ static void dccp_insert_option_timestamp_echo(struct sock *sk, elapsed_time_len = dccp_elapsed_time_len(elapsed_time); len = 6 + elapsed_time_len; - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) { - LIMIT_NETDEBUG(KERN_INFO "DCCP: packet too small to insert " - "timestamp echo!\n"); - return; - } + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) + return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; @@ -402,51 +429,149 @@ static void dccp_insert_option_timestamp_echo(struct sock *sk, tstamp_echo = htonl(dp->dccps_timestamp_echo); memcpy(to, &tstamp_echo, 4); to += 4; - + if (elapsed_time_len == 2) { - const u16 var16 = htons((u16)elapsed_time); + const __be16 var16 = htons((u16)elapsed_time); memcpy(to, &var16, 2); } else if (elapsed_time_len == 4) { - const u32 var32 = htonl(elapsed_time); + const __be32 var32 = htonl(elapsed_time); memcpy(to, &var32, 4); } - dccp_pr_debug("%sTIMESTAMP_ECHO=%u, len=%d, seqno=%llu\n", - debug_prefix, dp->dccps_timestamp_echo, - len, - (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq); - dp->dccps_timestamp_echo = 0; dp->dccps_timestamp_time.tv_sec = 0; dp->dccps_timestamp_time.tv_usec = 0; + return 0; } -void dccp_insert_options(struct sock *sk, struct sk_buff *skb) +static int dccp_insert_feat_opt(struct sk_buff *skb, u8 type, u8 feat, + u8 *val, u8 len) +{ + u8 *to; + + if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 3 > DCCP_MAX_OPT_LEN) { + LIMIT_NETDEBUG(KERN_INFO "DCCP: packet too small" + " to insert feature %d option!\n", feat); + return -1; + } + + DCCP_SKB_CB(skb)->dccpd_opt_len += len + 3; + + to = skb_push(skb, len + 3); + *to++ = type; + *to++ = len + 3; + *to++ = feat; + + if (len) + memcpy(to, val, len); + dccp_pr_debug("option %d feat %d len %d\n", type, feat, len); + + return 0; +} + +static int dccp_insert_options_feat(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); + struct dccp_opt_pend *opt, *next; + int change = 0; + + /* confirm any options [NN opts] */ + list_for_each_entry_safe(opt, next, &dmsk->dccpms_conf, dccpop_node) { + dccp_insert_feat_opt(skb, opt->dccpop_type, + opt->dccpop_feat, opt->dccpop_val, + opt->dccpop_len); + /* fear empty confirms */ + if (opt->dccpop_val) + kfree(opt->dccpop_val); + kfree(opt); + } + INIT_LIST_HEAD(&dmsk->dccpms_conf); + + /* see which features we need to send */ + list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { + /* see if we need to send any confirm */ + if (opt->dccpop_sc) { + dccp_insert_feat_opt(skb, opt->dccpop_type + 1, + opt->dccpop_feat, + opt->dccpop_sc->dccpoc_val, + opt->dccpop_sc->dccpoc_len); + + BUG_ON(!opt->dccpop_sc->dccpoc_val); + kfree(opt->dccpop_sc->dccpoc_val); + kfree(opt->dccpop_sc); + opt->dccpop_sc = NULL; + } + + /* any option not confirmed, re-send it */ + if (!opt->dccpop_conf) { + dccp_insert_feat_opt(skb, opt->dccpop_type, + opt->dccpop_feat, opt->dccpop_val, + opt->dccpop_len); + change++; + } + } + + /* Retransmit timer. + * If this is the master listening sock, we don't set a timer on it. It + * should be fine because if the dude doesn't receive our RESPONSE + * [which will contain the CHANGE] he will send another REQUEST which + * will "retrnasmit" the change. + */ + if (change && dp->dccps_role != DCCP_ROLE_LISTEN) { + dccp_pr_debug("reset feat negotiation timer %p\n", sk); + + /* XXX don't reset the timer on re-transmissions. I.e. reset it + * only when sending new stuff i guess. Currently the timer + * never backs off because on re-transmission it just resets it! + */ + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + inet_csk(sk)->icsk_rto, DCCP_RTO_MAX); + } + + return 0; +} + +int dccp_insert_options(struct sock *sk, struct sk_buff *skb) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); DCCP_SKB_CB(skb)->dccpd_opt_len = 0; - if (dp->dccps_options.dccpo_send_ndp_count) - dccp_insert_option_ndp(sk, skb); + if (dmsk->dccpms_send_ndp_count && + dccp_insert_option_ndp(sk, skb)) + return -1; if (!dccp_packet_without_ack(skb)) { - if (dp->dccps_options.dccpo_send_ack_vector && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) - dccp_insert_option_ackvec(sk, skb); - if (dp->dccps_timestamp_echo != 0) - dccp_insert_option_timestamp_echo(sk, skb); + if (dmsk->dccpms_send_ack_vector && + dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) && + dccp_insert_option_ackvec(sk, skb)) + return -1; + + if (dp->dccps_timestamp_echo != 0 && + dccp_insert_option_timestamp_echo(sk, skb)) + return -1; } if (dp->dccps_hc_rx_insert_options) { - ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb); + if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb)) + return -1; dp->dccps_hc_rx_insert_options = 0; } if (dp->dccps_hc_tx_insert_options) { - ccid_hc_tx_insert_options(dp->dccps_hc_tx_ccid, sk, skb); + if (ccid_hc_tx_insert_options(dp->dccps_hc_tx_ccid, sk, skb)) + return -1; dp->dccps_hc_tx_insert_options = 0; } + /* Feature negotiation */ + /* Data packets can't do feat negotiation */ + if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA && + DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATAACK && + dccp_insert_options_feat(sk, skb)) + return -1; + /* XXX: insert other options when appropriate */ if (DCCP_SKB_CB(skb)->dccpd_opt_len != 0) { @@ -459,4 +584,6 @@ void dccp_insert_options(struct sock *sk, struct sk_buff *skb) DCCP_SKB_CB(skb)->dccpd_opt_len += padding; } } + + return 0; } diff --git a/net/dccp/output.c b/net/dccp/output.c index efd7ffb903a1..7409e4a3abdf 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -27,7 +27,7 @@ static inline void dccp_event_ack_sent(struct sock *sk) inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } -static inline void dccp_skb_entail(struct sock *sk, struct sk_buff *skb) +static void dccp_skb_entail(struct sock *sk, struct sk_buff *skb) { skb_set_owner_w(skb, sk); WARN_ON(sk->sk_send_head); @@ -49,7 +49,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); struct dccp_hdr *dh; /* XXX For now we're using only 48 bits sequence numbers */ - const int dccp_header_size = sizeof(*dh) + + const u32 dccp_header_size = sizeof(*dh) + sizeof(struct dccp_hdr_ext) + dccp_packet_hdr_len(dcb->dccpd_type); int err, set_ack = 1; @@ -64,6 +64,10 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) case DCCP_PKT_DATAACK: break; + case DCCP_PKT_REQUEST: + set_ack = 0; + /* fall through */ + case DCCP_PKT_SYNC: case DCCP_PKT_SYNCACK: ackno = dcb->dccpd_seq; @@ -79,7 +83,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) } dcb->dccpd_seq = dp->dccps_gss; - dccp_insert_options(sk, skb); + + if (dccp_insert_options(sk, skb)) { + kfree_skb(skb); + return -EPROTO; + } skb->h.raw = skb_push(skb, dccp_header_size); dh = dccp_hdr(skb); @@ -275,17 +283,16 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, { struct dccp_hdr *dh; struct dccp_request_sock *dreq; - const int dccp_header_size = sizeof(struct dccp_hdr) + + const u32 dccp_header_size = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_response); - struct sk_buff *skb = sock_wmalloc(sk, MAX_HEADER + DCCP_MAX_OPT_LEN + - dccp_header_size, 1, + struct sk_buff *skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1, GFP_ATOMIC); if (skb == NULL) return NULL; /* Reserve space for headers. */ - skb_reserve(skb, MAX_HEADER + DCCP_MAX_OPT_LEN + dccp_header_size); + skb_reserve(skb, sk->sk_prot->max_header); skb->dst = dst_clone(dst); skb->csum = 0; @@ -293,7 +300,11 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, dreq = dccp_rsk(req); DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESPONSE; DCCP_SKB_CB(skb)->dccpd_seq = dreq->dreq_iss; - dccp_insert_options(sk, skb); + + if (dccp_insert_options(sk, skb)) { + kfree_skb(skb); + return NULL; + } skb->h.raw = skb_push(skb, dccp_header_size); @@ -310,32 +321,28 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dreq->dreq_isr); dccp_hdr_response(skb)->dccph_resp_service = dreq->dreq_service; - dh->dccph_checksum = dccp_v4_checksum(skb, inet_rsk(req)->loc_addr, - inet_rsk(req)->rmt_addr); - DCCP_INC_STATS(DCCP_MIB_OUTSEGS); return skb; } EXPORT_SYMBOL_GPL(dccp_make_response); -struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, - const enum dccp_reset_codes code) +static struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, + const enum dccp_reset_codes code) { struct dccp_hdr *dh; struct dccp_sock *dp = dccp_sk(sk); - const int dccp_header_size = sizeof(struct dccp_hdr) + + const u32 dccp_header_size = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_reset); - struct sk_buff *skb = sock_wmalloc(sk, MAX_HEADER + DCCP_MAX_OPT_LEN + - dccp_header_size, 1, + struct sk_buff *skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1, GFP_ATOMIC); if (skb == NULL) return NULL; /* Reserve space for headers. */ - skb_reserve(skb, MAX_HEADER + DCCP_MAX_OPT_LEN + dccp_header_size); + skb_reserve(skb, sk->sk_prot->max_header); skb->dst = dst_clone(dst); skb->csum = 0; @@ -345,7 +352,11 @@ struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, DCCP_SKB_CB(skb)->dccpd_reset_code = code; DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESET; DCCP_SKB_CB(skb)->dccpd_seq = dp->dccps_gss; - dccp_insert_options(sk, skb); + + if (dccp_insert_options(sk, skb)) { + kfree_skb(skb); + return NULL; + } skb->h.raw = skb_push(skb, dccp_header_size); @@ -362,14 +373,34 @@ struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dp->dccps_gsr); dccp_hdr_reset(skb)->dccph_reset_code = code; - - dh->dccph_checksum = dccp_v4_checksum(skb, inet_sk(sk)->saddr, - inet_sk(sk)->daddr); + inet_csk(sk)->icsk_af_ops->send_check(sk, skb->len, skb); DCCP_INC_STATS(DCCP_MIB_OUTSEGS); return skb; } +int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code) +{ + /* + * FIXME: what if rebuild_header fails? + * Should we be doing a rebuild_header here? + */ + int err = inet_sk_rebuild_header(sk); + + if (err == 0) { + struct sk_buff *skb = dccp_make_reset(sk, sk->sk_dst_cache, + code); + if (skb != NULL) { + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + err = inet_csk(sk)->icsk_af_ops->queue_xmit(skb, 0); + if (err == NET_XMIT_CN) + err = 0; + } + } + + return err; +} + /* * Do all connect socket setups that can be done AF independent. */ @@ -405,12 +436,12 @@ int dccp_connect(struct sock *sk) dccp_connect_init(sk); - skb = alloc_skb(MAX_DCCP_HEADER + 15, sk->sk_allocation); + skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation); if (unlikely(skb == NULL)) return -ENOBUFS; /* Reserve space for headers. */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, sk->sk_prot->max_header); DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_REQUEST; skb->csum = 0; @@ -431,7 +462,8 @@ void dccp_send_ack(struct sock *sk) { /* If we have been reset, we may not send again. */ if (sk->sk_state != DCCP_CLOSED) { - struct sk_buff *skb = alloc_skb(MAX_DCCP_HEADER, GFP_ATOMIC); + struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, + GFP_ATOMIC); if (skb == NULL) { inet_csk_schedule_ack(sk); @@ -443,7 +475,7 @@ void dccp_send_ack(struct sock *sk) } /* Reserve space for headers */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, sk->sk_prot->max_header); skb->csum = 0; DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_ACK; dccp_transmit_skb(sk, skb); @@ -490,14 +522,14 @@ void dccp_send_sync(struct sock *sk, const u64 seq, * dccp_transmit_skb() will set the ownership to this * sock. */ - struct sk_buff *skb = alloc_skb(MAX_DCCP_HEADER, GFP_ATOMIC); + struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC); if (skb == NULL) /* FIXME: how to make sure the sync is sent? */ return; /* Reserve space for headers and prepare control bits. */ - skb_reserve(skb, MAX_DCCP_HEADER); + skb_reserve(skb, sk->sk_prot->max_header); skb->csum = 0; DCCP_SKB_CB(skb)->dccpd_type = pkt_type; DCCP_SKB_CB(skb)->dccpd_seq = seq; @@ -505,6 +537,8 @@ void dccp_send_sync(struct sock *sk, const u64 seq, dccp_transmit_skb(sk, skb); } +EXPORT_SYMBOL_GPL(dccp_send_sync); + /* * Send a DCCP_PKT_CLOSE/CLOSEREQ. The caller locks the socket for us. This * cannot be allowed to fail queueing a DCCP_PKT_CLOSE/CLOSEREQ frame under diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 65b11ea90d85..d4b293e16283 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -23,9 +23,7 @@ #include <linux/random.h> #include <net/checksum.h> -#include <net/inet_common.h> #include <net/inet_sock.h> -#include <net/protocol.h> #include <net/sock.h> #include <net/xfrm.h> @@ -37,6 +35,7 @@ #include "ccid.h" #include "dccp.h" +#include "feat.h" DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; @@ -46,12 +45,66 @@ atomic_t dccp_orphan_count = ATOMIC_INIT(0); EXPORT_SYMBOL_GPL(dccp_orphan_count); -static struct net_protocol dccp_protocol = { - .handler = dccp_v4_rcv, - .err_handler = dccp_v4_err, - .no_policy = 1, +struct inet_hashinfo __cacheline_aligned dccp_hashinfo = { + .lhash_lock = RW_LOCK_UNLOCKED, + .lhash_users = ATOMIC_INIT(0), + .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait), }; +EXPORT_SYMBOL_GPL(dccp_hashinfo); + +void dccp_set_state(struct sock *sk, const int state) +{ + const int oldstate = sk->sk_state; + + dccp_pr_debug("%s(%p) %-10.10s -> %s\n", + dccp_role(sk), sk, + dccp_state_name(oldstate), dccp_state_name(state)); + WARN_ON(state == oldstate); + + switch (state) { + case DCCP_OPEN: + if (oldstate != DCCP_OPEN) + DCCP_INC_STATS(DCCP_MIB_CURRESTAB); + break; + + case DCCP_CLOSED: + if (oldstate == DCCP_CLOSING || oldstate == DCCP_OPEN) + DCCP_INC_STATS(DCCP_MIB_ESTABRESETS); + + sk->sk_prot->unhash(sk); + if (inet_csk(sk)->icsk_bind_hash != NULL && + !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + inet_put_port(&dccp_hashinfo, sk); + /* fall through */ + default: + if (oldstate == DCCP_OPEN) + DCCP_DEC_STATS(DCCP_MIB_CURRESTAB); + } + + /* Change state AFTER socket is unhashed to avoid closed + * socket sitting in hash tables. + */ + sk->sk_state = state; +} + +EXPORT_SYMBOL_GPL(dccp_set_state); + +void dccp_done(struct sock *sk) +{ + dccp_set_state(sk, DCCP_CLOSED); + dccp_clear_xmit_timers(sk); + + sk->sk_shutdown = SHUTDOWN_MASK; + + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_state_change(sk); + else + inet_csk_destroy_sock(sk); +} + +EXPORT_SYMBOL_GPL(dccp_done); + const char *dccp_packet_name(const int type) { static const char *dccp_packet_names[] = { @@ -96,6 +149,120 @@ const char *dccp_state_name(const int state) EXPORT_SYMBOL_GPL(dccp_state_name); +void dccp_hash(struct sock *sk) +{ + inet_hash(&dccp_hashinfo, sk); +} + +EXPORT_SYMBOL_GPL(dccp_hash); + +void dccp_unhash(struct sock *sk) +{ + inet_unhash(&dccp_hashinfo, sk); +} + +EXPORT_SYMBOL_GPL(dccp_unhash); + +int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + + dccp_minisock_init(&dp->dccps_minisock); + do_gettimeofday(&dp->dccps_epoch); + + /* + * FIXME: We're hardcoding the CCID, and doing this at this point makes + * the listening (master) sock get CCID control blocks, which is not + * necessary, but for now, to not mess with the test userspace apps, + * lets leave it here, later the real solution is to do this in a + * setsockopt(CCIDs-I-want/accept). -acme + */ + if (likely(ctl_sock_initialized)) { + int rc = dccp_feat_init(dmsk); + + if (rc) + return rc; + + if (dmsk->dccpms_send_ack_vector) { + dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(GFP_KERNEL); + if (dp->dccps_hc_rx_ackvec == NULL) + return -ENOMEM; + } + dp->dccps_hc_rx_ccid = ccid_hc_rx_new(dmsk->dccpms_rx_ccid, + sk, GFP_KERNEL); + dp->dccps_hc_tx_ccid = ccid_hc_tx_new(dmsk->dccpms_tx_ccid, + sk, GFP_KERNEL); + if (unlikely(dp->dccps_hc_rx_ccid == NULL || + dp->dccps_hc_tx_ccid == NULL)) { + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + if (dmsk->dccpms_send_ack_vector) { + dccp_ackvec_free(dp->dccps_hc_rx_ackvec); + dp->dccps_hc_rx_ackvec = NULL; + } + dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; + return -ENOMEM; + } + } else { + /* control socket doesn't need feat nego */ + INIT_LIST_HEAD(&dmsk->dccpms_pending); + INIT_LIST_HEAD(&dmsk->dccpms_conf); + } + + dccp_init_xmit_timers(sk); + icsk->icsk_rto = DCCP_TIMEOUT_INIT; + sk->sk_state = DCCP_CLOSED; + sk->sk_write_space = dccp_write_space; + icsk->icsk_sync_mss = dccp_sync_mss; + dp->dccps_mss_cache = 536; + dp->dccps_role = DCCP_ROLE_UNDEFINED; + dp->dccps_service = DCCP_SERVICE_INVALID_VALUE; + dp->dccps_l_ack_ratio = dp->dccps_r_ack_ratio = 1; + + return 0; +} + +EXPORT_SYMBOL_GPL(dccp_init_sock); + +int dccp_destroy_sock(struct sock *sk) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_minisock *dmsk = dccp_msk(sk); + + /* + * DCCP doesn't use sk_write_queue, just sk_send_head + * for retransmissions + */ + if (sk->sk_send_head != NULL) { + kfree_skb(sk->sk_send_head); + sk->sk_send_head = NULL; + } + + /* Clean up a referenced DCCP bind bucket. */ + if (inet_csk(sk)->icsk_bind_hash != NULL) + inet_put_port(&dccp_hashinfo, sk); + + kfree(dp->dccps_service_list); + dp->dccps_service_list = NULL; + + if (dmsk->dccpms_send_ack_vector) { + dccp_ackvec_free(dp->dccps_hc_rx_ackvec); + dp->dccps_hc_rx_ackvec = NULL; + } + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; + + /* clean up feature negotiation state */ + dccp_feat_clean(dmsk); + + return 0; +} + +EXPORT_SYMBOL_GPL(dccp_destroy_sock); + static inline int dccp_listen_start(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); @@ -220,7 +387,7 @@ int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) EXPORT_SYMBOL_GPL(dccp_ioctl); -static int dccp_setsockopt_service(struct sock *sk, const u32 service, +static int dccp_setsockopt_service(struct sock *sk, const __be32 service, char __user *optval, int optlen) { struct dccp_sock *dp = dccp_sk(sk); @@ -255,18 +422,46 @@ static int dccp_setsockopt_service(struct sock *sk, const u32 service, return 0; } -int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) +/* byte 1 is feature. the rest is the preference list */ +static int dccp_setsockopt_change(struct sock *sk, int type, + struct dccp_so_feat __user *optval) +{ + struct dccp_so_feat opt; + u8 *val; + int rc; + + if (copy_from_user(&opt, optval, sizeof(opt))) + return -EFAULT; + + val = kmalloc(opt.dccpsf_len, GFP_KERNEL); + if (!val) + return -ENOMEM; + + if (copy_from_user(val, opt.dccpsf_val, opt.dccpsf_len)) { + rc = -EFAULT; + goto out_free_val; + } + + rc = dccp_feat_change(dccp_msk(sk), type, opt.dccpsf_feat, + val, opt.dccpsf_len, GFP_KERNEL); + if (rc) + goto out_free_val; + +out: + return rc; + +out_free_val: + kfree(val); + goto out; +} + +static int do_dccp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) { struct dccp_sock *dp; int err; int val; - if (level != SOL_DCCP) - return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, - optname, optval, - optlen); - if (optlen < sizeof(int)) return -EINVAL; @@ -284,6 +479,25 @@ int dccp_setsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_PACKET_SIZE: dp->dccps_packet_size = val; break; + + case DCCP_SOCKOPT_CHANGE_L: + if (optlen != sizeof(struct dccp_so_feat)) + err = -EINVAL; + else + err = dccp_setsockopt_change(sk, DCCPO_CHANGE_L, + (struct dccp_so_feat *) + optval); + break; + + case DCCP_SOCKOPT_CHANGE_R: + if (optlen != sizeof(struct dccp_so_feat)) + err = -EINVAL; + else + err = dccp_setsockopt_change(sk, DCCPO_CHANGE_R, + (struct dccp_so_feat *) + optval); + break; + default: err = -ENOPROTOOPT; break; @@ -293,10 +507,33 @@ int dccp_setsockopt(struct sock *sk, int level, int optname, return err; } +int dccp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level != SOL_DCCP) + return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, + optname, optval, + optlen); + return do_dccp_setsockopt(sk, level, optname, optval, optlen); +} + EXPORT_SYMBOL_GPL(dccp_setsockopt); +#ifdef CONFIG_COMPAT +int compat_dccp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level != SOL_DCCP) + return inet_csk_compat_setsockopt(sk, level, optname, + optval, optlen); + return do_dccp_setsockopt(sk, level, optname, optval, optlen); +} + +EXPORT_SYMBOL_GPL(compat_dccp_setsockopt); +#endif + static int dccp_getsockopt_service(struct sock *sk, int len, - u32 __user *optval, + __be32 __user *optval, int __user *optlen) { const struct dccp_sock *dp = dccp_sk(sk); @@ -326,16 +563,12 @@ out: return err; } -int dccp_getsockopt(struct sock *sk, int level, int optname, +static int do_dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct dccp_sock *dp; int val, len; - if (level != SOL_DCCP) - return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level, - optname, optval, - optlen); if (get_user(len, optlen)) return -EFAULT; @@ -351,7 +584,7 @@ int dccp_getsockopt(struct sock *sk, int level, int optname, break; case DCCP_SOCKOPT_SERVICE: return dccp_getsockopt_service(sk, len, - (u32 __user *)optval, optlen); + (__be32 __user *)optval, optlen); case 128 ... 191: return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname, len, (u32 __user *)optval, optlen); @@ -368,8 +601,31 @@ int dccp_getsockopt(struct sock *sk, int level, int optname, return 0; } +int dccp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_DCCP) + return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level, + optname, optval, + optlen); + return do_dccp_getsockopt(sk, level, optname, optval, optlen); +} + EXPORT_SYMBOL_GPL(dccp_getsockopt); +#ifdef CONFIG_COMPAT +int compat_dccp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_DCCP) + return inet_csk_compat_getsockopt(sk, level, optname, + optval, optlen); + return do_dccp_getsockopt(sk, level, optname, optval, optlen); +} + +EXPORT_SYMBOL_GPL(compat_dccp_getsockopt); +#endif + int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { @@ -679,84 +935,7 @@ void dccp_shutdown(struct sock *sk, int how) EXPORT_SYMBOL_GPL(dccp_shutdown); -static const struct proto_ops inet_dccp_ops = { - .family = PF_INET, - .owner = THIS_MODULE, - .release = inet_release, - .bind = inet_bind, - .connect = inet_stream_connect, - .socketpair = sock_no_socketpair, - .accept = inet_accept, - .getname = inet_getname, - /* FIXME: work on tcp_poll to rename it to inet_csk_poll */ - .poll = dccp_poll, - .ioctl = inet_ioctl, - /* FIXME: work on inet_listen to rename it to sock_common_listen */ - .listen = inet_dccp_listen, - .shutdown = inet_shutdown, - .setsockopt = sock_common_setsockopt, - .getsockopt = sock_common_getsockopt, - .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, -}; - -extern struct net_proto_family inet_family_ops; - -static struct inet_protosw dccp_v4_protosw = { - .type = SOCK_DCCP, - .protocol = IPPROTO_DCCP, - .prot = &dccp_prot, - .ops = &inet_dccp_ops, - .capability = -1, - .no_check = 0, - .flags = INET_PROTOSW_ICSK, -}; - -/* - * This is the global socket data structure used for responding to - * the Out-of-the-blue (OOTB) packets. A control sock will be created - * for this socket at the initialization time. - */ -struct socket *dccp_ctl_socket; - -static char dccp_ctl_socket_err_msg[] __initdata = - KERN_ERR "DCCP: Failed to create the control socket.\n"; - -static int __init dccp_ctl_sock_init(void) -{ - int rc = sock_create_kern(PF_INET, SOCK_DCCP, IPPROTO_DCCP, - &dccp_ctl_socket); - if (rc < 0) - printk(dccp_ctl_socket_err_msg); - else { - dccp_ctl_socket->sk->sk_allocation = GFP_ATOMIC; - inet_sk(dccp_ctl_socket->sk)->uc_ttl = -1; - - /* Unhash it so that IP input processing does not even - * see it, we do not wish this socket to see incoming - * packets. - */ - dccp_ctl_socket->sk->sk_prot->unhash(dccp_ctl_socket->sk); - } - - return rc; -} - -#ifdef CONFIG_IP_DCCP_UNLOAD_HACK -void dccp_ctl_sock_exit(void) -{ - if (dccp_ctl_socket != NULL) { - sock_release(dccp_ctl_socket); - dccp_ctl_socket = NULL; - } -} - -EXPORT_SYMBOL_GPL(dccp_ctl_sock_exit); -#endif - -static int __init init_dccp_v4_mibs(void) +static int __init dccp_mib_init(void) { int rc = -ENOMEM; @@ -778,6 +957,13 @@ out_free_one: } +static void dccp_mib_exit(void) +{ + free_percpu(dccp_statistics[0]); + free_percpu(dccp_statistics[1]); + dccp_statistics[0] = dccp_statistics[1] = NULL; +} + static int thash_entries; module_param(thash_entries, int, 0444); MODULE_PARM_DESC(thash_entries, "Number of ehash buckets"); @@ -794,17 +980,14 @@ static int __init dccp_init(void) { unsigned long goal; int ehash_order, bhash_order, i; - int rc = proto_register(&dccp_prot, 1); - - if (rc) - goto out; + int rc = -ENOBUFS; dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN, NULL, NULL); if (!dccp_hashinfo.bind_bucket_cachep) - goto out_proto_unregister; + goto out; /* * Size and allocate the main established and bind bucket @@ -866,27 +1049,23 @@ static int __init dccp_init(void) INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain); } - if (init_dccp_v4_mibs()) + rc = dccp_mib_init(); + if (rc) goto out_free_dccp_bhash; - rc = -EAGAIN; - if (inet_add_protocol(&dccp_protocol, IPPROTO_DCCP)) - goto out_free_dccp_v4_mibs; - - inet_register_protosw(&dccp_v4_protosw); + rc = dccp_ackvec_init(); + if (rc) + goto out_free_dccp_mib; - rc = dccp_ctl_sock_init(); + rc = dccp_sysctl_init(); if (rc) - goto out_unregister_protosw; + goto out_ackvec_exit; out: return rc; -out_unregister_protosw: - inet_unregister_protosw(&dccp_v4_protosw); - inet_del_protocol(&dccp_protocol, IPPROTO_DCCP); -out_free_dccp_v4_mibs: - free_percpu(dccp_statistics[0]); - free_percpu(dccp_statistics[1]); - dccp_statistics[0] = dccp_statistics[1] = NULL; +out_ackvec_exit: + dccp_ackvec_exit(); +out_free_dccp_mib: + dccp_mib_exit(); out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); dccp_hashinfo.bhash = NULL; @@ -896,23 +1075,12 @@ out_free_dccp_ehash: out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_hashinfo.bind_bucket_cachep = NULL; -out_proto_unregister: - proto_unregister(&dccp_prot); goto out; } -static const char dccp_del_proto_err_msg[] __exitdata = - KERN_ERR "can't remove dccp net_protocol\n"; - static void __exit dccp_fini(void) { - inet_unregister_protosw(&dccp_v4_protosw); - - if (inet_del_protocol(&dccp_protocol, IPPROTO_DCCP) < 0) - printk(dccp_del_proto_err_msg); - - free_percpu(dccp_statistics[0]); - free_percpu(dccp_statistics[1]); + dccp_mib_exit(); free_pages((unsigned long)dccp_hashinfo.bhash, get_order(dccp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket))); @@ -920,19 +1088,13 @@ static void __exit dccp_fini(void) get_order(dccp_hashinfo.ehash_size * sizeof(struct inet_ehash_bucket))); kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); - proto_unregister(&dccp_prot); + dccp_ackvec_exit(); + dccp_sysctl_exit(); } module_init(dccp_init); module_exit(dccp_fini); -/* - * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33) - * values directly, Also cover the case where the protocol is not specified, - * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP - */ -MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-33-type-6"); -MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-0-type-6"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@conectiva.com.br>"); MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol"); diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c new file mode 100644 index 000000000000..64c89e9c229e --- /dev/null +++ b/net/dccp/sysctl.c @@ -0,0 +1,124 @@ +/* + * net/dccp/sysctl.c + * + * An implementation of the DCCP protocol + * Arnaldo Carvalho de Melo <acme@mandriva.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License v2 + * as published by the Free Software Foundation. + */ + +#include <linux/config.h> +#include <linux/mm.h> +#include <linux/sysctl.h> + +#ifndef CONFIG_SYSCTL +#error This file should not be compiled without CONFIG_SYSCTL defined +#endif + +extern int dccp_feat_default_sequence_window; +extern int dccp_feat_default_rx_ccid; +extern int dccp_feat_default_tx_ccid; +extern int dccp_feat_default_ack_ratio; +extern int dccp_feat_default_send_ack_vector; +extern int dccp_feat_default_send_ndp_count; + +static struct ctl_table dccp_default_table[] = { + { + .ctl_name = NET_DCCP_DEFAULT_SEQ_WINDOW, + .procname = "seq_window", + .data = &dccp_feat_default_sequence_window, + .maxlen = sizeof(dccp_feat_default_sequence_window), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_RX_CCID, + .procname = "rx_ccid", + .data = &dccp_feat_default_rx_ccid, + .maxlen = sizeof(dccp_feat_default_rx_ccid), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_TX_CCID, + .procname = "tx_ccid", + .data = &dccp_feat_default_tx_ccid, + .maxlen = sizeof(dccp_feat_default_tx_ccid), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_ACK_RATIO, + .procname = "ack_ratio", + .data = &dccp_feat_default_ack_ratio, + .maxlen = sizeof(dccp_feat_default_ack_ratio), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_SEND_ACKVEC, + .procname = "send_ackvec", + .data = &dccp_feat_default_send_ack_vector, + .maxlen = sizeof(dccp_feat_default_send_ack_vector), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .ctl_name = NET_DCCP_DEFAULT_SEND_NDP, + .procname = "send_ndp", + .data = &dccp_feat_default_send_ndp_count, + .maxlen = sizeof(dccp_feat_default_send_ndp_count), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .ctl_name = 0, } +}; + +static struct ctl_table dccp_table[] = { + { + .ctl_name = NET_DCCP_DEFAULT, + .procname = "default", + .mode = 0555, + .child = dccp_default_table, + }, + { .ctl_name = 0, }, +}; + +static struct ctl_table dccp_dir_table[] = { + { + .ctl_name = NET_DCCP, + .procname = "dccp", + .mode = 0555, + .child = dccp_table, + }, + { .ctl_name = 0, }, +}; + +static struct ctl_table dccp_root_table[] = { + { + .ctl_name = CTL_NET, + .procname = "net", + .mode = 0555, + .child = dccp_dir_table, + }, + { .ctl_name = 0, }, +}; + +static struct ctl_table_header *dccp_table_header; + +int __init dccp_sysctl_init(void) +{ + dccp_table_header = register_sysctl_table(dccp_root_table, 1); + + return dccp_table_header != NULL ? 0 : -ENOMEM; +} + +void dccp_sysctl_exit(void) +{ + if (dccp_table_header != NULL) { + unregister_sysctl_table(dccp_table_header); + dccp_table_header = NULL; + } +} diff --git a/net/dccp/timer.c b/net/dccp/timer.c index aa34b576e228..5244415e5f18 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -31,7 +31,7 @@ static void dccp_write_err(struct sock *sk) sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; sk->sk_error_report(sk); - dccp_v4_send_reset(sk, DCCP_RESET_CODE_ABORTED); + dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_done(sk); DCCP_INC_STATS_BH(DCCP_MIB_ABORTONTIMEOUT); } @@ -141,6 +141,17 @@ static void dccp_retransmit_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + /* retransmit timer is used for feature negotiation throughout + * connection. In this case, no packet is re-transmitted, but rather an + * ack is generated and pending changes are splaced into its options. + */ + if (sk->sk_send_head == NULL) { + dccp_pr_debug("feat negotiation retransmit timeout %p\n", sk); + if (sk->sk_state == DCCP_OPEN) + dccp_send_ack(sk); + goto backoff; + } + /* * sk->sk_send_head has to have one skb with * DCCP_SKB_CB(skb)->dccpd_type set to one of the retransmittable DCCP @@ -177,6 +188,7 @@ static void dccp_retransmit_timer(struct sock *sk) goto out; } +backoff: icsk->icsk_backoff++; icsk->icsk_retransmits++; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index ce4aaf94860d..2b289ef20ab3 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -172,7 +172,7 @@ static struct hlist_head *dn_find_list(struct sock *sk) /* * Valid ports are those greater than zero and not already in use. */ -static int check_port(unsigned short port) +static int check_port(__le16 port) { struct sock *sk; struct hlist_node *node; @@ -661,7 +661,7 @@ disc_reject: } } -char *dn_addr2asc(dn_address addr, char *buf) +char *dn_addr2asc(__u16 addr, char *buf) { unsigned short node, area; @@ -801,7 +801,7 @@ static int dn_auto_bind(struct socket *sock) /* End of compatibility stuff */ scp->addr.sdn_add.a_len = dn_htons(2); - rv = dn_dev_bind_default((dn_address *)scp->addr.sdn_add.a_addr); + rv = dn_dev_bind_default((__le16 *)scp->addr.sdn_add.a_addr); if (rv == 0) { rv = dn_hash_sock(sk); if (rv) @@ -1021,7 +1021,7 @@ static void dn_user_copy(struct sk_buff *skb, struct optdata_dn *opt) opt->opt_optl = *ptr++; opt->opt_status = 0; memcpy(opt->opt_data, ptr, opt->opt_optl); - skb_pull(skb, opt->opt_optl + 1); + skb_pull(skb, dn_ntohs(opt->opt_optl) + 1); } @@ -1121,8 +1121,8 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) skb_pull(skb, dn_username2sockaddr(skb->data, skb->len, &(DN_SK(newsk)->addr), &type)); skb_pull(skb, dn_username2sockaddr(skb->data, skb->len, &(DN_SK(newsk)->peer), &type)); - *(dn_address *)(DN_SK(newsk)->peer.sdn_add.a_addr) = cb->src; - *(dn_address *)(DN_SK(newsk)->addr.sdn_add.a_addr) = cb->dst; + *(__le16 *)(DN_SK(newsk)->peer.sdn_add.a_addr) = cb->src; + *(__le16 *)(DN_SK(newsk)->addr.sdn_add.a_addr) = cb->dst; menuver = *skb->data; skb_pull(skb, 1); @@ -1365,7 +1365,7 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us if (optlen != sizeof(struct optdata_dn)) return -EINVAL; - if (u.opt.opt_optl > 16) + if (dn_ntohs(u.opt.opt_optl) > 16) return -EINVAL; memcpy(&scp->conndata_out, &u.opt, optlen); @@ -1378,7 +1378,7 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us if (optlen != sizeof(struct optdata_dn)) return -EINVAL; - if (u.opt.opt_optl > 16) + if (dn_ntohs(u.opt.opt_optl) > 16) return -EINVAL; memcpy(&scp->discdata_out, &u.opt, optlen); @@ -1693,7 +1693,7 @@ static int dn_recvmsg(struct kiocb *iocb, struct socket *sock, if (rv) goto out; - if (flags & ~(MSG_PEEK|MSG_OOB|MSG_WAITALL|MSG_DONTWAIT|MSG_NOSIGNAL)) { + if (flags & ~(MSG_CMSG_COMPAT|MSG_PEEK|MSG_OOB|MSG_WAITALL|MSG_DONTWAIT|MSG_NOSIGNAL)) { rv = -EOPNOTSUPP; goto out; } diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index efbead83ba7f..cc7b9d9255ef 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -64,7 +64,7 @@ extern struct neigh_table dn_neigh_table; /* * decnet_address is kept in network order. */ -dn_address decnet_address = 0; +__le16 decnet_address = 0; static DEFINE_RWLOCK(dndev_lock); static struct net_device *decnet_default_device; @@ -439,7 +439,7 @@ static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr **ifap, int de *ifap = ifa1->ifa_next; if (dn_db->dev->type == ARPHRD_ETHER) { - if (ifa1->ifa_local != dn_htons(dn_eth2dn(dev->dev_addr))) { + if (ifa1->ifa_local != dn_eth2dn(dev->dev_addr)) { dn_dn2eth(mac_addr, ifa1->ifa_local); dev_mc_delete(dev, mac_addr, ETH_ALEN, 0); } @@ -470,7 +470,7 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) } if (dev->type == ARPHRD_ETHER) { - if (ifa->ifa_local != dn_htons(dn_eth2dn(dev->dev_addr))) { + if (ifa->ifa_local != dn_eth2dn(dev->dev_addr)) { dn_dn2eth(mac_addr, ifa->ifa_local); dev_mc_add(dev, mac_addr, ETH_ALEN, 0); dev_mc_upload(dev); @@ -561,7 +561,7 @@ int dn_dev_ioctl(unsigned int cmd, void __user *arg) switch(cmd) { case SIOCGIFADDR: - *((dn_address *)sdn->sdn_nodeaddr) = ifa->ifa_local; + *((__le16 *)sdn->sdn_nodeaddr) = ifa->ifa_local; goto rarok; case SIOCSIFADDR: @@ -804,7 +804,7 @@ done: return skb->len; } -static int dn_dev_get_first(struct net_device *dev, dn_address *addr) +static int dn_dev_get_first(struct net_device *dev, __le16 *addr) { struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; struct dn_ifaddr *ifa; @@ -830,7 +830,7 @@ out: * a sensible default. Eventually the routing code will take care of all the * nasties for us I hope. */ -int dn_dev_bind_default(dn_address *addr) +int dn_dev_bind_default(__le16 *addr) { struct net_device *dev; int rv; @@ -853,7 +853,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) { struct endnode_hello_message *msg; struct sk_buff *skb = NULL; - unsigned short int *pktlen; + __le16 *pktlen; struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; if ((skb = dn_alloc_skb(NULL, sizeof(*msg), GFP_ATOMIC)) == NULL) @@ -882,7 +882,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) msg->datalen = 0x02; memset(msg->data, 0xAA, 2); - pktlen = (unsigned short *)skb_push(skb,2); + pktlen = (__le16 *)skb_push(skb,2); *pktlen = dn_htons(skb->len - 2); skb->nh.raw = skb->data; @@ -926,7 +926,7 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) size_t size; unsigned char *ptr; unsigned char *i1, *i2; - unsigned short *pktlen; + __le16 *pktlen; char *src; if (mtu2blksize(dev) < (26 + 7)) @@ -955,11 +955,11 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) ptr += ETH_ALEN; *ptr++ = dn_db->parms.forwarding == 1 ? DN_RT_INFO_L1RT : DN_RT_INFO_L2RT; - *((unsigned short *)ptr) = dn_htons(mtu2blksize(dev)); + *((__le16 *)ptr) = dn_htons(mtu2blksize(dev)); ptr += 2; *ptr++ = dn_db->parms.priority; /* Priority */ *ptr++ = 0; /* Area: Reserved */ - *((unsigned short *)ptr) = dn_htons((unsigned short)dn_db->parms.t3); + *((__le16 *)ptr) = dn_htons((unsigned short)dn_db->parms.t3); ptr += 2; *ptr++ = 0; /* MPD: Reserved */ i1 = ptr++; @@ -974,7 +974,7 @@ static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) skb_trim(skb, (27 + *i2)); - pktlen = (unsigned short *)skb_push(skb, 2); + pktlen = (__le16 *)skb_push(skb, 2); *pktlen = dn_htons(skb->len - 2); skb->nh.raw = skb->data; @@ -1016,7 +1016,7 @@ static void dn_send_ptp_hello(struct net_device *dev, struct dn_ifaddr *ifa) ptr = skb_put(skb, 2 + 4 + tdlen); *ptr++ = DN_RT_PKT_HELO; - *((dn_address *)ptr) = ifa->ifa_local; + *((__le16 *)ptr) = ifa->ifa_local; ptr += 2; *ptr++ = tdlen; @@ -1150,7 +1150,7 @@ struct dn_dev *dn_dev_create(struct net_device *dev, int *err) void dn_dev_up(struct net_device *dev) { struct dn_ifaddr *ifa; - dn_address addr = decnet_address; + __le16 addr = decnet_address; int maybe_default = 0; struct dn_dev *dn_db = (struct dn_dev *)dev->dn_ptr; @@ -1173,7 +1173,7 @@ void dn_dev_up(struct net_device *dev) if (dev->type == ARPHRD_ETHER) { if (memcmp(dev->dev_addr, dn_hiord, 4) != 0) return; - addr = dn_htons(dn_eth2dn(dev->dev_addr)); + addr = dn_eth2dn(dev->dev_addr); maybe_default = 1; } @@ -1385,8 +1385,8 @@ static int dn_dev_seq_show(struct seq_file *seq, void *v) mtu2blksize(dev), dn_db->parms.priority, dn_db->parms.state, dn_db->parms.name, - dn_db->router ? dn_addr2asc(dn_ntohs(*(dn_address *)dn_db->router->primary_key), router_buf) : "", - dn_db->peer ? dn_addr2asc(dn_ntohs(*(dn_address *)dn_db->peer->primary_key), peer_buf) : ""); + dn_db->router ? dn_addr2asc(dn_ntohs(*(__le16 *)dn_db->router->primary_key), router_buf) : "", + dn_db->peer ? dn_addr2asc(dn_ntohs(*(__le16 *)dn_db->peer->primary_key), peer_buf) : ""); } return 0; } diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 99bc061759c3..bd4ce8681a12 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -143,11 +143,11 @@ static inline struct dn_fib_info *dn_fib_find_info(const struct dn_fib_info *nfi return NULL; } -u16 dn_fib_get_attr16(struct rtattr *attr, int attrlen, int type) +__le16 dn_fib_get_attr16(struct rtattr *attr, int attrlen, int type) { while(RTA_OK(attr,attrlen)) { if (attr->rta_type == type) - return *(u16*)RTA_DATA(attr); + return *(__le16*)RTA_DATA(attr); attr = RTA_NEXT(attr, attrlen); } @@ -565,7 +565,7 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -static void fib_magic(int cmd, int type, __u16 dst, int dst_len, struct dn_ifaddr *ifa) +static void fib_magic(int cmd, int type, __le16 dst, int dst_len, struct dn_ifaddr *ifa) { struct dn_fib_table *tb; struct { @@ -684,7 +684,7 @@ static int dn_fib_dnaddr_event(struct notifier_block *this, unsigned long event, return NOTIFY_DONE; } -int dn_fib_sync_down(dn_address local, struct net_device *dev, int force) +int dn_fib_sync_down(__le16 local, struct net_device *dev, int force) { int ret = 0; int scope = RT_SCOPE_NOWHERE; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 33ab256cfd4a..7c8692c26bfe 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -95,7 +95,7 @@ static struct neigh_ops dn_phase3_ops = { struct neigh_table dn_neigh_table = { .family = PF_DECnet, .entry_size = sizeof(struct dn_neigh), - .key_len = sizeof(dn_address), + .key_len = sizeof(__le16), .hash = dn_neigh_hash, .constructor = dn_neigh_construct, .id = "dn_neigh_cache", @@ -123,7 +123,7 @@ struct neigh_table dn_neigh_table = { static u32 dn_neigh_hash(const void *pkey, const struct net_device *dev) { - return jhash_2words(*(dn_address *)pkey, 0, dn_neigh_table.hash_rnd); + return jhash_2words(*(__u16 *)pkey, 0, dn_neigh_table.hash_rnd); } static int dn_neigh_construct(struct neighbour *neigh) @@ -249,14 +249,14 @@ static int dn_long_output(struct sk_buff *skb) data = skb_push(skb, sizeof(struct dn_long_packet) + 3); lp = (struct dn_long_packet *)(data+3); - *((unsigned short *)data) = dn_htons(skb->len - 2); + *((__le16 *)data) = dn_htons(skb->len - 2); *(data + 2) = 1 | DN_RT_F_PF; /* Padding */ lp->msgflg = DN_RT_PKT_LONG|(cb->rt_flags&(DN_RT_F_IE|DN_RT_F_RQR|DN_RT_F_RTS)); lp->d_area = lp->d_subarea = 0; - dn_dn2eth(lp->d_id, dn_ntohs(cb->dst)); + dn_dn2eth(lp->d_id, cb->dst); lp->s_area = lp->s_subarea = 0; - dn_dn2eth(lp->s_id, dn_ntohs(cb->src)); + dn_dn2eth(lp->s_id, cb->src); lp->nl2 = 0; lp->visit_ct = cb->hops & 0x3f; lp->s_class = 0; @@ -293,7 +293,7 @@ static int dn_short_output(struct sk_buff *skb) } data = skb_push(skb, sizeof(struct dn_short_packet) + 2); - *((unsigned short *)data) = dn_htons(skb->len - 2); + *((__le16 *)data) = dn_htons(skb->len - 2); sp = (struct dn_short_packet *)(data+2); sp->msgflg = DN_RT_PKT_SHORT|(cb->rt_flags&(DN_RT_F_RQR|DN_RT_F_RTS)); @@ -335,7 +335,7 @@ static int dn_phase3_output(struct sk_buff *skb) } data = skb_push(skb, sizeof(struct dn_short_packet) + 2); - *((unsigned short *)data) = dn_htons(skb->len - 2); + *((__le16 *)data) = dn_htons(skb->len - 2); sp = (struct dn_short_packet *)(data + 2); sp->msgflg = DN_RT_PKT_SHORT|(cb->rt_flags&(DN_RT_F_RQR|DN_RT_F_RTS)); @@ -373,9 +373,9 @@ int dn_neigh_router_hello(struct sk_buff *skb) struct neighbour *neigh; struct dn_neigh *dn; struct dn_dev *dn_db; - dn_address src; + __le16 src; - src = dn_htons(dn_eth2dn(msg->id)); + src = dn_eth2dn(msg->id); neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1); @@ -409,7 +409,7 @@ int dn_neigh_router_hello(struct sk_buff *skb) } /* Only use routers in our area */ - if ((dn_ntohs(src)>>10) == dn_ntohs((decnet_address)>>10)) { + if ((dn_ntohs(src)>>10) == (dn_ntohs((decnet_address))>>10)) { if (!dn_db->router) { dn_db->router = neigh_clone(neigh); } else { @@ -433,9 +433,9 @@ int dn_neigh_endnode_hello(struct sk_buff *skb) struct endnode_hello_message *msg = (struct endnode_hello_message *)skb->data; struct neighbour *neigh; struct dn_neigh *dn; - dn_address src; + __le16 src; - src = dn_htons(dn_eth2dn(msg->id)); + src = dn_eth2dn(msg->id); neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1); diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index 44bda85e678f..547523b41c81 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -85,7 +85,7 @@ static void dn_log_martian(struct sk_buff *skb, const char *msg) if (decnet_log_martians && net_ratelimit()) { char *devname = skb->dev ? skb->dev->name : "???"; struct dn_skb_cb *cb = DN_SKB_CB(skb); - printk(KERN_INFO "DECnet: Martian packet (%s) dev=%s src=0x%04hx dst=0x%04hx srcport=0x%04hx dstport=0x%04hx\n", msg, devname, cb->src, cb->dst, cb->src_port, cb->dst_port); + printk(KERN_INFO "DECnet: Martian packet (%s) dev=%s src=0x%04hx dst=0x%04hx srcport=0x%04hx dstport=0x%04hx\n", msg, devname, dn_ntohs(cb->src), dn_ntohs(cb->dst), dn_ntohs(cb->src_port), dn_ntohs(cb->dst_port)); } } @@ -128,7 +128,7 @@ static void dn_ack(struct sock *sk, struct sk_buff *skb, unsigned short ack) */ static int dn_process_ack(struct sock *sk, struct sk_buff *skb, int oth) { - unsigned short *ptr = (unsigned short *)skb->data; + __le16 *ptr = (__le16 *)skb->data; int len = 0; unsigned short ack; @@ -346,7 +346,7 @@ static void dn_nsp_conn_conf(struct sock *sk, struct sk_buff *skb) ptr = skb->data; cb->services = *ptr++; cb->info = *ptr++; - cb->segsize = dn_ntohs(*(__u16 *)ptr); + cb->segsize = dn_ntohs(*(__le16 *)ptr); if ((scp->state == DN_CI) || (scp->state == DN_CD)) { scp->persist = 0; @@ -363,7 +363,7 @@ static void dn_nsp_conn_conf(struct sock *sk, struct sk_buff *skb) if (skb->len > 0) { unsigned char dlen = *skb->data; if ((dlen <= 16) && (dlen <= skb->len)) { - scp->conndata_in.opt_optl = dlen; + scp->conndata_in.opt_optl = dn_htons((__u16)dlen); memcpy(scp->conndata_in.opt_data, skb->data + 1, dlen); } } @@ -397,17 +397,17 @@ static void dn_nsp_disc_init(struct sock *sk, struct sk_buff *skb) if (skb->len < 2) goto out; - reason = dn_ntohs(*(__u16 *)skb->data); + reason = dn_ntohs(*(__le16 *)skb->data); skb_pull(skb, 2); - scp->discdata_in.opt_status = reason; + scp->discdata_in.opt_status = dn_htons(reason); scp->discdata_in.opt_optl = 0; memset(scp->discdata_in.opt_data, 0, 16); if (skb->len > 0) { unsigned char dlen = *skb->data; if ((dlen <= 16) && (dlen <= skb->len)) { - scp->discdata_in.opt_optl = dlen; + scp->discdata_in.opt_optl = dn_htons((__u16)dlen); memcpy(scp->discdata_in.opt_data, skb->data + 1, dlen); } } @@ -464,7 +464,7 @@ static void dn_nsp_disc_conf(struct sock *sk, struct sk_buff *skb) if (skb->len != 2) goto out; - reason = dn_ntohs(*(__u16 *)skb->data); + reason = dn_ntohs(*(__le16 *)skb->data); sk->sk_state = TCP_CLOSE; @@ -513,7 +513,7 @@ static void dn_nsp_linkservice(struct sock *sk, struct sk_buff *skb) if (skb->len != 4) goto out; - segnum = dn_ntohs(*(__u16 *)ptr); + segnum = dn_ntohs(*(__le16 *)ptr); ptr += 2; lsflags = *(unsigned char *)ptr++; fcval = *ptr; @@ -621,7 +621,7 @@ static void dn_nsp_otherdata(struct sock *sk, struct sk_buff *skb) if (skb->len < 2) goto out; - cb->segnum = segnum = dn_ntohs(*(__u16 *)skb->data); + cb->segnum = segnum = dn_ntohs(*(__le16 *)skb->data); skb_pull(skb, 2); if (seq_next(scp->numoth_rcv, segnum)) { @@ -649,7 +649,7 @@ static void dn_nsp_data(struct sock *sk, struct sk_buff *skb) if (skb->len < 2) goto out; - cb->segnum = segnum = dn_ntohs(*(__u16 *)skb->data); + cb->segnum = segnum = dn_ntohs(*(__le16 *)skb->data); skb_pull(skb, 2); if (seq_next(scp->numdat_rcv, segnum)) { @@ -760,7 +760,7 @@ static int dn_nsp_rx_packet(struct sk_buff *skb) /* * Grab the destination address. */ - cb->dst_port = *(unsigned short *)ptr; + cb->dst_port = *(__le16 *)ptr; cb->src_port = 0; ptr += 2; @@ -768,7 +768,7 @@ static int dn_nsp_rx_packet(struct sk_buff *skb) * If not a connack, grab the source address too. */ if (pskb_may_pull(skb, 5)) { - cb->src_port = *(unsigned short *)ptr; + cb->src_port = *(__le16 *)ptr; ptr += 2; skb_pull(skb, 5); } @@ -778,7 +778,7 @@ static int dn_nsp_rx_packet(struct sk_buff *skb) * Swap src & dst and look up in the normal way. */ if (unlikely(cb->rt_flags & DN_RT_F_RTS)) { - unsigned short tmp = cb->dst_port; + __le16 tmp = cb->dst_port; cb->dst_port = cb->src_port; cb->src_port = tmp; tmp = cb->dst; diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index c96c767b1f74..c2e21cd89b3c 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -287,26 +287,26 @@ int dn_nsp_xmit_timeout(struct sock *sk) return 0; } -static inline unsigned char *dn_mk_common_header(struct dn_scp *scp, struct sk_buff *skb, unsigned char msgflag, int len) +static inline __le16 *dn_mk_common_header(struct dn_scp *scp, struct sk_buff *skb, unsigned char msgflag, int len) { unsigned char *ptr = skb_push(skb, len); BUG_ON(len < 5); *ptr++ = msgflag; - *((unsigned short *)ptr) = scp->addrrem; + *((__le16 *)ptr) = scp->addrrem; ptr += 2; - *((unsigned short *)ptr) = scp->addrloc; + *((__le16 *)ptr) = scp->addrloc; ptr += 2; - return ptr; + return (__le16 __force *)ptr; } -static unsigned short *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, unsigned char msgflag, int hlen, int other) +static __le16 *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, unsigned char msgflag, int hlen, int other) { struct dn_scp *scp = DN_SK(sk); unsigned short acknum = scp->numdat_rcv & 0x0FFF; unsigned short ackcrs = scp->numoth_rcv & 0x0FFF; - unsigned short *ptr; + __le16 *ptr; BUG_ON(hlen < 9); @@ -325,7 +325,7 @@ static unsigned short *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, un /* Set "cross subchannel" bit in ackcrs */ ackcrs |= 0x2000; - ptr = (unsigned short *)dn_mk_common_header(scp, skb, msgflag, hlen); + ptr = (__le16 *)dn_mk_common_header(scp, skb, msgflag, hlen); *ptr++ = dn_htons(acknum); *ptr++ = dn_htons(ackcrs); @@ -333,11 +333,11 @@ static unsigned short *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, un return ptr; } -static unsigned short *dn_nsp_mk_data_header(struct sock *sk, struct sk_buff *skb, int oth) +static __le16 *dn_nsp_mk_data_header(struct sock *sk, struct sk_buff *skb, int oth) { struct dn_scp *scp = DN_SK(sk); struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned short *ptr = dn_mk_ack_header(sk, skb, cb->nsp_flags, 11, oth); + __le16 *ptr = dn_mk_ack_header(sk, skb, cb->nsp_flags, 11, oth); if (unlikely(oth)) { cb->segnum = scp->numoth; @@ -524,9 +524,9 @@ void dn_send_conn_conf(struct sock *sk, gfp_t gfp) struct dn_scp *scp = DN_SK(sk); struct sk_buff *skb = NULL; struct nsp_conn_init_msg *msg; - unsigned char len = scp->conndata_out.opt_optl; + __u8 len = (__u8)dn_ntohs(scp->conndata_out.opt_optl); - if ((skb = dn_alloc_skb(sk, 50 + scp->conndata_out.opt_optl, gfp)) == NULL) + if ((skb = dn_alloc_skb(sk, 50 + dn_ntohs(scp->conndata_out.opt_optl), gfp)) == NULL) return; msg = (struct nsp_conn_init_msg *)skb_put(skb, sizeof(*msg)); @@ -553,7 +553,7 @@ void dn_send_conn_conf(struct sock *sk, gfp_t gfp) static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, unsigned short reason, gfp_t gfp, struct dst_entry *dst, - int ddl, unsigned char *dd, __u16 rem, __u16 loc) + int ddl, unsigned char *dd, __le16 rem, __le16 loc) { struct sk_buff *skb = NULL; int size = 7 + ddl + ((msgflg == NSP_DISCINIT) ? 1 : 0); @@ -561,7 +561,7 @@ static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, if ((dst == NULL) || (rem == 0)) { if (net_ratelimit()) - printk(KERN_DEBUG "DECnet: dn_nsp_do_disc: BUG! Please report this to SteveW@ACM.org rem=%u dst=%p\n", (unsigned)rem, dst); + printk(KERN_DEBUG "DECnet: dn_nsp_do_disc: BUG! Please report this to SteveW@ACM.org rem=%u dst=%p\n", dn_ntohs(rem), dst); return; } @@ -570,11 +570,11 @@ static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, msg = skb_put(skb, size); *msg++ = msgflg; - *(__u16 *)msg = rem; + *(__le16 *)msg = rem; msg += 2; - *(__u16 *)msg = loc; + *(__le16 *)msg = loc; msg += 2; - *(__u16 *)msg = dn_htons(reason); + *(__le16 *)msg = dn_htons(reason); msg += 2; if (msgflg == NSP_DISCINIT) *msg++ = ddl; @@ -600,10 +600,10 @@ void dn_nsp_send_disc(struct sock *sk, unsigned char msgflg, int ddl = 0; if (msgflg == NSP_DISCINIT) - ddl = scp->discdata_out.opt_optl; + ddl = dn_ntohs(scp->discdata_out.opt_optl); if (reason == 0) - reason = scp->discdata_out.opt_status; + reason = dn_ntohs(scp->discdata_out.opt_status); dn_nsp_do_disc(sk, msgflg, reason, gfp, sk->sk_dst_cache, ddl, scp->discdata_out.opt_data, scp->addrrem, scp->addrloc); @@ -708,7 +708,7 @@ void dn_nsp_send_conninit(struct sock *sk, unsigned char msgflg) if (aux > 0) memcpy(skb_put(skb, aux), scp->accessdata.acc_acc, aux); - aux = scp->conndata_out.opt_optl; + aux = (__u8)dn_ntohs(scp->conndata_out.opt_optl); *skb_put(skb, 1) = aux; if (aux > 0) memcpy(skb_put(skb,aux), scp->conndata_out.opt_data, aux); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 3407f190afe8..e172cf98d7fc 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -133,9 +133,9 @@ static struct dst_ops dn_dst_ops = { .entries = ATOMIC_INIT(0), }; -static __inline__ unsigned dn_hash(unsigned short src, unsigned short dst) +static __inline__ unsigned dn_hash(__le16 src, __le16 dst) { - unsigned short tmp = src ^ dst; + __u16 tmp = (__u16 __force)(src ^ dst); tmp ^= (tmp >> 3); tmp ^= (tmp >> 5); tmp ^= (tmp >> 10); @@ -149,8 +149,7 @@ static inline void dnrt_free(struct dn_route *rt) static inline void dnrt_drop(struct dn_route *rt) { - if (rt) - dst_release(&rt->u.dst); + dst_release(&rt->u.dst); call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free); } @@ -379,9 +378,9 @@ static int dn_return_short(struct sk_buff *skb) { struct dn_skb_cb *cb; unsigned char *ptr; - dn_address *src; - dn_address *dst; - dn_address tmp; + __le16 *src; + __le16 *dst; + __le16 tmp; /* Add back headers */ skb_push(skb, skb->data - skb->nh.raw); @@ -394,9 +393,9 @@ static int dn_return_short(struct sk_buff *skb) ptr = skb->data + 2; *ptr++ = (cb->rt_flags & ~DN_RT_F_RQR) | DN_RT_F_RTS; - dst = (dn_address *)ptr; + dst = (__le16 *)ptr; ptr += 2; - src = (dn_address *)ptr; + src = (__le16 *)ptr; ptr += 2; *ptr = 0; /* Zero hop count */ @@ -475,7 +474,8 @@ static int dn_route_rx_packet(struct sk_buff *skb) struct dn_skb_cb *cb = DN_SKB_CB(skb); printk(KERN_DEBUG "DECnet: dn_route_rx_packet: rt_flags=0x%02x dev=%s len=%d src=0x%04hx dst=0x%04hx err=%d type=%d\n", - (int)cb->rt_flags, devname, skb->len, cb->src, cb->dst, + (int)cb->rt_flags, devname, skb->len, + dn_ntohs(cb->src), dn_ntohs(cb->dst), err, skb->pkt_type); } @@ -505,7 +505,7 @@ static int dn_route_rx_long(struct sk_buff *skb) /* Destination info */ ptr += 2; - cb->dst = dn_htons(dn_eth2dn(ptr)); + cb->dst = dn_eth2dn(ptr); if (memcmp(ptr, dn_hiord_addr, 4) != 0) goto drop_it; ptr += 6; @@ -513,7 +513,7 @@ static int dn_route_rx_long(struct sk_buff *skb) /* Source info */ ptr += 2; - cb->src = dn_htons(dn_eth2dn(ptr)); + cb->src = dn_eth2dn(ptr); if (memcmp(ptr, dn_hiord_addr, 4) != 0) goto drop_it; ptr += 6; @@ -541,9 +541,9 @@ static int dn_route_rx_short(struct sk_buff *skb) skb_pull(skb, 5); skb->h.raw = skb->data; - cb->dst = *(dn_address *)ptr; + cb->dst = *(__le16 *)ptr; ptr += 2; - cb->src = *(dn_address *)ptr; + cb->src = *(__le16 *)ptr; ptr += 2; cb->hops = *ptr & 0x3f; @@ -575,7 +575,7 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type { struct dn_skb_cb *cb; unsigned char flags = 0; - __u16 len = dn_ntohs(*(__u16 *)skb->data); + __u16 len = dn_ntohs(*(__le16 *)skb->data); struct dn_dev *dn = (struct dn_dev *)dev->dn_ptr; unsigned char padlen = 0; @@ -782,7 +782,7 @@ static int dn_rt_bug(struct sk_buff *skb) struct dn_skb_cb *cb = DN_SKB_CB(skb); printk(KERN_DEBUG "dn_rt_bug: skb from:%04x to:%04x\n", - cb->src, cb->dst); + dn_ntohs(cb->src), dn_ntohs(cb->dst)); } kfree_skb(skb); @@ -823,7 +823,7 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) return 0; } -static inline int dn_match_addr(__u16 addr1, __u16 addr2) +static inline int dn_match_addr(__le16 addr1, __le16 addr2) { __u16 tmp = dn_ntohs(addr1) ^ dn_ntohs(addr2); int match = 16; @@ -834,9 +834,9 @@ static inline int dn_match_addr(__u16 addr1, __u16 addr2) return match; } -static __u16 dnet_select_source(const struct net_device *dev, __u16 daddr, int scope) +static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int scope) { - __u16 saddr = 0; + __le16 saddr = 0; struct dn_dev *dn_db = dev->dn_ptr; struct dn_ifaddr *ifa; int best_match = 0; @@ -861,14 +861,14 @@ static __u16 dnet_select_source(const struct net_device *dev, __u16 daddr, int s return saddr; } -static inline __u16 __dn_fib_res_prefsrc(struct dn_fib_res *res) +static inline __le16 __dn_fib_res_prefsrc(struct dn_fib_res *res) { return dnet_select_source(DN_FIB_RES_DEV(*res), DN_FIB_RES_GW(*res), res->scope); } -static inline __u16 dn_fib_rules_map_destination(__u16 daddr, struct dn_fib_res *res) +static inline __le16 dn_fib_rules_map_destination(__le16 daddr, struct dn_fib_res *res) { - __u16 mask = dnet_make_mask(res->prefixlen); + __le16 mask = dnet_make_mask(res->prefixlen); return (daddr&~mask)|res->fi->fib_nh->nh_gw; } @@ -892,12 +892,13 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *old struct dn_fib_res res = { .fi = NULL, .type = RTN_UNICAST }; int err; int free_res = 0; - __u16 gateway = 0; + __le16 gateway = 0; if (decnet_debug_level & 16) printk(KERN_DEBUG "dn_route_output_slow: dst=%04x src=%04x mark=%d" - " iif=%d oif=%d\n", oldflp->fld_dst, oldflp->fld_src, + " iif=%d oif=%d\n", dn_ntohs(oldflp->fld_dst), + dn_ntohs(oldflp->fld_src), oldflp->fld_fwmark, loopback_dev.ifindex, oldflp->oif); /* If we have an output interface, verify its a DECnet device */ @@ -961,8 +962,9 @@ source_ok: if (decnet_debug_level & 16) printk(KERN_DEBUG "dn_route_output_slow: initial checks complete." - " dst=%o4x src=%04x oif=%d try_hard=%d\n", fl.fld_dst, - fl.fld_src, fl.oif, try_hard); + " dst=%o4x src=%04x oif=%d try_hard=%d\n", + dn_ntohs(fl.fld_dst), dn_ntohs(fl.fld_src), + fl.oif, try_hard); /* * N.B. If the kernel is compiled without router support then @@ -1218,8 +1220,8 @@ static int dn_route_input_slow(struct sk_buff *skb) struct neighbour *neigh = NULL; unsigned hash; int flags = 0; - __u16 gateway = 0; - __u16 local_src = 0; + __le16 gateway = 0; + __le16 local_src = 0; struct flowi fl = { .nl_u = { .dn_u = { .daddr = cb->dst, .saddr = cb->src, @@ -1266,7 +1268,7 @@ static int dn_route_input_slow(struct sk_buff *skb) res.type = RTN_LOCAL; flags |= RTCF_DIRECTSRC; } else { - __u16 src_map = fl.fld_src; + __le16 src_map = fl.fld_src; free_res = 1; out_dev = DN_FIB_RES_DEV(res); diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 1060de70bc0c..446faafe2065 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -27,6 +27,8 @@ #include <linux/timer.h> #include <linux/spinlock.h> #include <linux/in_route.h> +#include <linux/list.h> +#include <linux/rcupdate.h> #include <asm/atomic.h> #include <asm/uaccess.h> #include <net/neighbour.h> @@ -39,18 +41,18 @@ struct dn_fib_rule { - struct dn_fib_rule *r_next; + struct hlist_node r_hlist; atomic_t r_clntref; u32 r_preference; unsigned char r_table; unsigned char r_action; unsigned char r_dst_len; unsigned char r_src_len; - dn_address r_src; - dn_address r_srcmask; - dn_address r_dst; - dn_address r_dstmask; - dn_address r_srcmap; + __le16 r_src; + __le16 r_srcmask; + __le16 r_dst; + __le16 r_dstmask; + __le16 r_srcmap; u8 r_flags; #ifdef CONFIG_DECNET_ROUTE_FWMARK u32 r_fwmark; @@ -58,6 +60,7 @@ struct dn_fib_rule int r_ifindex; char r_ifname[IFNAMSIZ]; int r_dead; + struct rcu_head rcu; }; static struct dn_fib_rule default_rule = { @@ -67,18 +70,17 @@ static struct dn_fib_rule default_rule = { .r_action = RTN_UNICAST }; -static struct dn_fib_rule *dn_fib_rules = &default_rule; -static DEFINE_RWLOCK(dn_fib_rules_lock); - +static struct hlist_head dn_fib_rules; int dn_fib_rtm_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct rtattr **rta = arg; struct rtmsg *rtm = NLMSG_DATA(nlh); - struct dn_fib_rule *r, **rp; + struct dn_fib_rule *r; + struct hlist_node *node; int err = -ESRCH; - for(rp=&dn_fib_rules; (r=*rp) != NULL; rp = &r->r_next) { + hlist_for_each_entry(r, node, &dn_fib_rules, r_hlist) { if ((!rta[RTA_SRC-1] || memcmp(RTA_DATA(rta[RTA_SRC-1]), &r->r_src, 2) == 0) && rtm->rtm_src_len == r->r_src_len && rtm->rtm_dst_len == r->r_dst_len && @@ -95,10 +97,8 @@ int dn_fib_rtm_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (r == &default_rule) break; - write_lock_bh(&dn_fib_rules_lock); - *rp = r->r_next; + hlist_del_rcu(&r->r_hlist); r->r_dead = 1; - write_unlock_bh(&dn_fib_rules_lock); dn_fib_rule_put(r); err = 0; break; @@ -108,11 +108,17 @@ int dn_fib_rtm_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) return err; } +static inline void dn_fib_rule_put_rcu(struct rcu_head *head) +{ + struct dn_fib_rule *r = container_of(head, struct dn_fib_rule, rcu); + kfree(r); +} + void dn_fib_rule_put(struct dn_fib_rule *r) { if (atomic_dec_and_test(&r->r_clntref)) { if (r->r_dead) - kfree(r); + call_rcu(&r->rcu, dn_fib_rule_put_rcu); else printk(KERN_DEBUG "Attempt to free alive dn_fib_rule\n"); } @@ -123,7 +129,8 @@ int dn_fib_rtm_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct rtattr **rta = arg; struct rtmsg *rtm = NLMSG_DATA(nlh); - struct dn_fib_rule *r, *new_r, **rp; + struct dn_fib_rule *r, *new_r, *last = NULL; + struct hlist_node *node = NULL; unsigned char table_id; if (rtm->rtm_src_len > 16 || rtm->rtm_dst_len > 16) @@ -149,6 +156,7 @@ int dn_fib_rtm_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (!new_r) return -ENOMEM; memset(new_r, 0, sizeof(*new_r)); + if (rta[RTA_SRC-1]) memcpy(&new_r->r_src, RTA_DATA(rta[RTA_SRC-1]), 2); if (rta[RTA_DST-1]) @@ -179,27 +187,26 @@ int dn_fib_rtm_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) } } - rp = &dn_fib_rules; + r = container_of(dn_fib_rules.first, struct dn_fib_rule, r_hlist); if (!new_r->r_preference) { - r = dn_fib_rules; - if (r && (r = r->r_next) != NULL) { - rp = &dn_fib_rules->r_next; + if (r && r->r_hlist.next != NULL) { + r = container_of(r->r_hlist.next, struct dn_fib_rule, r_hlist); if (r->r_preference) new_r->r_preference = r->r_preference - 1; } } - while((r=*rp) != NULL) { + hlist_for_each_entry(r, node, &dn_fib_rules, r_hlist) { if (r->r_preference > new_r->r_preference) break; - rp = &r->r_next; + last = r; } - - new_r->r_next = r; atomic_inc(&new_r->r_clntref); - write_lock_bh(&dn_fib_rules_lock); - *rp = new_r; - write_unlock_bh(&dn_fib_rules_lock); + + if (last) + hlist_add_after_rcu(&last->r_hlist, &new_r->r_hlist); + else + hlist_add_before_rcu(&new_r->r_hlist, &r->r_hlist); return 0; } @@ -208,12 +215,14 @@ int dn_fib_lookup(const struct flowi *flp, struct dn_fib_res *res) { struct dn_fib_rule *r, *policy; struct dn_fib_table *tb; - dn_address saddr = flp->fld_src; - dn_address daddr = flp->fld_dst; + __le16 saddr = flp->fld_src; + __le16 daddr = flp->fld_dst; + struct hlist_node *node; int err; - read_lock(&dn_fib_rules_lock); - for(r = dn_fib_rules; r; r = r->r_next) { + rcu_read_lock(); + + hlist_for_each_entry_rcu(r, node, &dn_fib_rules, r_hlist) { if (((saddr^r->r_src) & r->r_srcmask) || ((daddr^r->r_dst) & r->r_dstmask) || #ifdef CONFIG_DECNET_ROUTE_FWMARK @@ -228,14 +237,14 @@ int dn_fib_lookup(const struct flowi *flp, struct dn_fib_res *res) policy = r; break; case RTN_UNREACHABLE: - read_unlock(&dn_fib_rules_lock); + rcu_read_unlock(); return -ENETUNREACH; default: case RTN_BLACKHOLE: - read_unlock(&dn_fib_rules_lock); + rcu_read_unlock(); return -EINVAL; case RTN_PROHIBIT: - read_unlock(&dn_fib_rules_lock); + rcu_read_unlock(); return -EACCES; } @@ -246,20 +255,20 @@ int dn_fib_lookup(const struct flowi *flp, struct dn_fib_res *res) res->r = policy; if (policy) atomic_inc(&policy->r_clntref); - read_unlock(&dn_fib_rules_lock); + rcu_read_unlock(); return 0; } if (err < 0 && err != -EAGAIN) { - read_unlock(&dn_fib_rules_lock); + rcu_read_unlock(); return err; } } - read_unlock(&dn_fib_rules_lock); + rcu_read_unlock(); return -ESRCH; } -unsigned dnet_addr_type(__u16 addr) +unsigned dnet_addr_type(__le16 addr) { struct flowi fl = { .nl_u = { .dn_u = { .daddr = addr } } }; struct dn_fib_res res; @@ -277,7 +286,7 @@ unsigned dnet_addr_type(__u16 addr) return ret; } -__u16 dn_fib_rules_policy(__u16 saddr, struct dn_fib_res *res, unsigned *flags) +__le16 dn_fib_rules_policy(__le16 saddr, struct dn_fib_res *res, unsigned *flags) { struct dn_fib_rule *r = res->r; @@ -297,27 +306,23 @@ __u16 dn_fib_rules_policy(__u16 saddr, struct dn_fib_res *res, unsigned *flags) static void dn_fib_rules_detach(struct net_device *dev) { + struct hlist_node *node; struct dn_fib_rule *r; - for(r = dn_fib_rules; r; r = r->r_next) { - if (r->r_ifindex == dev->ifindex) { - write_lock_bh(&dn_fib_rules_lock); + hlist_for_each_entry(r, node, &dn_fib_rules, r_hlist) { + if (r->r_ifindex == dev->ifindex) r->r_ifindex = -1; - write_unlock_bh(&dn_fib_rules_lock); - } } } static void dn_fib_rules_attach(struct net_device *dev) { + struct hlist_node *node; struct dn_fib_rule *r; - for(r = dn_fib_rules; r; r = r->r_next) { - if (r->r_ifindex == -1 && strcmp(dev->name, r->r_ifname) == 0) { - write_lock_bh(&dn_fib_rules_lock); + hlist_for_each_entry(r, node, &dn_fib_rules, r_hlist) { + if (r->r_ifindex == -1 && strcmp(dev->name, r->r_ifname) == 0) r->r_ifindex = dev->ifindex; - write_unlock_bh(&dn_fib_rules_lock); - } } } @@ -387,18 +392,20 @@ rtattr_failure: int dn_fib_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) { - int idx; + int idx = 0; int s_idx = cb->args[0]; struct dn_fib_rule *r; + struct hlist_node *node; - read_lock(&dn_fib_rules_lock); - for(r = dn_fib_rules, idx = 0; r; r = r->r_next, idx++) { + rcu_read_lock(); + hlist_for_each_entry(r, node, &dn_fib_rules, r_hlist) { if (idx < s_idx) continue; if (dn_fib_fill_rule(skb, r, cb, NLM_F_MULTI) < 0) break; + idx++; } - read_unlock(&dn_fib_rules_lock); + rcu_read_unlock(); cb->args[0] = idx; return skb->len; @@ -406,6 +413,8 @@ int dn_fib_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) void __init dn_fib_rules_init(void) { + INIT_HLIST_HEAD(&dn_fib_rules); + hlist_add_head(&default_rule.r_hlist, &dn_fib_rules); register_netdevice_notifier(&dn_fib_rules_notifier); } diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 6f8b5658cb4e..0ebc46af1bdd 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -46,7 +46,7 @@ struct dn_zone u32 dz_hashmask; #define DZ_HASHMASK(dz) ((dz)->dz_hashmask) int dz_order; - u16 dz_mask; + __le16 dz_mask; #define DZ_MASK(dz) ((dz)->dz_mask) }; @@ -84,14 +84,14 @@ static int dn_fib_hash_zombies; static inline dn_fib_idx_t dn_hash(dn_fib_key_t key, struct dn_zone *dz) { - u16 h = ntohs(key.datum)>>(16 - dz->dz_order); + u16 h = dn_ntohs(key.datum)>>(16 - dz->dz_order); h ^= (h >> 10); h ^= (h >> 6); h &= DZ_HASHMASK(dz); return *(dn_fib_idx_t *)&h; } -static inline dn_fib_key_t dz_key(u16 dst, struct dn_zone *dz) +static inline dn_fib_key_t dz_key(__le16 dst, struct dn_zone *dz) { dn_fib_key_t k; k.datum = dst & DZ_MASK(dz); @@ -250,7 +250,7 @@ static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct dn_kern for_nexthops(fi) { int attrlen = nhlen - sizeof(struct rtnexthop); - dn_address gw; + __le16 gw; if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0) return -EINVAL; @@ -457,7 +457,7 @@ static int dn_fib_table_insert(struct dn_fib_table *tb, struct rtmsg *r, struct dz_key_0(key); if (rta->rta_dst) { - dn_address dst; + __le16 dst; memcpy(&dst, rta->rta_dst, 2); if (dst & ~DZ_MASK(dz)) return -EINVAL; @@ -593,7 +593,7 @@ static int dn_fib_table_delete(struct dn_fib_table *tb, struct rtmsg *r, struct dz_key_0(key); if (rta->rta_dst) { - dn_address dst; + __le16 dst; memcpy(&dst, rta->rta_dst, 2); if (dst & ~DZ_MASK(dz)) return -EINVAL; diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index 0e9d2c571165..bda5920215fd 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -86,9 +86,9 @@ static void strip_it(char *str) * Simple routine to parse an ascii DECnet address * into a network order address. */ -static int parse_addr(dn_address *addr, char *str) +static int parse_addr(__le16 *addr, char *str) { - dn_address area, node; + __u16 area, node; while(*str && !ISNUM(*str)) str++; @@ -139,7 +139,7 @@ static int dn_node_address_strategy(ctl_table *table, int __user *name, int nlen void **context) { size_t len; - dn_address addr; + __le16 addr; if (oldval && oldlenp) { if (get_user(len, oldlenp)) @@ -147,14 +147,14 @@ static int dn_node_address_strategy(ctl_table *table, int __user *name, int nlen if (len) { if (len != sizeof(unsigned short)) return -EINVAL; - if (put_user(decnet_address, (unsigned short __user *)oldval)) + if (put_user(decnet_address, (__le16 __user *)oldval)) return -EFAULT; } } if (newval && newlen) { if (newlen != sizeof(unsigned short)) return -EINVAL; - if (get_user(addr, (unsigned short __user *)newval)) + if (get_user(addr, (__le16 __user *)newval)) return -EFAULT; dn_dev_devices_off(); @@ -173,7 +173,7 @@ static int dn_node_address_handler(ctl_table *table, int write, { char addr[DN_ASCBUF_LEN]; size_t len; - dn_address dnaddr; + __le16 dnaddr; if (!*lenp || (*ppos && !write)) { *lenp = 0; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 97c276f95b35..dc206f1f914f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -788,45 +788,53 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } const struct proto_ops inet_stream_ops = { - .family = PF_INET, - .owner = THIS_MODULE, - .release = inet_release, - .bind = inet_bind, - .connect = inet_stream_connect, - .socketpair = sock_no_socketpair, - .accept = inet_accept, - .getname = inet_getname, - .poll = tcp_poll, - .ioctl = inet_ioctl, - .listen = inet_listen, - .shutdown = inet_shutdown, - .setsockopt = sock_common_setsockopt, - .getsockopt = sock_common_getsockopt, - .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, - .mmap = sock_no_mmap, - .sendpage = tcp_sendpage + .family = PF_INET, + .owner = THIS_MODULE, + .release = inet_release, + .bind = inet_bind, + .connect = inet_stream_connect, + .socketpair = sock_no_socketpair, + .accept = inet_accept, + .getname = inet_getname, + .poll = tcp_poll, + .ioctl = inet_ioctl, + .listen = inet_listen, + .shutdown = inet_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, + .sendpage = tcp_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; const struct proto_ops inet_dgram_ops = { - .family = PF_INET, - .owner = THIS_MODULE, - .release = inet_release, - .bind = inet_bind, - .connect = inet_dgram_connect, - .socketpair = sock_no_socketpair, - .accept = sock_no_accept, - .getname = inet_getname, - .poll = udp_poll, - .ioctl = inet_ioctl, - .listen = sock_no_listen, - .shutdown = inet_shutdown, - .setsockopt = sock_common_setsockopt, - .getsockopt = sock_common_getsockopt, - .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, - .mmap = sock_no_mmap, - .sendpage = inet_sendpage, + .family = PF_INET, + .owner = THIS_MODULE, + .release = inet_release, + .bind = inet_bind, + .connect = inet_dgram_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = inet_getname, + .poll = udp_poll, + .ioctl = inet_ioctl, + .listen = sock_no_listen, + .shutdown = inet_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, + .sendpage = inet_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; /* @@ -834,24 +842,28 @@ const struct proto_ops inet_dgram_ops = { * udp_poll */ static const struct proto_ops inet_sockraw_ops = { - .family = PF_INET, - .owner = THIS_MODULE, - .release = inet_release, - .bind = inet_bind, - .connect = inet_dgram_connect, - .socketpair = sock_no_socketpair, - .accept = sock_no_accept, - .getname = inet_getname, - .poll = datagram_poll, - .ioctl = inet_ioctl, - .listen = sock_no_listen, - .shutdown = inet_shutdown, - .setsockopt = sock_common_setsockopt, - .getsockopt = sock_common_getsockopt, - .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, - .mmap = sock_no_mmap, - .sendpage = inet_sendpage, + .family = PF_INET, + .owner = THIS_MODULE, + .release = inet_release, + .bind = inet_bind, + .connect = inet_dgram_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = inet_getname, + .poll = datagram_poll, + .ioctl = inet_ioctl, + .listen = sock_no_listen, + .shutdown = inet_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, + .sendpage = inet_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; static struct net_proto_family inet_family_ops = { diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index aed537fa2c88..e16d8b42b953 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -97,6 +97,7 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah->reserved = 0; ah->spi = x->id.spi; ah->seq_no = htonl(++x->replay.oseq); + xfrm_aevent_doreplay(x); ahp->icv(ahp, skb, ah->auth_data); top_iph->tos = iph->tos; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index accdefedfed7..041dadde31af 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -879,16 +879,16 @@ static int arp_process(struct sk_buff *skb) n = __neigh_lookup(&arp_tbl, &sip, dev, 0); -#ifdef CONFIG_IP_ACCEPT_UNSOLICITED_ARP - /* Unsolicited ARP is not accepted by default. - It is possible, that this option should be enabled for some - devices (strip is candidate) - */ - if (n == NULL && - arp->ar_op == htons(ARPOP_REPLY) && - inet_addr_type(sip) == RTN_UNICAST) - n = __neigh_lookup(&arp_tbl, &sip, dev, -1); -#endif + if (ipv4_devconf.arp_accept) { + /* Unsolicited ARP is not accepted by default. + It is possible, that this option should be enabled for some + devices (strip is candidate) + */ + if (n == NULL && + arp->ar_op == htons(ARPOP_REPLY) && + inet_addr_type(sip) == RTN_UNICAST) + n = __neigh_lookup(&arp_tbl, &sip, dev, -1); + } if (n) { int state = NUD_REACHABLE; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 3ffa60dadc0c..44fdf1413e2c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1394,6 +1394,14 @@ static struct devinet_sysctl_table { .proc_handler = &proc_dointvec, }, { + .ctl_name = NET_IPV4_CONF_ARP_ACCEPT, + .procname = "arp_accept", + .data = &ipv4_devconf.arp_accept, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { .ctl_name = NET_IPV4_CONF_NOXFRM, .procname = "disable_xfrm", .data = &ipv4_devconf.no_xfrm, diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 09590f356086..bf88c620a954 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -90,6 +90,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) esph->spi = x->id.spi; esph->seq_no = htonl(++x->replay.oseq); + xfrm_aevent_doreplay(x); if (esp->conf.ivlen) crypto_cipher_set_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm)); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 0dd4d06e456d..768e8f5d7daa 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -40,6 +40,8 @@ #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> +#include <linux/list.h> +#include <linux/rcupdate.h> #include <net/ip.h> #include <net/protocol.h> @@ -52,7 +54,7 @@ struct fib_rule { - struct fib_rule *r_next; + struct hlist_node hlist; atomic_t r_clntref; u32 r_preference; unsigned char r_table; @@ -75,6 +77,7 @@ struct fib_rule #endif char r_ifname[IFNAMSIZ]; int r_dead; + struct rcu_head rcu; }; static struct fib_rule default_rule = { @@ -85,7 +88,6 @@ static struct fib_rule default_rule = { }; static struct fib_rule main_rule = { - .r_next = &default_rule, .r_clntref = ATOMIC_INIT(2), .r_preference = 0x7FFE, .r_table = RT_TABLE_MAIN, @@ -93,23 +95,24 @@ static struct fib_rule main_rule = { }; static struct fib_rule local_rule = { - .r_next = &main_rule, .r_clntref = ATOMIC_INIT(2), .r_table = RT_TABLE_LOCAL, .r_action = RTN_UNICAST, }; -static struct fib_rule *fib_rules = &local_rule; -static DEFINE_RWLOCK(fib_rules_lock); +static struct hlist_head fib_rules; + +/* writer func called from netlink -- rtnl_sem hold*/ int inet_rtm_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { struct rtattr **rta = arg; struct rtmsg *rtm = NLMSG_DATA(nlh); - struct fib_rule *r, **rp; + struct fib_rule *r; + struct hlist_node *node; int err = -ESRCH; - for (rp=&fib_rules; (r=*rp) != NULL; rp=&r->r_next) { + hlist_for_each_entry(r, node, &fib_rules, hlist) { if ((!rta[RTA_SRC-1] || memcmp(RTA_DATA(rta[RTA_SRC-1]), &r->r_src, 4) == 0) && rtm->rtm_src_len == r->r_src_len && rtm->rtm_dst_len == r->r_dst_len && @@ -126,10 +129,8 @@ int inet_rtm_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (r == &local_rule) break; - write_lock_bh(&fib_rules_lock); - *rp = r->r_next; + hlist_del_rcu(&r->hlist); r->r_dead = 1; - write_unlock_bh(&fib_rules_lock); fib_rule_put(r); err = 0; break; @@ -150,21 +151,30 @@ static struct fib_table *fib_empty_table(void) return NULL; } +static inline void fib_rule_put_rcu(struct rcu_head *head) +{ + struct fib_rule *r = container_of(head, struct fib_rule, rcu); + kfree(r); +} + void fib_rule_put(struct fib_rule *r) { if (atomic_dec_and_test(&r->r_clntref)) { if (r->r_dead) - kfree(r); + call_rcu(&r->rcu, fib_rule_put_rcu); else printk("Freeing alive rule %p\n", r); } } +/* writer func called from netlink -- rtnl_sem hold*/ + int inet_rtm_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { struct rtattr **rta = arg; struct rtmsg *rtm = NLMSG_DATA(nlh); - struct fib_rule *r, *new_r, **rp; + struct fib_rule *r, *new_r, *last = NULL; + struct hlist_node *node = NULL; unsigned char table_id; if (rtm->rtm_src_len > 32 || rtm->rtm_dst_len > 32 || @@ -188,6 +198,7 @@ int inet_rtm_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (!new_r) return -ENOMEM; memset(new_r, 0, sizeof(*new_r)); + if (rta[RTA_SRC-1]) memcpy(&new_r->r_src, RTA_DATA(rta[RTA_SRC-1]), 4); if (rta[RTA_DST-1]) @@ -220,28 +231,28 @@ int inet_rtm_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (rta[RTA_FLOW-1]) memcpy(&new_r->r_tclassid, RTA_DATA(rta[RTA_FLOW-1]), 4); #endif + r = container_of(fib_rules.first, struct fib_rule, hlist); - rp = &fib_rules; if (!new_r->r_preference) { - r = fib_rules; - if (r && (r = r->r_next) != NULL) { - rp = &fib_rules->r_next; + if (r && r->hlist.next != NULL) { + r = container_of(r->hlist.next, struct fib_rule, hlist); if (r->r_preference) new_r->r_preference = r->r_preference - 1; } } - while ( (r = *rp) != NULL ) { + hlist_for_each_entry(r, node, &fib_rules, hlist) { if (r->r_preference > new_r->r_preference) break; - rp = &r->r_next; + last = r; } - - new_r->r_next = r; atomic_inc(&new_r->r_clntref); - write_lock_bh(&fib_rules_lock); - *rp = new_r; - write_unlock_bh(&fib_rules_lock); + + if (last) + hlist_add_after_rcu(&last->hlist, &new_r->hlist); + else + hlist_add_before_rcu(&new_r->hlist, &r->hlist); + return 0; } @@ -254,30 +265,30 @@ u32 fib_rules_tclass(struct fib_result *res) } #endif +/* callers should hold rtnl semaphore */ static void fib_rules_detach(struct net_device *dev) { + struct hlist_node *node; struct fib_rule *r; - for (r=fib_rules; r; r=r->r_next) { - if (r->r_ifindex == dev->ifindex) { - write_lock_bh(&fib_rules_lock); + hlist_for_each_entry(r, node, &fib_rules, hlist) { + if (r->r_ifindex == dev->ifindex) r->r_ifindex = -1; - write_unlock_bh(&fib_rules_lock); - } + } } +/* callers should hold rtnl semaphore */ + static void fib_rules_attach(struct net_device *dev) { + struct hlist_node *node; struct fib_rule *r; - for (r=fib_rules; r; r=r->r_next) { - if (r->r_ifindex == -1 && strcmp(dev->name, r->r_ifname) == 0) { - write_lock_bh(&fib_rules_lock); + hlist_for_each_entry(r, node, &fib_rules, hlist) { + if (r->r_ifindex == -1 && strcmp(dev->name, r->r_ifname) == 0) r->r_ifindex = dev->ifindex; - write_unlock_bh(&fib_rules_lock); - } } } @@ -286,14 +297,17 @@ int fib_lookup(const struct flowi *flp, struct fib_result *res) int err; struct fib_rule *r, *policy; struct fib_table *tb; + struct hlist_node *node; u32 daddr = flp->fl4_dst; u32 saddr = flp->fl4_src; FRprintk("Lookup: %u.%u.%u.%u <- %u.%u.%u.%u ", NIPQUAD(flp->fl4_dst), NIPQUAD(flp->fl4_src)); - read_lock(&fib_rules_lock); - for (r = fib_rules; r; r=r->r_next) { + + rcu_read_lock(); + + hlist_for_each_entry_rcu(r, node, &fib_rules, hlist) { if (((saddr^r->r_src) & r->r_srcmask) || ((daddr^r->r_dst) & r->r_dstmask) || (r->r_tos && r->r_tos != flp->fl4_tos) || @@ -309,14 +323,14 @@ FRprintk("tb %d r %d ", r->r_table, r->r_action); policy = r; break; case RTN_UNREACHABLE: - read_unlock(&fib_rules_lock); + rcu_read_unlock(); return -ENETUNREACH; default: case RTN_BLACKHOLE: - read_unlock(&fib_rules_lock); + rcu_read_unlock(); return -EINVAL; case RTN_PROHIBIT: - read_unlock(&fib_rules_lock); + rcu_read_unlock(); return -EACCES; } @@ -327,16 +341,16 @@ FRprintk("tb %d r %d ", r->r_table, r->r_action); res->r = policy; if (policy) atomic_inc(&policy->r_clntref); - read_unlock(&fib_rules_lock); + rcu_read_unlock(); return 0; } if (err < 0 && err != -EAGAIN) { - read_unlock(&fib_rules_lock); + rcu_read_unlock(); return err; } } FRprintk("FAILURE\n"); - read_unlock(&fib_rules_lock); + rcu_read_unlock(); return -ENETUNREACH; } @@ -414,20 +428,25 @@ rtattr_failure: return -1; } +/* callers should hold rtnl semaphore */ + int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) { - int idx; + int idx = 0; int s_idx = cb->args[0]; struct fib_rule *r; + struct hlist_node *node; + + rcu_read_lock(); + hlist_for_each_entry(r, node, &fib_rules, hlist) { - read_lock(&fib_rules_lock); - for (r=fib_rules, idx=0; r; r = r->r_next, idx++) { if (idx < s_idx) continue; if (inet_fill_rule(skb, r, cb, NLM_F_MULTI) < 0) break; + idx++; } - read_unlock(&fib_rules_lock); + rcu_read_unlock(); cb->args[0] = idx; return skb->len; @@ -435,5 +454,9 @@ int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) void __init fib_rules_init(void) { + INIT_HLIST_HEAD(&fib_rules); + hlist_add_head(&local_rule.hlist, &fib_rules); + hlist_add_after(&local_rule.hlist, &main_rule.hlist); + hlist_add_after(&main_rule.hlist, &default_rule.hlist); register_netdevice_notifier(&fib_rules_notifier); } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e320b32373e5..ccd3efc6a173 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -50,7 +50,7 @@ * Patrick McHardy <kaber@trash.net> */ -#define VERSION "0.404" +#define VERSION "0.406" #include <linux/config.h> #include <asm/uaccess.h> @@ -84,7 +84,7 @@ #include "fib_lookup.h" #undef CONFIG_IP_FIB_TRIE_STATS -#define MAX_CHILDS 16384 +#define MAX_STAT_DEPTH 32 #define KEYLENGTH (8*sizeof(t_key)) #define MASK_PFX(k, l) (((l)==0)?0:(k >> (KEYLENGTH-l)) << (KEYLENGTH-l)) @@ -154,7 +154,7 @@ struct trie_stat { unsigned int tnodes; unsigned int leaves; unsigned int nullpointers; - unsigned int nodesizes[MAX_CHILDS]; + unsigned int nodesizes[MAX_STAT_DEPTH]; }; struct trie { @@ -2040,7 +2040,15 @@ rescan: static struct node *fib_trie_get_first(struct fib_trie_iter *iter, struct trie *t) { - struct node *n = rcu_dereference(t->trie); + struct node *n ; + + if(!t) + return NULL; + + n = rcu_dereference(t->trie); + + if(!iter) + return NULL; if (n && IS_TNODE(n)) { iter->tnode = (struct tnode *) n; @@ -2072,7 +2080,9 @@ static void trie_collect_stats(struct trie *t, struct trie_stat *s) int i; s->tnodes++; - s->nodesizes[tn->bits]++; + if(tn->bits < MAX_STAT_DEPTH) + s->nodesizes[tn->bits]++; + for (i = 0; i < (1<<tn->bits); i++) if (!tn->child[i]) s->nullpointers++; @@ -2102,8 +2112,8 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) seq_printf(seq, "\tInternal nodes: %d\n\t", stat->tnodes); bytes += sizeof(struct tnode) * stat->tnodes; - max = MAX_CHILDS-1; - while (max >= 0 && stat->nodesizes[max] == 0) + max = MAX_STAT_DEPTH; + while (max > 0 && stat->nodesizes[max-1] == 0) max--; pointers = 0; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 64ce52bf0485..d512239a1473 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1382,7 +1382,7 @@ static struct in_device * ip_mc_find_dev(struct ip_mreqn *imr) dev = ip_dev_find(imr->imr_address.s_addr); if (!dev) return NULL; - __dev_put(dev); + dev_put(dev); } if (!dev && !ip_route_output_key(&rt, &fl)) { @@ -1730,7 +1730,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) if (!MULTICAST(addr)) return -EINVAL; - rtnl_shlock(); + rtnl_lock(); in_dev = ip_mc_find_dev(imr); @@ -1763,7 +1763,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) ip_mc_inc_group(in_dev, addr); err = 0; done: - rtnl_shunlock(); + rtnl_unlock(); return err; } @@ -1837,7 +1837,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct if (!MULTICAST(addr)) return -EINVAL; - rtnl_shlock(); + rtnl_lock(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; @@ -1947,7 +1947,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: - rtnl_shunlock(); + rtnl_unlock(); if (leavegroup) return ip_mc_leave_group(sk, &imr); return err; @@ -1970,7 +1970,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; - rtnl_shlock(); + rtnl_lock(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; @@ -2030,7 +2030,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) pmc->sfmode = msf->imsf_fmode; err = 0; done: - rtnl_shunlock(); + rtnl_unlock(); if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; @@ -2050,7 +2050,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, if (!MULTICAST(addr)) return -EINVAL; - rtnl_shlock(); + rtnl_lock(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; @@ -2072,7 +2072,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, goto done; msf->imsf_fmode = pmc->sfmode; psl = pmc->sflist; - rtnl_shunlock(); + rtnl_unlock(); if (!psl) { len = 0; count = 0; @@ -2091,7 +2091,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, return -EFAULT; return 0; done: - rtnl_shunlock(); + rtnl_unlock(); return err; } @@ -2112,7 +2112,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, if (!MULTICAST(addr)) return -EINVAL; - rtnl_shlock(); + rtnl_lock(); err = -EADDRNOTAVAIL; @@ -2125,7 +2125,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, goto done; gsf->gf_fmode = pmc->sfmode; psl = pmc->sflist; - rtnl_shunlock(); + rtnl_unlock(); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; @@ -2146,7 +2146,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, } return 0; done: - rtnl_shunlock(); + rtnl_unlock(); return err; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index ae20281d8deb..9a01bb81f8bf 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -648,3 +648,52 @@ void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr) } EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr); + +int inet_csk_ctl_sock_create(struct socket **sock, unsigned short family, + unsigned short type, unsigned char protocol) +{ + int rc = sock_create_kern(family, type, protocol, sock); + + if (rc == 0) { + (*sock)->sk->sk_allocation = GFP_ATOMIC; + inet_sk((*sock)->sk)->uc_ttl = -1; + /* + * Unhash it so that IP input processing does not even see it, + * we do not wish this socket to see incoming packets. + */ + (*sock)->sk->sk_prot->unhash((*sock)->sk); + } + return rc; +} + +EXPORT_SYMBOL_GPL(inet_csk_ctl_sock_create); + +#ifdef CONFIG_COMPAT +int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_af_ops->compat_getsockopt != NULL) + return icsk->icsk_af_ops->compat_getsockopt(sk, level, optname, + optval, optlen); + return icsk->icsk_af_ops->getsockopt(sk, level, optname, + optval, optlen); +} + +EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt); + +int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_af_ops->compat_setsockopt != NULL) + return icsk->icsk_af_ops->compat_setsockopt(sk, level, optname, + optval, optlen); + return icsk->icsk_af_ops->setsockopt(sk, level, optname, + optval, optlen); +} + +EXPORT_SYMBOL_GPL(inet_csk_compat_setsockopt); +#endif diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 2bf8d782f678..12e0bf19f24a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -50,6 +50,7 @@ #define IP_CMSG_TOS 4 #define IP_CMSG_RECVOPTS 8 #define IP_CMSG_RETOPTS 16 +#define IP_CMSG_PASSSEC 32 /* * SOL_IP control messages. @@ -109,6 +110,19 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data); } +static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) +{ + char *secdata; + u32 seclen; + int err; + + err = security_socket_getpeersec_dgram(skb, &secdata, &seclen); + if (err) + return; + + put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata); +} + void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) { @@ -138,6 +152,11 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) if (flags & 1) ip_cmsg_recv_retopts(msg, skb); + if ((flags>>=1) == 0) + return; + + if (flags & 1) + ip_cmsg_recv_security(msg, skb); } int ip_cmsg_send(struct msghdr *msg, struct ipcm_cookie *ipc) @@ -380,20 +399,19 @@ out: * an IP socket. */ -int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) +static int do_ip_setsockopt(struct sock *sk, int level, + int optname, char __user *optval, int optlen) { struct inet_sock *inet = inet_sk(sk); int val=0,err; - if (level != SOL_IP) - return -ENOPROTOOPT; - if (((1<<optname) & ((1<<IP_PKTINFO) | (1<<IP_RECVTTL) | (1<<IP_RECVOPTS) | (1<<IP_RECVTOS) | (1<<IP_RETOPTS) | (1<<IP_TOS) | (1<<IP_TTL) | (1<<IP_HDRINCL) | (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) | - (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND))) || + (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) | + (1<<IP_PASSSEC))) || optname == IP_MULTICAST_TTL || optname == IP_MULTICAST_LOOP) { if (optlen >= sizeof(int)) { @@ -478,6 +496,12 @@ int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, else inet->cmsg_flags &= ~IP_CMSG_RETOPTS; break; + case IP_PASSSEC: + if (val) + inet->cmsg_flags |= IP_CMSG_PASSSEC; + else + inet->cmsg_flags &= ~IP_CMSG_PASSSEC; + break; case IP_TOS: /* This sets both TOS and Precedence */ if (sk->sk_type == SOCK_STREAM) { val &= ~3; @@ -849,12 +873,7 @@ mc_msf_out: break; default: -#ifdef CONFIG_NETFILTER - err = nf_setsockopt(sk, PF_INET, optname, optval, - optlen); -#else err = -ENOPROTOOPT; -#endif break; } release_sock(sk); @@ -865,12 +884,68 @@ e_inval: return -EINVAL; } +int ip_setsockopt(struct sock *sk, int level, + int optname, char __user *optval, int optlen) +{ + int err; + + if (level != SOL_IP) + return -ENOPROTOOPT; + + err = do_ip_setsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IP_HDRINCL && + optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY +#ifdef CONFIG_IP_MROUTE + && (optname < MRT_BASE || optname > (MRT_BASE + 10)) +#endif + ) { + lock_sock(sk); + err = nf_setsockopt(sk, PF_INET, optname, optval, optlen); + release_sock(sk); + } +#endif + return err; +} + +#ifdef CONFIG_COMPAT +int compat_ip_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + int err; + + if (level != SOL_IP) + return -ENOPROTOOPT; + + err = do_ip_setsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IP_HDRINCL && + optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY +#ifdef CONFIG_IP_MROUTE + && (optname < MRT_BASE || optname > (MRT_BASE + 10)) +#endif + ) { + lock_sock(sk); + err = compat_nf_setsockopt(sk, PF_INET, optname, + optval, optlen); + release_sock(sk); + } +#endif + return err; +} + +EXPORT_SYMBOL(compat_ip_setsockopt); +#endif + /* * Get the options. Note for future reference. The GET of IP options gets the * _received_ ones. The set sets the _sent_ ones. */ -int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) +static int do_ip_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) { struct inet_sock *inet = inet_sk(sk); int val; @@ -932,6 +1007,9 @@ int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, case IP_RETOPTS: val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0; break; + case IP_PASSSEC: + val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0; + break; case IP_TOS: val = inet->tos; break; @@ -1051,17 +1129,8 @@ int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, val = inet->freebind; break; default: -#ifdef CONFIG_NETFILTER - val = nf_getsockopt(sk, PF_INET, optname, optval, - &len); - release_sock(sk); - if (val >= 0) - val = put_user(len, optlen); - return val; -#else release_sock(sk); return -ENOPROTOOPT; -#endif } release_sock(sk); @@ -1082,6 +1151,67 @@ int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, return 0; } +int ip_getsockopt(struct sock *sk, int level, + int optname, char __user *optval, int __user *optlen) +{ + int err; + + err = do_ip_getsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS +#ifdef CONFIG_IP_MROUTE + && (optname < MRT_BASE || optname > MRT_BASE+10) +#endif + ) { + int len; + + if(get_user(len,optlen)) + return -EFAULT; + + lock_sock(sk); + err = nf_getsockopt(sk, PF_INET, optname, optval, + &len); + release_sock(sk); + if (err >= 0) + err = put_user(len, optlen); + return err; + } +#endif + return err; +} + +#ifdef CONFIG_COMPAT +int compat_ip_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + int err = do_ip_getsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS +#ifdef CONFIG_IP_MROUTE + && (optname < MRT_BASE || optname > MRT_BASE+10) +#endif + ) { + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + lock_sock(sk); + err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len); + release_sock(sk); + if (err >= 0) + err = put_user(len, optlen); + return err; + } +#endif + return err; +} + +EXPORT_SYMBOL(compat_ip_getsockopt); +#endif + EXPORT_SYMBOL(ip_cmsg_recv); EXPORT_SYMBOL(ip_getsockopt); diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index d64e2ec8da7b..c95020f7c81e 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -24,6 +24,7 @@ #include <linux/list.h> #include <linux/vmalloc.h> #include <linux/rtnetlink.h> +#include <linux/mutex.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/icmp.h> @@ -36,7 +37,7 @@ struct ipcomp_tfms { int users; }; -static DECLARE_MUTEX(ipcomp_resource_sem); +static DEFINE_MUTEX(ipcomp_resource_mutex); static void **ipcomp_scratches; static int ipcomp_scratch_users; static LIST_HEAD(ipcomp_tfms_list); @@ -253,7 +254,7 @@ error: } /* - * Must be protected by xfrm_cfg_sem. State and tunnel user references are + * Must be protected by xfrm_cfg_mutex. State and tunnel user references are * always incremented on success. */ static int ipcomp_tunnel_attach(struct xfrm_state *x) @@ -411,9 +412,9 @@ static void ipcomp_destroy(struct xfrm_state *x) if (!ipcd) return; xfrm_state_delete_tunnel(x); - down(&ipcomp_resource_sem); + mutex_lock(&ipcomp_resource_mutex); ipcomp_free_data(ipcd); - up(&ipcomp_resource_sem); + mutex_unlock(&ipcomp_resource_mutex); kfree(ipcd); } @@ -440,14 +441,14 @@ static int ipcomp_init_state(struct xfrm_state *x) if (x->props.mode) x->props.header_len += sizeof(struct iphdr); - down(&ipcomp_resource_sem); + mutex_lock(&ipcomp_resource_mutex); if (!ipcomp_alloc_scratches()) goto error; ipcd->tfms = ipcomp_alloc_tfms(x->calg->alg_name); if (!ipcd->tfms) goto error; - up(&ipcomp_resource_sem); + mutex_unlock(&ipcomp_resource_mutex); if (x->props.mode) { err = ipcomp_tunnel_attach(x); @@ -464,10 +465,10 @@ out: return err; error_tunnel: - down(&ipcomp_resource_sem); + mutex_lock(&ipcomp_resource_mutex); error: ipcomp_free_data(ipcd); - up(&ipcomp_resource_sem); + mutex_unlock(&ipcomp_resource_mutex); kfree(ipcd); goto out; } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index bb3613ec448c..cb8a92f18ef6 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -186,7 +186,7 @@ static int __init ic_open_devs(void) unsigned short oflags; last = &ic_first_dev; - rtnl_shlock(); + rtnl_lock(); /* bring loopback device up first */ if (dev_change_flags(&loopback_dev, loopback_dev.flags | IFF_UP) < 0) @@ -215,7 +215,7 @@ static int __init ic_open_devs(void) continue; } if (!(d = kmalloc(sizeof(struct ic_device), GFP_KERNEL))) { - rtnl_shunlock(); + rtnl_unlock(); return -1; } d->dev = dev; @@ -232,7 +232,7 @@ static int __init ic_open_devs(void) dev->name, able, d->xid)); } } - rtnl_shunlock(); + rtnl_unlock(); *last = NULL; @@ -251,7 +251,7 @@ static void __init ic_close_devs(void) struct ic_device *d, *next; struct net_device *dev; - rtnl_shlock(); + rtnl_lock(); next = ic_first_dev; while ((d = next)) { next = d->next; @@ -262,7 +262,7 @@ static void __init ic_close_devs(void) } kfree(d); } - rtnl_shunlock(); + rtnl_unlock(); } /* diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 5c94c222e3f3..717ab7d6d7b6 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -415,10 +415,10 @@ static int vif_add(struct vifctl *vifc, int mrtsock) return -ENOBUFS; break; case 0: - dev=ip_dev_find(vifc->vifc_lcl_addr.s_addr); + dev = ip_dev_find(vifc->vifc_lcl_addr.s_addr); if (!dev) return -EADDRNOTAVAIL; - __dev_put(dev); + dev_put(dev); break; default: return -EINVAL; diff --git a/net/ipv4/ipvs/ip_vs_app.c b/net/ipv4/ipvs/ip_vs_app.c index 9b176a942ac5..e7752334d296 100644 --- a/net/ipv4/ipvs/ip_vs_app.c +++ b/net/ipv4/ipvs/ip_vs_app.c @@ -31,6 +31,7 @@ #include <linux/stat.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/mutex.h> #include <net/ip_vs.h> @@ -40,7 +41,7 @@ EXPORT_SYMBOL(register_ip_vs_app_inc); /* ipvs application list head */ static LIST_HEAD(ip_vs_app_list); -static DECLARE_MUTEX(__ip_vs_app_mutex); +static DEFINE_MUTEX(__ip_vs_app_mutex); /* @@ -173,11 +174,11 @@ register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port) { int result; - down(&__ip_vs_app_mutex); + mutex_lock(&__ip_vs_app_mutex); result = ip_vs_app_inc_new(app, proto, port); - up(&__ip_vs_app_mutex); + mutex_unlock(&__ip_vs_app_mutex); return result; } @@ -191,11 +192,11 @@ int register_ip_vs_app(struct ip_vs_app *app) /* increase the module use count */ ip_vs_use_count_inc(); - down(&__ip_vs_app_mutex); + mutex_lock(&__ip_vs_app_mutex); list_add(&app->a_list, &ip_vs_app_list); - up(&__ip_vs_app_mutex); + mutex_unlock(&__ip_vs_app_mutex); return 0; } @@ -209,7 +210,7 @@ void unregister_ip_vs_app(struct ip_vs_app *app) { struct ip_vs_app *inc, *nxt; - down(&__ip_vs_app_mutex); + mutex_lock(&__ip_vs_app_mutex); list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) { ip_vs_app_inc_release(inc); @@ -217,7 +218,7 @@ void unregister_ip_vs_app(struct ip_vs_app *app) list_del(&app->a_list); - up(&__ip_vs_app_mutex); + mutex_unlock(&__ip_vs_app_mutex); /* decrease the module use count */ ip_vs_use_count_dec(); @@ -498,7 +499,7 @@ static struct ip_vs_app *ip_vs_app_idx(loff_t pos) static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos) { - down(&__ip_vs_app_mutex); + mutex_lock(&__ip_vs_app_mutex); return *pos ? ip_vs_app_idx(*pos - 1) : SEQ_START_TOKEN; } @@ -530,7 +531,7 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ip_vs_app_seq_stop(struct seq_file *seq, void *v) { - up(&__ip_vs_app_mutex); + mutex_unlock(&__ip_vs_app_mutex); } static int ip_vs_app_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index db783036e4d8..882b842c25d4 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -168,6 +168,26 @@ config IP_NF_PPTP If you want to compile it as a module, say M here and read Documentation/modules.txt. If unsure, say `N'. +config IP_NF_H323 + tristate 'H.323 protocol support' + depends on IP_NF_CONNTRACK + help + H.323 is a VoIP signalling protocol from ITU-T. As one of the most + important VoIP protocols, it is widely used by voice hardware and + software including voice gateways, IP phones, Netmeeting, OpenPhone, + Gnomemeeting, etc. + + With this module you can support H.323 on a connection tracking/NAT + firewall. + + This module supports RAS, Fast-start, H.245 tunnelling, RTP/RTCP + and T.120 based data and applications including audio, video, FAX, + chat, whiteboard, file transfer, etc. For more information, please + see http://nath323.sourceforge.net/. + + If you want to compile it as a module, say 'M' here and read + Documentation/modules.txt. If unsure, say 'N'. + config IP_NF_QUEUE tristate "IP Userspace queueing via NETLINK (OBSOLETE)" help @@ -303,16 +323,6 @@ config IP_NF_MATCH_HASHLIMIT destination IP' or `500pps from any given source IP' with a single IPtables rule. -config IP_NF_MATCH_POLICY - tristate "IPsec policy match support" - depends on IP_NF_IPTABLES && XFRM - help - Policy matching allows you to match packets based on the - IPsec policy that was used during decapsulation/will - be used during encapsulation. - - To compile it as a module, choose M here. If unsure, say N. - # `filter', generic and specific targets config IP_NF_FILTER tristate "Packet filtering" @@ -494,6 +504,12 @@ config IP_NF_NAT_PPTP default IP_NF_NAT if IP_NF_PPTP=y default m if IP_NF_PPTP=m +config IP_NF_NAT_H323 + tristate + depends on IP_NF_IPTABLES!=n && IP_NF_CONNTRACK!=n && IP_NF_NAT!=n + default IP_NF_NAT if IP_NF_H323=y + default m if IP_NF_H323=m + # mangle + specific targets config IP_NF_MANGLE tristate "Packet mangling" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index e5c5b3202f02..f2cd9a6c5b91 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -10,6 +10,9 @@ iptable_nat-objs := ip_nat_rule.o ip_nat_standalone.o ip_conntrack_pptp-objs := ip_conntrack_helper_pptp.o ip_conntrack_proto_gre.o ip_nat_pptp-objs := ip_nat_helper_pptp.o ip_nat_proto_gre.o +ip_conntrack_h323-objs := ip_conntrack_helper_h323.o ip_conntrack_helper_h323_asn1.o +ip_nat_h323-objs := ip_nat_helper_h323.o + # connection tracking obj-$(CONFIG_IP_NF_CONNTRACK) += ip_conntrack.o obj-$(CONFIG_IP_NF_NAT) += ip_nat.o @@ -22,6 +25,7 @@ obj-$(CONFIG_IP_NF_CONNTRACK_NETLINK) += ip_conntrack_netlink.o obj-$(CONFIG_IP_NF_CT_PROTO_SCTP) += ip_conntrack_proto_sctp.o # connection tracking helpers +obj-$(CONFIG_IP_NF_H323) += ip_conntrack_h323.o obj-$(CONFIG_IP_NF_PPTP) += ip_conntrack_pptp.o obj-$(CONFIG_IP_NF_AMANDA) += ip_conntrack_amanda.o obj-$(CONFIG_IP_NF_TFTP) += ip_conntrack_tftp.o @@ -30,6 +34,7 @@ obj-$(CONFIG_IP_NF_IRC) += ip_conntrack_irc.o obj-$(CONFIG_IP_NF_NETBIOS_NS) += ip_conntrack_netbios_ns.o # NAT helpers +obj-$(CONFIG_IP_NF_NAT_H323) += ip_nat_h323.o obj-$(CONFIG_IP_NF_NAT_PPTP) += ip_nat_pptp.o obj-$(CONFIG_IP_NF_NAT_AMANDA) += ip_nat_amanda.o obj-$(CONFIG_IP_NF_NAT_TFTP) += ip_nat_tftp.o @@ -57,7 +62,6 @@ obj-$(CONFIG_IP_NF_MATCH_DSCP) += ipt_dscp.o obj-$(CONFIG_IP_NF_MATCH_AH_ESP) += ipt_ah.o ipt_esp.o obj-$(CONFIG_IP_NF_MATCH_TTL) += ipt_ttl.o obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o -obj-$(CONFIG_IP_NF_MATCH_POLICY) += ipt_policy.o # targets obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 7d7ab94a7a2e..f7efb3f27bf5 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -22,7 +22,7 @@ #include <linux/init.h> #include <asm/uaccess.h> -#include <asm/semaphore.h> +#include <linux/mutex.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp/arp_tables.h> @@ -208,6 +208,7 @@ static unsigned int arpt_error(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -300,6 +301,7 @@ unsigned int arpt_do_table(struct sk_buff **pskb, verdict = t->u.kernel.target->target(pskb, in, out, hook, + t->u.kernel.target, t->data, userdata); @@ -480,26 +482,31 @@ static inline int check_entry(struct arpt_entry *e, const char *name, unsigned i } t->u.kernel.target = target; + ret = xt_check_target(target, NF_ARP, t->u.target_size - sizeof(*t), + name, e->comefrom, 0, 0); + if (ret) + goto err; + if (t->u.kernel.target == &arpt_standard_target) { if (!standard_check(t, size)) { ret = -EINVAL; goto out; } } else if (t->u.kernel.target->checkentry - && !t->u.kernel.target->checkentry(name, e, t->data, + && !t->u.kernel.target->checkentry(name, e, target, t->data, t->u.target_size - sizeof(*t), e->comefrom)) { - module_put(t->u.kernel.target->me); duprintf("arp_tables: check failed for `%s'.\n", t->u.kernel.target->name); ret = -EINVAL; - goto out; + goto err; } (*i)++; return 0; - +err: + module_put(t->u.kernel.target->me); out: return ret; } @@ -555,7 +562,7 @@ static inline int cleanup_entry(struct arpt_entry *e, unsigned int *i) t = arpt_get_target(e); if (t->u.kernel.target->destroy) - t->u.kernel.target->destroy(t->data, + t->u.kernel.target->destroy(t->u.kernel.target, t->data, t->u.target_size - sizeof(*t)); module_put(t->u.kernel.target->me); return 0; @@ -1138,11 +1145,13 @@ void arpt_unregister_table(struct arpt_table *table) /* The built-in targets: standard (NULL) and error. */ static struct arpt_target arpt_standard_target = { .name = ARPT_STANDARD_TARGET, + .targetsize = sizeof(int), }; static struct arpt_target arpt_error_target = { .name = ARPT_ERROR_TARGET, .target = arpt_error, + .targetsize = ARPT_FUNCTION_MAXNAMELEN, }; static struct nf_sockopt_ops arpt_sockopts = { diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index c97650a16a5b..0f2a95350e26 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -8,9 +8,10 @@ MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); MODULE_DESCRIPTION("arptables arp payload mangle target"); static unsigned int -target(struct sk_buff **pskb, const struct net_device *in, - const struct net_device *out, unsigned int hooknum, const void *targinfo, - void *userinfo) +target(struct sk_buff **pskb, + const struct net_device *in, const struct net_device *out, + unsigned int hooknum, const struct xt_target *target, + const void *targinfo, void *userinfo) { const struct arpt_mangle *mangle = targinfo; struct arphdr *arp; @@ -65,8 +66,8 @@ target(struct sk_buff **pskb, const struct net_device *in, } static int -checkentry(const char *tablename, const void *e, void *targinfo, - unsigned int targinfosize, unsigned int hook_mask) +checkentry(const char *tablename, const void *e, const struct xt_target *target, + void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct arpt_mangle *mangle = targinfo; @@ -80,12 +81,12 @@ checkentry(const char *tablename, const void *e, void *targinfo, return 1; } -static struct arpt_target arpt_mangle_reg -= { - .name = "mangle", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE, +static struct arpt_target arpt_mangle_reg = { + .name = "mangle", + .target = target, + .targetsize = sizeof(struct arpt_mangle), + .checkentry = checkentry, + .me = THIS_MODULE, }; static int __init init(void) diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323.c b/net/ipv4/netfilter/ip_conntrack_helper_h323.c new file mode 100644 index 000000000000..20da6730b860 --- /dev/null +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323.c @@ -0,0 +1,1731 @@ +/* + * H.323 connection tracking helper + * + * Copyright (c) 2006 Jing Min Zhao <zhaojingmin@users.sourceforge.net> + * + * This source code is licensed under General Public License version 2. + * + * Based on the 'brute force' H.323 connection tracking module by + * Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * For more information, please see http://nath323.sourceforge.net/ + * + * Changes: + * 2006-02-01 - initial version 0.1 + * + * 2006-02-20 - version 0.2 + * 1. Changed source format to follow kernel conventions + * 2. Deleted some unnecessary structures + * 3. Minor fixes + * + * 2006-03-10 - version 0.3 + * 1. Added support for multiple TPKTs in one packet (suggested by + * Patrick McHardy) + * 2. Avoid excessive stack usage (based on Patrick McHardy's patch) + * 3. Added support for non-linear skb (based on Patrick McHardy's patch) + * 4. Fixed missing H.245 module owner (Patrick McHardy) + * 5. Avoid long RAS expectation chains (Patrick McHardy) + * 6. Fixed incorrect __exit attribute (Patrick McHardy) + * 7. Eliminated unnecessary return code + * 8. Fixed incorrect use of NAT data from conntrack code (suggested by + * Patrick McHardy) + * 9. Fixed TTL calculation error in RCF + * 10. Added TTL support in RRQ + * 11. Better support for separate TPKT header and data + * + * 2006-03-15 - version 0.4 + * 1. Added support for T.120 channels + * 2. Added parameter gkrouted_only (suggested by Patrick McHardy) + * 3. Splitted ASN.1 code and data (suggested by Patrick McHardy) + * 4. Sort ASN.1 data to avoid forwarding declarations (suggested by + * Patrick McHardy) + * 5. Reset next TPKT data length in get_tpkt_data() + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/ip.h> +#include <net/tcp.h> +#include <linux/netfilter_ipv4/ip_conntrack.h> +#include <linux/netfilter_ipv4/ip_conntrack_core.h> +#include <linux/netfilter_ipv4/ip_conntrack_helper.h> +#include <linux/netfilter_ipv4/ip_conntrack_tuple.h> +#include <linux/netfilter_ipv4/ip_conntrack_h323.h> +#include <linux/moduleparam.h> + +#include "ip_conntrack_helper_h323_asn1.h" + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + +/* Parameters */ +static int gkrouted_only = 1; +module_param(gkrouted_only, int, 0600); +MODULE_PARM_DESC(gkrouted_only, "only accept calls from gatekeeper"); + +/* Hooks for NAT */ +int (*set_h245_addr_hook) (struct sk_buff ** pskb, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, + u_int32_t ip, u_int16_t port); +int (*set_h225_addr_hook) (struct sk_buff ** pskb, + unsigned char **data, int dataoff, + TransportAddress * addr, + u_int32_t ip, u_int16_t port); +int (*set_sig_addr_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress * addr, int count); +int (*set_ras_addr_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress * addr, int count); +int (*nat_rtp_rtcp_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, + u_int16_t port, u_int16_t rtp_port, + struct ip_conntrack_expect * rtp_exp, + struct ip_conntrack_expect * rtcp_exp); +int (*nat_t120_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect * exp); +int (*nat_h245_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect * exp); +int (*nat_q931_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, TransportAddress * addr, int idx, + u_int16_t port, struct ip_conntrack_expect * exp); + + +static DEFINE_SPINLOCK(ip_h323_lock); +static char *h323_buffer; + +/****************************************************************************/ +static int get_tpkt_data(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int *datalen, int *dataoff) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int dir = CTINFO2DIR(ctinfo); + struct tcphdr _tcph, *th; + int tcpdatalen; + int tcpdataoff; + unsigned char *tpkt; + int tpktlen; + int tpktoff; + + /* Get TCP header */ + th = skb_header_pointer(*pskb, (*pskb)->nh.iph->ihl * 4, + sizeof(_tcph), &_tcph); + if (th == NULL) + return 0; + + /* Get TCP data offset */ + tcpdataoff = (*pskb)->nh.iph->ihl * 4 + th->doff * 4; + + /* Get TCP data length */ + tcpdatalen = (*pskb)->len - tcpdataoff; + if (tcpdatalen <= 0) /* No TCP data */ + goto clear_out; + + if (*data == NULL) { /* first TPKT */ + /* Get first TPKT pointer */ + tpkt = skb_header_pointer(*pskb, tcpdataoff, tcpdatalen, + h323_buffer); + BUG_ON(tpkt == NULL); + + /* Validate TPKT identifier */ + if (tcpdatalen < 4 || tpkt[0] != 0x03 || tpkt[1] != 0) { + /* Netmeeting sends TPKT header and data separately */ + if (info->tpkt_len[dir] > 0) { + DEBUGP("ip_ct_h323: previous packet " + "indicated separate TPKT data of %hu " + "bytes\n", info->tpkt_len[dir]); + if (info->tpkt_len[dir] <= tcpdatalen) { + /* Yes, there was a TPKT header + * received */ + *data = tpkt; + *datalen = info->tpkt_len[dir]; + *dataoff = 0; + goto out; + } + + /* Fragmented TPKT */ + if (net_ratelimit()) + printk("ip_ct_h323: " + "fragmented TPKT\n"); + goto clear_out; + } + + /* It is not even a TPKT */ + return 0; + } + tpktoff = 0; + } else { /* Next TPKT */ + tpktoff = *dataoff + *datalen; + tcpdatalen -= tpktoff; + if (tcpdatalen <= 4) /* No more TPKT */ + goto clear_out; + tpkt = *data + *datalen; + + /* Validate TPKT identifier */ + if (tpkt[0] != 0x03 || tpkt[1] != 0) + goto clear_out; + } + + /* Validate TPKT length */ + tpktlen = tpkt[2] * 256 + tpkt[3]; + if (tpktlen > tcpdatalen) { + if (tcpdatalen == 4) { /* Separate TPKT header */ + /* Netmeeting sends TPKT header and data separately */ + DEBUGP("ip_ct_h323: separate TPKT header indicates " + "there will be TPKT data of %hu bytes\n", + tpktlen - 4); + info->tpkt_len[dir] = tpktlen - 4; + return 0; + } + + if (net_ratelimit()) + printk("ip_ct_h323: incomplete TPKT (fragmented?)\n"); + goto clear_out; + } + + /* This is the encapsulated data */ + *data = tpkt + 4; + *datalen = tpktlen - 4; + *dataoff = tpktoff + 4; + + out: + /* Clear TPKT length */ + info->tpkt_len[dir] = 0; + return 1; + + clear_out: + info->tpkt_len[dir] = 0; + return 0; +} + +/****************************************************************************/ +int get_h245_addr(unsigned char *data, H245_TransportAddress * addr, + u_int32_t * ip, u_int16_t * port) +{ + unsigned char *p; + + if (addr->choice != eH245_TransportAddress_unicastAddress || + addr->unicastAddress.choice != eUnicastAddress_iPAddress) + return 0; + + p = data + addr->unicastAddress.iPAddress.network; + *ip = htonl((p[0] << 24) | (p[1] << 16) | (p[2] << 8) | (p[3])); + *port = (p[4] << 8) | (p[5]); + + return 1; +} + +/****************************************************************************/ +static int expect_rtp_rtcp(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr) +{ + int dir = CTINFO2DIR(ctinfo); + int ret = 0; + u_int32_t ip; + u_int16_t port; + u_int16_t rtp_port; + struct ip_conntrack_expect *rtp_exp; + struct ip_conntrack_expect *rtcp_exp; + + /* Read RTP or RTCP address */ + if (!get_h245_addr(*data, addr, &ip, &port) || + ip != ct->tuplehash[dir].tuple.src.ip || port == 0) + return 0; + + /* RTP port is even */ + rtp_port = port & (~1); + + /* Create expect for RTP */ + if ((rtp_exp = ip_conntrack_expect_alloc(ct)) == NULL) + return -1; + rtp_exp->tuple.src.ip = ct->tuplehash[!dir].tuple.src.ip; + rtp_exp->tuple.src.u.udp.port = 0; + rtp_exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; + rtp_exp->tuple.dst.u.udp.port = htons(rtp_port); + rtp_exp->tuple.dst.protonum = IPPROTO_UDP; + rtp_exp->mask.src.ip = 0xFFFFFFFF; + rtp_exp->mask.src.u.udp.port = 0; + rtp_exp->mask.dst.ip = 0xFFFFFFFF; + rtp_exp->mask.dst.u.udp.port = 0xFFFF; + rtp_exp->mask.dst.protonum = 0xFF; + rtp_exp->flags = 0; + + /* Create expect for RTCP */ + if ((rtcp_exp = ip_conntrack_expect_alloc(ct)) == NULL) { + ip_conntrack_expect_put(rtp_exp); + return -1; + } + rtcp_exp->tuple.src.ip = ct->tuplehash[!dir].tuple.src.ip; + rtcp_exp->tuple.src.u.udp.port = 0; + rtcp_exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; + rtcp_exp->tuple.dst.u.udp.port = htons(rtp_port + 1); + rtcp_exp->tuple.dst.protonum = IPPROTO_UDP; + rtcp_exp->mask.src.ip = 0xFFFFFFFF; + rtcp_exp->mask.src.u.udp.port = 0; + rtcp_exp->mask.dst.ip = 0xFFFFFFFF; + rtcp_exp->mask.dst.u.udp.port = 0xFFFF; + rtcp_exp->mask.dst.protonum = 0xFF; + rtcp_exp->flags = 0; + + if (ct->tuplehash[dir].tuple.src.ip != + ct->tuplehash[!dir].tuple.dst.ip && nat_rtp_rtcp_hook) { + /* NAT needed */ + ret = nat_rtp_rtcp_hook(pskb, ct, ctinfo, data, dataoff, + addr, port, rtp_port, rtp_exp, + rtcp_exp); + } else { /* Conntrack only */ + rtp_exp->expectfn = NULL; + rtcp_exp->expectfn = NULL; + + if (ip_conntrack_expect_related(rtp_exp) == 0) { + if (ip_conntrack_expect_related(rtcp_exp) == 0) { + DEBUGP("ip_ct_h323: expect RTP " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(rtp_exp->tuple.src.ip), + ntohs(rtp_exp->tuple.src.u.udp.port), + NIPQUAD(rtp_exp->tuple.dst.ip), + ntohs(rtp_exp->tuple.dst.u.udp.port)); + DEBUGP("ip_ct_h323: expect RTCP " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(rtcp_exp->tuple.src.ip), + ntohs(rtcp_exp->tuple.src.u.udp.port), + NIPQUAD(rtcp_exp->tuple.dst.ip), + ntohs(rtcp_exp->tuple.dst.u.udp.port)); + } else { + ip_conntrack_unexpect_related(rtp_exp); + ret = -1; + } + } else + ret = -1; + } + + ip_conntrack_expect_put(rtp_exp); + ip_conntrack_expect_put(rtcp_exp); + + return ret; +} + +/****************************************************************************/ +static int expect_t120(struct sk_buff **pskb, + struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr) +{ + int dir = CTINFO2DIR(ctinfo); + int ret = 0; + u_int32_t ip; + u_int16_t port; + struct ip_conntrack_expect *exp = NULL; + + /* Read T.120 address */ + if (!get_h245_addr(*data, addr, &ip, &port) || + ip != ct->tuplehash[dir].tuple.src.ip || port == 0) + return 0; + + /* Create expect for T.120 connections */ + if ((exp = ip_conntrack_expect_alloc(ct)) == NULL) + return -1; + exp->tuple.src.ip = ct->tuplehash[!dir].tuple.src.ip; + exp->tuple.src.u.tcp.port = 0; + exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; + exp->tuple.dst.u.tcp.port = htons(port); + exp->tuple.dst.protonum = IPPROTO_TCP; + exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.u.tcp.port = 0; + exp->mask.dst.ip = 0xFFFFFFFF; + exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.protonum = 0xFF; + exp->flags = IP_CT_EXPECT_PERMANENT; /* Accept multiple channels */ + + if (ct->tuplehash[dir].tuple.src.ip != + ct->tuplehash[!dir].tuple.dst.ip && nat_t120_hook) { + /* NAT needed */ + ret = nat_t120_hook(pskb, ct, ctinfo, data, dataoff, addr, + port, exp); + } else { /* Conntrack only */ + exp->expectfn = NULL; + if (ip_conntrack_expect_related(exp) == 0) { + DEBUGP("ip_ct_h323: expect T.120 " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), + ntohs(exp->tuple.dst.u.tcp.port)); + } else + ret = -1; + } + + ip_conntrack_expect_put(exp); + + return ret; +} + +/****************************************************************************/ +static int process_h245_channel(struct sk_buff **pskb, + struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H2250LogicalChannelParameters * channel) +{ + int ret; + + if (channel->options & eH2250LogicalChannelParameters_mediaChannel) { + /* RTP */ + ret = expect_rtp_rtcp(pskb, ct, ctinfo, data, dataoff, + &channel->mediaChannel); + if (ret < 0) + return -1; + } + + if (channel-> + options & eH2250LogicalChannelParameters_mediaControlChannel) { + /* RTCP */ + ret = expect_rtp_rtcp(pskb, ct, ctinfo, data, dataoff, + &channel->mediaControlChannel); + if (ret < 0) + return -1; + } + + return 0; +} + +/****************************************************************************/ +static int process_olc(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + OpenLogicalChannel * olc) +{ + int ret; + + DEBUGP("ip_ct_h323: OpenLogicalChannel\n"); + + if (olc->forwardLogicalChannelParameters.multiplexParameters.choice == + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters) + { + ret = process_h245_channel(pskb, ct, ctinfo, data, dataoff, + &olc-> + forwardLogicalChannelParameters. + multiplexParameters. + h2250LogicalChannelParameters); + if (ret < 0) + return -1; + } + + if ((olc->options & + eOpenLogicalChannel_reverseLogicalChannelParameters) && + (olc->reverseLogicalChannelParameters.options & + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters) + && (olc->reverseLogicalChannelParameters.multiplexParameters. + choice == + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters)) + { + ret = + process_h245_channel(pskb, ct, ctinfo, data, dataoff, + &olc-> + reverseLogicalChannelParameters. + multiplexParameters. + h2250LogicalChannelParameters); + if (ret < 0) + return -1; + } + + if ((olc->options & eOpenLogicalChannel_separateStack) && + olc->forwardLogicalChannelParameters.dataType.choice == + eDataType_data && + olc->forwardLogicalChannelParameters.dataType.data.application. + choice == eDataApplicationCapability_application_t120 && + olc->forwardLogicalChannelParameters.dataType.data.application. + t120.choice == eDataProtocolCapability_separateLANStack && + olc->separateStack.networkAddress.choice == + eNetworkAccessParameters_networkAddress_localAreaAddress) { + ret = expect_t120(pskb, ct, ctinfo, data, dataoff, + &olc->separateStack.networkAddress. + localAreaAddress); + if (ret < 0) + return -1; + } + + return 0; +} + +/****************************************************************************/ +static int process_olca(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + OpenLogicalChannelAck * olca) +{ + H2250LogicalChannelAckParameters *ack; + int ret; + + DEBUGP("ip_ct_h323: OpenLogicalChannelAck\n"); + + if ((olca->options & + eOpenLogicalChannelAck_reverseLogicalChannelParameters) && + (olca->reverseLogicalChannelParameters.options & + eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters) + && (olca->reverseLogicalChannelParameters.multiplexParameters. + choice == + eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters)) + { + ret = process_h245_channel(pskb, ct, ctinfo, data, dataoff, + &olca-> + reverseLogicalChannelParameters. + multiplexParameters. + h2250LogicalChannelParameters); + if (ret < 0) + return -1; + } + + if ((olca->options & + eOpenLogicalChannelAck_forwardMultiplexAckParameters) && + (olca->forwardMultiplexAckParameters.choice == + eOpenLogicalChannelAck_forwardMultiplexAckParameters_h2250LogicalChannelAckParameters)) + { + ack = &olca->forwardMultiplexAckParameters. + h2250LogicalChannelAckParameters; + if (ack->options & + eH2250LogicalChannelAckParameters_mediaChannel) { + /* RTP */ + ret = expect_rtp_rtcp(pskb, ct, ctinfo, data, dataoff, + &ack->mediaChannel); + if (ret < 0) + return -1; + } + + if (ack->options & + eH2250LogicalChannelAckParameters_mediaControlChannel) { + /* RTCP */ + ret = expect_rtp_rtcp(pskb, ct, ctinfo, data, dataoff, + &ack->mediaControlChannel); + if (ret < 0) + return -1; + } + } + + return 0; +} + +/****************************************************************************/ +static int process_h245(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + MultimediaSystemControlMessage * mscm) +{ + switch (mscm->choice) { + case eMultimediaSystemControlMessage_request: + if (mscm->request.choice == + eRequestMessage_openLogicalChannel) { + return process_olc(pskb, ct, ctinfo, data, dataoff, + &mscm->request.openLogicalChannel); + } + DEBUGP("ip_ct_h323: H.245 Request %d\n", + mscm->request.choice); + break; + case eMultimediaSystemControlMessage_response: + if (mscm->response.choice == + eResponseMessage_openLogicalChannelAck) { + return process_olca(pskb, ct, ctinfo, data, dataoff, + &mscm->response. + openLogicalChannelAck); + } + DEBUGP("ip_ct_h323: H.245 Response %d\n", + mscm->response.choice); + break; + default: + DEBUGP("ip_ct_h323: H.245 signal %d\n", mscm->choice); + break; + } + + return 0; +} + +/****************************************************************************/ +static int h245_help(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo) +{ + static MultimediaSystemControlMessage mscm; + unsigned char *data = NULL; + int datalen; + int dataoff; + int ret; + + /* Until there's been traffic both ways, don't look in packets. */ + if (ctinfo != IP_CT_ESTABLISHED + && ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) { + return NF_ACCEPT; + } + DEBUGP("ip_ct_h245: skblen = %u\n", (*pskb)->len); + + spin_lock_bh(&ip_h323_lock); + + /* Process each TPKT */ + while (get_tpkt_data(pskb, ct, ctinfo, &data, &datalen, &dataoff)) { + DEBUGP("ip_ct_h245: TPKT %u.%u.%u.%u->%u.%u.%u.%u, len=%d\n", + NIPQUAD((*pskb)->nh.iph->saddr), + NIPQUAD((*pskb)->nh.iph->daddr), datalen); + + /* Decode H.245 signal */ + ret = DecodeMultimediaSystemControlMessage(data, datalen, + &mscm); + if (ret < 0) { + if (net_ratelimit()) + printk("ip_ct_h245: decoding error: %s\n", + ret == H323_ERROR_BOUND ? + "out of bound" : "out of range"); + /* We don't drop when decoding error */ + break; + } + + /* Process H.245 signal */ + if (process_h245(pskb, ct, ctinfo, &data, dataoff, &mscm) < 0) + goto drop; + } + + spin_unlock_bh(&ip_h323_lock); + return NF_ACCEPT; + + drop: + spin_unlock_bh(&ip_h323_lock); + if (net_ratelimit()) + printk("ip_ct_h245: packet dropped\n"); + return NF_DROP; +} + +/****************************************************************************/ +static struct ip_conntrack_helper ip_conntrack_helper_h245 = { + .name = "H.245", + .me = THIS_MODULE, + .max_expected = H323_RTP_CHANNEL_MAX * 4 + 2 /* T.120 */ , + .timeout = 240, + .tuple = {.dst = {.protonum = IPPROTO_TCP}}, + .mask = {.src = {.u = {0xFFFF}}, + .dst = {.protonum = 0xFF}}, + .help = h245_help +}; + +/****************************************************************************/ +void ip_conntrack_h245_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this) +{ + write_lock_bh(&ip_conntrack_lock); + new->helper = &ip_conntrack_helper_h245; + write_unlock_bh(&ip_conntrack_lock); +} + +/****************************************************************************/ +static int get_h225_addr(unsigned char *data, TransportAddress * addr, + u_int32_t * ip, u_int16_t * port) +{ + unsigned char *p; + + if (addr->choice != eTransportAddress_ipAddress) + return 0; + + p = data + addr->ipAddress.ip; + *ip = htonl((p[0] << 24) | (p[1] << 16) | (p[2] << 8) | (p[3])); + *port = (p[4] << 8) | (p[5]); + + return 1; +} + +/****************************************************************************/ +static int expect_h245(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress * addr) +{ + int dir = CTINFO2DIR(ctinfo); + int ret = 0; + u_int32_t ip; + u_int16_t port; + struct ip_conntrack_expect *exp = NULL; + + /* Read h245Address */ + if (!get_h225_addr(*data, addr, &ip, &port) || + ip != ct->tuplehash[dir].tuple.src.ip || port == 0) + return 0; + + /* Create expect for h245 connection */ + if ((exp = ip_conntrack_expect_alloc(ct)) == NULL) + return -1; + exp->tuple.src.ip = ct->tuplehash[!dir].tuple.src.ip; + exp->tuple.src.u.tcp.port = 0; + exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; + exp->tuple.dst.u.tcp.port = htons(port); + exp->tuple.dst.protonum = IPPROTO_TCP; + exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.u.tcp.port = 0; + exp->mask.dst.ip = 0xFFFFFFFF; + exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.protonum = 0xFF; + exp->flags = 0; + + if (ct->tuplehash[dir].tuple.src.ip != + ct->tuplehash[!dir].tuple.dst.ip && nat_h245_hook) { + /* NAT needed */ + ret = nat_h245_hook(pskb, ct, ctinfo, data, dataoff, addr, + port, exp); + } else { /* Conntrack only */ + exp->expectfn = ip_conntrack_h245_expect; + + if (ip_conntrack_expect_related(exp) == 0) { + DEBUGP("ip_ct_q931: expect H.245 " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), + ntohs(exp->tuple.dst.u.tcp.port)); + } else + ret = -1; + } + + ip_conntrack_expect_put(exp); + + return ret; +} + +/****************************************************************************/ +static int process_setup(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + Setup_UUIE * setup) +{ + int dir = CTINFO2DIR(ctinfo); + int ret; + int i; + u_int32_t ip; + u_int16_t port; + + DEBUGP("ip_ct_q931: Setup\n"); + + if (setup->options & eSetup_UUIE_h245Address) { + ret = expect_h245(pskb, ct, ctinfo, data, dataoff, + &setup->h245Address); + if (ret < 0) + return -1; + } + + if ((setup->options & eSetup_UUIE_destCallSignalAddress) && + (set_h225_addr_hook) && + get_h225_addr(*data, &setup->destCallSignalAddress, &ip, &port) && + ip != ct->tuplehash[!dir].tuple.src.ip) { + DEBUGP("ip_ct_q931: set destCallSignalAddress " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(ip), port, + NIPQUAD(ct->tuplehash[!dir].tuple.src.ip), + ntohs(ct->tuplehash[!dir].tuple.src.u.tcp.port)); + ret = set_h225_addr_hook(pskb, data, dataoff, + &setup->destCallSignalAddress, + ct->tuplehash[!dir].tuple.src.ip, + ntohs(ct->tuplehash[!dir].tuple.src. + u.tcp.port)); + if (ret < 0) + return -1; + } + + if ((setup->options & eSetup_UUIE_sourceCallSignalAddress) && + (set_h225_addr_hook) && + get_h225_addr(*data, &setup->sourceCallSignalAddress, &ip, &port) + && ip != ct->tuplehash[!dir].tuple.dst.ip) { + DEBUGP("ip_ct_q931: set sourceCallSignalAddress " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(ip), port, + NIPQUAD(ct->tuplehash[!dir].tuple.dst.ip), + ntohs(ct->tuplehash[!dir].tuple.dst.u.tcp.port)); + ret = set_h225_addr_hook(pskb, data, dataoff, + &setup->sourceCallSignalAddress, + ct->tuplehash[!dir].tuple.dst.ip, + ntohs(ct->tuplehash[!dir].tuple.dst. + u.tcp.port)); + if (ret < 0) + return -1; + } + + if (setup->options & eSetup_UUIE_fastStart) { + for (i = 0; i < setup->fastStart.count; i++) { + ret = process_olc(pskb, ct, ctinfo, data, dataoff, + &setup->fastStart.item[i]); + if (ret < 0) + return -1; + } + } + + return 0; +} + +/****************************************************************************/ +static int process_callproceeding(struct sk_buff **pskb, + struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + CallProceeding_UUIE * callproc) +{ + int ret; + int i; + + DEBUGP("ip_ct_q931: CallProceeding\n"); + + if (callproc->options & eCallProceeding_UUIE_h245Address) { + ret = expect_h245(pskb, ct, ctinfo, data, dataoff, + &callproc->h245Address); + if (ret < 0) + return -1; + } + + if (callproc->options & eCallProceeding_UUIE_fastStart) { + for (i = 0; i < callproc->fastStart.count; i++) { + ret = process_olc(pskb, ct, ctinfo, data, dataoff, + &callproc->fastStart.item[i]); + if (ret < 0) + return -1; + } + } + + return 0; +} + +/****************************************************************************/ +static int process_connect(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + Connect_UUIE * connect) +{ + int ret; + int i; + + DEBUGP("ip_ct_q931: Connect\n"); + + if (connect->options & eConnect_UUIE_h245Address) { + ret = expect_h245(pskb, ct, ctinfo, data, dataoff, + &connect->h245Address); + if (ret < 0) + return -1; + } + + if (connect->options & eConnect_UUIE_fastStart) { + for (i = 0; i < connect->fastStart.count; i++) { + ret = process_olc(pskb, ct, ctinfo, data, dataoff, + &connect->fastStart.item[i]); + if (ret < 0) + return -1; + } + } + + return 0; +} + +/****************************************************************************/ +static int process_alerting(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + Alerting_UUIE * alert) +{ + int ret; + int i; + + DEBUGP("ip_ct_q931: Alerting\n"); + + if (alert->options & eAlerting_UUIE_h245Address) { + ret = expect_h245(pskb, ct, ctinfo, data, dataoff, + &alert->h245Address); + if (ret < 0) + return -1; + } + + if (alert->options & eAlerting_UUIE_fastStart) { + for (i = 0; i < alert->fastStart.count; i++) { + ret = process_olc(pskb, ct, ctinfo, data, dataoff, + &alert->fastStart.item[i]); + if (ret < 0) + return -1; + } + } + + return 0; +} + +/****************************************************************************/ +static int process_information(struct sk_buff **pskb, + struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + Information_UUIE * info) +{ + int ret; + int i; + + DEBUGP("ip_ct_q931: Information\n"); + + if (info->options & eInformation_UUIE_fastStart) { + for (i = 0; i < info->fastStart.count; i++) { + ret = process_olc(pskb, ct, ctinfo, data, dataoff, + &info->fastStart.item[i]); + if (ret < 0) + return -1; + } + } + + return 0; +} + +/****************************************************************************/ +static int process_facility(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + Facility_UUIE * facility) +{ + int ret; + int i; + + DEBUGP("ip_ct_q931: Facility\n"); + + if (facility->options & eFacility_UUIE_h245Address) { + ret = expect_h245(pskb, ct, ctinfo, data, dataoff, + &facility->h245Address); + if (ret < 0) + return -1; + } + + if (facility->options & eFacility_UUIE_fastStart) { + for (i = 0; i < facility->fastStart.count; i++) { + ret = process_olc(pskb, ct, ctinfo, data, dataoff, + &facility->fastStart.item[i]); + if (ret < 0) + return -1; + } + } + + return 0; +} + +/****************************************************************************/ +static int process_progress(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + Progress_UUIE * progress) +{ + int ret; + int i; + + DEBUGP("ip_ct_q931: Progress\n"); + + if (progress->options & eProgress_UUIE_h245Address) { + ret = expect_h245(pskb, ct, ctinfo, data, dataoff, + &progress->h245Address); + if (ret < 0) + return -1; + } + + if (progress->options & eProgress_UUIE_fastStart) { + for (i = 0; i < progress->fastStart.count; i++) { + ret = process_olc(pskb, ct, ctinfo, data, dataoff, + &progress->fastStart.item[i]); + if (ret < 0) + return -1; + } + } + + return 0; +} + +/****************************************************************************/ +static int process_q931(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, Q931 * q931) +{ + H323_UU_PDU *pdu = &q931->UUIE.h323_uu_pdu; + int i; + int ret = 0; + + switch (pdu->h323_message_body.choice) { + case eH323_UU_PDU_h323_message_body_setup: + ret = process_setup(pskb, ct, ctinfo, data, dataoff, + &pdu->h323_message_body.setup); + break; + case eH323_UU_PDU_h323_message_body_callProceeding: + ret = process_callproceeding(pskb, ct, ctinfo, data, dataoff, + &pdu->h323_message_body. + callProceeding); + break; + case eH323_UU_PDU_h323_message_body_connect: + ret = process_connect(pskb, ct, ctinfo, data, dataoff, + &pdu->h323_message_body.connect); + break; + case eH323_UU_PDU_h323_message_body_alerting: + ret = process_alerting(pskb, ct, ctinfo, data, dataoff, + &pdu->h323_message_body.alerting); + break; + case eH323_UU_PDU_h323_message_body_information: + ret = process_information(pskb, ct, ctinfo, data, dataoff, + &pdu->h323_message_body. + information); + break; + case eH323_UU_PDU_h323_message_body_facility: + ret = process_facility(pskb, ct, ctinfo, data, dataoff, + &pdu->h323_message_body.facility); + break; + case eH323_UU_PDU_h323_message_body_progress: + ret = process_progress(pskb, ct, ctinfo, data, dataoff, + &pdu->h323_message_body.progress); + break; + default: + DEBUGP("ip_ct_q931: Q.931 signal %d\n", + pdu->h323_message_body.choice); + break; + } + + if (ret < 0) + return -1; + + if (pdu->options & eH323_UU_PDU_h245Control) { + for (i = 0; i < pdu->h245Control.count; i++) { + ret = process_h245(pskb, ct, ctinfo, data, dataoff, + &pdu->h245Control.item[i]); + if (ret < 0) + return -1; + } + } + + return 0; +} + +/****************************************************************************/ +static int q931_help(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo) +{ + static Q931 q931; + unsigned char *data = NULL; + int datalen; + int dataoff; + int ret; + + /* Until there's been traffic both ways, don't look in packets. */ + if (ctinfo != IP_CT_ESTABLISHED + && ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) { + return NF_ACCEPT; + } + DEBUGP("ip_ct_q931: skblen = %u\n", (*pskb)->len); + + spin_lock_bh(&ip_h323_lock); + + /* Process each TPKT */ + while (get_tpkt_data(pskb, ct, ctinfo, &data, &datalen, &dataoff)) { + DEBUGP("ip_ct_q931: TPKT %u.%u.%u.%u->%u.%u.%u.%u, len=%d\n", + NIPQUAD((*pskb)->nh.iph->saddr), + NIPQUAD((*pskb)->nh.iph->daddr), datalen); + + /* Decode Q.931 signal */ + ret = DecodeQ931(data, datalen, &q931); + if (ret < 0) { + if (net_ratelimit()) + printk("ip_ct_q931: decoding error: %s\n", + ret == H323_ERROR_BOUND ? + "out of bound" : "out of range"); + /* We don't drop when decoding error */ + break; + } + + /* Process Q.931 signal */ + if (process_q931(pskb, ct, ctinfo, &data, dataoff, &q931) < 0) + goto drop; + } + + spin_unlock_bh(&ip_h323_lock); + return NF_ACCEPT; + + drop: + spin_unlock_bh(&ip_h323_lock); + if (net_ratelimit()) + printk("ip_ct_q931: packet dropped\n"); + return NF_DROP; +} + +/****************************************************************************/ +static struct ip_conntrack_helper ip_conntrack_helper_q931 = { + .name = "Q.931", + .me = THIS_MODULE, + .max_expected = H323_RTP_CHANNEL_MAX * 4 + 4 /* T.120 and H.245 */ , + .timeout = 240, + .tuple = {.src = {.u = {__constant_htons(Q931_PORT)}}, + .dst = {.protonum = IPPROTO_TCP}}, + .mask = {.src = {.u = {0xFFFF}}, + .dst = {.protonum = 0xFF}}, + .help = q931_help +}; + +/****************************************************************************/ +void ip_conntrack_q931_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this) +{ + write_lock_bh(&ip_conntrack_lock); + new->helper = &ip_conntrack_helper_q931; + write_unlock_bh(&ip_conntrack_lock); +} + +/****************************************************************************/ +static unsigned char *get_udp_data(struct sk_buff **pskb, int *datalen) +{ + struct udphdr _uh, *uh; + int dataoff; + + uh = skb_header_pointer(*pskb, (*pskb)->nh.iph->ihl * 4, sizeof(_uh), + &_uh); + if (uh == NULL) + return NULL; + dataoff = (*pskb)->nh.iph->ihl * 4 + sizeof(_uh); + if (dataoff >= (*pskb)->len) + return NULL; + *datalen = (*pskb)->len - dataoff; + return skb_header_pointer(*pskb, dataoff, *datalen, h323_buffer); +} + +/****************************************************************************/ +static struct ip_conntrack_expect *find_expect(struct ip_conntrack *ct, + u_int32_t ip, u_int16_t port) +{ + struct ip_conntrack_expect *exp; + struct ip_conntrack_tuple tuple; + + tuple.src.ip = 0; + tuple.src.u.tcp.port = 0; + tuple.dst.ip = ip; + tuple.dst.u.tcp.port = htons(port); + tuple.dst.protonum = IPPROTO_TCP; + + exp = __ip_conntrack_expect_find(&tuple); + if (exp->master == ct) + return exp; + return NULL; +} + +/****************************************************************************/ +static int set_expect_timeout(struct ip_conntrack_expect *exp, + unsigned timeout) +{ + if (!exp || !del_timer(&exp->timeout)) + return 0; + + exp->timeout.expires = jiffies + timeout * HZ; + add_timer(&exp->timeout); + + return 1; +} + +/****************************************************************************/ +static int expect_q931(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress * addr, int count) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int dir = CTINFO2DIR(ctinfo); + int ret = 0; + int i; + u_int32_t ip; + u_int16_t port; + struct ip_conntrack_expect *exp; + + /* Look for the first related address */ + for (i = 0; i < count; i++) { + if (get_h225_addr(*data, &addr[i], &ip, &port) && + ip == ct->tuplehash[dir].tuple.src.ip && port != 0) + break; + } + + if (i >= count) /* Not found */ + return 0; + + /* Create expect for Q.931 */ + if ((exp = ip_conntrack_expect_alloc(ct)) == NULL) + return -1; + exp->tuple.src.ip = gkrouted_only ? /* only accept calls from GK? */ + ct->tuplehash[!dir].tuple.src.ip : 0; + exp->tuple.src.u.tcp.port = 0; + exp->tuple.dst.ip = ct->tuplehash[!dir].tuple.dst.ip; + exp->tuple.dst.u.tcp.port = htons(port); + exp->tuple.dst.protonum = IPPROTO_TCP; + exp->mask.src.ip = gkrouted_only ? 0xFFFFFFFF : 0; + exp->mask.src.u.tcp.port = 0; + exp->mask.dst.ip = 0xFFFFFFFF; + exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.protonum = 0xFF; + exp->flags = IP_CT_EXPECT_PERMANENT; /* Accept multiple calls */ + + if (nat_q931_hook) { /* Need NAT */ + ret = nat_q931_hook(pskb, ct, ctinfo, data, addr, i, + port, exp); + } else { /* Conntrack only */ + exp->expectfn = ip_conntrack_q931_expect; + + if (ip_conntrack_expect_related(exp) == 0) { + DEBUGP("ip_ct_ras: expect Q.931 " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), + ntohs(exp->tuple.dst.u.tcp.port)); + + /* Save port for looking up expect in processing RCF */ + info->sig_port[dir] = port; + } else + ret = -1; + } + + ip_conntrack_expect_put(exp); + + return ret; +} + +/****************************************************************************/ +static int process_grq(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, GatekeeperRequest * grq) +{ + DEBUGP("ip_ct_ras: GRQ\n"); + + if (set_ras_addr_hook) /* NATed */ + return set_ras_addr_hook(pskb, ct, ctinfo, data, + &grq->rasAddress, 1); + return 0; +} + +/* Declare before using */ +static void ip_conntrack_ras_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this); + +/****************************************************************************/ +static int process_gcf(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, GatekeeperConfirm * gcf) +{ + int dir = CTINFO2DIR(ctinfo); + int ret = 0; + u_int32_t ip; + u_int16_t port; + struct ip_conntrack_expect *exp; + + DEBUGP("ip_ct_ras: GCF\n"); + + if (!get_h225_addr(*data, &gcf->rasAddress, &ip, &port)) + return 0; + + /* Registration port is the same as discovery port */ + if (ip == ct->tuplehash[dir].tuple.src.ip && + port == ntohs(ct->tuplehash[dir].tuple.src.u.udp.port)) + return 0; + + /* Avoid RAS expectation loops. A GCF is never expected. */ + if (test_bit(IPS_EXPECTED_BIT, &ct->status)) + return 0; + + /* Need new expect */ + if ((exp = ip_conntrack_expect_alloc(ct)) == NULL) + return -1; + exp->tuple.src.ip = ct->tuplehash[!dir].tuple.src.ip; + exp->tuple.src.u.tcp.port = 0; + exp->tuple.dst.ip = ip; + exp->tuple.dst.u.tcp.port = htons(port); + exp->tuple.dst.protonum = IPPROTO_UDP; + exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.u.tcp.port = 0; + exp->mask.dst.ip = 0xFFFFFFFF; + exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.protonum = 0xFF; + exp->flags = 0; + exp->expectfn = ip_conntrack_ras_expect; + if (ip_conntrack_expect_related(exp) == 0) { + DEBUGP("ip_ct_ras: expect RAS " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), + ntohs(exp->tuple.dst.u.tcp.port)); + } else + ret = -1; + + ip_conntrack_expect_put(exp); + + return ret; +} + +/****************************************************************************/ +static int process_rrq(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, RegistrationRequest * rrq) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int ret; + + DEBUGP("ip_ct_ras: RRQ\n"); + + ret = expect_q931(pskb, ct, ctinfo, data, + rrq->callSignalAddress.item, + rrq->callSignalAddress.count); + if (ret < 0) + return -1; + + if (set_ras_addr_hook) { + ret = set_ras_addr_hook(pskb, ct, ctinfo, data, + rrq->rasAddress.item, + rrq->rasAddress.count); + if (ret < 0) + return -1; + } + + if (rrq->options & eRegistrationRequest_timeToLive) { + DEBUGP("ip_ct_ras: RRQ TTL = %u seconds\n", rrq->timeToLive); + info->timeout = rrq->timeToLive; + } else + info->timeout = 0; + + return 0; +} + +/****************************************************************************/ +static int process_rcf(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, RegistrationConfirm * rcf) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int dir = CTINFO2DIR(ctinfo); + int ret; + struct ip_conntrack_expect *exp; + + DEBUGP("ip_ct_ras: RCF\n"); + + if (set_sig_addr_hook) { + ret = set_sig_addr_hook(pskb, ct, ctinfo, data, + rcf->callSignalAddress.item, + rcf->callSignalAddress.count); + if (ret < 0) + return -1; + } + + if (rcf->options & eRegistrationConfirm_timeToLive) { + DEBUGP("ip_ct_ras: RCF TTL = %u seconds\n", rcf->timeToLive); + info->timeout = rcf->timeToLive; + } + + if (info->timeout > 0) { + DEBUGP + ("ip_ct_ras: set RAS connection timeout to %u seconds\n", + info->timeout); + ip_ct_refresh_acct(ct, ctinfo, NULL, info->timeout * HZ); + + /* Set expect timeout */ + read_lock_bh(&ip_conntrack_lock); + exp = find_expect(ct, ct->tuplehash[dir].tuple.dst.ip, + info->sig_port[!dir]); + if (exp) { + DEBUGP("ip_ct_ras: set Q.931 expect " + "(%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu) " + "timeout to %u seconds\n", + NIPQUAD(exp->tuple.src.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), + ntohs(exp->tuple.dst.u.tcp.port), + info->timeout); + set_expect_timeout(exp, info->timeout); + } + read_unlock_bh(&ip_conntrack_lock); + } + + return 0; +} + +/****************************************************************************/ +static int process_urq(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, UnregistrationRequest * urq) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int dir = CTINFO2DIR(ctinfo); + int ret; + + DEBUGP("ip_ct_ras: URQ\n"); + + if (set_sig_addr_hook) { + ret = set_sig_addr_hook(pskb, ct, ctinfo, data, + urq->callSignalAddress.item, + urq->callSignalAddress.count); + if (ret < 0) + return -1; + } + + /* Clear old expect */ + ip_ct_remove_expectations(ct); + info->sig_port[dir] = 0; + info->sig_port[!dir] = 0; + + /* Give it 30 seconds for UCF or URJ */ + ip_ct_refresh_acct(ct, ctinfo, NULL, 30 * HZ); + + return 0; +} + +/****************************************************************************/ +static int process_arq(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, AdmissionRequest * arq) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int dir = CTINFO2DIR(ctinfo); + u_int32_t ip; + u_int16_t port; + + DEBUGP("ip_ct_ras: ARQ\n"); + + if ((arq->options & eAdmissionRequest_destCallSignalAddress) && + get_h225_addr(*data, &arq->destCallSignalAddress, &ip, &port) && + ip == ct->tuplehash[dir].tuple.src.ip && + port == info->sig_port[dir] && set_h225_addr_hook) { + /* Answering ARQ */ + return set_h225_addr_hook(pskb, data, 0, + &arq->destCallSignalAddress, + ct->tuplehash[!dir].tuple.dst.ip, + info->sig_port[!dir]); + } + + if ((arq->options & eAdmissionRequest_srcCallSignalAddress) && + get_h225_addr(*data, &arq->srcCallSignalAddress, &ip, &port) && + ip == ct->tuplehash[dir].tuple.src.ip && set_h225_addr_hook) { + /* Calling ARQ */ + return set_h225_addr_hook(pskb, data, 0, + &arq->srcCallSignalAddress, + ct->tuplehash[!dir].tuple.dst.ip, + port); + } + + return 0; +} + +/****************************************************************************/ +static int process_acf(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, AdmissionConfirm * acf) +{ + int dir = CTINFO2DIR(ctinfo); + int ret = 0; + u_int32_t ip; + u_int16_t port; + struct ip_conntrack_expect *exp; + + DEBUGP("ip_ct_ras: ACF\n"); + + if (!get_h225_addr(*data, &acf->destCallSignalAddress, &ip, &port)) + return 0; + + if (ip == ct->tuplehash[dir].tuple.dst.ip) { /* Answering ACF */ + if (set_sig_addr_hook) + return set_sig_addr_hook(pskb, ct, ctinfo, data, + &acf->destCallSignalAddress, + 1); + return 0; + } + + /* Need new expect */ + if ((exp = ip_conntrack_expect_alloc(ct)) == NULL) + return -1; + exp->tuple.src.ip = ct->tuplehash[!dir].tuple.src.ip; + exp->tuple.src.u.tcp.port = 0; + exp->tuple.dst.ip = ip; + exp->tuple.dst.u.tcp.port = htons(port); + exp->tuple.dst.protonum = IPPROTO_TCP; + exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.u.tcp.port = 0; + exp->mask.dst.ip = 0xFFFFFFFF; + exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.protonum = 0xFF; + exp->flags = IP_CT_EXPECT_PERMANENT; + exp->expectfn = ip_conntrack_q931_expect; + + if (ip_conntrack_expect_related(exp) == 0) { + DEBUGP("ip_ct_ras: expect Q.931 " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), + ntohs(exp->tuple.dst.u.tcp.port)); + } else + ret = -1; + + ip_conntrack_expect_put(exp); + + return ret; +} + +/****************************************************************************/ +static int process_lrq(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, LocationRequest * lrq) +{ + DEBUGP("ip_ct_ras: LRQ\n"); + + if (set_ras_addr_hook) + return set_ras_addr_hook(pskb, ct, ctinfo, data, + &lrq->replyAddress, 1); + return 0; +} + +/****************************************************************************/ +static int process_lcf(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, LocationConfirm * lcf) +{ + int dir = CTINFO2DIR(ctinfo); + int ret = 0; + u_int32_t ip; + u_int16_t port; + struct ip_conntrack_expect *exp = NULL; + + DEBUGP("ip_ct_ras: LCF\n"); + + if (!get_h225_addr(*data, &lcf->callSignalAddress, &ip, &port)) + return 0; + + /* Need new expect for call signal */ + if ((exp = ip_conntrack_expect_alloc(ct)) == NULL) + return -1; + exp->tuple.src.ip = ct->tuplehash[!dir].tuple.src.ip; + exp->tuple.src.u.tcp.port = 0; + exp->tuple.dst.ip = ip; + exp->tuple.dst.u.tcp.port = htons(port); + exp->tuple.dst.protonum = IPPROTO_TCP; + exp->mask.src.ip = 0xFFFFFFFF; + exp->mask.src.u.tcp.port = 0; + exp->mask.dst.ip = 0xFFFFFFFF; + exp->mask.dst.u.tcp.port = 0xFFFF; + exp->mask.dst.protonum = 0xFF; + exp->flags = IP_CT_EXPECT_PERMANENT; + exp->expectfn = ip_conntrack_q931_expect; + + if (ip_conntrack_expect_related(exp) == 0) { + DEBUGP("ip_ct_ras: expect Q.931 " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), + ntohs(exp->tuple.dst.u.tcp.port)); + } else + ret = -1; + + ip_conntrack_expect_put(exp); + + /* Ignore rasAddress */ + + return ret; +} + +/****************************************************************************/ +static int process_irr(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, InfoRequestResponse * irr) +{ + int ret; + + DEBUGP("ip_ct_ras: IRR\n"); + + if (set_ras_addr_hook) { + ret = set_ras_addr_hook(pskb, ct, ctinfo, data, + &irr->rasAddress, 1); + if (ret < 0) + return -1; + } + + if (set_sig_addr_hook) { + ret = set_sig_addr_hook(pskb, ct, ctinfo, data, + irr->callSignalAddress.item, + irr->callSignalAddress.count); + if (ret < 0) + return -1; + } + + return 0; +} + +/****************************************************************************/ +static int process_ras(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, RasMessage * ras) +{ + switch (ras->choice) { + case eRasMessage_gatekeeperRequest: + return process_grq(pskb, ct, ctinfo, data, + &ras->gatekeeperRequest); + case eRasMessage_gatekeeperConfirm: + return process_gcf(pskb, ct, ctinfo, data, + &ras->gatekeeperConfirm); + case eRasMessage_registrationRequest: + return process_rrq(pskb, ct, ctinfo, data, + &ras->registrationRequest); + case eRasMessage_registrationConfirm: + return process_rcf(pskb, ct, ctinfo, data, + &ras->registrationConfirm); + case eRasMessage_unregistrationRequest: + return process_urq(pskb, ct, ctinfo, data, + &ras->unregistrationRequest); + case eRasMessage_admissionRequest: + return process_arq(pskb, ct, ctinfo, data, + &ras->admissionRequest); + case eRasMessage_admissionConfirm: + return process_acf(pskb, ct, ctinfo, data, + &ras->admissionConfirm); + case eRasMessage_locationRequest: + return process_lrq(pskb, ct, ctinfo, data, + &ras->locationRequest); + case eRasMessage_locationConfirm: + return process_lcf(pskb, ct, ctinfo, data, + &ras->locationConfirm); + case eRasMessage_infoRequestResponse: + return process_irr(pskb, ct, ctinfo, data, + &ras->infoRequestResponse); + default: + DEBUGP("ip_ct_ras: RAS message %d\n", ras->choice); + break; + } + + return 0; +} + +/****************************************************************************/ +static int ras_help(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo) +{ + static RasMessage ras; + unsigned char *data; + int datalen = 0; + int ret; + + DEBUGP("ip_ct_ras: skblen = %u\n", (*pskb)->len); + + spin_lock_bh(&ip_h323_lock); + + /* Get UDP data */ + data = get_udp_data(pskb, &datalen); + if (data == NULL) + goto accept; + DEBUGP("ip_ct_ras: RAS message %u.%u.%u.%u->%u.%u.%u.%u, len=%d\n", + NIPQUAD((*pskb)->nh.iph->saddr), + NIPQUAD((*pskb)->nh.iph->daddr), datalen); + + /* Decode RAS message */ + ret = DecodeRasMessage(data, datalen, &ras); + if (ret < 0) { + if (net_ratelimit()) + printk("ip_ct_ras: decoding error: %s\n", + ret == H323_ERROR_BOUND ? + "out of bound" : "out of range"); + goto accept; + } + + /* Process RAS message */ + if (process_ras(pskb, ct, ctinfo, &data, &ras) < 0) + goto drop; + + accept: + spin_unlock_bh(&ip_h323_lock); + return NF_ACCEPT; + + drop: + spin_unlock_bh(&ip_h323_lock); + if (net_ratelimit()) + printk("ip_ct_ras: packet dropped\n"); + return NF_DROP; +} + +/****************************************************************************/ +static struct ip_conntrack_helper ip_conntrack_helper_ras = { + .name = "RAS", + .me = THIS_MODULE, + .max_expected = 32, + .timeout = 240, + .tuple = {.src = {.u = {__constant_htons(RAS_PORT)}}, + .dst = {.protonum = IPPROTO_UDP}}, + .mask = {.src = {.u = {0xFFFE}}, + .dst = {.protonum = 0xFF}}, + .help = ras_help, +}; + +/****************************************************************************/ +static void ip_conntrack_ras_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this) +{ + write_lock_bh(&ip_conntrack_lock); + new->helper = &ip_conntrack_helper_ras; + write_unlock_bh(&ip_conntrack_lock); +} + +/****************************************************************************/ +/* Not __exit - called from init() */ +static void fini(void) +{ + ip_conntrack_helper_unregister(&ip_conntrack_helper_ras); + ip_conntrack_helper_unregister(&ip_conntrack_helper_q931); + kfree(h323_buffer); + DEBUGP("ip_ct_h323: fini\n"); +} + +/****************************************************************************/ +static int __init init(void) +{ + int ret; + + h323_buffer = kmalloc(65536, GFP_KERNEL); + if (!h323_buffer) + return -ENOMEM; + if ((ret = ip_conntrack_helper_register(&ip_conntrack_helper_q931)) || + (ret = ip_conntrack_helper_register(&ip_conntrack_helper_ras))) { + fini(); + return ret; + } + + DEBUGP("ip_ct_h323: init success\n"); + return 0; +} + +/****************************************************************************/ +module_init(init); +module_exit(fini); + +EXPORT_SYMBOL(get_h245_addr); +EXPORT_SYMBOL(get_h225_addr); +EXPORT_SYMBOL(ip_conntrack_h245_expect); +EXPORT_SYMBOL(ip_conntrack_q931_expect); +EXPORT_SYMBOL(set_h245_addr_hook); +EXPORT_SYMBOL(set_h225_addr_hook); +EXPORT_SYMBOL(set_sig_addr_hook); +EXPORT_SYMBOL(set_ras_addr_hook); +EXPORT_SYMBOL(nat_rtp_rtcp_hook); +EXPORT_SYMBOL(nat_t120_hook); +EXPORT_SYMBOL(nat_h245_hook); +EXPORT_SYMBOL(nat_q931_hook); + +MODULE_AUTHOR("Jing Min Zhao <zhaojingmin@users.sourceforge.net>"); +MODULE_DESCRIPTION("H.323 connection tracking helper"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c b/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c new file mode 100644 index 000000000000..afa525129b51 --- /dev/null +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c @@ -0,0 +1,870 @@ +/**************************************************************************** + * ip_conntrack_helper_h323_asn1.c - BER and PER decoding library for H.323 + * conntrack/NAT module. + * + * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@hotmail.com> + * + * This source code is licensed under General Public License version 2. + * + * See ip_conntrack_helper_h323_asn1.h for details. + * + ****************************************************************************/ + +#ifdef __KERNEL__ +#include <linux/kernel.h> +#else +#include <stdio.h> +#endif +#include "ip_conntrack_helper_h323_asn1.h" + +/* Trace Flag */ +#ifndef H323_TRACE +#define H323_TRACE 0 +#endif + +#if H323_TRACE +#define TAB_SIZE 4 +#define IFTHEN(cond, act) if(cond){act;} +#ifdef __KERNEL__ +#define PRINT printk +#else +#define PRINT printf +#endif +#define FNAME(name) name, +#else +#define IFTHEN(cond, act) +#define PRINT(fmt, args...) +#define FNAME(name) +#endif + +/* ASN.1 Types */ +#define NUL 0 +#define BOOL 1 +#define OID 2 +#define INT 3 +#define ENUM 4 +#define BITSTR 5 +#define NUMSTR 6 +#define NUMDGT 6 +#define TBCDSTR 6 +#define OCTSTR 7 +#define PRTSTR 7 +#define IA5STR 7 +#define GENSTR 7 +#define BMPSTR 8 +#define SEQ 9 +#define SET 9 +#define SEQOF 10 +#define SETOF 10 +#define CHOICE 11 + +/* Constraint Types */ +#define FIXD 0 +/* #define BITS 1-8 */ +#define BYTE 9 +#define WORD 10 +#define CONS 11 +#define SEMI 12 +#define UNCO 13 + +/* ASN.1 Type Attributes */ +#define SKIP 0 +#define STOP 1 +#define DECODE 2 +#define EXT 4 +#define OPEN 8 +#define OPT 16 + + +/* ASN.1 Field Structure */ +typedef struct field_t { +#if H323_TRACE + char *name; +#endif + unsigned char type; + unsigned char sz; + unsigned char lb; + unsigned char ub; + unsigned short attr; + unsigned short offset; + struct field_t *fields; +} field_t; + +/* Bit Stream */ +typedef struct { + unsigned char *buf; + unsigned char *beg; + unsigned char *end; + unsigned char *cur; + unsigned bit; +} bitstr_t; + +/* Tool Functions */ +#define INC_BIT(bs) if((++bs->bit)>7){bs->cur++;bs->bit=0;} +#define INC_BITS(bs,b) if((bs->bit+=b)>7){bs->cur+=bs->bit>>3;bs->bit&=7;} +#define BYTE_ALIGN(bs) if(bs->bit){bs->cur++;bs->bit=0;} +#define CHECK_BOUND(bs,n) if(bs->cur+(n)>bs->end)return(H323_ERROR_BOUND) +static unsigned get_len(bitstr_t * bs); +static unsigned get_bit(bitstr_t * bs); +static unsigned get_bits(bitstr_t * bs, unsigned b); +static unsigned get_bitmap(bitstr_t * bs, unsigned b); +static unsigned get_uint(bitstr_t * bs, int b); + +/* Decoder Functions */ +static int decode_nul(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_bool(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_oid(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_int(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_enum(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_bitstr(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_numstr(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_octstr(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_bmpstr(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_seq(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_seqof(bitstr_t * bs, field_t * f, char *base, int level); +static int decode_choice(bitstr_t * bs, field_t * f, char *base, int level); + +/* Decoder Functions Vector */ +typedef int (*decoder_t) (bitstr_t *, field_t *, char *, int); +static decoder_t Decoders[] = { + decode_nul, + decode_bool, + decode_oid, + decode_int, + decode_enum, + decode_bitstr, + decode_numstr, + decode_octstr, + decode_bmpstr, + decode_seq, + decode_seqof, + decode_choice, +}; + +/**************************************************************************** + * H.323 Types + ****************************************************************************/ +#include "ip_conntrack_helper_h323_types.c" + +/**************************************************************************** + * Functions + ****************************************************************************/ +/* Assume bs is aligned && v < 16384 */ +unsigned get_len(bitstr_t * bs) +{ + unsigned v; + + v = *bs->cur++; + + if (v & 0x80) { + v &= 0x3f; + v <<= 8; + v += *bs->cur++; + } + + return v; +} + +/****************************************************************************/ +unsigned get_bit(bitstr_t * bs) +{ + unsigned b = (*bs->cur) & (0x80 >> bs->bit); + + INC_BIT(bs); + + return b; +} + +/****************************************************************************/ +/* Assume b <= 8 */ +unsigned get_bits(bitstr_t * bs, unsigned b) +{ + unsigned v, l; + + v = (*bs->cur) & (0xffU >> bs->bit); + l = b + bs->bit; + + if (l < 8) { + v >>= 8 - l; + bs->bit = l; + } else if (l == 8) { + bs->cur++; + bs->bit = 0; + } else { /* l > 8 */ + + v <<= 8; + v += *(++bs->cur); + v >>= 16 - l; + bs->bit = l - 8; + } + + return v; +} + +/****************************************************************************/ +/* Assume b <= 32 */ +unsigned get_bitmap(bitstr_t * bs, unsigned b) +{ + unsigned v, l, shift, bytes; + + if (!b) + return 0; + + l = bs->bit + b; + + if (l < 8) { + v = (unsigned) (*bs->cur) << (bs->bit + 24); + bs->bit = l; + } else if (l == 8) { + v = (unsigned) (*bs->cur++) << (bs->bit + 24); + bs->bit = 0; + } else { + for (bytes = l >> 3, shift = 24, v = 0; bytes; + bytes--, shift -= 8) + v |= (unsigned) (*bs->cur++) << shift; + + if (l < 32) { + v |= (unsigned) (*bs->cur) << shift; + v <<= bs->bit; + } else if (l > 32) { + v <<= bs->bit; + v |= (*bs->cur) >> (8 - bs->bit); + } + + bs->bit = l & 0x7; + } + + v &= 0xffffffff << (32 - b); + + return v; +} + +/**************************************************************************** + * Assume bs is aligned and sizeof(unsigned int) == 4 + ****************************************************************************/ +unsigned get_uint(bitstr_t * bs, int b) +{ + unsigned v = 0; + + switch (b) { + case 4: + v |= *bs->cur++; + v <<= 8; + case 3: + v |= *bs->cur++; + v <<= 8; + case 2: + v |= *bs->cur++; + v <<= 8; + case 1: + v |= *bs->cur++; + break; + } + return v; +} + +/****************************************************************************/ +int decode_nul(bitstr_t * bs, field_t * f, char *base, int level) +{ + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_bool(bitstr_t * bs, field_t * f, char *base, int level) +{ + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + INC_BIT(bs); + + CHECK_BOUND(bs, 0); + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_oid(bitstr_t * bs, field_t * f, char *base, int level) +{ + int len; + + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + BYTE_ALIGN(bs); + CHECK_BOUND(bs, 1); + len = *bs->cur++; + bs->cur += len; + + CHECK_BOUND(bs, 0); + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_int(bitstr_t * bs, field_t * f, char *base, int level) +{ + unsigned len; + + PRINT("%*.s%s", level * TAB_SIZE, " ", f->name); + + switch (f->sz) { + case BYTE: /* Range == 256 */ + BYTE_ALIGN(bs); + bs->cur++; + break; + case WORD: /* 257 <= Range <= 64K */ + BYTE_ALIGN(bs); + bs->cur += 2; + break; + case CONS: /* 64K < Range < 4G */ + len = get_bits(bs, 2) + 1; + BYTE_ALIGN(bs); + if (base && (f->attr & DECODE)) { /* timeToLive */ + unsigned v = get_uint(bs, len) + f->lb; + PRINT(" = %u", v); + *((unsigned *) (base + f->offset)) = v; + } + bs->cur += len; + break; + case UNCO: + BYTE_ALIGN(bs); + CHECK_BOUND(bs, 2); + len = get_len(bs); + bs->cur += len; + break; + default: /* 2 <= Range <= 255 */ + INC_BITS(bs, f->sz); + break; + } + + PRINT("\n"); + + CHECK_BOUND(bs, 0); + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_enum(bitstr_t * bs, field_t * f, char *base, int level) +{ + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + if ((f->attr & EXT) && get_bit(bs)) { + INC_BITS(bs, 7); + } else { + INC_BITS(bs, f->sz); + } + + CHECK_BOUND(bs, 0); + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_bitstr(bitstr_t * bs, field_t * f, char *base, int level) +{ + unsigned len; + + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + BYTE_ALIGN(bs); + switch (f->sz) { + case FIXD: /* fixed length > 16 */ + len = f->lb; + break; + case WORD: /* 2-byte length */ + CHECK_BOUND(bs, 2); + len = (*bs->cur++) << 8; + len += (*bs->cur++) + f->lb; + break; + case SEMI: + CHECK_BOUND(bs, 2); + len = get_len(bs); + break; + default: + len = 0; + break; + } + + bs->cur += len >> 3; + bs->bit = len & 7; + + CHECK_BOUND(bs, 0); + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_numstr(bitstr_t * bs, field_t * f, char *base, int level) +{ + unsigned len; + + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + /* 2 <= Range <= 255 */ + len = get_bits(bs, f->sz) + f->lb; + + BYTE_ALIGN(bs); + INC_BITS(bs, (len << 2)); + + CHECK_BOUND(bs, 0); + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_octstr(bitstr_t * bs, field_t * f, char *base, int level) +{ + unsigned len; + + PRINT("%*.s%s", level * TAB_SIZE, " ", f->name); + + switch (f->sz) { + case FIXD: /* Range == 1 */ + if (f->lb > 2) { + BYTE_ALIGN(bs); + if (base && (f->attr & DECODE)) { + /* The IP Address */ + IFTHEN(f->lb == 4, + PRINT(" = %d.%d.%d.%d:%d", + bs->cur[0], bs->cur[1], + bs->cur[2], bs->cur[3], + bs->cur[4] * 256 + bs->cur[5])); + *((unsigned *) (base + f->offset)) = + bs->cur - bs->buf; + } + } + len = f->lb; + break; + case BYTE: /* Range == 256 */ + BYTE_ALIGN(bs); + CHECK_BOUND(bs, 1); + len = (*bs->cur++) + f->lb; + break; + case SEMI: + BYTE_ALIGN(bs); + CHECK_BOUND(bs, 2); + len = get_len(bs) + f->lb; + break; + default: /* 2 <= Range <= 255 */ + len = get_bits(bs, f->sz) + f->lb; + BYTE_ALIGN(bs); + break; + } + + bs->cur += len; + + PRINT("\n"); + + CHECK_BOUND(bs, 0); + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_bmpstr(bitstr_t * bs, field_t * f, char *base, int level) +{ + unsigned len; + + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + switch (f->sz) { + case BYTE: /* Range == 256 */ + BYTE_ALIGN(bs); + CHECK_BOUND(bs, 1); + len = (*bs->cur++) + f->lb; + break; + default: /* 2 <= Range <= 255 */ + len = get_bits(bs, f->sz) + f->lb; + BYTE_ALIGN(bs); + break; + } + + bs->cur += len << 1; + + CHECK_BOUND(bs, 0); + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_seq(bitstr_t * bs, field_t * f, char *base, int level) +{ + unsigned ext, bmp, i, opt, len = 0, bmp2, bmp2_len; + int err; + field_t *son; + unsigned char *beg = NULL; + + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + /* Decode? */ + base = (base && (f->attr & DECODE)) ? base + f->offset : NULL; + + /* Extensible? */ + ext = (f->attr & EXT) ? get_bit(bs) : 0; + + /* Get fields bitmap */ + bmp = get_bitmap(bs, f->sz); + if (base) + *(unsigned *) base = bmp; + + /* Decode the root components */ + for (i = opt = 0, son = f->fields; i < f->lb; i++, son++) { + if (son->attr & STOP) { + PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", + son->name); + return H323_ERROR_STOP; + } + + if (son->attr & OPT) { /* Optional component */ + if (!((0x80000000U >> (opt++)) & bmp)) /* Not exist */ + continue; + } + + /* Decode */ + if (son->attr & OPEN) { /* Open field */ + CHECK_BOUND(bs, 2); + len = get_len(bs); + CHECK_BOUND(bs, len); + if (!base) { + PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, + " ", son->name); + bs->cur += len; + continue; + } + beg = bs->cur; + + /* Decode */ + if ((err = (Decoders[son->type]) (bs, son, base, + level + 1)) > + H323_ERROR_STOP) + return err; + + bs->cur = beg + len; + bs->bit = 0; + } else if ((err = (Decoders[son->type]) (bs, son, base, + level + 1))) + return err; + } + + /* No extension? */ + if (!ext) + return H323_ERROR_NONE; + + /* Get the extension bitmap */ + bmp2_len = get_bits(bs, 7) + 1; + CHECK_BOUND(bs, (bmp2_len + 7) >> 3); + bmp2 = get_bitmap(bs, bmp2_len); + bmp |= bmp2 >> f->sz; + if (base) + *(unsigned *) base = bmp; + BYTE_ALIGN(bs); + + /* Decode the extension components */ + for (opt = 0; opt < bmp2_len; opt++, i++, son++) { + if (son->attr & STOP) { + PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", + son->name); + return H323_ERROR_STOP; + } + + if (!((0x80000000 >> opt) & bmp2)) /* Not present */ + continue; + + /* Check Range */ + if (i >= f->ub) { /* Newer Version? */ + CHECK_BOUND(bs, 2); + len = get_len(bs); + CHECK_BOUND(bs, len); + bs->cur += len; + continue; + } + + CHECK_BOUND(bs, 2); + len = get_len(bs); + CHECK_BOUND(bs, len); + if (!base || !(son->attr & DECODE)) { + PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", + son->name); + bs->cur += len; + continue; + } + beg = bs->cur; + + if ((err = (Decoders[son->type]) (bs, son, base, + level + 1)) > + H323_ERROR_STOP) + return err; + + bs->cur = beg + len; + bs->bit = 0; + } + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int decode_seqof(bitstr_t * bs, field_t * f, char *base, int level) +{ + unsigned count, effective_count = 0, i, len = 0; + int err; + field_t *son; + unsigned char *beg = NULL; + + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + /* Decode? */ + base = (base && (f->attr & DECODE)) ? base + f->offset : NULL; + + /* Decode item count */ + switch (f->sz) { + case BYTE: + BYTE_ALIGN(bs); + CHECK_BOUND(bs, 1); + count = *bs->cur++; + break; + case WORD: + BYTE_ALIGN(bs); + CHECK_BOUND(bs, 2); + count = *bs->cur++; + count <<= 8; + count = *bs->cur++; + break; + case SEMI: + BYTE_ALIGN(bs); + CHECK_BOUND(bs, 2); + count = get_len(bs); + break; + default: + count = get_bits(bs, f->sz); + break; + } + count += f->lb; + + /* Write Count */ + if (base) { + effective_count = count > f->ub ? f->ub : count; + *(unsigned *) base = effective_count; + base += sizeof(unsigned); + } + + /* Decode nested field */ + son = f->fields; + if (base) + base -= son->offset; + for (i = 0; i < count; i++) { + if (son->attr & OPEN) { + BYTE_ALIGN(bs); + len = get_len(bs); + CHECK_BOUND(bs, len); + if (!base || !(son->attr & DECODE)) { + PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, + " ", son->name); + bs->cur += len; + continue; + } + beg = bs->cur; + + if ((err = (Decoders[son->type]) (bs, son, + i < + effective_count ? + base : NULL, + level + 1)) > + H323_ERROR_STOP) + return err; + + bs->cur = beg + len; + bs->bit = 0; + } else + if ((err = (Decoders[son->type]) (bs, son, + i < effective_count ? + base : NULL, + level + 1))) + return err; + + if (base) + base += son->offset; + } + + return H323_ERROR_NONE; +} + + +/****************************************************************************/ +int decode_choice(bitstr_t * bs, field_t * f, char *base, int level) +{ + unsigned type, ext, len = 0; + int err; + field_t *son; + unsigned char *beg = NULL; + + PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); + + /* Decode? */ + base = (base && (f->attr & DECODE)) ? base + f->offset : NULL; + + /* Decode the choice index number */ + if ((f->attr & EXT) && get_bit(bs)) { + ext = 1; + type = get_bits(bs, 7) + f->lb; + } else { + ext = 0; + type = get_bits(bs, f->sz); + } + + /* Check Range */ + if (type >= f->ub) { /* Newer version? */ + BYTE_ALIGN(bs); + len = get_len(bs); + CHECK_BOUND(bs, len); + bs->cur += len; + return H323_ERROR_NONE; + } + + /* Write Type */ + if (base) + *(unsigned *) base = type; + + /* Transfer to son level */ + son = &f->fields[type]; + if (son->attr & STOP) { + PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", son->name); + return H323_ERROR_STOP; + } + + if (ext || (son->attr & OPEN)) { + BYTE_ALIGN(bs); + len = get_len(bs); + CHECK_BOUND(bs, len); + if (!base || !(son->attr & DECODE)) { + PRINT("%*.s%s\n", (level + 1) * TAB_SIZE, " ", + son->name); + bs->cur += len; + return H323_ERROR_NONE; + } + beg = bs->cur; + + if ((err = (Decoders[son->type]) (bs, son, base, level + 1)) > + H323_ERROR_STOP) + return err; + + bs->cur = beg + len; + bs->bit = 0; + } else if ((err = (Decoders[son->type]) (bs, son, base, level + 1))) + return err; + + return H323_ERROR_NONE; +} + +/****************************************************************************/ +int DecodeRasMessage(unsigned char *buf, size_t sz, RasMessage * ras) +{ + static field_t ras_message = { + FNAME("RasMessage") CHOICE, 5, 24, 32, DECODE | EXT, + 0, _RasMessage + }; + bitstr_t bs; + + bs.buf = bs.beg = bs.cur = buf; + bs.end = buf + sz; + bs.bit = 0; + + return decode_choice(&bs, &ras_message, (char *) ras, 0); +} + +/****************************************************************************/ +static int DecodeH323_UserInformation(unsigned char *buf, unsigned char *beg, + size_t sz, H323_UserInformation * uuie) +{ + static field_t h323_userinformation = { + FNAME("H323-UserInformation") SEQ, 1, 2, 2, DECODE | EXT, + 0, _H323_UserInformation + }; + bitstr_t bs; + + bs.buf = buf; + bs.beg = bs.cur = beg; + bs.end = beg + sz; + bs.bit = 0; + + return decode_seq(&bs, &h323_userinformation, (char *) uuie, 0); +} + +/****************************************************************************/ +int DecodeMultimediaSystemControlMessage(unsigned char *buf, size_t sz, + MultimediaSystemControlMessage * + mscm) +{ + static field_t multimediasystemcontrolmessage = { + FNAME("MultimediaSystemControlMessage") CHOICE, 2, 4, 4, + DECODE | EXT, 0, _MultimediaSystemControlMessage + }; + bitstr_t bs; + + bs.buf = bs.beg = bs.cur = buf; + bs.end = buf + sz; + bs.bit = 0; + + return decode_choice(&bs, &multimediasystemcontrolmessage, + (char *) mscm, 0); +} + +/****************************************************************************/ +int DecodeQ931(unsigned char *buf, size_t sz, Q931 * q931) +{ + unsigned char *p = buf; + int len; + + if (!p || sz < 1) + return H323_ERROR_BOUND; + + /* Protocol Discriminator */ + if (*p != 0x08) { + PRINT("Unknown Protocol Discriminator\n"); + return H323_ERROR_RANGE; + } + p++; + sz--; + + /* CallReferenceValue */ + if (sz < 1) + return H323_ERROR_BOUND; + len = *p++; + sz--; + if (sz < len) + return H323_ERROR_BOUND; + p += len; + sz -= len; + + /* Message Type */ + if (sz < 1) + return H323_ERROR_BOUND; + q931->MessageType = *p++; + PRINT("MessageType = %02X\n", q931->MessageType); + if (*p & 0x80) { + p++; + sz--; + } + + /* Decode Information Elements */ + while (sz > 0) { + if (*p == 0x7e) { /* UserUserIE */ + if (sz < 3) + break; + p++; + len = *p++ << 8; + len |= *p++; + sz -= 3; + if (sz < len) + break; + p++; + len--; + return DecodeH323_UserInformation(buf, p, len, + &q931->UUIE); + } + p++; + sz--; + if (sz < 1) + break; + len = *p++; + if (sz < len) + break; + p += len; + sz -= len; + } + + PRINT("Q.931 UUIE not found\n"); + + return H323_ERROR_BOUND; +} diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.h b/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.h new file mode 100644 index 000000000000..0bd828081c0c --- /dev/null +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.h @@ -0,0 +1,98 @@ +/**************************************************************************** + * ip_conntrack_helper_h323_asn1.h - BER and PER decoding library for H.323 + * conntrack/NAT module. + * + * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@hotmail.com> + * + * This source code is licensed under General Public License version 2. + * + * + * This library is based on H.225 version 4, H.235 version 2 and H.245 + * version 7. It is extremely optimized to decode only the absolutely + * necessary objects in a signal for Linux kernel NAT module use, so don't + * expect it to be a full ASN.1 library. + * + * Features: + * + * 1. Small. The total size of code plus data is less than 20 KB (IA32). + * 2. Fast. Decoding Netmeeting's Setup signal 1 million times on a PIII 866 + * takes only 3.9 seconds. + * 3. No memory allocation. It uses a static object. No need to initialize or + * cleanup. + * 4. Thread safe. + * 5. Support embedded architectures that has no misaligned memory access + * support. + * + * Limitations: + * + * 1. At most 30 faststart entries. Actually this is limited by ethernet's MTU. + * If a Setup signal contains more than 30 faststart, the packet size will + * very likely exceed the MTU size, then the TPKT will be fragmented. I + * don't know how to handle this in a Netfilter module. Anybody can help? + * Although I think 30 is enough for most of the cases. + * 2. IPv4 addresses only. + * + ****************************************************************************/ + +#ifndef _IP_CONNTRACK_HELPER_H323_ASN1_H_ +#define _IP_CONNTRACK_HELPER_H323_ASN1_H_ + +/***************************************************************************** + * H.323 Types + ****************************************************************************/ +#include "ip_conntrack_helper_h323_types.h" + +typedef struct { + enum { + Q931_NationalEscape = 0x00, + Q931_Alerting = 0x01, + Q931_CallProceeding = 0x02, + Q931_Connect = 0x07, + Q931_ConnectAck = 0x0F, + Q931_Progress = 0x03, + Q931_Setup = 0x05, + Q931_SetupAck = 0x0D, + Q931_Resume = 0x26, + Q931_ResumeAck = 0x2E, + Q931_ResumeReject = 0x22, + Q931_Suspend = 0x25, + Q931_SuspendAck = 0x2D, + Q931_SuspendReject = 0x21, + Q931_UserInformation = 0x20, + Q931_Disconnect = 0x45, + Q931_Release = 0x4D, + Q931_ReleaseComplete = 0x5A, + Q931_Restart = 0x46, + Q931_RestartAck = 0x4E, + Q931_Segment = 0x60, + Q931_CongestionCtrl = 0x79, + Q931_Information = 0x7B, + Q931_Notify = 0x6E, + Q931_Status = 0x7D, + Q931_StatusEnquiry = 0x75, + Q931_Facility = 0x62 + } MessageType; + H323_UserInformation UUIE; +} Q931; + +/***************************************************************************** + * Decode Functions Return Codes + ****************************************************************************/ + +#define H323_ERROR_NONE 0 /* Decoded successfully */ +#define H323_ERROR_STOP 1 /* Decoding stopped, not really an error */ +#define H323_ERROR_BOUND -1 +#define H323_ERROR_RANGE -2 + + +/***************************************************************************** + * Decode Functions + ****************************************************************************/ + +int DecodeRasMessage(unsigned char *buf, size_t sz, RasMessage * ras); +int DecodeQ931(unsigned char *buf, size_t sz, Q931 * q931); +int DecodeMultimediaSystemControlMessage(unsigned char *buf, size_t sz, + MultimediaSystemControlMessage * + mscm); + +#endif diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323_types.c b/net/ipv4/netfilter/ip_conntrack_helper_h323_types.c new file mode 100644 index 000000000000..022c47b9f6c9 --- /dev/null +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323_types.c @@ -0,0 +1,1926 @@ +/* Generated by Jing Min Zhao's ASN.1 parser, Mar 15 2006 + * + * Copyright (c) 2006 Jing Min Zhao <zhaojingmin@users.sourceforge.net> + * + * This source code is licensed under General Public License version 2. + */ + +static field_t _TransportAddress_ipAddress[] = { /* SEQUENCE */ + {FNAME("ip") OCTSTR, FIXD, 4, 0, DECODE, + offsetof(TransportAddress_ipAddress, ip), NULL}, + {FNAME("port") INT, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _TransportAddress_ipSourceRoute_route[] = { /* SEQUENCE OF */ + {FNAME("item") OCTSTR, FIXD, 4, 0, SKIP, 0, NULL}, +}; + +static field_t _TransportAddress_ipSourceRoute_routing[] = { /* CHOICE */ + {FNAME("strict") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("loose") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _TransportAddress_ipSourceRoute[] = { /* SEQUENCE */ + {FNAME("ip") OCTSTR, FIXD, 4, 0, SKIP, 0, NULL}, + {FNAME("port") INT, WORD, 0, 0, SKIP, 0, NULL}, + {FNAME("route") SEQOF, SEMI, 0, 0, SKIP, 0, + _TransportAddress_ipSourceRoute_route}, + {FNAME("routing") CHOICE, 1, 2, 2, SKIP | EXT, 0, + _TransportAddress_ipSourceRoute_routing}, +}; + +static field_t _TransportAddress_ipxAddress[] = { /* SEQUENCE */ + {FNAME("node") OCTSTR, FIXD, 6, 0, SKIP, 0, NULL}, + {FNAME("netnum") OCTSTR, FIXD, 4, 0, SKIP, 0, NULL}, + {FNAME("port") OCTSTR, FIXD, 2, 0, SKIP, 0, NULL}, +}; + +static field_t _TransportAddress_ip6Address[] = { /* SEQUENCE */ + {FNAME("ip") OCTSTR, FIXD, 16, 0, SKIP, 0, NULL}, + {FNAME("port") INT, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H221NonStandard[] = { /* SEQUENCE */ + {FNAME("t35CountryCode") INT, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("t35Extension") INT, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("manufacturerCode") INT, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _NonStandardIdentifier[] = { /* CHOICE */ + {FNAME("object") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("h221NonStandard") SEQ, 0, 3, 3, SKIP | EXT, 0, + _H221NonStandard}, +}; + +static field_t _NonStandardParameter[] = { /* SEQUENCE */ + {FNAME("nonStandardIdentifier") CHOICE, 1, 2, 2, SKIP | EXT, 0, + _NonStandardIdentifier}, + {FNAME("data") OCTSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _TransportAddress[] = { /* CHOICE */ + {FNAME("ipAddress") SEQ, 0, 2, 2, DECODE, + offsetof(TransportAddress, ipAddress), _TransportAddress_ipAddress}, + {FNAME("ipSourceRoute") SEQ, 0, 4, 4, SKIP | EXT, 0, + _TransportAddress_ipSourceRoute}, + {FNAME("ipxAddress") SEQ, 0, 3, 3, SKIP, 0, + _TransportAddress_ipxAddress}, + {FNAME("ip6Address") SEQ, 0, 2, 2, SKIP | EXT, 0, + _TransportAddress_ip6Address}, + {FNAME("netBios") OCTSTR, FIXD, 16, 0, SKIP, 0, NULL}, + {FNAME("nsap") OCTSTR, 5, 1, 0, SKIP, 0, NULL}, + {FNAME("nonStandardAddress") SEQ, 0, 2, 2, SKIP, 0, + _NonStandardParameter}, +}; + +static field_t _AliasAddress[] = { /* CHOICE */ + {FNAME("dialedDigits") NUMDGT, 7, 1, 0, SKIP, 0, NULL}, + {FNAME("h323-ID") BMPSTR, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("url-ID") IA5STR, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("transportID") CHOICE, 3, 7, 7, SKIP | EXT, 0, NULL}, + {FNAME("email-ID") IA5STR, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("partyNumber") CHOICE, 3, 5, 5, SKIP | EXT, 0, NULL}, + {FNAME("mobileUIM") CHOICE, 1, 2, 2, SKIP | EXT, 0, NULL}, +}; + +static field_t _Setup_UUIE_sourceAddress[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _VendorIdentifier[] = { /* SEQUENCE */ + {FNAME("vendor") SEQ, 0, 3, 3, SKIP | EXT, 0, _H221NonStandard}, + {FNAME("productId") OCTSTR, BYTE, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("versionId") OCTSTR, BYTE, 1, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _GatekeeperInfo[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, +}; + +static field_t _H310Caps[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("dataRatesSupported") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H320Caps[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("dataRatesSupported") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H321Caps[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("dataRatesSupported") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H322Caps[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("dataRatesSupported") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H323Caps[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("dataRatesSupported") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H324Caps[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("dataRatesSupported") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _VoiceCaps[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("dataRatesSupported") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _T120OnlyCaps[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("dataRatesSupported") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _SupportedProtocols[] = { /* CHOICE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP, 0, + _NonStandardParameter}, + {FNAME("h310") SEQ, 1, 1, 3, SKIP | EXT, 0, _H310Caps}, + {FNAME("h320") SEQ, 1, 1, 3, SKIP | EXT, 0, _H320Caps}, + {FNAME("h321") SEQ, 1, 1, 3, SKIP | EXT, 0, _H321Caps}, + {FNAME("h322") SEQ, 1, 1, 3, SKIP | EXT, 0, _H322Caps}, + {FNAME("h323") SEQ, 1, 1, 3, SKIP | EXT, 0, _H323Caps}, + {FNAME("h324") SEQ, 1, 1, 3, SKIP | EXT, 0, _H324Caps}, + {FNAME("voice") SEQ, 1, 1, 3, SKIP | EXT, 0, _VoiceCaps}, + {FNAME("t120-only") SEQ, 1, 1, 3, SKIP | EXT, 0, _T120OnlyCaps}, + {FNAME("nonStandardProtocol") SEQ, 2, 3, 3, SKIP | EXT, 0, NULL}, + {FNAME("t38FaxAnnexbOnly") SEQ, 2, 5, 5, SKIP | EXT, 0, NULL}, +}; + +static field_t _GatewayInfo_protocol[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 4, 9, 11, SKIP | EXT, 0, _SupportedProtocols}, +}; + +static field_t _GatewayInfo[] = { /* SEQUENCE */ + {FNAME("protocol") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _GatewayInfo_protocol}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, +}; + +static field_t _McuInfo[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("protocol") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _TerminalInfo[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, +}; + +static field_t _EndpointType[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("vendor") SEQ, 2, 3, 3, SKIP | EXT | OPT, 0, + _VendorIdentifier}, + {FNAME("gatekeeper") SEQ, 1, 1, 1, SKIP | EXT | OPT, 0, + _GatekeeperInfo}, + {FNAME("gateway") SEQ, 2, 2, 2, SKIP | EXT | OPT, 0, _GatewayInfo}, + {FNAME("mcu") SEQ, 1, 1, 2, SKIP | EXT | OPT, 0, _McuInfo}, + {FNAME("terminal") SEQ, 1, 1, 1, SKIP | EXT | OPT, 0, _TerminalInfo}, + {FNAME("mc") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("undefinedNode") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("set") BITSTR, FIXD, 32, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedTunnelledProtocols") SEQOF, SEMI, 0, 0, SKIP | OPT, + 0, NULL}, +}; + +static field_t _Setup_UUIE_destinationAddress[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _Setup_UUIE_destExtraCallInfo[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _Setup_UUIE_destExtraCRV[] = { /* SEQUENCE OF */ + {FNAME("item") INT, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _Setup_UUIE_conferenceGoal[] = { /* CHOICE */ + {FNAME("create") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("join") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("invite") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("capability-negotiation") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("callIndependentSupplementaryService") NUL, FIXD, 0, 0, SKIP, + 0, NULL}, +}; + +static field_t _Q954Details[] = { /* SEQUENCE */ + {FNAME("conferenceCalling") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("threePartyService") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _QseriesOptions[] = { /* SEQUENCE */ + {FNAME("q932Full") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("q951Full") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("q952Full") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("q953Full") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("q955Full") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("q956Full") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("q957Full") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("q954Info") SEQ, 0, 2, 2, SKIP | EXT, 0, _Q954Details}, +}; + +static field_t _CallType[] = { /* CHOICE */ + {FNAME("pointToPoint") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("oneToN") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("nToOne") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("nToN") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H245_NonStandardIdentifier_h221NonStandard[] = { /* SEQUENCE */ + {FNAME("t35CountryCode") INT, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("t35Extension") INT, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("manufacturerCode") INT, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H245_NonStandardIdentifier[] = { /* CHOICE */ + {FNAME("object") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("h221NonStandard") SEQ, 0, 3, 3, SKIP, 0, + _H245_NonStandardIdentifier_h221NonStandard}, +}; + +static field_t _H245_NonStandardParameter[] = { /* SEQUENCE */ + {FNAME("nonStandardIdentifier") CHOICE, 1, 2, 2, SKIP, 0, + _H245_NonStandardIdentifier}, + {FNAME("data") OCTSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H261VideoCapability[] = { /* SEQUENCE */ + {FNAME("qcifMPI") INT, 2, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("cifMPI") INT, 2, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("temporalSpatialTradeOffCapability") BOOL, FIXD, 0, 0, SKIP, 0, + NULL}, + {FNAME("maxBitRate") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("stillImageTransmission") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("videoBadMBsCap") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H262VideoCapability[] = { /* SEQUENCE */ + {FNAME("profileAndLevel-SPatML") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("profileAndLevel-MPatLL") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("profileAndLevel-MPatML") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("profileAndLevel-MPatH-14") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("profileAndLevel-MPatHL") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("profileAndLevel-SNRatLL") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("profileAndLevel-SNRatML") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("profileAndLevel-SpatialatH-14") BOOL, FIXD, 0, 0, SKIP, 0, + NULL}, + {FNAME("profileAndLevel-HPatML") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("profileAndLevel-HPatH-14") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("profileAndLevel-HPatHL") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("videoBitRate") INT, CONS, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("vbvBufferSize") INT, CONS, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("samplesPerLine") INT, WORD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("linesPerFrame") INT, WORD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("framesPerSecond") INT, 4, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("luminanceSampleRate") INT, CONS, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("videoBadMBsCap") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H263VideoCapability[] = { /* SEQUENCE */ + {FNAME("sqcifMPI") INT, 5, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("qcifMPI") INT, 5, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("cifMPI") INT, 5, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("cif4MPI") INT, 5, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("cif16MPI") INT, 5, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("maxBitRate") INT, CONS, 1, 0, SKIP, 0, NULL}, + {FNAME("unrestrictedVector") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("arithmeticCoding") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("advancedPrediction") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("pbFrames") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("temporalSpatialTradeOffCapability") BOOL, FIXD, 0, 0, SKIP, 0, + NULL}, + {FNAME("hrd-B") INT, CONS, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("bppMaxKb") INT, WORD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("slowSqcifMPI") INT, WORD, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("slowQcifMPI") INT, WORD, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("slowCifMPI") INT, WORD, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("slowCif4MPI") INT, WORD, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("slowCif16MPI") INT, WORD, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("errorCompensation") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("enhancementLayerInfo") SEQ, 3, 4, 4, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("h263Options") SEQ, 5, 29, 31, SKIP | EXT | OPT, 0, NULL}, +}; + +static field_t _IS11172VideoCapability[] = { /* SEQUENCE */ + {FNAME("constrainedBitstream") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("videoBitRate") INT, CONS, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("vbvBufferSize") INT, CONS, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("samplesPerLine") INT, WORD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("linesPerFrame") INT, WORD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("pictureRate") INT, 4, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("luminanceSampleRate") INT, CONS, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("videoBadMBsCap") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _VideoCapability[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP, 0, + _H245_NonStandardParameter}, + {FNAME("h261VideoCapability") SEQ, 2, 5, 6, SKIP | EXT, 0, + _H261VideoCapability}, + {FNAME("h262VideoCapability") SEQ, 6, 17, 18, SKIP | EXT, 0, + _H262VideoCapability}, + {FNAME("h263VideoCapability") SEQ, 7, 13, 21, SKIP | EXT, 0, + _H263VideoCapability}, + {FNAME("is11172VideoCapability") SEQ, 6, 7, 8, SKIP | EXT, 0, + _IS11172VideoCapability}, + {FNAME("genericVideoCapability") SEQ, 5, 6, 6, SKIP | EXT, 0, NULL}, +}; + +static field_t _AudioCapability_g7231[] = { /* SEQUENCE */ + {FNAME("maxAl-sduAudioFrames") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("silenceSuppression") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _IS11172AudioCapability[] = { /* SEQUENCE */ + {FNAME("audioLayer1") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioLayer2") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioLayer3") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioSampling32k") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioSampling44k1") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioSampling48k") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("singleChannel") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("twoChannels") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("bitRate") INT, WORD, 1, 0, SKIP, 0, NULL}, +}; + +static field_t _IS13818AudioCapability[] = { /* SEQUENCE */ + {FNAME("audioLayer1") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioLayer2") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioLayer3") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioSampling16k") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioSampling22k05") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioSampling24k") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioSampling32k") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioSampling44k1") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("audioSampling48k") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("singleChannel") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("twoChannels") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("threeChannels2-1") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("threeChannels3-0") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("fourChannels2-0-2-0") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("fourChannels2-2") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("fourChannels3-1") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("fiveChannels3-0-2-0") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("fiveChannels3-2") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("lowFrequencyEnhancement") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("multilingual") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("bitRate") INT, WORD, 1, 0, SKIP, 0, NULL}, +}; + +static field_t _AudioCapability[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP, 0, + _H245_NonStandardParameter}, + {FNAME("g711Alaw64k") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g711Alaw56k") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g711Ulaw64k") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g711Ulaw56k") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g722-64k") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g722-56k") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g722-48k") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g7231") SEQ, 0, 2, 2, SKIP, 0, _AudioCapability_g7231}, + {FNAME("g728") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g729") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g729AnnexA") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("is11172AudioCapability") SEQ, 0, 9, 9, SKIP | EXT, 0, + _IS11172AudioCapability}, + {FNAME("is13818AudioCapability") SEQ, 0, 21, 21, SKIP | EXT, 0, + _IS13818AudioCapability}, + {FNAME("g729wAnnexB") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g729AnnexAwAnnexB") INT, BYTE, 1, 0, SKIP, 0, NULL}, + {FNAME("g7231AnnexCCapability") SEQ, 1, 3, 3, SKIP | EXT, 0, NULL}, + {FNAME("gsmFullRate") SEQ, 0, 3, 3, SKIP | EXT, 0, NULL}, + {FNAME("gsmHalfRate") SEQ, 0, 3, 3, SKIP | EXT, 0, NULL}, + {FNAME("gsmEnhancedFullRate") SEQ, 0, 3, 3, SKIP | EXT, 0, NULL}, + {FNAME("genericAudioCapability") SEQ, 5, 6, 6, SKIP | EXT, 0, NULL}, + {FNAME("g729Extensions") SEQ, 1, 8, 8, SKIP | EXT, 0, NULL}, +}; + +static field_t _DataProtocolCapability[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP, 0, + _H245_NonStandardParameter}, + {FNAME("v14buffered") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("v42lapm") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("hdlcFrameTunnelling") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("h310SeparateVCStack") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("h310SingleVCStack") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("transparent") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("segmentationAndReassembly") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("hdlcFrameTunnelingwSAR") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("v120") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("separateLANStack") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("v76wCompression") CHOICE, 2, 3, 3, SKIP | EXT, 0, NULL}, + {FNAME("tcp") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("udp") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _T84Profile_t84Restricted[] = { /* SEQUENCE */ + {FNAME("qcif") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("cif") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("ccir601Seq") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("ccir601Prog") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("hdtvSeq") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("hdtvProg") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("g3FacsMH200x100") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("g3FacsMH200x200") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("g4FacsMMR200x100") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("g4FacsMMR200x200") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("jbig200x200Seq") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("jbig200x200Prog") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("jbig300x300Seq") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("jbig300x300Prog") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("digPhotoLow") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("digPhotoMedSeq") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("digPhotoMedProg") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("digPhotoHighSeq") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("digPhotoHighProg") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _T84Profile[] = { /* CHOICE */ + {FNAME("t84Unrestricted") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("t84Restricted") SEQ, 0, 19, 19, SKIP | EXT, 0, + _T84Profile_t84Restricted}, +}; + +static field_t _DataApplicationCapability_application_t84[] = { /* SEQUENCE */ + {FNAME("t84Protocol") CHOICE, 3, 7, 14, SKIP | EXT, 0, + _DataProtocolCapability}, + {FNAME("t84Profile") CHOICE, 1, 2, 2, SKIP, 0, _T84Profile}, +}; + +static field_t _DataApplicationCapability_application_nlpid[] = { /* SEQUENCE */ + {FNAME("nlpidProtocol") CHOICE, 3, 7, 14, SKIP | EXT, 0, + _DataProtocolCapability}, + {FNAME("nlpidData") OCTSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _DataApplicationCapability_application[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP, 0, + _H245_NonStandardParameter}, + {FNAME("t120") CHOICE, 3, 7, 14, DECODE | EXT, + offsetof(DataApplicationCapability_application, t120), + _DataProtocolCapability}, + {FNAME("dsm-cc") CHOICE, 3, 7, 14, SKIP | EXT, 0, + _DataProtocolCapability}, + {FNAME("userData") CHOICE, 3, 7, 14, SKIP | EXT, 0, + _DataProtocolCapability}, + {FNAME("t84") SEQ, 0, 2, 2, SKIP, 0, + _DataApplicationCapability_application_t84}, + {FNAME("t434") CHOICE, 3, 7, 14, SKIP | EXT, 0, + _DataProtocolCapability}, + {FNAME("h224") CHOICE, 3, 7, 14, SKIP | EXT, 0, + _DataProtocolCapability}, + {FNAME("nlpid") SEQ, 0, 2, 2, SKIP, 0, + _DataApplicationCapability_application_nlpid}, + {FNAME("dsvdControl") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("h222DataPartitioning") CHOICE, 3, 7, 14, SKIP | EXT, 0, + _DataProtocolCapability}, + {FNAME("t30fax") CHOICE, 3, 7, 14, SKIP | EXT, 0, NULL}, + {FNAME("t140") CHOICE, 3, 7, 14, SKIP | EXT, 0, NULL}, + {FNAME("t38fax") SEQ, 0, 2, 2, SKIP, 0, NULL}, + {FNAME("genericDataCapability") SEQ, 5, 6, 6, SKIP | EXT, 0, NULL}, +}; + +static field_t _DataApplicationCapability[] = { /* SEQUENCE */ + {FNAME("application") CHOICE, 4, 10, 14, DECODE | EXT, + offsetof(DataApplicationCapability, application), + _DataApplicationCapability_application}, + {FNAME("maxBitRate") INT, CONS, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _EncryptionMode[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP, 0, + _H245_NonStandardParameter}, + {FNAME("h233Encryption") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _DataType[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP, 0, + _H245_NonStandardParameter}, + {FNAME("nullData") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("videoData") CHOICE, 3, 5, 6, SKIP | EXT, 0, _VideoCapability}, + {FNAME("audioData") CHOICE, 4, 14, 22, SKIP | EXT, 0, + _AudioCapability}, + {FNAME("data") SEQ, 0, 2, 2, DECODE | EXT, offsetof(DataType, data), + _DataApplicationCapability}, + {FNAME("encryptionData") CHOICE, 1, 2, 2, SKIP | EXT, 0, + _EncryptionMode}, + {FNAME("h235Control") SEQ, 0, 2, 2, SKIP, 0, NULL}, + {FNAME("h235Media") SEQ, 0, 2, 2, SKIP | EXT, 0, NULL}, + {FNAME("multiplexedStream") SEQ, 0, 2, 2, SKIP | EXT, 0, NULL}, +}; + +static field_t _H222LogicalChannelParameters[] = { /* SEQUENCE */ + {FNAME("resourceID") INT, WORD, 0, 0, SKIP, 0, NULL}, + {FNAME("subChannelID") INT, WORD, 0, 0, SKIP, 0, NULL}, + {FNAME("pcr-pid") INT, WORD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("programDescriptors") OCTSTR, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("streamDescriptors") OCTSTR, SEMI, 0, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _H223LogicalChannelParameters_adaptationLayerType_al3[] = { /* SEQUENCE */ + {FNAME("controlFieldOctets") INT, 2, 0, 0, SKIP, 0, NULL}, + {FNAME("sendBufferSize") INT, CONS, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H223LogicalChannelParameters_adaptationLayerType[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP, 0, + _H245_NonStandardParameter}, + {FNAME("al1Framed") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("al1NotFramed") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("al2WithoutSequenceNumbers") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("al2WithSequenceNumbers") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("al3") SEQ, 0, 2, 2, SKIP, 0, + _H223LogicalChannelParameters_adaptationLayerType_al3}, + {FNAME("al1M") SEQ, 0, 7, 8, SKIP | EXT, 0, NULL}, + {FNAME("al2M") SEQ, 0, 2, 2, SKIP | EXT, 0, NULL}, + {FNAME("al3M") SEQ, 0, 5, 6, SKIP | EXT, 0, NULL}, +}; + +static field_t _H223LogicalChannelParameters[] = { /* SEQUENCE */ + {FNAME("adaptationLayerType") CHOICE, 3, 6, 9, SKIP | EXT, 0, + _H223LogicalChannelParameters_adaptationLayerType}, + {FNAME("segmentableFlag") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CRCLength[] = { /* CHOICE */ + {FNAME("crc8bit") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("crc16bit") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("crc32bit") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _V76HDLCParameters[] = { /* SEQUENCE */ + {FNAME("crcLength") CHOICE, 2, 3, 3, SKIP | EXT, 0, _CRCLength}, + {FNAME("n401") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("loopbackTestProcedure") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _V76LogicalChannelParameters_suspendResume[] = { /* CHOICE */ + {FNAME("noSuspendResume") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("suspendResumewAddress") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("suspendResumewoAddress") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _V76LogicalChannelParameters_mode_eRM_recovery[] = { /* CHOICE */ + {FNAME("rej") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("sREJ") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("mSREJ") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _V76LogicalChannelParameters_mode_eRM[] = { /* SEQUENCE */ + {FNAME("windowSize") INT, 7, 1, 0, SKIP, 0, NULL}, + {FNAME("recovery") CHOICE, 2, 3, 3, SKIP | EXT, 0, + _V76LogicalChannelParameters_mode_eRM_recovery}, +}; + +static field_t _V76LogicalChannelParameters_mode[] = { /* CHOICE */ + {FNAME("eRM") SEQ, 0, 2, 2, SKIP | EXT, 0, + _V76LogicalChannelParameters_mode_eRM}, + {FNAME("uNERM") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _V75Parameters[] = { /* SEQUENCE */ + {FNAME("audioHeaderPresent") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _V76LogicalChannelParameters[] = { /* SEQUENCE */ + {FNAME("hdlcParameters") SEQ, 0, 3, 3, SKIP | EXT, 0, + _V76HDLCParameters}, + {FNAME("suspendResume") CHOICE, 2, 3, 3, SKIP | EXT, 0, + _V76LogicalChannelParameters_suspendResume}, + {FNAME("uIH") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("mode") CHOICE, 1, 2, 2, SKIP | EXT, 0, + _V76LogicalChannelParameters_mode}, + {FNAME("v75Parameters") SEQ, 0, 1, 1, SKIP | EXT, 0, _V75Parameters}, +}; + +static field_t _H2250LogicalChannelParameters_nonStandard[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 0, 2, 2, SKIP, 0, _H245_NonStandardParameter}, +}; + +static field_t _UnicastAddress_iPAddress[] = { /* SEQUENCE */ + {FNAME("network") OCTSTR, FIXD, 4, 0, DECODE, + offsetof(UnicastAddress_iPAddress, network), NULL}, + {FNAME("tsapIdentifier") INT, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _UnicastAddress_iPXAddress[] = { /* SEQUENCE */ + {FNAME("node") OCTSTR, FIXD, 6, 0, SKIP, 0, NULL}, + {FNAME("netnum") OCTSTR, FIXD, 4, 0, SKIP, 0, NULL}, + {FNAME("tsapIdentifier") OCTSTR, FIXD, 2, 0, SKIP, 0, NULL}, +}; + +static field_t _UnicastAddress_iP6Address[] = { /* SEQUENCE */ + {FNAME("network") OCTSTR, FIXD, 16, 0, SKIP, 0, NULL}, + {FNAME("tsapIdentifier") INT, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _UnicastAddress_iPSourceRouteAddress_routing[] = { /* CHOICE */ + {FNAME("strict") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("loose") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _UnicastAddress_iPSourceRouteAddress_route[] = { /* SEQUENCE OF */ + {FNAME("item") OCTSTR, FIXD, 4, 0, SKIP, 0, NULL}, +}; + +static field_t _UnicastAddress_iPSourceRouteAddress[] = { /* SEQUENCE */ + {FNAME("routing") CHOICE, 1, 2, 2, SKIP, 0, + _UnicastAddress_iPSourceRouteAddress_routing}, + {FNAME("network") OCTSTR, FIXD, 4, 0, SKIP, 0, NULL}, + {FNAME("tsapIdentifier") INT, WORD, 0, 0, SKIP, 0, NULL}, + {FNAME("route") SEQOF, SEMI, 0, 0, SKIP, 0, + _UnicastAddress_iPSourceRouteAddress_route}, +}; + +static field_t _UnicastAddress[] = { /* CHOICE */ + {FNAME("iPAddress") SEQ, 0, 2, 2, DECODE | EXT, + offsetof(UnicastAddress, iPAddress), _UnicastAddress_iPAddress}, + {FNAME("iPXAddress") SEQ, 0, 3, 3, SKIP | EXT, 0, + _UnicastAddress_iPXAddress}, + {FNAME("iP6Address") SEQ, 0, 2, 2, SKIP | EXT, 0, + _UnicastAddress_iP6Address}, + {FNAME("netBios") OCTSTR, FIXD, 16, 0, SKIP, 0, NULL}, + {FNAME("iPSourceRouteAddress") SEQ, 0, 4, 4, SKIP | EXT, 0, + _UnicastAddress_iPSourceRouteAddress}, + {FNAME("nsap") OCTSTR, 5, 1, 0, SKIP, 0, NULL}, + {FNAME("nonStandardAddress") SEQ, 0, 2, 2, SKIP, 0, NULL}, +}; + +static field_t _MulticastAddress_iPAddress[] = { /* SEQUENCE */ + {FNAME("network") OCTSTR, FIXD, 4, 0, SKIP, 0, NULL}, + {FNAME("tsapIdentifier") INT, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _MulticastAddress_iP6Address[] = { /* SEQUENCE */ + {FNAME("network") OCTSTR, FIXD, 16, 0, SKIP, 0, NULL}, + {FNAME("tsapIdentifier") INT, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _MulticastAddress[] = { /* CHOICE */ + {FNAME("iPAddress") SEQ, 0, 2, 2, SKIP | EXT, 0, + _MulticastAddress_iPAddress}, + {FNAME("iP6Address") SEQ, 0, 2, 2, SKIP | EXT, 0, + _MulticastAddress_iP6Address}, + {FNAME("nsap") OCTSTR, 5, 1, 0, SKIP, 0, NULL}, + {FNAME("nonStandardAddress") SEQ, 0, 2, 2, SKIP, 0, NULL}, +}; + +static field_t _H245_TransportAddress[] = { /* CHOICE */ + {FNAME("unicastAddress") CHOICE, 3, 5, 7, DECODE | EXT, + offsetof(H245_TransportAddress, unicastAddress), _UnicastAddress}, + {FNAME("multicastAddress") CHOICE, 1, 2, 4, SKIP | EXT, 0, + _MulticastAddress}, +}; + +static field_t _H2250LogicalChannelParameters[] = { /* SEQUENCE */ + {FNAME("nonStandard") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _H2250LogicalChannelParameters_nonStandard}, + {FNAME("sessionID") INT, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("associatedSessionID") INT, 8, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("mediaChannel") CHOICE, 1, 2, 2, DECODE | EXT | OPT, + offsetof(H2250LogicalChannelParameters, mediaChannel), + _H245_TransportAddress}, + {FNAME("mediaGuaranteedDelivery") BOOL, FIXD, 0, 0, SKIP | OPT, 0, + NULL}, + {FNAME("mediaControlChannel") CHOICE, 1, 2, 2, DECODE | EXT | OPT, + offsetof(H2250LogicalChannelParameters, mediaControlChannel), + _H245_TransportAddress}, + {FNAME("mediaControlGuaranteedDelivery") BOOL, FIXD, 0, 0, STOP | OPT, + 0, NULL}, + {FNAME("silenceSuppression") BOOL, FIXD, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("destination") SEQ, 0, 2, 2, STOP | EXT | OPT, 0, NULL}, + {FNAME("dynamicRTPPayloadType") INT, 5, 96, 0, STOP | OPT, 0, NULL}, + {FNAME("mediaPacketization") CHOICE, 0, 1, 2, STOP | EXT | OPT, 0, + NULL}, + {FNAME("transportCapability") SEQ, 3, 3, 3, STOP | EXT | OPT, 0, + NULL}, + {FNAME("redundancyEncoding") SEQ, 1, 2, 2, STOP | EXT | OPT, 0, NULL}, + {FNAME("source") SEQ, 0, 2, 2, SKIP | EXT | OPT, 0, NULL}, +}; + +static field_t _OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters[] = { /* CHOICE */ + {FNAME("h222LogicalChannelParameters") SEQ, 3, 5, 5, SKIP | EXT, 0, + _H222LogicalChannelParameters}, + {FNAME("h223LogicalChannelParameters") SEQ, 0, 2, 2, SKIP | EXT, 0, + _H223LogicalChannelParameters}, + {FNAME("v76LogicalChannelParameters") SEQ, 0, 5, 5, SKIP | EXT, 0, + _V76LogicalChannelParameters}, + {FNAME("h2250LogicalChannelParameters") SEQ, 10, 11, 14, DECODE | EXT, + offsetof + (OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters, + h2250LogicalChannelParameters), _H2250LogicalChannelParameters}, + {FNAME("none") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _OpenLogicalChannel_forwardLogicalChannelParameters[] = { /* SEQUENCE */ + {FNAME("portNumber") INT, WORD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("dataType") CHOICE, 3, 6, 9, DECODE | EXT, + offsetof(OpenLogicalChannel_forwardLogicalChannelParameters, + dataType), _DataType}, + {FNAME("multiplexParameters") CHOICE, 2, 3, 5, DECODE | EXT, + offsetof(OpenLogicalChannel_forwardLogicalChannelParameters, + multiplexParameters), + _OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters}, + {FNAME("forwardLogicalChannelDependency") INT, WORD, 1, 0, SKIP | OPT, + 0, NULL}, + {FNAME("replacementFor") INT, WORD, 1, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters[] = { /* CHOICE */ + {FNAME("h223LogicalChannelParameters") SEQ, 0, 2, 2, SKIP | EXT, 0, + _H223LogicalChannelParameters}, + {FNAME("v76LogicalChannelParameters") SEQ, 0, 5, 5, SKIP | EXT, 0, + _V76LogicalChannelParameters}, + {FNAME("h2250LogicalChannelParameters") SEQ, 10, 11, 14, DECODE | EXT, + offsetof + (OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters, + h2250LogicalChannelParameters), _H2250LogicalChannelParameters}, +}; + +static field_t _OpenLogicalChannel_reverseLogicalChannelParameters[] = { /* SEQUENCE */ + {FNAME("dataType") CHOICE, 3, 6, 9, SKIP | EXT, 0, _DataType}, + {FNAME("multiplexParameters") CHOICE, 1, 2, 3, DECODE | EXT | OPT, + offsetof(OpenLogicalChannel_reverseLogicalChannelParameters, + multiplexParameters), + _OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters}, + {FNAME("reverseLogicalChannelDependency") INT, WORD, 1, 0, SKIP | OPT, + 0, NULL}, + {FNAME("replacementFor") INT, WORD, 1, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _NetworkAccessParameters_distribution[] = { /* CHOICE */ + {FNAME("unicast") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("multicast") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _Q2931Address_address[] = { /* CHOICE */ + {FNAME("internationalNumber") NUMSTR, 4, 1, 0, SKIP, 0, NULL}, + {FNAME("nsapAddress") OCTSTR, 5, 1, 0, SKIP, 0, NULL}, +}; + +static field_t _Q2931Address[] = { /* SEQUENCE */ + {FNAME("address") CHOICE, 1, 2, 2, SKIP | EXT, 0, + _Q2931Address_address}, + {FNAME("subaddress") OCTSTR, 5, 1, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _NetworkAccessParameters_networkAddress[] = { /* CHOICE */ + {FNAME("q2931Address") SEQ, 1, 2, 2, SKIP | EXT, 0, _Q2931Address}, + {FNAME("e164Address") NUMDGT, 7, 1, 0, SKIP, 0, NULL}, + {FNAME("localAreaAddress") CHOICE, 1, 2, 2, DECODE | EXT, + offsetof(NetworkAccessParameters_networkAddress, localAreaAddress), + _H245_TransportAddress}, +}; + +static field_t _NetworkAccessParameters[] = { /* SEQUENCE */ + {FNAME("distribution") CHOICE, 1, 2, 2, SKIP | EXT | OPT, 0, + _NetworkAccessParameters_distribution}, + {FNAME("networkAddress") CHOICE, 2, 3, 3, DECODE | EXT, + offsetof(NetworkAccessParameters, networkAddress), + _NetworkAccessParameters_networkAddress}, + {FNAME("associateConference") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("externalReference") OCTSTR, 8, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("t120SetupProcedure") CHOICE, 2, 3, 3, SKIP | EXT | OPT, 0, + NULL}, +}; + +static field_t _OpenLogicalChannel[] = { /* SEQUENCE */ + {FNAME("forwardLogicalChannelNumber") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("forwardLogicalChannelParameters") SEQ, 1, 3, 5, DECODE | EXT, + offsetof(OpenLogicalChannel, forwardLogicalChannelParameters), + _OpenLogicalChannel_forwardLogicalChannelParameters}, + {FNAME("reverseLogicalChannelParameters") SEQ, 1, 2, 4, + DECODE | EXT | OPT, offsetof(OpenLogicalChannel, + reverseLogicalChannelParameters), + _OpenLogicalChannel_reverseLogicalChannelParameters}, + {FNAME("separateStack") SEQ, 2, 4, 5, DECODE | EXT | OPT, + offsetof(OpenLogicalChannel, separateStack), + _NetworkAccessParameters}, + {FNAME("encryptionSync") SEQ, 2, 4, 4, STOP | EXT | OPT, 0, NULL}, +}; + +static field_t _Setup_UUIE_fastStart[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 1, 3, 5, DECODE | OPEN | EXT, + sizeof(OpenLogicalChannel), _OpenLogicalChannel} + , +}; + +static field_t _Setup_UUIE[] = { /* SEQUENCE */ + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("h245Address") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(Setup_UUIE, h245Address), _TransportAddress}, + {FNAME("sourceAddress") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _Setup_UUIE_sourceAddress}, + {FNAME("sourceInfo") SEQ, 6, 8, 10, SKIP | EXT, 0, _EndpointType}, + {FNAME("destinationAddress") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _Setup_UUIE_destinationAddress}, + {FNAME("destCallSignalAddress") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(Setup_UUIE, destCallSignalAddress), _TransportAddress}, + {FNAME("destExtraCallInfo") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _Setup_UUIE_destExtraCallInfo}, + {FNAME("destExtraCRV") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _Setup_UUIE_destExtraCRV}, + {FNAME("activeMC") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("conferenceID") OCTSTR, FIXD, 16, 0, SKIP, 0, NULL}, + {FNAME("conferenceGoal") CHOICE, 2, 3, 5, SKIP | EXT, 0, + _Setup_UUIE_conferenceGoal}, + {FNAME("callServices") SEQ, 0, 8, 8, SKIP | EXT | OPT, 0, + _QseriesOptions}, + {FNAME("callType") CHOICE, 2, 4, 4, SKIP | EXT, 0, _CallType}, + {FNAME("sourceCallSignalAddress") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(Setup_UUIE, sourceCallSignalAddress), _TransportAddress}, + {FNAME("remoteExtensionAddress") CHOICE, 1, 2, 7, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("callIdentifier") SEQ, 0, 1, 1, SKIP | EXT, 0, NULL}, + {FNAME("h245SecurityCapability") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("fastStart") SEQOF, SEMI, 0, 30, DECODE | OPT, + offsetof(Setup_UUIE, fastStart), _Setup_UUIE_fastStart}, + {FNAME("mediaWaitForConnect") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("canOverlapSend") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("endpointIdentifier") BMPSTR, 7, 1, 0, STOP | OPT, 0, NULL}, + {FNAME("multipleCalls") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("maintainConnection") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("connectionParameters") SEQ, 0, 3, 3, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("language") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("presentationIndicator") CHOICE, 2, 3, 3, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("screeningIndicator") ENUM, 2, 0, 0, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("serviceControl") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("symmetricOperationRequired") NUL, FIXD, 0, 0, SKIP | OPT, 0, + NULL}, + {FNAME("capacity") SEQ, 2, 2, 2, SKIP | EXT | OPT, 0, NULL}, + {FNAME("circuitInfo") SEQ, 3, 3, 3, SKIP | EXT | OPT, 0, NULL}, + {FNAME("desiredProtocols") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("neededFeatures") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("desiredFeatures") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("supportedFeatures") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("parallelH245Control") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("additionalSourceAddresses") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + NULL}, +}; + +static field_t _CallProceeding_UUIE_fastStart[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 1, 3, 5, DECODE | OPEN | EXT, + sizeof(OpenLogicalChannel), _OpenLogicalChannel} + , +}; + +static field_t _CallProceeding_UUIE[] = { /* SEQUENCE */ + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("destinationInfo") SEQ, 6, 8, 10, SKIP | EXT, 0, + _EndpointType}, + {FNAME("h245Address") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(CallProceeding_UUIE, h245Address), _TransportAddress}, + {FNAME("callIdentifier") SEQ, 0, 1, 1, SKIP | EXT, 0, NULL}, + {FNAME("h245SecurityMode") CHOICE, 2, 4, 4, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("fastStart") SEQOF, SEMI, 0, 30, DECODE | OPT, + offsetof(CallProceeding_UUIE, fastStart), + _CallProceeding_UUIE_fastStart}, + {FNAME("multipleCalls") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("maintainConnection") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("fastConnectRefused") NUL, FIXD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, SKIP | EXT | OPT, 0, NULL}, +}; + +static field_t _Connect_UUIE_fastStart[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 1, 3, 5, DECODE | OPEN | EXT, + sizeof(OpenLogicalChannel), _OpenLogicalChannel} + , +}; + +static field_t _Connect_UUIE[] = { /* SEQUENCE */ + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("h245Address") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(Connect_UUIE, h245Address), _TransportAddress}, + {FNAME("destinationInfo") SEQ, 6, 8, 10, SKIP | EXT, 0, + _EndpointType}, + {FNAME("conferenceID") OCTSTR, FIXD, 16, 0, SKIP, 0, NULL}, + {FNAME("callIdentifier") SEQ, 0, 1, 1, SKIP | EXT, 0, NULL}, + {FNAME("h245SecurityMode") CHOICE, 2, 4, 4, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("fastStart") SEQOF, SEMI, 0, 30, DECODE | OPT, + offsetof(Connect_UUIE, fastStart), _Connect_UUIE_fastStart}, + {FNAME("multipleCalls") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("maintainConnection") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("language") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("connectedAddress") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("presentationIndicator") CHOICE, 2, 3, 3, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("screeningIndicator") ENUM, 2, 0, 0, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("fastConnectRefused") NUL, FIXD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("serviceControl") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("capacity") SEQ, 2, 2, 2, SKIP | EXT | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, SKIP | EXT | OPT, 0, NULL}, +}; + +static field_t _Alerting_UUIE_fastStart[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 1, 3, 5, DECODE | OPEN | EXT, + sizeof(OpenLogicalChannel), _OpenLogicalChannel} + , +}; + +static field_t _Alerting_UUIE[] = { /* SEQUENCE */ + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("destinationInfo") SEQ, 6, 8, 10, SKIP | EXT, 0, + _EndpointType}, + {FNAME("h245Address") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(Alerting_UUIE, h245Address), _TransportAddress}, + {FNAME("callIdentifier") SEQ, 0, 1, 1, SKIP | EXT, 0, NULL}, + {FNAME("h245SecurityMode") CHOICE, 2, 4, 4, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("fastStart") SEQOF, SEMI, 0, 30, DECODE | OPT, + offsetof(Alerting_UUIE, fastStart), _Alerting_UUIE_fastStart}, + {FNAME("multipleCalls") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("maintainConnection") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("alertingAddress") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("presentationIndicator") CHOICE, 2, 3, 3, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("screeningIndicator") ENUM, 2, 0, 0, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("fastConnectRefused") NUL, FIXD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("serviceControl") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("capacity") SEQ, 2, 2, 2, SKIP | EXT | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, SKIP | EXT | OPT, 0, NULL}, +}; + +static field_t _Information_UUIE_fastStart[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 1, 3, 5, DECODE | OPEN | EXT, + sizeof(OpenLogicalChannel), _OpenLogicalChannel} + , +}; + +static field_t _Information_UUIE[] = { /* SEQUENCE */ + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("callIdentifier") SEQ, 0, 1, 1, SKIP | EXT, 0, NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("fastStart") SEQOF, SEMI, 0, 30, DECODE | OPT, + offsetof(Information_UUIE, fastStart), _Information_UUIE_fastStart}, + {FNAME("fastConnectRefused") NUL, FIXD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("circuitInfo") SEQ, 3, 3, 3, SKIP | EXT | OPT, 0, NULL}, +}; + +static field_t _ReleaseCompleteReason[] = { /* CHOICE */ + {FNAME("noBandwidth") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("gatekeeperResources") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("unreachableDestination") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("destinationRejection") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("invalidRevision") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("noPermission") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("unreachableGatekeeper") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("gatewayResources") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("badFormatAddress") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("adaptiveBusy") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("inConf") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("undefinedReason") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("facilityCallDeflection") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("securityDenied") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("calledPartyNotRegistered") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("callerNotRegistered") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("newConnectionNeeded") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("nonStandardReason") SEQ, 0, 2, 2, SKIP, 0, NULL}, + {FNAME("replaceWithConferenceInvite") OCTSTR, FIXD, 16, 0, SKIP, 0, + NULL}, + {FNAME("genericDataReason") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("neededFeatureNotSupported") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("tunnelledSignallingRejected") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _ReleaseComplete_UUIE[] = { /* SEQUENCE */ + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("reason") CHOICE, 4, 12, 22, SKIP | EXT | OPT, 0, + _ReleaseCompleteReason}, + {FNAME("callIdentifier") SEQ, 0, 1, 1, SKIP | EXT, 0, NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("busyAddress") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("presentationIndicator") CHOICE, 2, 3, 3, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("screeningIndicator") ENUM, 2, 0, 0, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("capacity") SEQ, 2, 2, 2, SKIP | EXT | OPT, 0, NULL}, + {FNAME("serviceControl") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, SKIP | EXT | OPT, 0, NULL}, +}; + +static field_t _Facility_UUIE_alternativeAliasAddress[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _FacilityReason[] = { /* CHOICE */ + {FNAME("routeCallToGatekeeper") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("callForwarded") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("routeCallToMC") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("undefinedReason") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("conferenceListChoice") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("startH245") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("noH245") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("newTokens") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("featureSetUpdate") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("forwardedElements") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("transportedInformation") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _Facility_UUIE_fastStart[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 1, 3, 5, DECODE | OPEN | EXT, + sizeof(OpenLogicalChannel), _OpenLogicalChannel} + , +}; + +static field_t _Facility_UUIE[] = { /* SEQUENCE */ + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("alternativeAddress") CHOICE, 3, 7, 7, SKIP | EXT | OPT, 0, + _TransportAddress}, + {FNAME("alternativeAliasAddress") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _Facility_UUIE_alternativeAliasAddress}, + {FNAME("conferenceID") OCTSTR, FIXD, 16, 0, SKIP | OPT, 0, NULL}, + {FNAME("reason") CHOICE, 2, 4, 11, DECODE | EXT, + offsetof(Facility_UUIE, reason), _FacilityReason}, + {FNAME("callIdentifier") SEQ, 0, 1, 1, SKIP | EXT, 0, NULL}, + {FNAME("destExtraCallInfo") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("remoteExtensionAddress") CHOICE, 1, 2, 7, SKIP | EXT | OPT, 0, + NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("conferences") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("h245Address") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(Facility_UUIE, h245Address), _TransportAddress}, + {FNAME("fastStart") SEQOF, SEMI, 0, 30, DECODE | OPT, + offsetof(Facility_UUIE, fastStart), _Facility_UUIE_fastStart}, + {FNAME("multipleCalls") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("maintainConnection") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("fastConnectRefused") NUL, FIXD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("serviceControl") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("circuitInfo") SEQ, 3, 3, 3, SKIP | EXT | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, SKIP | EXT | OPT, 0, NULL}, + {FNAME("destinationInfo") SEQ, 6, 8, 10, SKIP | EXT | OPT, 0, NULL}, + {FNAME("h245SecurityMode") CHOICE, 2, 4, 4, SKIP | EXT | OPT, 0, + NULL}, +}; + +static field_t _CallIdentifier[] = { /* SEQUENCE */ + {FNAME("guid") OCTSTR, FIXD, 16, 0, SKIP, 0, NULL}, +}; + +static field_t _SecurityServiceMode[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP, 0, _NonStandardParameter}, + {FNAME("none") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("default") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _SecurityCapabilities[] = { /* SEQUENCE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("encryption") CHOICE, 2, 3, 3, SKIP | EXT, 0, + _SecurityServiceMode}, + {FNAME("authenticaton") CHOICE, 2, 3, 3, SKIP | EXT, 0, + _SecurityServiceMode}, + {FNAME("integrity") CHOICE, 2, 3, 3, SKIP | EXT, 0, + _SecurityServiceMode}, +}; + +static field_t _H245Security[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP, 0, _NonStandardParameter}, + {FNAME("noSecurity") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("tls") SEQ, 1, 4, 4, SKIP | EXT, 0, _SecurityCapabilities}, + {FNAME("ipsec") SEQ, 1, 4, 4, SKIP | EXT, 0, _SecurityCapabilities}, +}; + +static field_t _DHset[] = { /* SEQUENCE */ + {FNAME("halfkey") BITSTR, WORD, 0, 0, SKIP, 0, NULL}, + {FNAME("modSize") BITSTR, WORD, 0, 0, SKIP, 0, NULL}, + {FNAME("generator") BITSTR, WORD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _TypedCertificate[] = { /* SEQUENCE */ + {FNAME("type") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("certificate") OCTSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _H235_NonStandardParameter[] = { /* SEQUENCE */ + {FNAME("nonStandardIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("data") OCTSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _ClearToken[] = { /* SEQUENCE */ + {FNAME("tokenOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("timeStamp") INT, CONS, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("password") BMPSTR, 7, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("dhkey") SEQ, 0, 3, 3, SKIP | EXT | OPT, 0, _DHset}, + {FNAME("challenge") OCTSTR, 7, 8, 0, SKIP | OPT, 0, NULL}, + {FNAME("random") INT, UNCO, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("certificate") SEQ, 0, 2, 2, SKIP | EXT | OPT, 0, + _TypedCertificate}, + {FNAME("generalID") BMPSTR, 7, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("nonStandard") SEQ, 0, 2, 2, SKIP | OPT, 0, + _H235_NonStandardParameter}, + {FNAME("eckasdhkey") CHOICE, 1, 2, 2, SKIP | EXT | OPT, 0, NULL}, + {FNAME("sendersID") BMPSTR, 7, 1, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _Progress_UUIE_tokens[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 8, 9, 11, SKIP | EXT, 0, _ClearToken}, +}; + +static field_t _Params[] = { /* SEQUENCE */ + {FNAME("ranInt") INT, UNCO, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("iv8") OCTSTR, FIXD, 8, 0, SKIP | OPT, 0, NULL}, + {FNAME("iv16") OCTSTR, FIXD, 16, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _CryptoH323Token_cryptoEPPwdHash_token[] = { /* SEQUENCE */ + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("hash") BITSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoH323Token_cryptoEPPwdHash[] = { /* SEQUENCE */ + {FNAME("alias") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, + {FNAME("timeStamp") INT, CONS, 1, 0, SKIP, 0, NULL}, + {FNAME("token") SEQ, 0, 3, 3, SKIP, 0, + _CryptoH323Token_cryptoEPPwdHash_token}, +}; + +static field_t _CryptoH323Token_cryptoGKPwdHash_token[] = { /* SEQUENCE */ + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("hash") BITSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoH323Token_cryptoGKPwdHash[] = { /* SEQUENCE */ + {FNAME("gatekeeperId") BMPSTR, 7, 1, 0, SKIP, 0, NULL}, + {FNAME("timeStamp") INT, CONS, 1, 0, SKIP, 0, NULL}, + {FNAME("token") SEQ, 0, 3, 3, SKIP, 0, + _CryptoH323Token_cryptoGKPwdHash_token}, +}; + +static field_t _CryptoH323Token_cryptoEPPwdEncr[] = { /* SEQUENCE */ + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("encryptedData") OCTSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoH323Token_cryptoGKPwdEncr[] = { /* SEQUENCE */ + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("encryptedData") OCTSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoH323Token_cryptoEPCert[] = { /* SEQUENCE */ + {FNAME("toBeSigned") SEQ, 8, 9, 11, SKIP | OPEN | EXT, 0, NULL}, + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("signature") BITSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoH323Token_cryptoGKCert[] = { /* SEQUENCE */ + {FNAME("toBeSigned") SEQ, 8, 9, 11, SKIP | OPEN | EXT, 0, NULL}, + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("signature") BITSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoH323Token_cryptoFastStart[] = { /* SEQUENCE */ + {FNAME("toBeSigned") SEQ, 8, 9, 11, SKIP | OPEN | EXT, 0, NULL}, + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("signature") BITSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoToken_cryptoEncryptedToken_token[] = { /* SEQUENCE */ + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("encryptedData") OCTSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoToken_cryptoEncryptedToken[] = { /* SEQUENCE */ + {FNAME("tokenOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("token") SEQ, 0, 3, 3, SKIP, 0, + _CryptoToken_cryptoEncryptedToken_token}, +}; + +static field_t _CryptoToken_cryptoSignedToken_token[] = { /* SEQUENCE */ + {FNAME("toBeSigned") SEQ, 8, 9, 11, SKIP | OPEN | EXT, 0, NULL}, + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("signature") BITSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoToken_cryptoSignedToken[] = { /* SEQUENCE */ + {FNAME("tokenOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("token") SEQ, 0, 4, 4, SKIP, 0, + _CryptoToken_cryptoSignedToken_token}, +}; + +static field_t _CryptoToken_cryptoHashedToken_token[] = { /* SEQUENCE */ + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("hash") BITSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoToken_cryptoHashedToken[] = { /* SEQUENCE */ + {FNAME("tokenOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("hashedVals") SEQ, 8, 9, 11, SKIP | EXT, 0, _ClearToken}, + {FNAME("token") SEQ, 0, 3, 3, SKIP, 0, + _CryptoToken_cryptoHashedToken_token}, +}; + +static field_t _CryptoToken_cryptoPwdEncr[] = { /* SEQUENCE */ + {FNAME("algorithmOID") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("paramS") SEQ, 2, 2, 3, SKIP | EXT, 0, _Params}, + {FNAME("encryptedData") OCTSTR, SEMI, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _CryptoToken[] = { /* CHOICE */ + {FNAME("cryptoEncryptedToken") SEQ, 0, 2, 2, SKIP, 0, + _CryptoToken_cryptoEncryptedToken}, + {FNAME("cryptoSignedToken") SEQ, 0, 2, 2, SKIP, 0, + _CryptoToken_cryptoSignedToken}, + {FNAME("cryptoHashedToken") SEQ, 0, 3, 3, SKIP, 0, + _CryptoToken_cryptoHashedToken}, + {FNAME("cryptoPwdEncr") SEQ, 0, 3, 3, SKIP, 0, + _CryptoToken_cryptoPwdEncr}, +}; + +static field_t _CryptoH323Token[] = { /* CHOICE */ + {FNAME("cryptoEPPwdHash") SEQ, 0, 3, 3, SKIP, 0, + _CryptoH323Token_cryptoEPPwdHash}, + {FNAME("cryptoGKPwdHash") SEQ, 0, 3, 3, SKIP, 0, + _CryptoH323Token_cryptoGKPwdHash}, + {FNAME("cryptoEPPwdEncr") SEQ, 0, 3, 3, SKIP, 0, + _CryptoH323Token_cryptoEPPwdEncr}, + {FNAME("cryptoGKPwdEncr") SEQ, 0, 3, 3, SKIP, 0, + _CryptoH323Token_cryptoGKPwdEncr}, + {FNAME("cryptoEPCert") SEQ, 0, 4, 4, SKIP, 0, + _CryptoH323Token_cryptoEPCert}, + {FNAME("cryptoGKCert") SEQ, 0, 4, 4, SKIP, 0, + _CryptoH323Token_cryptoGKCert}, + {FNAME("cryptoFastStart") SEQ, 0, 4, 4, SKIP, 0, + _CryptoH323Token_cryptoFastStart}, + {FNAME("nestedcryptoToken") CHOICE, 2, 4, 4, SKIP | EXT, 0, + _CryptoToken}, +}; + +static field_t _Progress_UUIE_cryptoTokens[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 3, 8, 8, SKIP | EXT, 0, _CryptoH323Token}, +}; + +static field_t _Progress_UUIE_fastStart[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 1, 3, 5, DECODE | OPEN | EXT, + sizeof(OpenLogicalChannel), _OpenLogicalChannel} + , +}; + +static field_t _Progress_UUIE[] = { /* SEQUENCE */ + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("destinationInfo") SEQ, 6, 8, 10, SKIP | EXT, 0, + _EndpointType}, + {FNAME("h245Address") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(Progress_UUIE, h245Address), _TransportAddress}, + {FNAME("callIdentifier") SEQ, 0, 1, 1, SKIP | EXT, 0, + _CallIdentifier}, + {FNAME("h245SecurityMode") CHOICE, 2, 4, 4, SKIP | EXT | OPT, 0, + _H245Security}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _Progress_UUIE_tokens}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _Progress_UUIE_cryptoTokens}, + {FNAME("fastStart") SEQOF, SEMI, 0, 30, DECODE | OPT, + offsetof(Progress_UUIE, fastStart), _Progress_UUIE_fastStart}, + {FNAME("multipleCalls") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("maintainConnection") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("fastConnectRefused") NUL, FIXD, 0, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _H323_UU_PDU_h323_message_body[] = { /* CHOICE */ + {FNAME("setup") SEQ, 7, 13, 39, DECODE | EXT, + offsetof(H323_UU_PDU_h323_message_body, setup), _Setup_UUIE}, + {FNAME("callProceeding") SEQ, 1, 3, 12, DECODE | EXT, + offsetof(H323_UU_PDU_h323_message_body, callProceeding), + _CallProceeding_UUIE}, + {FNAME("connect") SEQ, 1, 4, 19, DECODE | EXT, + offsetof(H323_UU_PDU_h323_message_body, connect), _Connect_UUIE}, + {FNAME("alerting") SEQ, 1, 3, 17, DECODE | EXT, + offsetof(H323_UU_PDU_h323_message_body, alerting), _Alerting_UUIE}, + {FNAME("information") SEQ, 0, 1, 7, DECODE | EXT, + offsetof(H323_UU_PDU_h323_message_body, information), + _Information_UUIE}, + {FNAME("releaseComplete") SEQ, 1, 2, 11, SKIP | EXT, 0, + _ReleaseComplete_UUIE}, + {FNAME("facility") SEQ, 3, 5, 21, DECODE | EXT, + offsetof(H323_UU_PDU_h323_message_body, facility), _Facility_UUIE}, + {FNAME("progress") SEQ, 5, 8, 11, DECODE | EXT, + offsetof(H323_UU_PDU_h323_message_body, progress), _Progress_UUIE}, + {FNAME("empty") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("status") SEQ, 2, 4, 4, SKIP | EXT, 0, NULL}, + {FNAME("statusInquiry") SEQ, 2, 4, 4, SKIP | EXT, 0, NULL}, + {FNAME("setupAcknowledge") SEQ, 2, 4, 4, SKIP | EXT, 0, NULL}, + {FNAME("notify") SEQ, 2, 4, 4, SKIP | EXT, 0, NULL}, +}; + +static field_t _RequestMessage[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("masterSlaveDetermination") SEQ, 0, 2, 2, STOP | EXT, 0, NULL}, + {FNAME("terminalCapabilitySet") SEQ, 3, 5, 5, STOP | EXT, 0, NULL}, + {FNAME("openLogicalChannel") SEQ, 1, 3, 5, DECODE | EXT, + offsetof(RequestMessage, openLogicalChannel), _OpenLogicalChannel}, + {FNAME("closeLogicalChannel") SEQ, 0, 2, 3, STOP | EXT, 0, NULL}, + {FNAME("requestChannelClose") SEQ, 0, 1, 3, STOP | EXT, 0, NULL}, + {FNAME("multiplexEntrySend") SEQ, 0, 2, 2, STOP | EXT, 0, NULL}, + {FNAME("requestMultiplexEntry") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("requestMode") SEQ, 0, 2, 2, STOP | EXT, 0, NULL}, + {FNAME("roundTripDelayRequest") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("maintenanceLoopRequest") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("communicationModeRequest") SEQ, 0, 0, 0, STOP | EXT, 0, NULL}, + {FNAME("conferenceRequest") CHOICE, 3, 8, 16, STOP | EXT, 0, NULL}, + {FNAME("multilinkRequest") CHOICE, 3, 5, 5, STOP | EXT, 0, NULL}, + {FNAME("logicalChannelRateRequest") SEQ, 0, 3, 3, STOP | EXT, 0, + NULL}, +}; + +static field_t _OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters[] = { /* CHOICE */ + {FNAME("h222LogicalChannelParameters") SEQ, 3, 5, 5, SKIP | EXT, 0, + _H222LogicalChannelParameters}, + {FNAME("h2250LogicalChannelParameters") SEQ, 10, 11, 14, DECODE | EXT, + offsetof + (OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters, + h2250LogicalChannelParameters), _H2250LogicalChannelParameters}, +}; + +static field_t _OpenLogicalChannelAck_reverseLogicalChannelParameters[] = { /* SEQUENCE */ + {FNAME("reverseLogicalChannelNumber") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("portNumber") INT, WORD, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("multiplexParameters") CHOICE, 0, 1, 2, DECODE | EXT | OPT, + offsetof(OpenLogicalChannelAck_reverseLogicalChannelParameters, + multiplexParameters), + _OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters}, + {FNAME("replacementFor") INT, WORD, 1, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _H2250LogicalChannelAckParameters_nonStandard[] = { /* SEQUENCE OF */ + {FNAME("item") SEQ, 0, 2, 2, SKIP, 0, _H245_NonStandardParameter}, +}; + +static field_t _H2250LogicalChannelAckParameters[] = { /* SEQUENCE */ + {FNAME("nonStandard") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _H2250LogicalChannelAckParameters_nonStandard}, + {FNAME("sessionID") INT, 8, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("mediaChannel") CHOICE, 1, 2, 2, DECODE | EXT | OPT, + offsetof(H2250LogicalChannelAckParameters, mediaChannel), + _H245_TransportAddress}, + {FNAME("mediaControlChannel") CHOICE, 1, 2, 2, DECODE | EXT | OPT, + offsetof(H2250LogicalChannelAckParameters, mediaControlChannel), + _H245_TransportAddress}, + {FNAME("dynamicRTPPayloadType") INT, 5, 96, 0, SKIP | OPT, 0, NULL}, + {FNAME("flowControlToZero") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("portNumber") INT, WORD, 0, 0, SKIP | OPT, 0, NULL}, +}; + +static field_t _OpenLogicalChannelAck_forwardMultiplexAckParameters[] = { /* CHOICE */ + {FNAME("h2250LogicalChannelAckParameters") SEQ, 5, 5, 7, DECODE | EXT, + offsetof(OpenLogicalChannelAck_forwardMultiplexAckParameters, + h2250LogicalChannelAckParameters), + _H2250LogicalChannelAckParameters}, +}; + +static field_t _OpenLogicalChannelAck[] = { /* SEQUENCE */ + {FNAME("forwardLogicalChannelNumber") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("reverseLogicalChannelParameters") SEQ, 2, 3, 4, + DECODE | EXT | OPT, offsetof(OpenLogicalChannelAck, + reverseLogicalChannelParameters), + _OpenLogicalChannelAck_reverseLogicalChannelParameters}, + {FNAME("separateStack") SEQ, 2, 4, 5, SKIP | EXT | OPT, 0, NULL}, + {FNAME("forwardMultiplexAckParameters") CHOICE, 0, 1, 1, + DECODE | EXT | OPT, offsetof(OpenLogicalChannelAck, + forwardMultiplexAckParameters), + _OpenLogicalChannelAck_forwardMultiplexAckParameters}, + {FNAME("encryptionSync") SEQ, 2, 4, 4, STOP | EXT | OPT, 0, NULL}, +}; + +static field_t _ResponseMessage[] = { /* CHOICE */ + {FNAME("nonStandard") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("masterSlaveDeterminationAck") SEQ, 0, 1, 1, STOP | EXT, 0, + NULL}, + {FNAME("masterSlaveDeterminationReject") SEQ, 0, 1, 1, STOP | EXT, 0, + NULL}, + {FNAME("terminalCapabilitySetAck") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("terminalCapabilitySetReject") SEQ, 0, 2, 2, STOP | EXT, 0, + NULL}, + {FNAME("openLogicalChannelAck") SEQ, 1, 2, 5, DECODE | EXT, + offsetof(ResponseMessage, openLogicalChannelAck), + _OpenLogicalChannelAck}, + {FNAME("openLogicalChannelReject") SEQ, 0, 2, 2, STOP | EXT, 0, NULL}, + {FNAME("closeLogicalChannelAck") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("requestChannelCloseAck") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("requestChannelCloseReject") SEQ, 0, 2, 2, STOP | EXT, 0, + NULL}, + {FNAME("multiplexEntrySendAck") SEQ, 0, 2, 2, STOP | EXT, 0, NULL}, + {FNAME("multiplexEntrySendReject") SEQ, 0, 2, 2, STOP | EXT, 0, NULL}, + {FNAME("requestMultiplexEntryAck") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("requestMultiplexEntryReject") SEQ, 0, 2, 2, STOP | EXT, 0, + NULL}, + {FNAME("requestModeAck") SEQ, 0, 2, 2, STOP | EXT, 0, NULL}, + {FNAME("requestModeReject") SEQ, 0, 2, 2, STOP | EXT, 0, NULL}, + {FNAME("roundTripDelayResponse") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("maintenanceLoopAck") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("maintenanceLoopReject") SEQ, 0, 2, 2, STOP | EXT, 0, NULL}, + {FNAME("communicationModeResponse") CHOICE, 0, 1, 1, STOP | EXT, 0, + NULL}, + {FNAME("conferenceResponse") CHOICE, 3, 8, 16, STOP | EXT, 0, NULL}, + {FNAME("multilinkResponse") CHOICE, 3, 5, 5, STOP | EXT, 0, NULL}, + {FNAME("logicalChannelRateAcknowledge") SEQ, 0, 3, 3, STOP | EXT, 0, + NULL}, + {FNAME("logicalChannelRateReject") SEQ, 1, 4, 4, STOP | EXT, 0, NULL}, +}; + +static field_t _MultimediaSystemControlMessage[] = { /* CHOICE */ + {FNAME("request") CHOICE, 4, 11, 15, DECODE | EXT, + offsetof(MultimediaSystemControlMessage, request), _RequestMessage}, + {FNAME("response") CHOICE, 5, 19, 24, DECODE | EXT, + offsetof(MultimediaSystemControlMessage, response), + _ResponseMessage}, + {FNAME("command") CHOICE, 3, 7, 12, STOP | EXT, 0, NULL}, + {FNAME("indication") CHOICE, 4, 14, 23, STOP | EXT, 0, NULL}, +}; + +static field_t _H323_UU_PDU_h245Control[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 2, 4, 4, DECODE | OPEN | EXT, + sizeof(MultimediaSystemControlMessage), + _MultimediaSystemControlMessage} + , +}; + +static field_t _H323_UU_PDU[] = { /* SEQUENCE */ + {FNAME("h323-message-body") CHOICE, 3, 7, 13, DECODE | EXT, + offsetof(H323_UU_PDU, h323_message_body), + _H323_UU_PDU_h323_message_body}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("h4501SupplementaryService") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + NULL}, + {FNAME("h245Tunneling") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("h245Control") SEQOF, SEMI, 0, 4, DECODE | OPT, + offsetof(H323_UU_PDU, h245Control), _H323_UU_PDU_h245Control}, + {FNAME("nonStandardControl") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("callLinkage") SEQ, 2, 2, 2, STOP | EXT | OPT, 0, NULL}, + {FNAME("tunnelledSignallingMessage") SEQ, 2, 4, 4, STOP | EXT | OPT, + 0, NULL}, + {FNAME("provisionalRespToH245Tunneling") NUL, FIXD, 0, 0, STOP | OPT, + 0, NULL}, + {FNAME("stimulusControl") SEQ, 3, 3, 3, STOP | EXT | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _H323_UserInformation[] = { /* SEQUENCE */ + {FNAME("h323-uu-pdu") SEQ, 1, 2, 11, DECODE | EXT, + offsetof(H323_UserInformation, h323_uu_pdu), _H323_UU_PDU}, + {FNAME("user-data") SEQ, 0, 2, 2, STOP | EXT | OPT, 0, NULL}, +}; + +static field_t _GatekeeperRequest[] = { /* SEQUENCE */ + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("rasAddress") CHOICE, 3, 7, 7, DECODE | EXT, + offsetof(GatekeeperRequest, rasAddress), _TransportAddress}, + {FNAME("endpointType") SEQ, 6, 8, 10, STOP | EXT, 0, NULL}, + {FNAME("gatekeeperIdentifier") BMPSTR, 7, 1, 0, STOP | OPT, 0, NULL}, + {FNAME("callServices") SEQ, 0, 8, 8, STOP | EXT | OPT, 0, NULL}, + {FNAME("endpointAlias") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("alternateEndpoints") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("authenticationCapability") SEQOF, SEMI, 0, 0, STOP | OPT, 0, + NULL}, + {FNAME("algorithmOIDs") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrity") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("supportsAltGK") NUL, FIXD, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, STOP | EXT | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _GatekeeperConfirm[] = { /* SEQUENCE */ + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("gatekeeperIdentifier") BMPSTR, 7, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("rasAddress") CHOICE, 3, 7, 7, DECODE | EXT, + offsetof(GatekeeperConfirm, rasAddress), _TransportAddress}, + {FNAME("alternateGatekeeper") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("authenticationMode") CHOICE, 3, 7, 8, STOP | EXT | OPT, 0, + NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("algorithmOID") OID, BYTE, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrity") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, STOP | EXT | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _RegistrationRequest_callSignalAddress[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 3, 7, 7, DECODE | EXT, + sizeof(TransportAddress), _TransportAddress} + , +}; + +static field_t _RegistrationRequest_rasAddress[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 3, 7, 7, DECODE | EXT, + sizeof(TransportAddress), _TransportAddress} + , +}; + +static field_t _RegistrationRequest_terminalAlias[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _RegistrationRequest[] = { /* SEQUENCE */ + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("discoveryComplete") BOOL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("callSignalAddress") SEQOF, SEMI, 0, 10, DECODE, + offsetof(RegistrationRequest, callSignalAddress), + _RegistrationRequest_callSignalAddress}, + {FNAME("rasAddress") SEQOF, SEMI, 0, 10, DECODE, + offsetof(RegistrationRequest, rasAddress), + _RegistrationRequest_rasAddress}, + {FNAME("terminalType") SEQ, 6, 8, 10, SKIP | EXT, 0, _EndpointType}, + {FNAME("terminalAlias") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _RegistrationRequest_terminalAlias}, + {FNAME("gatekeeperIdentifier") BMPSTR, 7, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("endpointVendor") SEQ, 2, 3, 3, SKIP | EXT, 0, + _VendorIdentifier}, + {FNAME("alternateEndpoints") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("timeToLive") INT, CONS, 1, 0, DECODE | OPT, + offsetof(RegistrationRequest, timeToLive), NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("keepAlive") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("endpointIdentifier") BMPSTR, 7, 1, 0, STOP | OPT, 0, NULL}, + {FNAME("willSupplyUUIEs") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("maintainConnection") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("alternateTransportAddresses") SEQ, 1, 1, 1, STOP | EXT | OPT, + 0, NULL}, + {FNAME("additiveRegistration") NUL, FIXD, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("terminalAliasPattern") SEQOF, SEMI, 0, 0, STOP | OPT, 0, + NULL}, + {FNAME("supportsAltGK") NUL, FIXD, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("usageReportingCapability") SEQ, 3, 4, 4, STOP | EXT | OPT, 0, + NULL}, + {FNAME("multipleCalls") BOOL, FIXD, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("supportedH248Packages") SEQOF, SEMI, 0, 0, STOP | OPT, 0, + NULL}, + {FNAME("callCreditCapability") SEQ, 2, 2, 2, STOP | EXT | OPT, 0, + NULL}, + {FNAME("capacityReportingCapability") SEQ, 0, 1, 1, STOP | EXT | OPT, + 0, NULL}, + {FNAME("capacity") SEQ, 2, 2, 2, STOP | EXT | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, STOP | EXT | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _RegistrationConfirm_callSignalAddress[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 3, 7, 7, DECODE | EXT, + sizeof(TransportAddress), _TransportAddress} + , +}; + +static field_t _RegistrationConfirm_terminalAlias[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _RegistrationConfirm[] = { /* SEQUENCE */ + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("protocolIdentifier") OID, BYTE, 0, 0, SKIP, 0, NULL}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("callSignalAddress") SEQOF, SEMI, 0, 10, DECODE, + offsetof(RegistrationConfirm, callSignalAddress), + _RegistrationConfirm_callSignalAddress}, + {FNAME("terminalAlias") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _RegistrationConfirm_terminalAlias}, + {FNAME("gatekeeperIdentifier") BMPSTR, 7, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("endpointIdentifier") BMPSTR, 7, 1, 0, SKIP, 0, NULL}, + {FNAME("alternateGatekeeper") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, NULL}, + {FNAME("timeToLive") INT, CONS, 1, 0, DECODE | OPT, + offsetof(RegistrationConfirm, timeToLive), NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("willRespondToIRR") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("preGrantedARQ") SEQ, 0, 4, 8, STOP | EXT | OPT, 0, NULL}, + {FNAME("maintainConnection") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("serviceControl") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("supportsAdditiveRegistration") NUL, FIXD, 0, 0, STOP | OPT, 0, + NULL}, + {FNAME("terminalAliasPattern") SEQOF, SEMI, 0, 0, STOP | OPT, 0, + NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("usageSpec") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("featureServerAlias") CHOICE, 1, 2, 7, STOP | EXT | OPT, 0, + NULL}, + {FNAME("capacityReportingSpec") SEQ, 0, 1, 1, STOP | EXT | OPT, 0, + NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, STOP | EXT | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _UnregistrationRequest_callSignalAddress[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 3, 7, 7, DECODE | EXT, + sizeof(TransportAddress), _TransportAddress} + , +}; + +static field_t _UnregistrationRequest[] = { /* SEQUENCE */ + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("callSignalAddress") SEQOF, SEMI, 0, 10, DECODE, + offsetof(UnregistrationRequest, callSignalAddress), + _UnregistrationRequest_callSignalAddress}, + {FNAME("endpointAlias") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("endpointIdentifier") BMPSTR, 7, 1, 0, STOP | OPT, 0, NULL}, + {FNAME("alternateEndpoints") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("gatekeeperIdentifier") BMPSTR, 7, 1, 0, STOP | OPT, 0, NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("reason") CHOICE, 2, 4, 5, STOP | EXT | OPT, 0, NULL}, + {FNAME("endpointAliasPattern") SEQOF, SEMI, 0, 0, STOP | OPT, 0, + NULL}, + {FNAME("supportedPrefixes") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("alternateGatekeeper") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _CallModel[] = { /* CHOICE */ + {FNAME("direct") NUL, FIXD, 0, 0, SKIP, 0, NULL}, + {FNAME("gatekeeperRouted") NUL, FIXD, 0, 0, SKIP, 0, NULL}, +}; + +static field_t _AdmissionRequest_destinationInfo[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _AdmissionRequest_destExtraCallInfo[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _AdmissionRequest_srcInfo[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _AdmissionRequest[] = { /* SEQUENCE */ + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("callType") CHOICE, 2, 4, 4, SKIP | EXT, 0, _CallType}, + {FNAME("callModel") CHOICE, 1, 2, 2, SKIP | EXT | OPT, 0, _CallModel}, + {FNAME("endpointIdentifier") BMPSTR, 7, 1, 0, SKIP, 0, NULL}, + {FNAME("destinationInfo") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _AdmissionRequest_destinationInfo}, + {FNAME("destCallSignalAddress") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(AdmissionRequest, destCallSignalAddress), + _TransportAddress}, + {FNAME("destExtraCallInfo") SEQOF, SEMI, 0, 0, SKIP | OPT, 0, + _AdmissionRequest_destExtraCallInfo}, + {FNAME("srcInfo") SEQOF, SEMI, 0, 0, SKIP, 0, + _AdmissionRequest_srcInfo}, + {FNAME("srcCallSignalAddress") CHOICE, 3, 7, 7, DECODE | EXT | OPT, + offsetof(AdmissionRequest, srcCallSignalAddress), _TransportAddress}, + {FNAME("bandWidth") INT, CONS, 0, 0, STOP, 0, NULL}, + {FNAME("callReferenceValue") INT, WORD, 0, 0, STOP, 0, NULL}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("callServices") SEQ, 0, 8, 8, STOP | EXT | OPT, 0, NULL}, + {FNAME("conferenceID") OCTSTR, FIXD, 16, 0, STOP, 0, NULL}, + {FNAME("activeMC") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("answerCall") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("canMapAlias") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("callIdentifier") SEQ, 0, 1, 1, STOP | EXT, 0, NULL}, + {FNAME("srcAlternatives") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("destAlternatives") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("gatekeeperIdentifier") BMPSTR, 7, 1, 0, STOP | OPT, 0, NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("transportQOS") CHOICE, 2, 3, 3, STOP | EXT | OPT, 0, NULL}, + {FNAME("willSupplyUUIEs") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("callLinkage") SEQ, 2, 2, 2, STOP | EXT | OPT, 0, NULL}, + {FNAME("gatewayDataRate") SEQ, 2, 3, 3, STOP | EXT | OPT, 0, NULL}, + {FNAME("capacity") SEQ, 2, 2, 2, STOP | EXT | OPT, 0, NULL}, + {FNAME("circuitInfo") SEQ, 3, 3, 3, STOP | EXT | OPT, 0, NULL}, + {FNAME("desiredProtocols") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("desiredTunnelledProtocol") SEQ, 1, 2, 2, STOP | EXT | OPT, 0, + NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, STOP | EXT | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _AdmissionConfirm[] = { /* SEQUENCE */ + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("bandWidth") INT, CONS, 0, 0, SKIP, 0, NULL}, + {FNAME("callModel") CHOICE, 1, 2, 2, SKIP | EXT, 0, _CallModel}, + {FNAME("destCallSignalAddress") CHOICE, 3, 7, 7, DECODE | EXT, + offsetof(AdmissionConfirm, destCallSignalAddress), + _TransportAddress}, + {FNAME("irrFrequency") INT, WORD, 1, 0, STOP | OPT, 0, NULL}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("destinationInfo") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("destExtraCallInfo") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("destinationType") SEQ, 6, 8, 10, STOP | EXT | OPT, 0, NULL}, + {FNAME("remoteExtensionAddress") SEQOF, SEMI, 0, 0, STOP | OPT, 0, + NULL}, + {FNAME("alternateEndpoints") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("transportQOS") CHOICE, 2, 3, 3, STOP | EXT | OPT, 0, NULL}, + {FNAME("willRespondToIRR") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("uuiesRequested") SEQ, 0, 9, 13, STOP | EXT, 0, NULL}, + {FNAME("language") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("alternateTransportAddresses") SEQ, 1, 1, 1, STOP | EXT | OPT, + 0, NULL}, + {FNAME("useSpecifiedTransport") CHOICE, 1, 2, 2, STOP | EXT | OPT, 0, + NULL}, + {FNAME("circuitInfo") SEQ, 3, 3, 3, STOP | EXT | OPT, 0, NULL}, + {FNAME("usageSpec") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("supportedProtocols") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("serviceControl") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("multipleCalls") BOOL, FIXD, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, STOP | EXT | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _LocationRequest_destinationInfo[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 1, 2, 7, SKIP | EXT, 0, _AliasAddress}, +}; + +static field_t _LocationRequest[] = { /* SEQUENCE */ + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("endpointIdentifier") BMPSTR, 7, 1, 0, SKIP | OPT, 0, NULL}, + {FNAME("destinationInfo") SEQOF, SEMI, 0, 0, SKIP, 0, + _LocationRequest_destinationInfo}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("replyAddress") CHOICE, 3, 7, 7, DECODE | EXT, + offsetof(LocationRequest, replyAddress), _TransportAddress}, + {FNAME("sourceInfo") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("canMapAlias") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("gatekeeperIdentifier") BMPSTR, 7, 1, 0, STOP | OPT, 0, NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("desiredProtocols") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("desiredTunnelledProtocol") SEQ, 1, 2, 2, STOP | EXT | OPT, 0, + NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, STOP | EXT | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("hopCount") INT, 8, 1, 0, STOP | OPT, 0, NULL}, + {FNAME("circuitInfo") SEQ, 3, 3, 3, STOP | EXT | OPT, 0, NULL}, +}; + +static field_t _LocationConfirm[] = { /* SEQUENCE */ + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("callSignalAddress") CHOICE, 3, 7, 7, DECODE | EXT, + offsetof(LocationConfirm, callSignalAddress), _TransportAddress}, + {FNAME("rasAddress") CHOICE, 3, 7, 7, DECODE | EXT, + offsetof(LocationConfirm, rasAddress), _TransportAddress}, + {FNAME("nonStandardData") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("destinationInfo") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("destExtraCallInfo") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("destinationType") SEQ, 6, 8, 10, STOP | EXT | OPT, 0, NULL}, + {FNAME("remoteExtensionAddress") SEQOF, SEMI, 0, 0, STOP | OPT, 0, + NULL}, + {FNAME("alternateEndpoints") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("alternateTransportAddresses") SEQ, 1, 1, 1, STOP | EXT | OPT, + 0, NULL}, + {FNAME("supportedProtocols") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("multipleCalls") BOOL, FIXD, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("featureSet") SEQ, 3, 4, 4, STOP | EXT | OPT, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("circuitInfo") SEQ, 3, 3, 3, STOP | EXT | OPT, 0, NULL}, + {FNAME("serviceControl") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _InfoRequestResponse_callSignalAddress[] = { /* SEQUENCE OF */ + {FNAME("item") CHOICE, 3, 7, 7, DECODE | EXT, + sizeof(TransportAddress), _TransportAddress} + , +}; + +static field_t _InfoRequestResponse[] = { /* SEQUENCE */ + {FNAME("nonStandardData") SEQ, 0, 2, 2, SKIP | OPT, 0, + _NonStandardParameter}, + {FNAME("requestSeqNum") INT, WORD, 1, 0, SKIP, 0, NULL}, + {FNAME("endpointType") SEQ, 6, 8, 10, SKIP | EXT, 0, _EndpointType}, + {FNAME("endpointIdentifier") BMPSTR, 7, 1, 0, SKIP, 0, NULL}, + {FNAME("rasAddress") CHOICE, 3, 7, 7, DECODE | EXT, + offsetof(InfoRequestResponse, rasAddress), _TransportAddress}, + {FNAME("callSignalAddress") SEQOF, SEMI, 0, 10, DECODE, + offsetof(InfoRequestResponse, callSignalAddress), + _InfoRequestResponse_callSignalAddress}, + {FNAME("endpointAlias") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("perCallInfo") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("tokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("cryptoTokens") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, + {FNAME("integrityCheckValue") SEQ, 0, 2, 2, STOP | OPT, 0, NULL}, + {FNAME("needResponse") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("capacity") SEQ, 2, 2, 2, STOP | EXT | OPT, 0, NULL}, + {FNAME("irrStatus") CHOICE, 2, 4, 4, STOP | EXT | OPT, 0, NULL}, + {FNAME("unsolicited") BOOL, FIXD, 0, 0, STOP, 0, NULL}, + {FNAME("genericData") SEQOF, SEMI, 0, 0, STOP | OPT, 0, NULL}, +}; + +static field_t _RasMessage[] = { /* CHOICE */ + {FNAME("gatekeeperRequest") SEQ, 4, 8, 18, DECODE | EXT, + offsetof(RasMessage, gatekeeperRequest), _GatekeeperRequest}, + {FNAME("gatekeeperConfirm") SEQ, 2, 5, 14, DECODE | EXT, + offsetof(RasMessage, gatekeeperConfirm), _GatekeeperConfirm}, + {FNAME("gatekeeperReject") SEQ, 2, 5, 11, STOP | EXT, 0, NULL}, + {FNAME("registrationRequest") SEQ, 3, 10, 31, DECODE | EXT, + offsetof(RasMessage, registrationRequest), _RegistrationRequest}, + {FNAME("registrationConfirm") SEQ, 3, 7, 24, DECODE | EXT, + offsetof(RasMessage, registrationConfirm), _RegistrationConfirm}, + {FNAME("registrationReject") SEQ, 2, 5, 11, STOP | EXT, 0, NULL}, + {FNAME("unregistrationRequest") SEQ, 3, 5, 15, DECODE | EXT, + offsetof(RasMessage, unregistrationRequest), _UnregistrationRequest}, + {FNAME("unregistrationConfirm") SEQ, 1, 2, 6, STOP | EXT, 0, NULL}, + {FNAME("unregistrationReject") SEQ, 1, 3, 8, STOP | EXT, 0, NULL}, + {FNAME("admissionRequest") SEQ, 7, 16, 34, DECODE | EXT, + offsetof(RasMessage, admissionRequest), _AdmissionRequest}, + {FNAME("admissionConfirm") SEQ, 2, 6, 27, DECODE | EXT, + offsetof(RasMessage, admissionConfirm), _AdmissionConfirm}, + {FNAME("admissionReject") SEQ, 1, 3, 11, STOP | EXT, 0, NULL}, + {FNAME("bandwidthRequest") SEQ, 2, 7, 18, STOP | EXT, 0, NULL}, + {FNAME("bandwidthConfirm") SEQ, 1, 3, 8, STOP | EXT, 0, NULL}, + {FNAME("bandwidthReject") SEQ, 1, 4, 9, STOP | EXT, 0, NULL}, + {FNAME("disengageRequest") SEQ, 1, 6, 19, STOP | EXT, 0, NULL}, + {FNAME("disengageConfirm") SEQ, 1, 2, 9, STOP | EXT, 0, NULL}, + {FNAME("disengageReject") SEQ, 1, 3, 8, STOP | EXT, 0, NULL}, + {FNAME("locationRequest") SEQ, 2, 5, 17, DECODE | EXT, + offsetof(RasMessage, locationRequest), _LocationRequest}, + {FNAME("locationConfirm") SEQ, 1, 4, 19, DECODE | EXT, + offsetof(RasMessage, locationConfirm), _LocationConfirm}, + {FNAME("locationReject") SEQ, 1, 3, 10, STOP | EXT, 0, NULL}, + {FNAME("infoRequest") SEQ, 2, 4, 15, STOP | EXT, 0, NULL}, + {FNAME("infoRequestResponse") SEQ, 3, 8, 16, DECODE | EXT, + offsetof(RasMessage, infoRequestResponse), _InfoRequestResponse}, + {FNAME("nonStandardMessage") SEQ, 0, 2, 7, STOP | EXT, 0, NULL}, + {FNAME("unknownMessageResponse") SEQ, 0, 1, 5, STOP | EXT, 0, NULL}, + {FNAME("requestInProgress") SEQ, 4, 6, 6, STOP | EXT, 0, NULL}, + {FNAME("resourcesAvailableIndicate") SEQ, 4, 9, 11, STOP | EXT, 0, + NULL}, + {FNAME("resourcesAvailableConfirm") SEQ, 4, 6, 7, STOP | EXT, 0, + NULL}, + {FNAME("infoRequestAck") SEQ, 4, 5, 5, STOP | EXT, 0, NULL}, + {FNAME("infoRequestNak") SEQ, 5, 7, 7, STOP | EXT, 0, NULL}, + {FNAME("serviceControlIndication") SEQ, 8, 10, 10, STOP | EXT, 0, + NULL}, + {FNAME("serviceControlResponse") SEQ, 7, 8, 8, STOP | EXT, 0, NULL}, +}; diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323_types.h b/net/ipv4/netfilter/ip_conntrack_helper_h323_types.h new file mode 100644 index 000000000000..cc98f7aa5abe --- /dev/null +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323_types.h @@ -0,0 +1,938 @@ +/* Generated by Jing Min Zhao's ASN.1 parser, Mar 15 2006 + * + * Copyright (c) 2006 Jing Min Zhao <zhaojingmin@users.sourceforge.net> + * + * This source code is licensed under General Public License version 2. + */ + +typedef struct TransportAddress_ipAddress { /* SEQUENCE */ + int options; /* No use */ + unsigned ip; +} TransportAddress_ipAddress; + +typedef struct TransportAddress { /* CHOICE */ + enum { + eTransportAddress_ipAddress, + eTransportAddress_ipSourceRoute, + eTransportAddress_ipxAddress, + eTransportAddress_ip6Address, + eTransportAddress_netBios, + eTransportAddress_nsap, + eTransportAddress_nonStandardAddress, + } choice; + union { + TransportAddress_ipAddress ipAddress; + }; +} TransportAddress; + +typedef struct DataProtocolCapability { /* CHOICE */ + enum { + eDataProtocolCapability_nonStandard, + eDataProtocolCapability_v14buffered, + eDataProtocolCapability_v42lapm, + eDataProtocolCapability_hdlcFrameTunnelling, + eDataProtocolCapability_h310SeparateVCStack, + eDataProtocolCapability_h310SingleVCStack, + eDataProtocolCapability_transparent, + eDataProtocolCapability_segmentationAndReassembly, + eDataProtocolCapability_hdlcFrameTunnelingwSAR, + eDataProtocolCapability_v120, + eDataProtocolCapability_separateLANStack, + eDataProtocolCapability_v76wCompression, + eDataProtocolCapability_tcp, + eDataProtocolCapability_udp, + } choice; +} DataProtocolCapability; + +typedef struct DataApplicationCapability_application { /* CHOICE */ + enum { + eDataApplicationCapability_application_nonStandard, + eDataApplicationCapability_application_t120, + eDataApplicationCapability_application_dsm_cc, + eDataApplicationCapability_application_userData, + eDataApplicationCapability_application_t84, + eDataApplicationCapability_application_t434, + eDataApplicationCapability_application_h224, + eDataApplicationCapability_application_nlpid, + eDataApplicationCapability_application_dsvdControl, + eDataApplicationCapability_application_h222DataPartitioning, + eDataApplicationCapability_application_t30fax, + eDataApplicationCapability_application_t140, + eDataApplicationCapability_application_t38fax, + eDataApplicationCapability_application_genericDataCapability, + } choice; + union { + DataProtocolCapability t120; + }; +} DataApplicationCapability_application; + +typedef struct DataApplicationCapability { /* SEQUENCE */ + int options; /* No use */ + DataApplicationCapability_application application; +} DataApplicationCapability; + +typedef struct DataType { /* CHOICE */ + enum { + eDataType_nonStandard, + eDataType_nullData, + eDataType_videoData, + eDataType_audioData, + eDataType_data, + eDataType_encryptionData, + eDataType_h235Control, + eDataType_h235Media, + eDataType_multiplexedStream, + } choice; + union { + DataApplicationCapability data; + }; +} DataType; + +typedef struct UnicastAddress_iPAddress { /* SEQUENCE */ + int options; /* No use */ + unsigned network; +} UnicastAddress_iPAddress; + +typedef struct UnicastAddress { /* CHOICE */ + enum { + eUnicastAddress_iPAddress, + eUnicastAddress_iPXAddress, + eUnicastAddress_iP6Address, + eUnicastAddress_netBios, + eUnicastAddress_iPSourceRouteAddress, + eUnicastAddress_nsap, + eUnicastAddress_nonStandardAddress, + } choice; + union { + UnicastAddress_iPAddress iPAddress; + }; +} UnicastAddress; + +typedef struct H245_TransportAddress { /* CHOICE */ + enum { + eH245_TransportAddress_unicastAddress, + eH245_TransportAddress_multicastAddress, + } choice; + union { + UnicastAddress unicastAddress; + }; +} H245_TransportAddress; + +typedef struct H2250LogicalChannelParameters { /* SEQUENCE */ + enum { + eH2250LogicalChannelParameters_nonStandard = (1 << 31), + eH2250LogicalChannelParameters_associatedSessionID = + (1 << 30), + eH2250LogicalChannelParameters_mediaChannel = (1 << 29), + eH2250LogicalChannelParameters_mediaGuaranteedDelivery = + (1 << 28), + eH2250LogicalChannelParameters_mediaControlChannel = + (1 << 27), + eH2250LogicalChannelParameters_mediaControlGuaranteedDelivery + = (1 << 26), + eH2250LogicalChannelParameters_silenceSuppression = (1 << 25), + eH2250LogicalChannelParameters_destination = (1 << 24), + eH2250LogicalChannelParameters_dynamicRTPPayloadType = + (1 << 23), + eH2250LogicalChannelParameters_mediaPacketization = (1 << 22), + eH2250LogicalChannelParameters_transportCapability = + (1 << 21), + eH2250LogicalChannelParameters_redundancyEncoding = (1 << 20), + eH2250LogicalChannelParameters_source = (1 << 19), + } options; + H245_TransportAddress mediaChannel; + H245_TransportAddress mediaControlChannel; +} H2250LogicalChannelParameters; + +typedef struct OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters { /* CHOICE */ + enum { + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h222LogicalChannelParameters, + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h223LogicalChannelParameters, + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_v76LogicalChannelParameters, + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters, + eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_none, + } choice; + union { + H2250LogicalChannelParameters h2250LogicalChannelParameters; + }; +} OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters; + +typedef struct OpenLogicalChannel_forwardLogicalChannelParameters { /* SEQUENCE */ + enum { + eOpenLogicalChannel_forwardLogicalChannelParameters_portNumber + = (1 << 31), + eOpenLogicalChannel_forwardLogicalChannelParameters_forwardLogicalChannelDependency + = (1 << 30), + eOpenLogicalChannel_forwardLogicalChannelParameters_replacementFor + = (1 << 29), + } options; + DataType dataType; + OpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters + multiplexParameters; +} OpenLogicalChannel_forwardLogicalChannelParameters; + +typedef struct OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters { /* CHOICE */ + enum { + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_h223LogicalChannelParameters, + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_v76LogicalChannelParameters, + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters, + } choice; + union { + H2250LogicalChannelParameters h2250LogicalChannelParameters; + }; +} OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters; + +typedef struct OpenLogicalChannel_reverseLogicalChannelParameters { /* SEQUENCE */ + enum { + eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters + = (1 << 31), + eOpenLogicalChannel_reverseLogicalChannelParameters_reverseLogicalChannelDependency + = (1 << 30), + eOpenLogicalChannel_reverseLogicalChannelParameters_replacementFor + = (1 << 29), + } options; + OpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters + multiplexParameters; +} OpenLogicalChannel_reverseLogicalChannelParameters; + +typedef struct NetworkAccessParameters_networkAddress { /* CHOICE */ + enum { + eNetworkAccessParameters_networkAddress_q2931Address, + eNetworkAccessParameters_networkAddress_e164Address, + eNetworkAccessParameters_networkAddress_localAreaAddress, + } choice; + union { + H245_TransportAddress localAreaAddress; + }; +} NetworkAccessParameters_networkAddress; + +typedef struct NetworkAccessParameters { /* SEQUENCE */ + enum { + eNetworkAccessParameters_distribution = (1 << 31), + eNetworkAccessParameters_externalReference = (1 << 30), + eNetworkAccessParameters_t120SetupProcedure = (1 << 29), + } options; + NetworkAccessParameters_networkAddress networkAddress; +} NetworkAccessParameters; + +typedef struct OpenLogicalChannel { /* SEQUENCE */ + enum { + eOpenLogicalChannel_reverseLogicalChannelParameters = + (1 << 31), + eOpenLogicalChannel_separateStack = (1 << 30), + eOpenLogicalChannel_encryptionSync = (1 << 29), + } options; + OpenLogicalChannel_forwardLogicalChannelParameters + forwardLogicalChannelParameters; + OpenLogicalChannel_reverseLogicalChannelParameters + reverseLogicalChannelParameters; + NetworkAccessParameters separateStack; +} OpenLogicalChannel; + +typedef struct Setup_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Setup_UUIE_fastStart; + +typedef struct Setup_UUIE { /* SEQUENCE */ + enum { + eSetup_UUIE_h245Address = (1 << 31), + eSetup_UUIE_sourceAddress = (1 << 30), + eSetup_UUIE_destinationAddress = (1 << 29), + eSetup_UUIE_destCallSignalAddress = (1 << 28), + eSetup_UUIE_destExtraCallInfo = (1 << 27), + eSetup_UUIE_destExtraCRV = (1 << 26), + eSetup_UUIE_callServices = (1 << 25), + eSetup_UUIE_sourceCallSignalAddress = (1 << 24), + eSetup_UUIE_remoteExtensionAddress = (1 << 23), + eSetup_UUIE_callIdentifier = (1 << 22), + eSetup_UUIE_h245SecurityCapability = (1 << 21), + eSetup_UUIE_tokens = (1 << 20), + eSetup_UUIE_cryptoTokens = (1 << 19), + eSetup_UUIE_fastStart = (1 << 18), + eSetup_UUIE_mediaWaitForConnect = (1 << 17), + eSetup_UUIE_canOverlapSend = (1 << 16), + eSetup_UUIE_endpointIdentifier = (1 << 15), + eSetup_UUIE_multipleCalls = (1 << 14), + eSetup_UUIE_maintainConnection = (1 << 13), + eSetup_UUIE_connectionParameters = (1 << 12), + eSetup_UUIE_language = (1 << 11), + eSetup_UUIE_presentationIndicator = (1 << 10), + eSetup_UUIE_screeningIndicator = (1 << 9), + eSetup_UUIE_serviceControl = (1 << 8), + eSetup_UUIE_symmetricOperationRequired = (1 << 7), + eSetup_UUIE_capacity = (1 << 6), + eSetup_UUIE_circuitInfo = (1 << 5), + eSetup_UUIE_desiredProtocols = (1 << 4), + eSetup_UUIE_neededFeatures = (1 << 3), + eSetup_UUIE_desiredFeatures = (1 << 2), + eSetup_UUIE_supportedFeatures = (1 << 1), + eSetup_UUIE_parallelH245Control = (1 << 0), + } options; + TransportAddress h245Address; + TransportAddress destCallSignalAddress; + TransportAddress sourceCallSignalAddress; + Setup_UUIE_fastStart fastStart; +} Setup_UUIE; + +typedef struct CallProceeding_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} CallProceeding_UUIE_fastStart; + +typedef struct CallProceeding_UUIE { /* SEQUENCE */ + enum { + eCallProceeding_UUIE_h245Address = (1 << 31), + eCallProceeding_UUIE_callIdentifier = (1 << 30), + eCallProceeding_UUIE_h245SecurityMode = (1 << 29), + eCallProceeding_UUIE_tokens = (1 << 28), + eCallProceeding_UUIE_cryptoTokens = (1 << 27), + eCallProceeding_UUIE_fastStart = (1 << 26), + eCallProceeding_UUIE_multipleCalls = (1 << 25), + eCallProceeding_UUIE_maintainConnection = (1 << 24), + eCallProceeding_UUIE_fastConnectRefused = (1 << 23), + eCallProceeding_UUIE_featureSet = (1 << 22), + } options; + TransportAddress h245Address; + CallProceeding_UUIE_fastStart fastStart; +} CallProceeding_UUIE; + +typedef struct Connect_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Connect_UUIE_fastStart; + +typedef struct Connect_UUIE { /* SEQUENCE */ + enum { + eConnect_UUIE_h245Address = (1 << 31), + eConnect_UUIE_callIdentifier = (1 << 30), + eConnect_UUIE_h245SecurityMode = (1 << 29), + eConnect_UUIE_tokens = (1 << 28), + eConnect_UUIE_cryptoTokens = (1 << 27), + eConnect_UUIE_fastStart = (1 << 26), + eConnect_UUIE_multipleCalls = (1 << 25), + eConnect_UUIE_maintainConnection = (1 << 24), + eConnect_UUIE_language = (1 << 23), + eConnect_UUIE_connectedAddress = (1 << 22), + eConnect_UUIE_presentationIndicator = (1 << 21), + eConnect_UUIE_screeningIndicator = (1 << 20), + eConnect_UUIE_fastConnectRefused = (1 << 19), + eConnect_UUIE_serviceControl = (1 << 18), + eConnect_UUIE_capacity = (1 << 17), + eConnect_UUIE_featureSet = (1 << 16), + } options; + TransportAddress h245Address; + Connect_UUIE_fastStart fastStart; +} Connect_UUIE; + +typedef struct Alerting_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Alerting_UUIE_fastStart; + +typedef struct Alerting_UUIE { /* SEQUENCE */ + enum { + eAlerting_UUIE_h245Address = (1 << 31), + eAlerting_UUIE_callIdentifier = (1 << 30), + eAlerting_UUIE_h245SecurityMode = (1 << 29), + eAlerting_UUIE_tokens = (1 << 28), + eAlerting_UUIE_cryptoTokens = (1 << 27), + eAlerting_UUIE_fastStart = (1 << 26), + eAlerting_UUIE_multipleCalls = (1 << 25), + eAlerting_UUIE_maintainConnection = (1 << 24), + eAlerting_UUIE_alertingAddress = (1 << 23), + eAlerting_UUIE_presentationIndicator = (1 << 22), + eAlerting_UUIE_screeningIndicator = (1 << 21), + eAlerting_UUIE_fastConnectRefused = (1 << 20), + eAlerting_UUIE_serviceControl = (1 << 19), + eAlerting_UUIE_capacity = (1 << 18), + eAlerting_UUIE_featureSet = (1 << 17), + } options; + TransportAddress h245Address; + Alerting_UUIE_fastStart fastStart; +} Alerting_UUIE; + +typedef struct Information_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Information_UUIE_fastStart; + +typedef struct Information_UUIE { /* SEQUENCE */ + enum { + eInformation_UUIE_callIdentifier = (1 << 31), + eInformation_UUIE_tokens = (1 << 30), + eInformation_UUIE_cryptoTokens = (1 << 29), + eInformation_UUIE_fastStart = (1 << 28), + eInformation_UUIE_fastConnectRefused = (1 << 27), + eInformation_UUIE_circuitInfo = (1 << 26), + } options; + Information_UUIE_fastStart fastStart; +} Information_UUIE; + +typedef struct FacilityReason { /* CHOICE */ + enum { + eFacilityReason_routeCallToGatekeeper, + eFacilityReason_callForwarded, + eFacilityReason_routeCallToMC, + eFacilityReason_undefinedReason, + eFacilityReason_conferenceListChoice, + eFacilityReason_startH245, + eFacilityReason_noH245, + eFacilityReason_newTokens, + eFacilityReason_featureSetUpdate, + eFacilityReason_forwardedElements, + eFacilityReason_transportedInformation, + } choice; +} FacilityReason; + +typedef struct Facility_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Facility_UUIE_fastStart; + +typedef struct Facility_UUIE { /* SEQUENCE */ + enum { + eFacility_UUIE_alternativeAddress = (1 << 31), + eFacility_UUIE_alternativeAliasAddress = (1 << 30), + eFacility_UUIE_conferenceID = (1 << 29), + eFacility_UUIE_callIdentifier = (1 << 28), + eFacility_UUIE_destExtraCallInfo = (1 << 27), + eFacility_UUIE_remoteExtensionAddress = (1 << 26), + eFacility_UUIE_tokens = (1 << 25), + eFacility_UUIE_cryptoTokens = (1 << 24), + eFacility_UUIE_conferences = (1 << 23), + eFacility_UUIE_h245Address = (1 << 22), + eFacility_UUIE_fastStart = (1 << 21), + eFacility_UUIE_multipleCalls = (1 << 20), + eFacility_UUIE_maintainConnection = (1 << 19), + eFacility_UUIE_fastConnectRefused = (1 << 18), + eFacility_UUIE_serviceControl = (1 << 17), + eFacility_UUIE_circuitInfo = (1 << 16), + eFacility_UUIE_featureSet = (1 << 15), + eFacility_UUIE_destinationInfo = (1 << 14), + eFacility_UUIE_h245SecurityMode = (1 << 13), + } options; + FacilityReason reason; + TransportAddress h245Address; + Facility_UUIE_fastStart fastStart; +} Facility_UUIE; + +typedef struct Progress_UUIE_fastStart { /* SEQUENCE OF */ + int count; + OpenLogicalChannel item[30]; +} Progress_UUIE_fastStart; + +typedef struct Progress_UUIE { /* SEQUENCE */ + enum { + eProgress_UUIE_h245Address = (1 << 31), + eProgress_UUIE_h245SecurityMode = (1 << 30), + eProgress_UUIE_tokens = (1 << 29), + eProgress_UUIE_cryptoTokens = (1 << 28), + eProgress_UUIE_fastStart = (1 << 27), + eProgress_UUIE_multipleCalls = (1 << 26), + eProgress_UUIE_maintainConnection = (1 << 25), + eProgress_UUIE_fastConnectRefused = (1 << 24), + } options; + TransportAddress h245Address; + Progress_UUIE_fastStart fastStart; +} Progress_UUIE; + +typedef struct H323_UU_PDU_h323_message_body { /* CHOICE */ + enum { + eH323_UU_PDU_h323_message_body_setup, + eH323_UU_PDU_h323_message_body_callProceeding, + eH323_UU_PDU_h323_message_body_connect, + eH323_UU_PDU_h323_message_body_alerting, + eH323_UU_PDU_h323_message_body_information, + eH323_UU_PDU_h323_message_body_releaseComplete, + eH323_UU_PDU_h323_message_body_facility, + eH323_UU_PDU_h323_message_body_progress, + eH323_UU_PDU_h323_message_body_empty, + eH323_UU_PDU_h323_message_body_status, + eH323_UU_PDU_h323_message_body_statusInquiry, + eH323_UU_PDU_h323_message_body_setupAcknowledge, + eH323_UU_PDU_h323_message_body_notify, + } choice; + union { + Setup_UUIE setup; + CallProceeding_UUIE callProceeding; + Connect_UUIE connect; + Alerting_UUIE alerting; + Information_UUIE information; + Facility_UUIE facility; + Progress_UUIE progress; + }; +} H323_UU_PDU_h323_message_body; + +typedef struct RequestMessage { /* CHOICE */ + enum { + eRequestMessage_nonStandard, + eRequestMessage_masterSlaveDetermination, + eRequestMessage_terminalCapabilitySet, + eRequestMessage_openLogicalChannel, + eRequestMessage_closeLogicalChannel, + eRequestMessage_requestChannelClose, + eRequestMessage_multiplexEntrySend, + eRequestMessage_requestMultiplexEntry, + eRequestMessage_requestMode, + eRequestMessage_roundTripDelayRequest, + eRequestMessage_maintenanceLoopRequest, + eRequestMessage_communicationModeRequest, + eRequestMessage_conferenceRequest, + eRequestMessage_multilinkRequest, + eRequestMessage_logicalChannelRateRequest, + } choice; + union { + OpenLogicalChannel openLogicalChannel; + }; +} RequestMessage; + +typedef struct OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters { /* CHOICE */ + enum { + eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters_h222LogicalChannelParameters, + eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters, + } choice; + union { + H2250LogicalChannelParameters h2250LogicalChannelParameters; + }; +} OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters; + +typedef struct OpenLogicalChannelAck_reverseLogicalChannelParameters { /* SEQUENCE */ + enum { + eOpenLogicalChannelAck_reverseLogicalChannelParameters_portNumber + = (1 << 31), + eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters + = (1 << 30), + eOpenLogicalChannelAck_reverseLogicalChannelParameters_replacementFor + = (1 << 29), + } options; + OpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters + multiplexParameters; +} OpenLogicalChannelAck_reverseLogicalChannelParameters; + +typedef struct H2250LogicalChannelAckParameters { /* SEQUENCE */ + enum { + eH2250LogicalChannelAckParameters_nonStandard = (1 << 31), + eH2250LogicalChannelAckParameters_sessionID = (1 << 30), + eH2250LogicalChannelAckParameters_mediaChannel = (1 << 29), + eH2250LogicalChannelAckParameters_mediaControlChannel = + (1 << 28), + eH2250LogicalChannelAckParameters_dynamicRTPPayloadType = + (1 << 27), + eH2250LogicalChannelAckParameters_flowControlToZero = + (1 << 26), + eH2250LogicalChannelAckParameters_portNumber = (1 << 25), + } options; + H245_TransportAddress mediaChannel; + H245_TransportAddress mediaControlChannel; +} H2250LogicalChannelAckParameters; + +typedef struct OpenLogicalChannelAck_forwardMultiplexAckParameters { /* CHOICE */ + enum { + eOpenLogicalChannelAck_forwardMultiplexAckParameters_h2250LogicalChannelAckParameters, + } choice; + union { + H2250LogicalChannelAckParameters + h2250LogicalChannelAckParameters; + }; +} OpenLogicalChannelAck_forwardMultiplexAckParameters; + +typedef struct OpenLogicalChannelAck { /* SEQUENCE */ + enum { + eOpenLogicalChannelAck_reverseLogicalChannelParameters = + (1 << 31), + eOpenLogicalChannelAck_separateStack = (1 << 30), + eOpenLogicalChannelAck_forwardMultiplexAckParameters = + (1 << 29), + eOpenLogicalChannelAck_encryptionSync = (1 << 28), + } options; + OpenLogicalChannelAck_reverseLogicalChannelParameters + reverseLogicalChannelParameters; + OpenLogicalChannelAck_forwardMultiplexAckParameters + forwardMultiplexAckParameters; +} OpenLogicalChannelAck; + +typedef struct ResponseMessage { /* CHOICE */ + enum { + eResponseMessage_nonStandard, + eResponseMessage_masterSlaveDeterminationAck, + eResponseMessage_masterSlaveDeterminationReject, + eResponseMessage_terminalCapabilitySetAck, + eResponseMessage_terminalCapabilitySetReject, + eResponseMessage_openLogicalChannelAck, + eResponseMessage_openLogicalChannelReject, + eResponseMessage_closeLogicalChannelAck, + eResponseMessage_requestChannelCloseAck, + eResponseMessage_requestChannelCloseReject, + eResponseMessage_multiplexEntrySendAck, + eResponseMessage_multiplexEntrySendReject, + eResponseMessage_requestMultiplexEntryAck, + eResponseMessage_requestMultiplexEntryReject, + eResponseMessage_requestModeAck, + eResponseMessage_requestModeReject, + eResponseMessage_roundTripDelayResponse, + eResponseMessage_maintenanceLoopAck, + eResponseMessage_maintenanceLoopReject, + eResponseMessage_communicationModeResponse, + eResponseMessage_conferenceResponse, + eResponseMessage_multilinkResponse, + eResponseMessage_logicalChannelRateAcknowledge, + eResponseMessage_logicalChannelRateReject, + } choice; + union { + OpenLogicalChannelAck openLogicalChannelAck; + }; +} ResponseMessage; + +typedef struct MultimediaSystemControlMessage { /* CHOICE */ + enum { + eMultimediaSystemControlMessage_request, + eMultimediaSystemControlMessage_response, + eMultimediaSystemControlMessage_command, + eMultimediaSystemControlMessage_indication, + } choice; + union { + RequestMessage request; + ResponseMessage response; + }; +} MultimediaSystemControlMessage; + +typedef struct H323_UU_PDU_h245Control { /* SEQUENCE OF */ + int count; + MultimediaSystemControlMessage item[4]; +} H323_UU_PDU_h245Control; + +typedef struct H323_UU_PDU { /* SEQUENCE */ + enum { + eH323_UU_PDU_nonStandardData = (1 << 31), + eH323_UU_PDU_h4501SupplementaryService = (1 << 30), + eH323_UU_PDU_h245Tunneling = (1 << 29), + eH323_UU_PDU_h245Control = (1 << 28), + eH323_UU_PDU_nonStandardControl = (1 << 27), + eH323_UU_PDU_callLinkage = (1 << 26), + eH323_UU_PDU_tunnelledSignallingMessage = (1 << 25), + eH323_UU_PDU_provisionalRespToH245Tunneling = (1 << 24), + eH323_UU_PDU_stimulusControl = (1 << 23), + eH323_UU_PDU_genericData = (1 << 22), + } options; + H323_UU_PDU_h323_message_body h323_message_body; + H323_UU_PDU_h245Control h245Control; +} H323_UU_PDU; + +typedef struct H323_UserInformation { /* SEQUENCE */ + enum { + eH323_UserInformation_user_data = (1 << 31), + } options; + H323_UU_PDU h323_uu_pdu; +} H323_UserInformation; + +typedef struct GatekeeperRequest { /* SEQUENCE */ + enum { + eGatekeeperRequest_nonStandardData = (1 << 31), + eGatekeeperRequest_gatekeeperIdentifier = (1 << 30), + eGatekeeperRequest_callServices = (1 << 29), + eGatekeeperRequest_endpointAlias = (1 << 28), + eGatekeeperRequest_alternateEndpoints = (1 << 27), + eGatekeeperRequest_tokens = (1 << 26), + eGatekeeperRequest_cryptoTokens = (1 << 25), + eGatekeeperRequest_authenticationCapability = (1 << 24), + eGatekeeperRequest_algorithmOIDs = (1 << 23), + eGatekeeperRequest_integrity = (1 << 22), + eGatekeeperRequest_integrityCheckValue = (1 << 21), + eGatekeeperRequest_supportsAltGK = (1 << 20), + eGatekeeperRequest_featureSet = (1 << 19), + eGatekeeperRequest_genericData = (1 << 18), + } options; + TransportAddress rasAddress; +} GatekeeperRequest; + +typedef struct GatekeeperConfirm { /* SEQUENCE */ + enum { + eGatekeeperConfirm_nonStandardData = (1 << 31), + eGatekeeperConfirm_gatekeeperIdentifier = (1 << 30), + eGatekeeperConfirm_alternateGatekeeper = (1 << 29), + eGatekeeperConfirm_authenticationMode = (1 << 28), + eGatekeeperConfirm_tokens = (1 << 27), + eGatekeeperConfirm_cryptoTokens = (1 << 26), + eGatekeeperConfirm_algorithmOID = (1 << 25), + eGatekeeperConfirm_integrity = (1 << 24), + eGatekeeperConfirm_integrityCheckValue = (1 << 23), + eGatekeeperConfirm_featureSet = (1 << 22), + eGatekeeperConfirm_genericData = (1 << 21), + } options; + TransportAddress rasAddress; +} GatekeeperConfirm; + +typedef struct RegistrationRequest_callSignalAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} RegistrationRequest_callSignalAddress; + +typedef struct RegistrationRequest_rasAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} RegistrationRequest_rasAddress; + +typedef struct RegistrationRequest { /* SEQUENCE */ + enum { + eRegistrationRequest_nonStandardData = (1 << 31), + eRegistrationRequest_terminalAlias = (1 << 30), + eRegistrationRequest_gatekeeperIdentifier = (1 << 29), + eRegistrationRequest_alternateEndpoints = (1 << 28), + eRegistrationRequest_timeToLive = (1 << 27), + eRegistrationRequest_tokens = (1 << 26), + eRegistrationRequest_cryptoTokens = (1 << 25), + eRegistrationRequest_integrityCheckValue = (1 << 24), + eRegistrationRequest_keepAlive = (1 << 23), + eRegistrationRequest_endpointIdentifier = (1 << 22), + eRegistrationRequest_willSupplyUUIEs = (1 << 21), + eRegistrationRequest_maintainConnection = (1 << 20), + eRegistrationRequest_alternateTransportAddresses = (1 << 19), + eRegistrationRequest_additiveRegistration = (1 << 18), + eRegistrationRequest_terminalAliasPattern = (1 << 17), + eRegistrationRequest_supportsAltGK = (1 << 16), + eRegistrationRequest_usageReportingCapability = (1 << 15), + eRegistrationRequest_multipleCalls = (1 << 14), + eRegistrationRequest_supportedH248Packages = (1 << 13), + eRegistrationRequest_callCreditCapability = (1 << 12), + eRegistrationRequest_capacityReportingCapability = (1 << 11), + eRegistrationRequest_capacity = (1 << 10), + eRegistrationRequest_featureSet = (1 << 9), + eRegistrationRequest_genericData = (1 << 8), + } options; + RegistrationRequest_callSignalAddress callSignalAddress; + RegistrationRequest_rasAddress rasAddress; + unsigned timeToLive; +} RegistrationRequest; + +typedef struct RegistrationConfirm_callSignalAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} RegistrationConfirm_callSignalAddress; + +typedef struct RegistrationConfirm { /* SEQUENCE */ + enum { + eRegistrationConfirm_nonStandardData = (1 << 31), + eRegistrationConfirm_terminalAlias = (1 << 30), + eRegistrationConfirm_gatekeeperIdentifier = (1 << 29), + eRegistrationConfirm_alternateGatekeeper = (1 << 28), + eRegistrationConfirm_timeToLive = (1 << 27), + eRegistrationConfirm_tokens = (1 << 26), + eRegistrationConfirm_cryptoTokens = (1 << 25), + eRegistrationConfirm_integrityCheckValue = (1 << 24), + eRegistrationConfirm_willRespondToIRR = (1 << 23), + eRegistrationConfirm_preGrantedARQ = (1 << 22), + eRegistrationConfirm_maintainConnection = (1 << 21), + eRegistrationConfirm_serviceControl = (1 << 20), + eRegistrationConfirm_supportsAdditiveRegistration = (1 << 19), + eRegistrationConfirm_terminalAliasPattern = (1 << 18), + eRegistrationConfirm_supportedPrefixes = (1 << 17), + eRegistrationConfirm_usageSpec = (1 << 16), + eRegistrationConfirm_featureServerAlias = (1 << 15), + eRegistrationConfirm_capacityReportingSpec = (1 << 14), + eRegistrationConfirm_featureSet = (1 << 13), + eRegistrationConfirm_genericData = (1 << 12), + } options; + RegistrationConfirm_callSignalAddress callSignalAddress; + unsigned timeToLive; +} RegistrationConfirm; + +typedef struct UnregistrationRequest_callSignalAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} UnregistrationRequest_callSignalAddress; + +typedef struct UnregistrationRequest { /* SEQUENCE */ + enum { + eUnregistrationRequest_endpointAlias = (1 << 31), + eUnregistrationRequest_nonStandardData = (1 << 30), + eUnregistrationRequest_endpointIdentifier = (1 << 29), + eUnregistrationRequest_alternateEndpoints = (1 << 28), + eUnregistrationRequest_gatekeeperIdentifier = (1 << 27), + eUnregistrationRequest_tokens = (1 << 26), + eUnregistrationRequest_cryptoTokens = (1 << 25), + eUnregistrationRequest_integrityCheckValue = (1 << 24), + eUnregistrationRequest_reason = (1 << 23), + eUnregistrationRequest_endpointAliasPattern = (1 << 22), + eUnregistrationRequest_supportedPrefixes = (1 << 21), + eUnregistrationRequest_alternateGatekeeper = (1 << 20), + eUnregistrationRequest_genericData = (1 << 19), + } options; + UnregistrationRequest_callSignalAddress callSignalAddress; +} UnregistrationRequest; + +typedef struct AdmissionRequest { /* SEQUENCE */ + enum { + eAdmissionRequest_callModel = (1 << 31), + eAdmissionRequest_destinationInfo = (1 << 30), + eAdmissionRequest_destCallSignalAddress = (1 << 29), + eAdmissionRequest_destExtraCallInfo = (1 << 28), + eAdmissionRequest_srcCallSignalAddress = (1 << 27), + eAdmissionRequest_nonStandardData = (1 << 26), + eAdmissionRequest_callServices = (1 << 25), + eAdmissionRequest_canMapAlias = (1 << 24), + eAdmissionRequest_callIdentifier = (1 << 23), + eAdmissionRequest_srcAlternatives = (1 << 22), + eAdmissionRequest_destAlternatives = (1 << 21), + eAdmissionRequest_gatekeeperIdentifier = (1 << 20), + eAdmissionRequest_tokens = (1 << 19), + eAdmissionRequest_cryptoTokens = (1 << 18), + eAdmissionRequest_integrityCheckValue = (1 << 17), + eAdmissionRequest_transportQOS = (1 << 16), + eAdmissionRequest_willSupplyUUIEs = (1 << 15), + eAdmissionRequest_callLinkage = (1 << 14), + eAdmissionRequest_gatewayDataRate = (1 << 13), + eAdmissionRequest_capacity = (1 << 12), + eAdmissionRequest_circuitInfo = (1 << 11), + eAdmissionRequest_desiredProtocols = (1 << 10), + eAdmissionRequest_desiredTunnelledProtocol = (1 << 9), + eAdmissionRequest_featureSet = (1 << 8), + eAdmissionRequest_genericData = (1 << 7), + } options; + TransportAddress destCallSignalAddress; + TransportAddress srcCallSignalAddress; +} AdmissionRequest; + +typedef struct AdmissionConfirm { /* SEQUENCE */ + enum { + eAdmissionConfirm_irrFrequency = (1 << 31), + eAdmissionConfirm_nonStandardData = (1 << 30), + eAdmissionConfirm_destinationInfo = (1 << 29), + eAdmissionConfirm_destExtraCallInfo = (1 << 28), + eAdmissionConfirm_destinationType = (1 << 27), + eAdmissionConfirm_remoteExtensionAddress = (1 << 26), + eAdmissionConfirm_alternateEndpoints = (1 << 25), + eAdmissionConfirm_tokens = (1 << 24), + eAdmissionConfirm_cryptoTokens = (1 << 23), + eAdmissionConfirm_integrityCheckValue = (1 << 22), + eAdmissionConfirm_transportQOS = (1 << 21), + eAdmissionConfirm_willRespondToIRR = (1 << 20), + eAdmissionConfirm_uuiesRequested = (1 << 19), + eAdmissionConfirm_language = (1 << 18), + eAdmissionConfirm_alternateTransportAddresses = (1 << 17), + eAdmissionConfirm_useSpecifiedTransport = (1 << 16), + eAdmissionConfirm_circuitInfo = (1 << 15), + eAdmissionConfirm_usageSpec = (1 << 14), + eAdmissionConfirm_supportedProtocols = (1 << 13), + eAdmissionConfirm_serviceControl = (1 << 12), + eAdmissionConfirm_multipleCalls = (1 << 11), + eAdmissionConfirm_featureSet = (1 << 10), + eAdmissionConfirm_genericData = (1 << 9), + } options; + TransportAddress destCallSignalAddress; +} AdmissionConfirm; + +typedef struct LocationRequest { /* SEQUENCE */ + enum { + eLocationRequest_endpointIdentifier = (1 << 31), + eLocationRequest_nonStandardData = (1 << 30), + eLocationRequest_sourceInfo = (1 << 29), + eLocationRequest_canMapAlias = (1 << 28), + eLocationRequest_gatekeeperIdentifier = (1 << 27), + eLocationRequest_tokens = (1 << 26), + eLocationRequest_cryptoTokens = (1 << 25), + eLocationRequest_integrityCheckValue = (1 << 24), + eLocationRequest_desiredProtocols = (1 << 23), + eLocationRequest_desiredTunnelledProtocol = (1 << 22), + eLocationRequest_featureSet = (1 << 21), + eLocationRequest_genericData = (1 << 20), + eLocationRequest_hopCount = (1 << 19), + eLocationRequest_circuitInfo = (1 << 18), + } options; + TransportAddress replyAddress; +} LocationRequest; + +typedef struct LocationConfirm { /* SEQUENCE */ + enum { + eLocationConfirm_nonStandardData = (1 << 31), + eLocationConfirm_destinationInfo = (1 << 30), + eLocationConfirm_destExtraCallInfo = (1 << 29), + eLocationConfirm_destinationType = (1 << 28), + eLocationConfirm_remoteExtensionAddress = (1 << 27), + eLocationConfirm_alternateEndpoints = (1 << 26), + eLocationConfirm_tokens = (1 << 25), + eLocationConfirm_cryptoTokens = (1 << 24), + eLocationConfirm_integrityCheckValue = (1 << 23), + eLocationConfirm_alternateTransportAddresses = (1 << 22), + eLocationConfirm_supportedProtocols = (1 << 21), + eLocationConfirm_multipleCalls = (1 << 20), + eLocationConfirm_featureSet = (1 << 19), + eLocationConfirm_genericData = (1 << 18), + eLocationConfirm_circuitInfo = (1 << 17), + eLocationConfirm_serviceControl = (1 << 16), + } options; + TransportAddress callSignalAddress; + TransportAddress rasAddress; +} LocationConfirm; + +typedef struct InfoRequestResponse_callSignalAddress { /* SEQUENCE OF */ + int count; + TransportAddress item[10]; +} InfoRequestResponse_callSignalAddress; + +typedef struct InfoRequestResponse { /* SEQUENCE */ + enum { + eInfoRequestResponse_nonStandardData = (1 << 31), + eInfoRequestResponse_endpointAlias = (1 << 30), + eInfoRequestResponse_perCallInfo = (1 << 29), + eInfoRequestResponse_tokens = (1 << 28), + eInfoRequestResponse_cryptoTokens = (1 << 27), + eInfoRequestResponse_integrityCheckValue = (1 << 26), + eInfoRequestResponse_needResponse = (1 << 25), + eInfoRequestResponse_capacity = (1 << 24), + eInfoRequestResponse_irrStatus = (1 << 23), + eInfoRequestResponse_unsolicited = (1 << 22), + eInfoRequestResponse_genericData = (1 << 21), + } options; + TransportAddress rasAddress; + InfoRequestResponse_callSignalAddress callSignalAddress; +} InfoRequestResponse; + +typedef struct RasMessage { /* CHOICE */ + enum { + eRasMessage_gatekeeperRequest, + eRasMessage_gatekeeperConfirm, + eRasMessage_gatekeeperReject, + eRasMessage_registrationRequest, + eRasMessage_registrationConfirm, + eRasMessage_registrationReject, + eRasMessage_unregistrationRequest, + eRasMessage_unregistrationConfirm, + eRasMessage_unregistrationReject, + eRasMessage_admissionRequest, + eRasMessage_admissionConfirm, + eRasMessage_admissionReject, + eRasMessage_bandwidthRequest, + eRasMessage_bandwidthConfirm, + eRasMessage_bandwidthReject, + eRasMessage_disengageRequest, + eRasMessage_disengageConfirm, + eRasMessage_disengageReject, + eRasMessage_locationRequest, + eRasMessage_locationConfirm, + eRasMessage_locationReject, + eRasMessage_infoRequest, + eRasMessage_infoRequestResponse, + eRasMessage_nonStandardMessage, + eRasMessage_unknownMessageResponse, + eRasMessage_requestInProgress, + eRasMessage_resourcesAvailableIndicate, + eRasMessage_resourcesAvailableConfirm, + eRasMessage_infoRequestAck, + eRasMessage_infoRequestNak, + eRasMessage_serviceControlIndication, + eRasMessage_serviceControlResponse, + } choice; + union { + GatekeeperRequest gatekeeperRequest; + GatekeeperConfirm gatekeeperConfirm; + RegistrationRequest registrationRequest; + RegistrationConfirm registrationConfirm; + UnregistrationRequest unregistrationRequest; + AdmissionRequest admissionRequest; + AdmissionConfirm admissionConfirm; + LocationRequest locationRequest; + LocationConfirm locationConfirm; + InfoRequestResponse infoRequestResponse; + }; +} RasMessage; diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c index e0b5926c76f9..5ce2e3fc2c7f 100644 --- a/net/ipv4/netfilter/ip_conntrack_netlink.c +++ b/net/ipv4/netfilter/ip_conntrack_netlink.c @@ -327,9 +327,10 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, group = NFNLGRP_CONNTRACK_UPDATE; } else return NOTIFY_DONE; - - /* FIXME: Check if there are any listeners before, don't hurt performance */ - + + if (!nfnetlink_has_listeners(group)) + return NOTIFY_DONE; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb) return NOTIFY_DONE; diff --git a/net/ipv4/netfilter/ip_nat_helper_h323.c b/net/ipv4/netfilter/ip_nat_helper_h323.c new file mode 100644 index 000000000000..a0bc883928c0 --- /dev/null +++ b/net/ipv4/netfilter/ip_nat_helper_h323.c @@ -0,0 +1,605 @@ +/* + * H.323 extension for NAT alteration. + * + * Copyright (c) 2006 Jing Min Zhao <zhaojingmin@users.sourceforge.net> + * + * This source code is licensed under General Public License version 2. + * + * Based on the 'brute force' H.323 NAT module by + * Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * Changes: + * 2006-02-01 - initial version 0.1 + * + * 2006-02-20 - version 0.2 + * 1. Changed source format to follow kernel conventions + * 2. Deleted some unnecessary structures + * 3. Minor fixes + * + * 2006-03-10 - version 0.3 + * 1. Added support for multiple TPKTs in one packet (suggested by + * Patrick McHardy) + * 2. Added support for non-linear skb (based on Patrick McHardy's patch) + * 3. Eliminated unnecessary return code + * + * 2006-03-15 - version 0.4 + * 1. Added support for T.120 channels + * 2. Added parameter gkrouted_only (suggested by Patrick McHardy) + */ + +#include <linux/module.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/moduleparam.h> +#include <net/tcp.h> +#include <linux/netfilter_ipv4/ip_nat.h> +#include <linux/netfilter_ipv4/ip_nat_helper.h> +#include <linux/netfilter_ipv4/ip_nat_rule.h> +#include <linux/netfilter_ipv4/ip_conntrack_tuple.h> +#include <linux/netfilter_ipv4/ip_conntrack_h323.h> +#include <linux/netfilter_ipv4/ip_conntrack_helper.h> + +#include "ip_conntrack_helper_h323_asn1.h" + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + +extern int get_h245_addr(unsigned char *data, H245_TransportAddress * addr, + u_int32_t * ip, u_int16_t * port); +extern int get_h225_addr(unsigned char *data, TransportAddress * addr, + u_int32_t * ip, u_int16_t * port); +extern void ip_conntrack_h245_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this); +extern void ip_conntrack_q931_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this); +extern int (*set_h245_addr_hook) (struct sk_buff ** pskb, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, + u_int32_t ip, u_int16_t port); +extern int (*set_h225_addr_hook) (struct sk_buff ** pskb, + unsigned char **data, int dataoff, + TransportAddress * addr, + u_int32_t ip, u_int16_t port); +extern int (*set_sig_addr_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress * addr, int count); +extern int (*set_ras_addr_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress * addr, int count); +extern int (*nat_rtp_rtcp_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, + u_int16_t port, u_int16_t rtp_port, + struct ip_conntrack_expect * rtp_exp, + struct ip_conntrack_expect * rtcp_exp); +extern int (*nat_t120_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect * exp); +extern int (*nat_h245_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect * exp); +extern int (*nat_q931_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, TransportAddress * addr, + int idx, u_int16_t port, + struct ip_conntrack_expect * exp); + + +/****************************************************************************/ +static int set_addr(struct sk_buff **pskb, + unsigned char **data, int dataoff, + unsigned int addroff, u_int32_t ip, u_int16_t port) +{ + enum ip_conntrack_info ctinfo; + struct ip_conntrack *ct = ip_conntrack_get(*pskb, &ctinfo); + struct { + u_int32_t ip; + u_int16_t port; + } __attribute__ ((__packed__)) buf; + struct tcphdr _tcph, *th; + + buf.ip = ip; + buf.port = htons(port); + addroff += dataoff; + + if ((*pskb)->nh.iph->protocol == IPPROTO_TCP) { + if (!ip_nat_mangle_tcp_packet(pskb, ct, ctinfo, + addroff, sizeof(buf), + (char *) &buf, sizeof(buf))) { + if (net_ratelimit()) + printk("ip_nat_h323: ip_nat_mangle_tcp_packet" + " error\n"); + return -1; + } + + /* Relocate data pointer */ + th = skb_header_pointer(*pskb, (*pskb)->nh.iph->ihl * 4, + sizeof(_tcph), &_tcph); + if (th == NULL) + return -1; + *data = (*pskb)->data + (*pskb)->nh.iph->ihl * 4 + + th->doff * 4 + dataoff; + } else { + if (!ip_nat_mangle_udp_packet(pskb, ct, ctinfo, + addroff, sizeof(buf), + (char *) &buf, sizeof(buf))) { + if (net_ratelimit()) + printk("ip_nat_h323: ip_nat_mangle_udp_packet" + " error\n"); + return -1; + } + /* ip_nat_mangle_udp_packet uses skb_make_writable() to copy + * or pull everything in a linear buffer, so we can safely + * use the skb pointers now */ + *data = (*pskb)->data + (*pskb)->nh.iph->ihl * 4 + + sizeof(struct udphdr); + } + + return 0; +} + +/****************************************************************************/ +static int set_h225_addr(struct sk_buff **pskb, + unsigned char **data, int dataoff, + TransportAddress * addr, + u_int32_t ip, u_int16_t port) +{ + return set_addr(pskb, data, dataoff, addr->ipAddress.ip, ip, port); +} + +/****************************************************************************/ +static int set_h245_addr(struct sk_buff **pskb, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, + u_int32_t ip, u_int16_t port) +{ + return set_addr(pskb, data, dataoff, + addr->unicastAddress.iPAddress.network, ip, port); +} + +/****************************************************************************/ +static int set_sig_addr(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress * addr, int count) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int dir = CTINFO2DIR(ctinfo); + int i; + u_int32_t ip; + u_int16_t port; + + for (i = 0; i < count; i++) { + if (get_h225_addr(*data, &addr[i], &ip, &port)) { + if (ip == ct->tuplehash[dir].tuple.src.ip && + port == info->sig_port[dir]) { + /* GW->GK */ + + /* Fix for Gnomemeeting */ + if (i > 0 && + get_h225_addr(*data, &addr[0], + &ip, &port) && + (ntohl(ip) & 0xff000000) == 0x7f000000) + i = 0; + + DEBUGP + ("ip_nat_ras: set signal address " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(ip), port, + NIPQUAD(ct->tuplehash[!dir].tuple.dst. + ip), info->sig_port[!dir]); + return set_h225_addr(pskb, data, 0, &addr[i], + ct->tuplehash[!dir]. + tuple.dst.ip, + info->sig_port[!dir]); + } else if (ip == ct->tuplehash[dir].tuple.dst.ip && + port == info->sig_port[dir]) { + /* GK->GW */ + DEBUGP + ("ip_nat_ras: set signal address " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(ip), port, + NIPQUAD(ct->tuplehash[!dir].tuple.src. + ip), info->sig_port[!dir]); + return set_h225_addr(pskb, data, 0, &addr[i], + ct->tuplehash[!dir]. + tuple.src.ip, + info->sig_port[!dir]); + } + } + } + + return 0; +} + +/****************************************************************************/ +static int set_ras_addr(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress * addr, int count) +{ + int dir = CTINFO2DIR(ctinfo); + int i; + u_int32_t ip; + u_int16_t port; + + for (i = 0; i < count; i++) { + if (get_h225_addr(*data, &addr[i], &ip, &port) && + ip == ct->tuplehash[dir].tuple.src.ip && + port == ntohs(ct->tuplehash[dir].tuple.src.u.udp.port)) { + DEBUGP("ip_nat_ras: set rasAddress " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(ip), port, + NIPQUAD(ct->tuplehash[!dir].tuple.dst.ip), + ntohs(ct->tuplehash[!dir].tuple.dst.u.udp. + port)); + return set_h225_addr(pskb, data, 0, &addr[i], + ct->tuplehash[!dir].tuple.dst.ip, + ntohs(ct->tuplehash[!dir].tuple. + dst.u.udp.port)); + } + } + + return 0; +} + +/****************************************************************************/ +static int nat_rtp_rtcp(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, + u_int16_t port, u_int16_t rtp_port, + struct ip_conntrack_expect *rtp_exp, + struct ip_conntrack_expect *rtcp_exp) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int dir = CTINFO2DIR(ctinfo); + int i; + u_int16_t nated_port; + + /* Set expectations for NAT */ + rtp_exp->saved_proto.udp.port = rtp_exp->tuple.dst.u.udp.port; + rtp_exp->expectfn = ip_nat_follow_master; + rtp_exp->dir = !dir; + rtcp_exp->saved_proto.udp.port = rtcp_exp->tuple.dst.u.udp.port; + rtcp_exp->expectfn = ip_nat_follow_master; + rtcp_exp->dir = !dir; + + /* Lookup existing expects */ + for (i = 0; i < H323_RTP_CHANNEL_MAX; i++) { + if (info->rtp_port[i][dir] == rtp_port) { + /* Expected */ + + /* Use allocated ports first. This will refresh + * the expects */ + rtp_exp->tuple.dst.u.udp.port = + htons(info->rtp_port[i][dir]); + rtcp_exp->tuple.dst.u.udp.port = + htons(info->rtp_port[i][dir] + 1); + break; + } else if (info->rtp_port[i][dir] == 0) { + /* Not expected */ + break; + } + } + + /* Run out of expectations */ + if (i >= H323_RTP_CHANNEL_MAX) { + if (net_ratelimit()) + printk("ip_nat_h323: out of expectations\n"); + return 0; + } + + /* Try to get a pair of ports. */ + for (nated_port = ntohs(rtp_exp->tuple.dst.u.udp.port); + nated_port != 0; nated_port += 2) { + rtp_exp->tuple.dst.u.udp.port = htons(nated_port); + if (ip_conntrack_expect_related(rtp_exp) == 0) { + rtcp_exp->tuple.dst.u.udp.port = + htons(nated_port + 1); + if (ip_conntrack_expect_related(rtcp_exp) == 0) + break; + ip_conntrack_unexpect_related(rtp_exp); + } + } + + if (nated_port == 0) { /* No port available */ + if (net_ratelimit()) + printk("ip_nat_h323: out of RTP ports\n"); + return 0; + } + + /* Modify signal */ + if (set_h245_addr(pskb, data, dataoff, addr, + ct->tuplehash[!dir].tuple.dst.ip, + (port & 1) ? nated_port + 1 : nated_port) == 0) { + /* Save ports */ + info->rtp_port[i][dir] = rtp_port; + info->rtp_port[i][!dir] = nated_port; + } else { + ip_conntrack_unexpect_related(rtp_exp); + ip_conntrack_unexpect_related(rtcp_exp); + return -1; + } + + /* Success */ + DEBUGP("ip_nat_h323: expect RTP %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(rtp_exp->tuple.src.ip), + ntohs(rtp_exp->tuple.src.u.udp.port), + NIPQUAD(rtp_exp->tuple.dst.ip), + ntohs(rtp_exp->tuple.dst.u.udp.port)); + DEBUGP("ip_nat_h323: expect RTCP %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(rtcp_exp->tuple.src.ip), + ntohs(rtcp_exp->tuple.src.u.udp.port), + NIPQUAD(rtcp_exp->tuple.dst.ip), + ntohs(rtcp_exp->tuple.dst.u.udp.port)); + + return 0; +} + +/****************************************************************************/ +static int nat_t120(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect *exp) +{ + int dir = CTINFO2DIR(ctinfo); + u_int16_t nated_port = port; + + /* Set expectations for NAT */ + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->expectfn = ip_nat_follow_master; + exp->dir = !dir; + + /* Try to get same port: if not, try to change it. */ + for (; nated_port != 0; nated_port++) { + exp->tuple.dst.u.tcp.port = htons(nated_port); + if (ip_conntrack_expect_related(exp) == 0) + break; + } + + if (nated_port == 0) { /* No port available */ + if (net_ratelimit()) + printk("ip_nat_h323: out of TCP ports\n"); + return 0; + } + + /* Modify signal */ + if (set_h245_addr(pskb, data, dataoff, addr, + ct->tuplehash[!dir].tuple.dst.ip, nated_port) < 0) { + ip_conntrack_unexpect_related(exp); + return -1; + } + + DEBUGP("ip_nat_h323: expect T.120 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), ntohs(exp->tuple.dst.u.tcp.port)); + + return 0; +} + +/**************************************************************************** + * This conntrack expect function replaces ip_conntrack_h245_expect() + * which was set by ip_conntrack_helper_h323.c. It calls both + * ip_nat_follow_master() and ip_conntrack_h245_expect() + ****************************************************************************/ +static void ip_nat_h245_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this) +{ + ip_nat_follow_master(new, this); + ip_conntrack_h245_expect(new, this); +} + +/****************************************************************************/ +static int nat_h245(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect *exp) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int dir = CTINFO2DIR(ctinfo); + u_int16_t nated_port = port; + + /* Set expectations for NAT */ + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->expectfn = ip_nat_h245_expect; + exp->dir = !dir; + + /* Check existing expects */ + if (info->sig_port[dir] == port) + nated_port = info->sig_port[!dir]; + + /* Try to get same port: if not, try to change it. */ + for (; nated_port != 0; nated_port++) { + exp->tuple.dst.u.tcp.port = htons(nated_port); + if (ip_conntrack_expect_related(exp) == 0) + break; + } + + if (nated_port == 0) { /* No port available */ + if (net_ratelimit()) + printk("ip_nat_q931: out of TCP ports\n"); + return 0; + } + + /* Modify signal */ + if (set_h225_addr(pskb, data, dataoff, addr, + ct->tuplehash[!dir].tuple.dst.ip, + nated_port) == 0) { + /* Save ports */ + info->sig_port[dir] = port; + info->sig_port[!dir] = nated_port; + } else { + ip_conntrack_unexpect_related(exp); + return -1; + } + + DEBUGP("ip_nat_q931: expect H.245 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), ntohs(exp->tuple.dst.u.tcp.port)); + + return 0; +} + +/**************************************************************************** + * This conntrack expect function replaces ip_conntrack_q931_expect() + * which was set by ip_conntrack_helper_h323.c. + ****************************************************************************/ +static void ip_nat_q931_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this) +{ + struct ip_nat_range range; + + if (this->tuple.src.ip != 0) { /* Only accept calls from GK */ + ip_nat_follow_master(new, this); + goto out; + } + + /* This must be a fresh one. */ + BUG_ON(new->status & IPS_NAT_DONE_MASK); + + /* Change src to where master sends to */ + range.flags = IP_NAT_RANGE_MAP_IPS; + range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.ip; + + /* hook doesn't matter, but it has to do source manip */ + ip_nat_setup_info(new, &range, NF_IP_POST_ROUTING); + + /* For DST manip, map port here to where it's expected. */ + range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED); + range.min = range.max = this->saved_proto; + range.min_ip = range.max_ip = + new->master->tuplehash[!this->dir].tuple.src.ip; + + /* hook doesn't matter, but it has to do destination manip */ + ip_nat_setup_info(new, &range, NF_IP_PRE_ROUTING); + + out: + ip_conntrack_q931_expect(new, this); +} + +/****************************************************************************/ +static int nat_q931(struct sk_buff **pskb, struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, TransportAddress * addr, int idx, + u_int16_t port, struct ip_conntrack_expect *exp) +{ + struct ip_ct_h323_master *info = &ct->help.ct_h323_info; + int dir = CTINFO2DIR(ctinfo); + u_int16_t nated_port = port; + u_int32_t ip; + + /* Set expectations for NAT */ + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->expectfn = ip_nat_q931_expect; + exp->dir = !dir; + + /* Check existing expects */ + if (info->sig_port[dir] == port) + nated_port = info->sig_port[!dir]; + + /* Try to get same port: if not, try to change it. */ + for (; nated_port != 0; nated_port++) { + exp->tuple.dst.u.tcp.port = htons(nated_port); + if (ip_conntrack_expect_related(exp) == 0) + break; + } + + if (nated_port == 0) { /* No port available */ + if (net_ratelimit()) + printk("ip_nat_ras: out of TCP ports\n"); + return 0; + } + + /* Modify signal */ + if (set_h225_addr(pskb, data, 0, &addr[idx], + ct->tuplehash[!dir].tuple.dst.ip, + nated_port) == 0) { + /* Save ports */ + info->sig_port[dir] = port; + info->sig_port[!dir] = nated_port; + + /* Fix for Gnomemeeting */ + if (idx > 0 && + get_h225_addr(*data, &addr[0], &ip, &port) && + (ntohl(ip) & 0xff000000) == 0x7f000000) { + set_h225_addr_hook(pskb, data, 0, &addr[0], + ct->tuplehash[!dir].tuple.dst.ip, + info->sig_port[!dir]); + } + } else { + ip_conntrack_unexpect_related(exp); + return -1; + } + + /* Success */ + DEBUGP("ip_nat_ras: expect Q.931 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.ip), ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.ip), ntohs(exp->tuple.dst.u.tcp.port)); + + return 0; +} + +/****************************************************************************/ +static int __init init(void) +{ + BUG_ON(set_h245_addr_hook != NULL); + BUG_ON(set_h225_addr_hook != NULL); + BUG_ON(set_sig_addr_hook != NULL); + BUG_ON(set_ras_addr_hook != NULL); + BUG_ON(nat_rtp_rtcp_hook != NULL); + BUG_ON(nat_t120_hook != NULL); + BUG_ON(nat_h245_hook != NULL); + BUG_ON(nat_q931_hook != NULL); + + set_h245_addr_hook = set_h245_addr; + set_h225_addr_hook = set_h225_addr; + set_sig_addr_hook = set_sig_addr; + set_ras_addr_hook = set_ras_addr; + nat_rtp_rtcp_hook = nat_rtp_rtcp; + nat_t120_hook = nat_t120; + nat_h245_hook = nat_h245; + nat_q931_hook = nat_q931; + + DEBUGP("ip_nat_h323: init success\n"); + return 0; +} + +/****************************************************************************/ +static void __exit fini(void) +{ + set_h245_addr_hook = NULL; + set_h225_addr_hook = NULL; + set_sig_addr_hook = NULL; + set_ras_addr_hook = NULL; + nat_rtp_rtcp_hook = NULL; + nat_t120_hook = NULL; + nat_h245_hook = NULL; + nat_q931_hook = NULL; + synchronize_net(); +} + +/****************************************************************************/ +module_init(init); +module_exit(fini); + +MODULE_AUTHOR("Jing Min Zhao <zhaojingmin@users.sourceforge.net>"); +MODULE_DESCRIPTION("H.323 NAT helper"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/ip_nat_helper_pptp.c b/net/ipv4/netfilter/ip_nat_helper_pptp.c index ac004895781a..b9c016c063b8 100644 --- a/net/ipv4/netfilter/ip_nat_helper_pptp.c +++ b/net/ipv4/netfilter/ip_nat_helper_pptp.c @@ -52,6 +52,8 @@ #define IP_NAT_PPTP_VERSION "3.0" +#define REQ_CID(req, off) (*(u_int16_t *)((char *)(req) + (off))) + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>"); MODULE_DESCRIPTION("Netfilter NAT helper module for PPTP"); @@ -198,7 +200,7 @@ pptp_outbound_pkt(struct sk_buff **pskb, /* only OUT_CALL_REQUEST, IN_CALL_REPLY, CALL_CLEAR_REQUEST pass * down to here */ DEBUGP("altering call id from 0x%04x to 0x%04x\n", - ntohs(*(u_int16_t *)pptpReq + cid_off), ntohs(new_callid)); + ntohs(REQ_CID(pptpReq, cid_off)), ntohs(new_callid)); /* mangle packet */ if (ip_nat_mangle_tcp_packet(pskb, ct, ctinfo, @@ -342,7 +344,7 @@ pptp_inbound_pkt(struct sk_buff **pskb, /* mangle packet */ DEBUGP("altering peer call id from 0x%04x to 0x%04x\n", - ntohs(*(u_int16_t *)pptpReq + pcid_off), ntohs(new_pcid)); + ntohs(REQ_CID(pptpReq, pcid_off)), ntohs(new_pcid)); if (ip_nat_mangle_tcp_packet(pskb, ct, ctinfo, pcid_off + sizeof(struct pptp_pkt_hdr) + @@ -353,7 +355,7 @@ pptp_inbound_pkt(struct sk_buff **pskb, if (new_cid) { DEBUGP("altering call id from 0x%04x to 0x%04x\n", - ntohs(*(u_int16_t *)pptpReq + cid_off), ntohs(new_cid)); + ntohs(REQ_CID(pptpReq, cid_off)), ntohs(new_cid)); if (ip_nat_mangle_tcp_packet(pskb, ct, ctinfo, cid_off + sizeof(struct pptp_pkt_hdr) + sizeof(struct PptpControlHeader), diff --git a/net/ipv4/netfilter/ip_nat_rule.c b/net/ipv4/netfilter/ip_nat_rule.c index 1de86282d232..efba8c4e42e0 100644 --- a/net/ipv4/netfilter/ip_nat_rule.c +++ b/net/ipv4/netfilter/ip_nat_rule.c @@ -103,6 +103,7 @@ static unsigned int ipt_snat_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct ipt_target *target, const void *targinfo, void *userinfo) { @@ -145,6 +146,7 @@ static unsigned int ipt_dnat_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct ipt_target *target, const void *targinfo, void *userinfo) { @@ -170,6 +172,7 @@ static unsigned int ipt_dnat_target(struct sk_buff **pskb, static int ipt_snat_checkentry(const char *tablename, const void *entry, + const struct ipt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -181,28 +184,12 @@ static int ipt_snat_checkentry(const char *tablename, printk("SNAT: multiple ranges no longer supported\n"); return 0; } - - if (targinfosize != IPT_ALIGN(sizeof(struct ip_nat_multi_range_compat))) { - DEBUGP("SNAT: Target size %u wrong for %u ranges\n", - targinfosize, mr->rangesize); - return 0; - } - - /* Only allow these for NAT. */ - if (strcmp(tablename, "nat") != 0) { - DEBUGP("SNAT: wrong table %s\n", tablename); - return 0; - } - - if (hook_mask & ~(1 << NF_IP_POST_ROUTING)) { - DEBUGP("SNAT: hook mask 0x%x bad\n", hook_mask); - return 0; - } return 1; } static int ipt_dnat_checkentry(const char *tablename, const void *entry, + const struct ipt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -214,24 +201,6 @@ static int ipt_dnat_checkentry(const char *tablename, printk("DNAT: multiple ranges no longer supported\n"); return 0; } - - if (targinfosize != IPT_ALIGN(sizeof(struct ip_nat_multi_range_compat))) { - DEBUGP("DNAT: Target size %u wrong for %u ranges\n", - targinfosize, mr->rangesize); - return 0; - } - - /* Only allow these for NAT. */ - if (strcmp(tablename, "nat") != 0) { - DEBUGP("DNAT: wrong table %s\n", tablename); - return 0; - } - - if (hook_mask & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_OUT))) { - DEBUGP("DNAT: hook mask 0x%x bad\n", hook_mask); - return 0; - } - return 1; } @@ -299,12 +268,18 @@ int ip_nat_rule_find(struct sk_buff **pskb, static struct ipt_target ipt_snat_reg = { .name = "SNAT", .target = ipt_snat_target, + .targetsize = sizeof(struct ip_nat_multi_range_compat), + .table = "nat", + .hooks = 1 << NF_IP_POST_ROUTING, .checkentry = ipt_snat_checkentry, }; static struct ipt_target ipt_dnat_reg = { .name = "DNAT", .target = ipt_dnat_target, + .targetsize = sizeof(struct ip_nat_multi_range_compat), + .table = "nat", + .hooks = 1 << NF_IP_PRE_ROUTING, .checkentry = ipt_dnat_checkentry, }; diff --git a/net/ipv4/netfilter/ip_nat_snmp_basic.c b/net/ipv4/netfilter/ip_nat_snmp_basic.c index 4f95d477805c..f029da2a60ee 100644 --- a/net/ipv4/netfilter/ip_nat_snmp_basic.c +++ b/net/ipv4/netfilter/ip_nat_snmp_basic.c @@ -250,6 +250,7 @@ static unsigned char asn1_header_decode(struct asn1_ctx *ctx, if (!asn1_id_decode(ctx, cls, con, tag)) return 0; + def = len = 0; if (!asn1_length_decode(ctx, &def, &len)) return 0; @@ -669,7 +670,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, unsigned char *eoc, *end, *p; unsigned long *lp, *id; unsigned long ul; - long l; + long l; *obj = NULL; id = NULL; @@ -699,11 +700,13 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, return 0; } + type = 0; if (!snmp_tag_cls2syntax(tag, cls, &type)) { kfree(id); return 0; } + l = 0; switch (type) { case SNMP_INTEGER: len = sizeof(long); diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index 08f80e2ea2aa..1655866c55b9 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -35,6 +35,7 @@ #include <linux/sysctl.h> #include <linux/proc_fs.h> #include <linux/security.h> +#include <linux/mutex.h> #include <net/sock.h> #include <net/route.h> @@ -61,7 +62,7 @@ static unsigned int queue_dropped = 0; static unsigned int queue_user_dropped = 0; static struct sock *ipqnl; static LIST_HEAD(queue_list); -static DECLARE_MUTEX(ipqnl_sem); +static DEFINE_MUTEX(ipqnl_mutex); static void ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict) @@ -539,7 +540,7 @@ ipq_rcv_sk(struct sock *sk, int len) struct sk_buff *skb; unsigned int qlen; - down(&ipqnl_sem); + mutex_lock(&ipqnl_mutex); for (qlen = skb_queue_len(&sk->sk_receive_queue); qlen; qlen--) { skb = skb_dequeue(&sk->sk_receive_queue); @@ -547,7 +548,7 @@ ipq_rcv_sk(struct sock *sk, int len) kfree_skb(skb); } - up(&ipqnl_sem); + mutex_unlock(&ipqnl_mutex); } static int @@ -708,8 +709,8 @@ cleanup_sysctl: cleanup_ipqnl: sock_release(ipqnl->sk_socket); - down(&ipqnl_sem); - up(&ipqnl_sem); + mutex_lock(&ipqnl_mutex); + mutex_unlock(&ipqnl_mutex); cleanup_netlink_notifier: netlink_unregister_notifier(&ipq_nl_notifier); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 16f47c675fef..39705f9bc154 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -25,7 +25,7 @@ #include <linux/icmp.h> #include <net/ip.h> #include <asm/uaccess.h> -#include <asm/semaphore.h> +#include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/err.h> #include <linux/cpumask.h> @@ -179,6 +179,7 @@ ipt_error(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -197,8 +198,8 @@ int do_match(struct ipt_entry_match *m, int *hotdrop) { /* Stop iteration if it doesn't match */ - if (!m->u.kernel.match->match(skb, in, out, m->data, offset, - skb->nh.iph->ihl*4, hotdrop)) + if (!m->u.kernel.match->match(skb, in, out, m->u.kernel.match, m->data, + offset, skb->nh.iph->ihl*4, hotdrop)) return 1; else return 0; @@ -305,6 +306,7 @@ ipt_do_table(struct sk_buff **pskb, verdict = t->u.kernel.target->target(pskb, in, out, hook, + t->u.kernel.target, t->data, userdata); @@ -464,7 +466,7 @@ cleanup_match(struct ipt_entry_match *m, unsigned int *i) return 1; if (m->u.kernel.match->destroy) - m->u.kernel.match->destroy(m->data, + m->u.kernel.match->destroy(m->u.kernel.match, m->data, m->u.match_size - sizeof(*m)); module_put(m->u.kernel.match->me); return 0; @@ -477,21 +479,12 @@ standard_check(const struct ipt_entry_target *t, struct ipt_standard_target *targ = (void *)t; /* Check standard info. */ - if (t->u.target_size - != IPT_ALIGN(sizeof(struct ipt_standard_target))) { - duprintf("standard_check: target size %u != %u\n", - t->u.target_size, - IPT_ALIGN(sizeof(struct ipt_standard_target))); - return 0; - } - if (targ->verdict >= 0 && targ->verdict > max_offset - sizeof(struct ipt_entry)) { duprintf("ipt_standard_check: bad verdict (%i)\n", targ->verdict); return 0; } - if (targ->verdict < -NF_MAX_VERDICT - 1) { duprintf("ipt_standard_check: bad negative verdict (%i)\n", targ->verdict); @@ -508,6 +501,7 @@ check_match(struct ipt_entry_match *m, unsigned int *i) { struct ipt_match *match; + int ret; match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name, m->u.user.revision), @@ -518,18 +512,27 @@ check_match(struct ipt_entry_match *m, } m->u.kernel.match = match; + ret = xt_check_match(match, AF_INET, m->u.match_size - sizeof(*m), + name, hookmask, ip->proto, + ip->invflags & IPT_INV_PROTO); + if (ret) + goto err; + if (m->u.kernel.match->checkentry - && !m->u.kernel.match->checkentry(name, ip, m->data, + && !m->u.kernel.match->checkentry(name, ip, match, m->data, m->u.match_size - sizeof(*m), hookmask)) { - module_put(m->u.kernel.match->me); duprintf("ip_tables: check failed for `%s'.\n", m->u.kernel.match->name); - return -EINVAL; + ret = -EINVAL; + goto err; } (*i)++; return 0; +err: + module_put(m->u.kernel.match->me); + return ret; } static struct ipt_target ipt_standard_target; @@ -565,26 +568,32 @@ check_entry(struct ipt_entry *e, const char *name, unsigned int size, } t->u.kernel.target = target; + ret = xt_check_target(target, AF_INET, t->u.target_size - sizeof(*t), + name, e->comefrom, e->ip.proto, + e->ip.invflags & IPT_INV_PROTO); + if (ret) + goto err; + if (t->u.kernel.target == &ipt_standard_target) { if (!standard_check(t, size)) { ret = -EINVAL; goto cleanup_matches; } } else if (t->u.kernel.target->checkentry - && !t->u.kernel.target->checkentry(name, e, t->data, + && !t->u.kernel.target->checkentry(name, e, target, t->data, t->u.target_size - sizeof(*t), e->comefrom)) { - module_put(t->u.kernel.target->me); duprintf("ip_tables: check failed for `%s'.\n", t->u.kernel.target->name); ret = -EINVAL; - goto cleanup_matches; + goto err; } (*i)++; return 0; - + err: + module_put(t->u.kernel.target->me); cleanup_matches: IPT_MATCH_ITERATE(e, cleanup_match, &j); return ret; @@ -645,7 +654,7 @@ cleanup_entry(struct ipt_entry *e, unsigned int *i) IPT_MATCH_ITERATE(e, cleanup_match, NULL); t = ipt_get_target(e); if (t->u.kernel.target->destroy) - t->u.kernel.target->destroy(t->data, + t->u.kernel.target->destroy(t->u.kernel.target, t->data, t->u.target_size - sizeof(*t)); module_put(t->u.kernel.target->me); return 0; @@ -1277,6 +1286,7 @@ static int icmp_match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -1310,28 +1320,27 @@ icmp_match(const struct sk_buff *skb, static int icmp_checkentry(const char *tablename, const void *info, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - const struct ipt_ip *ip = info; const struct ipt_icmp *icmpinfo = matchinfo; - /* Must specify proto == ICMP, and no unknown invflags */ - return ip->proto == IPPROTO_ICMP - && !(ip->invflags & IPT_INV_PROTO) - && matchsize == IPT_ALIGN(sizeof(struct ipt_icmp)) - && !(icmpinfo->invflags & ~IPT_ICMP_INV); + /* Must specify no unknown invflags */ + return !(icmpinfo->invflags & ~IPT_ICMP_INV); } /* The built-in targets: standard (NULL) and error. */ static struct ipt_target ipt_standard_target = { .name = IPT_STANDARD_TARGET, + .targetsize = sizeof(int), }; static struct ipt_target ipt_error_target = { .name = IPT_ERROR_TARGET, .target = ipt_error, + .targetsize = IPT_FUNCTION_MAXNAMELEN, }; static struct nf_sockopt_ops ipt_sockopts = { @@ -1346,8 +1355,10 @@ static struct nf_sockopt_ops ipt_sockopts = { static struct ipt_match icmp_matchstruct = { .name = "icmp", - .match = &icmp_match, - .checkentry = &icmp_checkentry, + .match = icmp_match, + .matchsize = sizeof(struct ipt_icmp), + .proto = IPPROTO_ICMP, + .checkentry = icmp_checkentry, }; static int __init init(void) diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index d9bc971f03af..61e11edcd6af 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -311,6 +311,7 @@ target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -380,6 +381,7 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, const void *e_void, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -389,13 +391,6 @@ checkentry(const char *tablename, struct clusterip_config *config; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_clusterip_tgt_info))) { - printk(KERN_WARNING "CLUSTERIP: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_clusterip_tgt_info))); - return 0; - } - if (cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP && cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT && cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT_DPT) { @@ -465,9 +460,10 @@ checkentry(const char *tablename, } /* drop reference count of cluster config when rule is deleted */ -static void destroy(void *matchinfo, unsigned int matchinfosize) +static void destroy(const struct xt_target *target, void *targinfo, + unsigned int targinfosize) { - struct ipt_clusterip_tgt_info *cipinfo = matchinfo; + struct ipt_clusterip_tgt_info *cipinfo = targinfo; /* if no more entries are referencing the config, remove it * from the list and destroy the proc entry */ @@ -476,12 +472,13 @@ static void destroy(void *matchinfo, unsigned int matchinfosize) clusterip_config_put(cipinfo->config); } -static struct ipt_target clusterip_tgt = { - .name = "CLUSTERIP", - .target = &target, - .checkentry = &checkentry, - .destroy = &destroy, - .me = THIS_MODULE +static struct ipt_target clusterip_tgt = { + .name = "CLUSTERIP", + .target = target, + .targetsize = sizeof(struct ipt_clusterip_tgt_info), + .checkentry = checkentry, + .destroy = destroy, + .me = THIS_MODULE }; diff --git a/net/ipv4/netfilter/ipt_DSCP.c b/net/ipv4/netfilter/ipt_DSCP.c index 898cdf79ce18..cfb0b90e598a 100644 --- a/net/ipv4/netfilter/ipt_DSCP.c +++ b/net/ipv4/netfilter/ipt_DSCP.c @@ -29,6 +29,7 @@ target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -58,35 +59,25 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, const void *e_void, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const u_int8_t dscp = ((struct ipt_DSCP_info *)targinfo)->dscp; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_DSCP_info))) { - printk(KERN_WARNING "DSCP: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_DSCP_info))); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "DSCP: can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - if ((dscp > IPT_DSCP_MAX)) { printk(KERN_WARNING "DSCP: dscp %x out of range\n", dscp); return 0; } - return 1; } static struct ipt_target ipt_dscp_reg = { .name = "DSCP", .target = target, + .targetsize = sizeof(struct ipt_DSCP_info), + .table = "mangle", .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 706445426a6d..b9b80f90c84e 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -94,6 +94,7 @@ target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -114,6 +115,7 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, const void *e_void, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -121,18 +123,6 @@ checkentry(const char *tablename, const struct ipt_ECN_info *einfo = (struct ipt_ECN_info *)targinfo; const struct ipt_entry *e = e_void; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_ECN_info))) { - printk(KERN_WARNING "ECN: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_ECN_info))); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "ECN: can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - if (einfo->operation & IPT_ECN_OP_MASK) { printk(KERN_WARNING "ECN: unsupported ECN operation %x\n", einfo->operation); @@ -143,20 +133,20 @@ checkentry(const char *tablename, einfo->ip_ect); return 0; } - if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & IPT_INV_PROTO))) { printk(KERN_WARNING "ECN: cannot use TCP operations on a " "non-tcp rule\n"); return 0; } - return 1; } static struct ipt_target ipt_ecn_reg = { .name = "ECN", .target = target, + .targetsize = sizeof(struct ipt_ECN_info), + .table = "mangle", .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index cc27545ff97f..750d3221b280 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -415,6 +415,7 @@ ipt_log_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -437,35 +438,29 @@ ipt_log_target(struct sk_buff **pskb, static int ipt_log_checkentry(const char *tablename, const void *e, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_log_info *loginfo = targinfo; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_log_info))) { - DEBUGP("LOG: targinfosize %u != %u\n", - targinfosize, IPT_ALIGN(sizeof(struct ipt_log_info))); - return 0; - } - if (loginfo->level >= 8) { DEBUGP("LOG: level %u >= 8\n", loginfo->level); return 0; } - if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { DEBUGP("LOG: prefix term %i\n", loginfo->prefix[sizeof(loginfo->prefix)-1]); return 0; } - return 1; } static struct ipt_target ipt_log_reg = { .name = "LOG", .target = ipt_log_target, + .targetsize = sizeof(struct ipt_log_info), .checkentry = ipt_log_checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 12c56d3343ca..e0c321c3bae5 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -41,25 +41,13 @@ static DEFINE_RWLOCK(masq_lock); static int masquerade_check(const char *tablename, const void *e, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ip_nat_multi_range_compat *mr = targinfo; - if (strcmp(tablename, "nat") != 0) { - DEBUGP("masquerade_check: bad table `%s'.\n", tablename); - return 0; - } - if (targinfosize != IPT_ALIGN(sizeof(*mr))) { - DEBUGP("masquerade_check: size %u != %u.\n", - targinfosize, sizeof(*mr)); - return 0; - } - if (hook_mask & ~(1 << NF_IP_POST_ROUTING)) { - DEBUGP("masquerade_check: bad hooks %x.\n", hook_mask); - return 0; - } if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) { DEBUGP("masquerade_check: bad MAP_IPS.\n"); return 0; @@ -76,6 +64,7 @@ masquerade_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -179,6 +168,9 @@ static struct notifier_block masq_inet_notifier = { static struct ipt_target masquerade = { .name = "MASQUERADE", .target = masquerade_target, + .targetsize = sizeof(struct ip_nat_multi_range_compat), + .table = "nat", + .hooks = 1 << NF_IP_POST_ROUTING, .checkentry = masquerade_check, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index b074467fe67b..fba181c2a426 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -32,25 +32,13 @@ MODULE_DESCRIPTION("iptables 1:1 NAT mapping of IP networks target"); static int check(const char *tablename, const void *e, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ip_nat_multi_range_compat *mr = targinfo; - if (strcmp(tablename, "nat") != 0) { - DEBUGP(MODULENAME":check: bad table `%s'.\n", tablename); - return 0; - } - if (targinfosize != IPT_ALIGN(sizeof(*mr))) { - DEBUGP(MODULENAME":check: size %u.\n", targinfosize); - return 0; - } - if (hook_mask & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_POST_ROUTING) | - (1 << NF_IP_LOCAL_OUT))) { - DEBUGP(MODULENAME":check: bad hooks %x.\n", hook_mask); - return 0; - } if (!(mr->range[0].flags & IP_NAT_RANGE_MAP_IPS)) { DEBUGP(MODULENAME":check: bad MAP_IPS.\n"); return 0; @@ -67,6 +55,7 @@ target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -101,6 +90,10 @@ target(struct sk_buff **pskb, static struct ipt_target target_module = { .name = MODULENAME, .target = target, + .targetsize = sizeof(struct ip_nat_multi_range_compat), + .table = "nat", + .hooks = (1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_POST_ROUTING) | + (1 << NF_IP_LOCAL_OUT), .checkentry = check, .me = THIS_MODULE }; diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index 140be51f2f01..be3da7c4b871 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -34,24 +34,13 @@ MODULE_DESCRIPTION("iptables REDIRECT target module"); static int redirect_check(const char *tablename, const void *e, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ip_nat_multi_range_compat *mr = targinfo; - if (strcmp(tablename, "nat") != 0) { - DEBUGP("redirect_check: bad table `%s'.\n", table); - return 0; - } - if (targinfosize != IPT_ALIGN(sizeof(*mr))) { - DEBUGP("redirect_check: size %u.\n", targinfosize); - return 0; - } - if (hook_mask & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_OUT))) { - DEBUGP("redirect_check: bad hooks %x.\n", hook_mask); - return 0; - } if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) { DEBUGP("redirect_check: bad MAP_IPS.\n"); return 0; @@ -68,6 +57,7 @@ redirect_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -115,6 +105,9 @@ redirect_target(struct sk_buff **pskb, static struct ipt_target redirect_reg = { .name = "REDIRECT", .target = redirect_target, + .targetsize = sizeof(struct ip_nat_multi_range_compat), + .table = "nat", + .hooks = (1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_OUT), .checkentry = redirect_check, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 3eb47aae78c5..9d3b3579f27c 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -154,10 +154,6 @@ static void send_reset(struct sk_buff *oldskb, int hook) /* This packet will not be the same as the other: clear nf fields */ nf_reset(nskb); nskb->nfmark = 0; -#ifdef CONFIG_BRIDGE_NETFILTER - nf_bridge_put(nskb->nf_bridge); - nskb->nf_bridge = NULL; -#endif tcph = (struct tcphdr *)((u_int32_t*)nskb->nh.iph + nskb->nh.iph->ihl); @@ -236,6 +232,7 @@ static unsigned int reject(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -283,6 +280,7 @@ static unsigned int reject(struct sk_buff **pskb, static int check(const char *tablename, const void *e_void, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -290,23 +288,6 @@ static int check(const char *tablename, const struct ipt_reject_info *rejinfo = targinfo; const struct ipt_entry *e = e_void; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_reject_info))) { - DEBUGP("REJECT: targinfosize %u != 0\n", targinfosize); - return 0; - } - - /* Only allow these for packet filtering. */ - if (strcmp(tablename, "filter") != 0) { - DEBUGP("REJECT: bad table `%s'.\n", tablename); - return 0; - } - if ((hook_mask & ~((1 << NF_IP_LOCAL_IN) - | (1 << NF_IP_FORWARD) - | (1 << NF_IP_LOCAL_OUT))) != 0) { - DEBUGP("REJECT: bad hook mask %X\n", hook_mask); - return 0; - } - if (rejinfo->with == IPT_ICMP_ECHOREPLY) { printk("REJECT: ECHOREPLY no longer supported.\n"); return 0; @@ -318,13 +299,16 @@ static int check(const char *tablename, return 0; } } - return 1; } static struct ipt_target ipt_reject_reg = { .name = "REJECT", .target = reject, + .targetsize = sizeof(struct ipt_reject_info), + .table = "filter", + .hooks = (1 << NF_IP_LOCAL_IN) | (1 << NF_IP_FORWARD) | + (1 << NF_IP_LOCAL_OUT), .checkentry = check, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_SAME.c b/net/ipv4/netfilter/ipt_SAME.c index a22de59bba0e..7e2ebc9d945e 100644 --- a/net/ipv4/netfilter/ipt_SAME.c +++ b/net/ipv4/netfilter/ipt_SAME.c @@ -50,6 +50,7 @@ MODULE_DESCRIPTION("iptables special SNAT module for consistent sourceip"); static int same_check(const char *tablename, const void *e, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -59,18 +60,6 @@ same_check(const char *tablename, mr->ipnum = 0; - if (strcmp(tablename, "nat") != 0) { - DEBUGP("same_check: bad table `%s'.\n", tablename); - return 0; - } - if (targinfosize != IPT_ALIGN(sizeof(*mr))) { - DEBUGP("same_check: size %u.\n", targinfosize); - return 0; - } - if (hook_mask & ~(1 << NF_IP_PRE_ROUTING | 1 << NF_IP_POST_ROUTING)) { - DEBUGP("same_check: bad hooks %x.\n", hook_mask); - return 0; - } if (mr->rangesize < 1) { DEBUGP("same_check: need at least one dest range.\n"); return 0; @@ -127,7 +116,7 @@ same_check(const char *tablename, } static void -same_destroy(void *targinfo, +same_destroy(const struct xt_target *target, void *targinfo, unsigned int targinfosize) { struct ipt_same_info *mr = targinfo; @@ -143,6 +132,7 @@ same_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -191,6 +181,9 @@ same_target(struct sk_buff **pskb, static struct ipt_target same_reg = { .name = "SAME", .target = same_target, + .targetsize = sizeof(struct ipt_same_info), + .table = "nat", + .hooks = (1 << NF_IP_PRE_ROUTING | 1 << NF_IP_POST_ROUTING), .checkentry = same_check, .destroy = same_destroy, .me = THIS_MODULE, diff --git a/net/ipv4/netfilter/ipt_TCPMSS.c b/net/ipv4/netfilter/ipt_TCPMSS.c index c122841e182c..c4fc50ec2ddb 100644 --- a/net/ipv4/netfilter/ipt_TCPMSS.c +++ b/net/ipv4/netfilter/ipt_TCPMSS.c @@ -48,6 +48,7 @@ ipt_tcpmss_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -211,6 +212,7 @@ static inline int find_syn_match(const struct ipt_entry_match *m) static int ipt_tcpmss_checkentry(const char *tablename, const void *e_void, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -218,13 +220,6 @@ ipt_tcpmss_checkentry(const char *tablename, const struct ipt_tcpmss_info *tcpmssinfo = targinfo; const struct ipt_entry *e = e_void; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_tcpmss_info))) { - DEBUGP("ipt_tcpmss_checkentry: targinfosize %u != %u\n", - targinfosize, IPT_ALIGN(sizeof(struct ipt_tcpmss_info))); - return 0; - } - - if((tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU) && ((hook_mask & ~((1 << NF_IP_FORWARD) | (1 << NF_IP_LOCAL_OUT) @@ -233,11 +228,8 @@ ipt_tcpmss_checkentry(const char *tablename, return 0; } - if (e->ip.proto == IPPROTO_TCP - && !(e->ip.invflags & IPT_INV_PROTO) - && IPT_MATCH_ITERATE(e, find_syn_match)) + if (IPT_MATCH_ITERATE(e, find_syn_match)) return 1; - printk("TCPMSS: Only works on TCP SYN packets\n"); return 0; } @@ -245,6 +237,8 @@ ipt_tcpmss_checkentry(const char *tablename, static struct ipt_target ipt_tcpmss_reg = { .name = "TCPMSS", .target = ipt_tcpmss_target, + .targetsize = sizeof(struct ipt_tcpmss_info), + .proto = IPPROTO_TCP, .checkentry = ipt_tcpmss_checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_TOS.c b/net/ipv4/netfilter/ipt_TOS.c index 3a44a56db239..9aa7817657f0 100644 --- a/net/ipv4/netfilter/ipt_TOS.c +++ b/net/ipv4/netfilter/ipt_TOS.c @@ -25,6 +25,7 @@ target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -53,24 +54,13 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, const void *e_void, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const u_int8_t tos = ((struct ipt_tos_target_info *)targinfo)->tos; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_tos_target_info))) { - printk(KERN_WARNING "TOS: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_tos_target_info))); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "TOS: can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - if (tos != IPTOS_LOWDELAY && tos != IPTOS_THROUGHPUT && tos != IPTOS_RELIABILITY @@ -79,13 +69,14 @@ checkentry(const char *tablename, printk(KERN_WARNING "TOS: bad tos value %#x\n", tos); return 0; } - return 1; } static struct ipt_target ipt_tos_reg = { .name = "TOS", .target = target, + .targetsize = sizeof(struct ipt_tos_target_info), + .table = "mangle", .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_TTL.c b/net/ipv4/netfilter/ipt_TTL.c index b769eb231970..5009a003d578 100644 --- a/net/ipv4/netfilter/ipt_TTL.c +++ b/net/ipv4/netfilter/ipt_TTL.c @@ -20,9 +20,10 @@ MODULE_DESCRIPTION("IP tables TTL modification module"); MODULE_LICENSE("GPL"); static unsigned int -ipt_ttl_target(struct sk_buff **pskb, const struct net_device *in, - const struct net_device *out, unsigned int hooknum, - const void *targinfo, void *userinfo) +ipt_ttl_target(struct sk_buff **pskb, + const struct net_device *in, const struct net_device *out, + unsigned int hooknum, const struct xt_target *target, + const void *targinfo, void *userinfo) { struct iphdr *iph; const struct ipt_TTL_info *info = targinfo; @@ -67,40 +68,28 @@ ipt_ttl_target(struct sk_buff **pskb, const struct net_device *in, static int ipt_ttl_checkentry(const char *tablename, const void *e, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { struct ipt_TTL_info *info = targinfo; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_TTL_info))) { - printk(KERN_WARNING "ipt_TTL: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_TTL_info))); - return 0; - } - - if (strcmp(tablename, "mangle")) { - printk(KERN_WARNING "ipt_TTL: can only be called from " - "\"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - if (info->mode > IPT_TTL_MAXMODE) { printk(KERN_WARNING "ipt_TTL: invalid or unknown Mode %u\n", info->mode); return 0; } - if ((info->mode != IPT_TTL_SET) && (info->ttl == 0)) return 0; - return 1; } static struct ipt_target ipt_TTL = { .name = "TTL", .target = ipt_ttl_target, + .targetsize = sizeof(struct ipt_TTL_info), + .table = "mangle", .checkentry = ipt_ttl_checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 180a9ea57b69..a82a32ed0e2f 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -303,6 +303,7 @@ static unsigned int ipt_ulog_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { struct ipt_ulog_info *loginfo = (struct ipt_ulog_info *) targinfo; @@ -339,42 +340,37 @@ static void ipt_logfn(unsigned int pf, static int ipt_ulog_checkentry(const char *tablename, const void *e, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hookmask) { struct ipt_ulog_info *loginfo = (struct ipt_ulog_info *) targinfo; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_ulog_info))) { - DEBUGP("ipt_ULOG: targinfosize %u != 0\n", targinfosize); - return 0; - } - if (loginfo->prefix[sizeof(loginfo->prefix) - 1] != '\0') { DEBUGP("ipt_ULOG: prefix term %i\n", loginfo->prefix[sizeof(loginfo->prefix) - 1]); return 0; } - if (loginfo->qthreshold > ULOG_MAX_QLEN) { DEBUGP("ipt_ULOG: queue threshold %i > MAX_QLEN\n", loginfo->qthreshold); return 0; } - return 1; } static struct ipt_target ipt_ulog_reg = { .name = "ULOG", .target = ipt_ulog_target, + .targetsize = sizeof(struct ipt_ulog_info), .checkentry = ipt_ulog_checkentry, .me = THIS_MODULE, }; static struct nf_logger ipt_ulog_logger = { .name = "ipt_ULOG", - .logfn = &ipt_logfn, + .logfn = ipt_logfn, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index d6b83a976518..5fdf85d0efcf 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -27,8 +27,9 @@ static inline int match_type(u_int32_t addr, u_int16_t mask) return !!(mask & (1 << inet_addr_type(addr))); } -static int match(const struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, const void *matchinfo, +static int match(const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, int *hotdrop) { const struct ipt_addrtype_info *info = matchinfo; @@ -43,23 +44,10 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return ret; } -static int checkentry(const char *tablename, const void *ip, - void *matchinfo, unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_addrtype_info))) { - printk(KERN_ERR "ipt_addrtype: invalid size (%u != %Zu)\n", - matchsize, IPT_ALIGN(sizeof(struct ipt_addrtype_info))); - return 0; - } - - return 1; -} - static struct ipt_match addrtype_match = { .name = "addrtype", .match = match, - .checkentry = checkentry, + .matchsize = sizeof(struct ipt_addrtype_info), .me = THIS_MODULE }; diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c index 144adfec13cc..35a21fb1f8e0 100644 --- a/net/ipv4/netfilter/ipt_ah.c +++ b/net/ipv4/netfilter/ipt_ah.c @@ -39,6 +39,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -71,37 +72,27 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *ip_void, + const struct xt_match *match, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ipt_ah *ahinfo = matchinfo; - const struct ipt_ip *ip = ip_void; - /* Must specify proto == AH, and no unknown invflags */ - if (ip->proto != IPPROTO_AH || (ip->invflags & IPT_INV_PROTO)) { - duprintf("ipt_ah: Protocol %u != %u\n", ip->proto, - IPPROTO_AH); - return 0; - } - if (matchinfosize != IPT_ALIGN(sizeof(struct ipt_ah))) { - duprintf("ipt_ah: matchsize %u != %u\n", - matchinfosize, IPT_ALIGN(sizeof(struct ipt_ah))); - return 0; - } + /* Must specify no unknown invflags */ if (ahinfo->invflags & ~IPT_AH_INV_MASK) { - duprintf("ipt_ah: unknown flags %X\n", - ahinfo->invflags); + duprintf("ipt_ah: unknown flags %X\n", ahinfo->invflags); return 0; } - return 1; } static struct ipt_match ah_match = { .name = "ah", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ipt_ah), + .proto = IPPROTO_AH, + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_dscp.c b/net/ipv4/netfilter/ipt_dscp.c index 92063b4f8602..11963c385dea 100644 --- a/net/ipv4/netfilter/ipt_dscp.c +++ b/net/ipv4/netfilter/ipt_dscp.c @@ -19,8 +19,9 @@ MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("iptables DSCP matching module"); MODULE_LICENSE("GPL"); -static int match(const struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, const void *matchinfo, +static int match(const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, int *hotdrop) { const struct ipt_dscp_info *info = matchinfo; @@ -31,20 +32,10 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return ((iph->tos&IPT_DSCP_MASK) == sh_dscp) ^ info->invert; } -static int checkentry(const char *tablename, const void *ip, - void *matchinfo, unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_dscp_info))) - return 0; - - return 1; -} - static struct ipt_match dscp_match = { .name = "dscp", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ipt_dscp_info), .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index e68b0c7981f0..d7e29f6a38d8 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -65,8 +65,9 @@ static inline int match_tcp(const struct sk_buff *skb, return 1; } -static int match(const struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, const void *matchinfo, +static int match(const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, int *hotdrop) { const struct ipt_ecn_info *info = matchinfo; @@ -86,15 +87,13 @@ static int match(const struct sk_buff *skb, const struct net_device *in, } static int checkentry(const char *tablename, const void *ip_void, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { const struct ipt_ecn_info *info = matchinfo; const struct ipt_ip *ip = ip_void; - if (matchsize != IPT_ALIGN(sizeof(struct ipt_ecn_info))) - return 0; - if (info->operation & IPT_ECN_OP_MATCH_MASK) return 0; @@ -113,8 +112,9 @@ static int checkentry(const char *tablename, const void *ip_void, static struct ipt_match ecn_match = { .name = "ecn", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ipt_ecn_info), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_esp.c b/net/ipv4/netfilter/ipt_esp.c index 9de191a8162d..af0d5ec79cb5 100644 --- a/net/ipv4/netfilter/ipt_esp.c +++ b/net/ipv4/netfilter/ipt_esp.c @@ -40,6 +40,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -72,37 +73,27 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *ip_void, + const struct xt_match *match, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ipt_esp *espinfo = matchinfo; - const struct ipt_ip *ip = ip_void; - /* Must specify proto == ESP, and no unknown invflags */ - if (ip->proto != IPPROTO_ESP || (ip->invflags & IPT_INV_PROTO)) { - duprintf("ipt_esp: Protocol %u != %u\n", ip->proto, - IPPROTO_ESP); - return 0; - } - if (matchinfosize != IPT_ALIGN(sizeof(struct ipt_esp))) { - duprintf("ipt_esp: matchsize %u != %u\n", - matchinfosize, IPT_ALIGN(sizeof(struct ipt_esp))); - return 0; - } + /* Must specify no unknown invflags */ if (espinfo->invflags & ~IPT_ESP_INV_MASK) { - duprintf("ipt_esp: unknown flags %X\n", - espinfo->invflags); + duprintf("ipt_esp: unknown flags %X\n", espinfo->invflags); return 0; } - return 1; } static struct ipt_match esp_match = { .name = "esp", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ipt_esp), + .proto = IPPROTO_ESP, + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_hashlimit.c b/net/ipv4/netfilter/ipt_hashlimit.c index 4fe48c1bd5f3..dc1521c5aa81 100644 --- a/net/ipv4/netfilter/ipt_hashlimit.c +++ b/net/ipv4/netfilter/ipt_hashlimit.c @@ -427,6 +427,7 @@ static int hashlimit_match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -506,15 +507,13 @@ hashlimit_match(const struct sk_buff *skb, static int hashlimit_checkentry(const char *tablename, const void *inf, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { struct ipt_hashlimit_info *r = matchinfo; - if (matchsize != IPT_ALIGN(sizeof(struct ipt_hashlimit_info))) - return 0; - /* Check for overflow. */ if (r->cfg.burst == 0 || user2credits(r->cfg.avg * r->cfg.burst) < @@ -558,19 +557,21 @@ hashlimit_checkentry(const char *tablename, } static void -hashlimit_destroy(void *matchinfo, unsigned int matchsize) +hashlimit_destroy(const struct xt_match *match, void *matchinfo, + unsigned int matchsize) { struct ipt_hashlimit_info *r = (struct ipt_hashlimit_info *) matchinfo; htable_put(r->hinfo); } -static struct ipt_match ipt_hashlimit = { - .name = "hashlimit", - .match = hashlimit_match, - .checkentry = hashlimit_checkentry, - .destroy = hashlimit_destroy, - .me = THIS_MODULE +static struct ipt_match ipt_hashlimit = { + .name = "hashlimit", + .match = hashlimit_match, + .matchsize = sizeof(struct ipt_hashlimit_info), + .checkentry = hashlimit_checkentry, + .destroy = hashlimit_destroy, + .me = THIS_MODULE }; /* PROC stuff */ diff --git a/net/ipv4/netfilter/ipt_iprange.c b/net/ipv4/netfilter/ipt_iprange.c index 13fb16fb7892..ae70112f5e06 100644 --- a/net/ipv4/netfilter/ipt_iprange.c +++ b/net/ipv4/netfilter/ipt_iprange.c @@ -27,6 +27,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, int *hotdrop) { @@ -62,27 +63,12 @@ match(const struct sk_buff *skb, return 1; } -static int check(const char *tablename, - const void *inf, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - /* verify size */ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_iprange_info))) - return 0; - - return 1; -} - -static struct ipt_match iprange_match = -{ - .list = { NULL, NULL }, - .name = "iprange", - .match = &match, - .checkentry = &check, - .destroy = NULL, - .me = THIS_MODULE +static struct ipt_match iprange_match = { + .name = "iprange", + .match = match, + .matchsize = sizeof(struct ipt_iprange_info), + .destroy = NULL, + .me = THIS_MODULE }; static int __init init(void) diff --git a/net/ipv4/netfilter/ipt_multiport.c b/net/ipv4/netfilter/ipt_multiport.c index 2d52326553f1..bd07f7c53872 100644 --- a/net/ipv4/netfilter/ipt_multiport.c +++ b/net/ipv4/netfilter/ipt_multiport.c @@ -95,6 +95,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -127,6 +128,7 @@ static int match_v1(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -153,40 +155,19 @@ match_v1(const struct sk_buff *skb, return ports_match_v1(multiinfo, ntohs(pptr[0]), ntohs(pptr[1])); } -/* Called when user tries to insert an entry of this type. */ -static int -checkentry(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - return (matchsize == IPT_ALIGN(sizeof(struct ipt_multiport))); -} - -static int -checkentry_v1(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - return (matchsize == IPT_ALIGN(sizeof(struct ipt_multiport_v1))); -} - static struct ipt_match multiport_match = { .name = "multiport", .revision = 0, - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ipt_multiport), .me = THIS_MODULE, }; static struct ipt_match multiport_match_v1 = { .name = "multiport", .revision = 1, - .match = &match_v1, - .checkentry = &checkentry_v1, + .match = match_v1, + .matchsize = sizeof(struct ipt_multiport_v1), .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_owner.c b/net/ipv4/netfilter/ipt_owner.c index 4843d0c9734f..3900428771f3 100644 --- a/net/ipv4/netfilter/ipt_owner.c +++ b/net/ipv4/netfilter/ipt_owner.c @@ -25,6 +25,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -53,37 +54,27 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { const struct ipt_owner_info *info = matchinfo; - if (hook_mask - & ~((1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_POST_ROUTING))) { - printk("ipt_owner: only valid for LOCAL_OUT or POST_ROUTING.\n"); - return 0; - } - - if (matchsize != IPT_ALIGN(sizeof(struct ipt_owner_info))) { - printk("Matchsize %u != %Zu\n", matchsize, - IPT_ALIGN(sizeof(struct ipt_owner_info))); - return 0; - } - if (info->match & (IPT_OWNER_PID|IPT_OWNER_SID|IPT_OWNER_COMM)) { printk("ipt_owner: pid, sid and command matching " "not supported anymore\n"); return 0; } - return 1; } static struct ipt_match owner_match = { .name = "owner", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ipt_owner_info), + .hooks = (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_POST_ROUTING), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_policy.c b/net/ipv4/netfilter/ipt_policy.c deleted file mode 100644 index 5a7a265280f9..000000000000 --- a/net/ipv4/netfilter/ipt_policy.c +++ /dev/null @@ -1,176 +0,0 @@ -/* IP tables module for matching IPsec policy - * - * Copyright (c) 2004,2005 Patrick McHardy, <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/config.h> -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/init.h> -#include <net/xfrm.h> - -#include <linux/netfilter_ipv4.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_policy.h> - -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_DESCRIPTION("IPtables IPsec policy matching module"); -MODULE_LICENSE("GPL"); - - -static inline int -match_xfrm_state(struct xfrm_state *x, const struct ipt_policy_elem *e) -{ -#define MATCH_ADDR(x,y,z) (!e->match.x || \ - ((e->x.a4.s_addr == (e->y.a4.s_addr & (z))) \ - ^ e->invert.x)) -#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) - - return MATCH_ADDR(saddr, smask, x->props.saddr.a4) && - MATCH_ADDR(daddr, dmask, x->id.daddr.a4) && - MATCH(proto, x->id.proto) && - MATCH(mode, x->props.mode) && - MATCH(spi, x->id.spi) && - MATCH(reqid, x->props.reqid); -} - -static int -match_policy_in(const struct sk_buff *skb, const struct ipt_policy_info *info) -{ - const struct ipt_policy_elem *e; - struct sec_path *sp = skb->sp; - int strict = info->flags & IPT_POLICY_MATCH_STRICT; - int i, pos; - - if (sp == NULL) - return -1; - if (strict && info->len != sp->len) - return 0; - - for (i = sp->len - 1; i >= 0; i--) { - pos = strict ? i - sp->len + 1 : 0; - if (pos >= info->len) - return 0; - e = &info->pol[pos]; - - if (match_xfrm_state(sp->x[i].xvec, e)) { - if (!strict) - return 1; - } else if (strict) - return 0; - } - - return strict ? 1 : 0; -} - -static int -match_policy_out(const struct sk_buff *skb, const struct ipt_policy_info *info) -{ - const struct ipt_policy_elem *e; - struct dst_entry *dst = skb->dst; - int strict = info->flags & IPT_POLICY_MATCH_STRICT; - int i, pos; - - if (dst->xfrm == NULL) - return -1; - - for (i = 0; dst && dst->xfrm; dst = dst->child, i++) { - pos = strict ? i : 0; - if (pos >= info->len) - return 0; - e = &info->pol[pos]; - - if (match_xfrm_state(dst->xfrm, e)) { - if (!strict) - return 1; - } else if (strict) - return 0; - } - - return strict ? i == info->len : 0; -} - -static int match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - const struct ipt_policy_info *info = matchinfo; - int ret; - - if (info->flags & IPT_POLICY_MATCH_IN) - ret = match_policy_in(skb, info); - else - ret = match_policy_out(skb, info); - - if (ret < 0) - ret = info->flags & IPT_POLICY_MATCH_NONE ? 1 : 0; - else if (info->flags & IPT_POLICY_MATCH_NONE) - ret = 0; - - return ret; -} - -static int checkentry(const char *tablename, const void *ip_void, - void *matchinfo, unsigned int matchsize, - unsigned int hook_mask) -{ - struct ipt_policy_info *info = matchinfo; - - if (matchsize != IPT_ALIGN(sizeof(*info))) { - printk(KERN_ERR "ipt_policy: matchsize %u != %zu\n", - matchsize, IPT_ALIGN(sizeof(*info))); - return 0; - } - if (!(info->flags & (IPT_POLICY_MATCH_IN|IPT_POLICY_MATCH_OUT))) { - printk(KERN_ERR "ipt_policy: neither incoming nor " - "outgoing policy selected\n"); - return 0; - } - if (hook_mask & (1 << NF_IP_PRE_ROUTING | 1 << NF_IP_LOCAL_IN) - && info->flags & IPT_POLICY_MATCH_OUT) { - printk(KERN_ERR "ipt_policy: output policy not valid in " - "PRE_ROUTING and INPUT\n"); - return 0; - } - if (hook_mask & (1 << NF_IP_POST_ROUTING | 1 << NF_IP_LOCAL_OUT) - && info->flags & IPT_POLICY_MATCH_IN) { - printk(KERN_ERR "ipt_policy: input policy not valid in " - "POST_ROUTING and OUTPUT\n"); - return 0; - } - if (info->len > IPT_POLICY_MAX_ELEM) { - printk(KERN_ERR "ipt_policy: too many policy elements\n"); - return 0; - } - - return 1; -} - -static struct ipt_match policy_match = { - .name = "policy", - .match = match, - .checkentry = checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_match(&policy_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&policy_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 44611d6d14f5..06792ead1da4 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -102,6 +102,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -318,7 +319,7 @@ static int ip_recent_ctrl(struct file *file, const char __user *input, unsigned skb->nh.iph->daddr = 0; /* Clear ttl since we have no way of knowing it */ skb->nh.iph->ttl = 0; - match(skb,NULL,NULL,info,0,0,NULL); + match(skb,NULL,NULL,NULL,info,0,0,NULL); kfree(skb->nh.iph); out_free_skb: @@ -356,6 +357,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -657,6 +659,7 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) @@ -670,8 +673,6 @@ checkentry(const char *tablename, if(debug) printk(KERN_INFO RECENT_NAME ": checkentry() entered.\n"); #endif - if (matchsize != IPT_ALIGN(sizeof(struct ipt_recent_info))) return 0; - /* seconds and hit_count only valid for CHECK/UPDATE */ if(info->check_set & IPT_RECENT_SET) { flag++; if(info->seconds || info->hit_count) return 0; } if(info->check_set & IPT_RECENT_REMOVE) { flag++; if(info->seconds || info->hit_count) return 0; } @@ -871,7 +872,7 @@ checkentry(const char *tablename, * up its memory. */ static void -destroy(void *matchinfo, unsigned int matchsize) +destroy(const struct xt_match *match, void *matchinfo, unsigned int matchsize) { const struct ipt_recent_info *info = matchinfo; struct recent_ip_tables *curr_table, *last_table; @@ -951,12 +952,13 @@ destroy(void *matchinfo, unsigned int matchsize) /* This is the structure we pass to ipt_register to register our * module with iptables. */ -static struct ipt_match recent_match = { - .name = "recent", - .match = &match, - .checkentry = &checkentry, - .destroy = &destroy, - .me = THIS_MODULE +static struct ipt_match recent_match = { + .name = "recent", + .match = match, + .matchsize = sizeof(struct ipt_recent_info), + .checkentry = checkentry, + .destroy = destroy, + .me = THIS_MODULE }; /* Kernel module initialization. */ diff --git a/net/ipv4/netfilter/ipt_tos.c b/net/ipv4/netfilter/ipt_tos.c index 9ab765e126f2..e404e92ddd01 100644 --- a/net/ipv4/netfilter/ipt_tos.c +++ b/net/ipv4/netfilter/ipt_tos.c @@ -21,6 +21,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -31,23 +32,10 @@ match(const struct sk_buff *skb, return (skb->nh.iph->tos == info->tos) ^ info->invert; } -static int -checkentry(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_tos_info))) - return 0; - - return 1; -} - static struct ipt_match tos_match = { .name = "tos", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ipt_tos_info), .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/ipt_ttl.c b/net/ipv4/netfilter/ipt_ttl.c index 82da53f430ab..ae7ce4d8d90e 100644 --- a/net/ipv4/netfilter/ipt_ttl.c +++ b/net/ipv4/netfilter/ipt_ttl.c @@ -19,8 +19,9 @@ MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("IP tables TTL matching module"); MODULE_LICENSE("GPL"); -static int match(const struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, const void *matchinfo, +static int match(const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, int *hotdrop) { const struct ipt_ttl_info *info = matchinfo; @@ -47,20 +48,10 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return 0; } -static int checkentry(const char *tablename, const void *ip, - void *matchinfo, unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_ttl_info))) - return 0; - - return 1; -} - static struct ipt_match ttl_match = { .name = "ttl", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ipt_ttl_info), .me = THIS_MODULE, }; diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 6c8624a54933..cb9c661f3f33 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -141,19 +141,21 @@ static unsigned int ipv4_conntrack_help(unsigned int hooknum, { struct nf_conn *ct; enum ip_conntrack_info ctinfo; + struct nf_conn_help *help; /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(*pskb, &ctinfo); - if (ct && ct->helper) { - unsigned int ret; - ret = ct->helper->help(pskb, - (*pskb)->nh.raw - (*pskb)->data - + (*pskb)->nh.iph->ihl*4, - ct, ctinfo); - if (ret != NF_ACCEPT) - return ret; - } - return NF_ACCEPT; + if (!ct) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help || !help->helper) + return NF_ACCEPT; + + return help->helper->help(pskb, + (*pskb)->nh.raw - (*pskb)->data + + (*pskb)->nh.iph->ihl*4, + ct, ctinfo); } static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index f29a12da5109..fc2562415555 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -660,12 +660,9 @@ static int raw_geticmpfilter(struct sock *sk, char __user *optval, int __user *o out: return ret; } -static int raw_setsockopt(struct sock *sk, int level, int optname, +static int do_raw_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) { - if (level != SOL_RAW) - return ip_setsockopt(sk, level, optname, optval, optlen); - if (optname == ICMP_FILTER) { if (inet_sk(sk)->num != IPPROTO_ICMP) return -EOPNOTSUPP; @@ -675,12 +672,27 @@ static int raw_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; } -static int raw_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) +static int raw_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) { if (level != SOL_RAW) - return ip_getsockopt(sk, level, optname, optval, optlen); + return ip_setsockopt(sk, level, optname, optval, optlen); + return do_raw_setsockopt(sk, level, optname, optval, optlen); +} +#ifdef CONFIG_COMPAT +static int compat_raw_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level != SOL_RAW) + return compat_ip_setsockopt(sk, level, optname, optval, optlen); + return do_raw_setsockopt(sk, level, optname, optval, optlen); +} +#endif + +static int do_raw_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ if (optname == ICMP_FILTER) { if (inet_sk(sk)->num != IPPROTO_ICMP) return -EOPNOTSUPP; @@ -690,6 +702,24 @@ static int raw_getsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; } +static int raw_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_RAW) + return ip_getsockopt(sk, level, optname, optval, optlen); + return do_raw_getsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +static int compat_raw_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_RAW) + return compat_ip_getsockopt(sk, level, optname, optval, optlen); + return do_raw_getsockopt(sk, level, optname, optval, optlen); +} +#endif + static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { @@ -719,22 +749,26 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) } struct proto raw_prot = { - .name = "RAW", - .owner = THIS_MODULE, - .close = raw_close, - .connect = ip4_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = raw_ioctl, - .init = raw_init, - .setsockopt = raw_setsockopt, - .getsockopt = raw_getsockopt, - .sendmsg = raw_sendmsg, - .recvmsg = raw_recvmsg, - .bind = raw_bind, - .backlog_rcv = raw_rcv_skb, - .hash = raw_v4_hash, - .unhash = raw_v4_unhash, - .obj_size = sizeof(struct raw_sock), + .name = "RAW", + .owner = THIS_MODULE, + .close = raw_close, + .connect = ip4_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = raw_ioctl, + .init = raw_init, + .setsockopt = raw_setsockopt, + .getsockopt = raw_getsockopt, + .sendmsg = raw_sendmsg, + .recvmsg = raw_recvmsg, + .bind = raw_bind, + .backlog_rcv = raw_rcv_skb, + .hash = raw_v4_hash, + .unhash = raw_v4_unhash, + .obj_size = sizeof(struct raw_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_raw_setsockopt, + .compat_getsockopt = compat_raw_getsockopt, +#endif }; #ifdef CONFIG_PROC_FS diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 16984d4a8a06..6b6c3adfcf00 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -664,7 +664,30 @@ ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, - + { + .ctl_name = NET_TCP_MTU_PROBING, + .procname = "tcp_mtu_probing", + .data = &sysctl_tcp_mtu_probing, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = NET_TCP_BASE_MSS, + .procname = "tcp_base_mss", + .data = &sysctl_tcp_base_mss, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, + .procname = "tcp_workaround_signed_windows", + .data = &sysctl_tcp_workaround_signed_windows, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec + }, { .ctl_name = 0 } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 00aa80e93243..4b0272c92d66 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1687,18 +1687,14 @@ int tcp_disconnect(struct sock *sk, int flags) /* * Socket option code for TCP. */ -int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, - int optlen) +static int do_tcp_setsockopt(struct sock *sk, int level, + int optname, char __user *optval, int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int val; int err = 0; - if (level != SOL_TCP) - return icsk->icsk_af_ops->setsockopt(sk, level, optname, - optval, optlen); - /* This is a string value all the others are int's */ if (optname == TCP_CONGESTION) { char name[TCP_CA_NAME_MAX]; @@ -1871,6 +1867,30 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, return err; } +int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, + int optlen) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (level != SOL_TCP) + return icsk->icsk_af_ops->setsockopt(sk, level, optname, + optval, optlen); + return do_tcp_setsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +int compat_tcp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level != SOL_TCP) + return inet_csk_compat_setsockopt(sk, level, optname, + optval, optlen); + return do_tcp_setsockopt(sk, level, optname, optval, optlen); +} + +EXPORT_SYMBOL(compat_tcp_setsockopt); +#endif + /* Return information about state of tcp endpoint in API format. */ void tcp_get_info(struct sock *sk, struct tcp_info *info) { @@ -1931,17 +1951,13 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) EXPORT_SYMBOL_GPL(tcp_get_info); -int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, - int __user *optlen) +static int do_tcp_getsockopt(struct sock *sk, int level, + int optname, char __user *optval, int __user *optlen) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int val, len; - if (level != SOL_TCP) - return icsk->icsk_af_ops->getsockopt(sk, level, optname, - optval, optlen); - if (get_user(len, optlen)) return -EFAULT; @@ -2025,6 +2041,29 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, return 0; } +int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, + int __user *optlen) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (level != SOL_TCP) + return icsk->icsk_af_ops->getsockopt(sk, level, optname, + optval, optlen); + return do_tcp_getsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +int compat_tcp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_TCP) + return inet_csk_compat_getsockopt(sk, level, optname, + optval, optlen); + return do_tcp_getsockopt(sk, level, optname, optval, optlen); +} + +EXPORT_SYMBOL(compat_tcp_getsockopt); +#endif extern void __skb_cb_too_small_for_tcp(int, int); extern struct tcp_congestion_ops tcp_reno; diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 128de4d7c0b7..1b2ff53f98ed 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -27,12 +27,12 @@ struct htcp { u16 alpha; /* Fixed point arith, << 7 */ u8 beta; /* Fixed point arith, << 7 */ u8 modeswitch; /* Delay modeswitch until we had at least one congestion event */ - u8 ccount; /* Number of RTTs since last congestion event */ - u8 undo_ccount; - u16 packetcount; + u32 last_cong; /* Time since last congestion event end */ + u32 undo_last_cong; + u16 pkts_acked; + u32 packetcount; u32 minRTT; u32 maxRTT; - u32 snd_cwnd_cnt2; u32 undo_maxRTT; u32 undo_old_maxB; @@ -45,21 +45,30 @@ struct htcp { u32 lasttime; }; +static inline u32 htcp_cong_time(struct htcp *ca) +{ + return jiffies - ca->last_cong; +} + +static inline u32 htcp_ccount(struct htcp *ca) +{ + return htcp_cong_time(ca)/ca->minRTT; +} + static inline void htcp_reset(struct htcp *ca) { - ca->undo_ccount = ca->ccount; + ca->undo_last_cong = ca->last_cong; ca->undo_maxRTT = ca->maxRTT; ca->undo_old_maxB = ca->old_maxB; - ca->ccount = 0; - ca->snd_cwnd_cnt2 = 0; + ca->last_cong = jiffies; } static u32 htcp_cwnd_undo(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct htcp *ca = inet_csk_ca(sk); - ca->ccount = ca->undo_ccount; + ca->last_cong = ca->undo_last_cong; ca->maxRTT = ca->undo_maxRTT; ca->old_maxB = ca->undo_old_maxB; return max(tp->snd_cwnd, (tp->snd_ssthresh<<7)/ca->beta); @@ -77,10 +86,10 @@ static inline void measure_rtt(struct sock *sk) ca->minRTT = srtt; /* max RTT */ - if (icsk->icsk_ca_state == TCP_CA_Open && tp->snd_ssthresh < 0xFFFF && ca->ccount > 3) { + if (icsk->icsk_ca_state == TCP_CA_Open && tp->snd_ssthresh < 0xFFFF && htcp_ccount(ca) > 3) { if (ca->maxRTT < ca->minRTT) ca->maxRTT = ca->minRTT; - if (ca->maxRTT < srtt && srtt <= ca->maxRTT+HZ/50) + if (ca->maxRTT < srtt && srtt <= ca->maxRTT+msecs_to_jiffies(20)) ca->maxRTT = srtt; } } @@ -92,6 +101,12 @@ static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked) struct htcp *ca = inet_csk_ca(sk); u32 now = tcp_time_stamp; + if (icsk->icsk_ca_state == TCP_CA_Open) + ca->pkts_acked = pkts_acked; + + if (!use_bandwidth_switch) + return; + /* achieved throughput calculations */ if (icsk->icsk_ca_state != TCP_CA_Open && icsk->icsk_ca_state != TCP_CA_Disorder) { @@ -106,7 +121,7 @@ static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked) && now - ca->lasttime >= ca->minRTT && ca->minRTT > 0) { __u32 cur_Bi = ca->packetcount*HZ/(now - ca->lasttime); - if (ca->ccount <= 3) { + if (htcp_ccount(ca) <= 3) { /* just after backoff */ ca->minB = ca->maxB = ca->Bi = cur_Bi; } else { @@ -135,7 +150,7 @@ static inline void htcp_beta_update(struct htcp *ca, u32 minRTT, u32 maxRTT) } } - if (ca->modeswitch && minRTT > max(HZ/100, 1) && maxRTT) { + if (ca->modeswitch && minRTT > msecs_to_jiffies(10) && maxRTT) { ca->beta = (minRTT<<7)/maxRTT; if (ca->beta < BETA_MIN) ca->beta = BETA_MIN; @@ -151,7 +166,7 @@ static inline void htcp_alpha_update(struct htcp *ca) { u32 minRTT = ca->minRTT; u32 factor = 1; - u32 diff = ca->ccount * minRTT; /* time since last backoff */ + u32 diff = htcp_cong_time(ca); if (diff > HZ) { diff -= HZ; @@ -216,21 +231,18 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt, measure_rtt(sk); - /* keep track of number of round-trip times since last backoff event */ - if (ca->snd_cwnd_cnt2++ > tp->snd_cwnd) { - ca->ccount++; - ca->snd_cwnd_cnt2 = 0; - htcp_alpha_update(ca); - } - /* In dangerous area, increase slowly. * In theory this is tp->snd_cwnd += alpha / tp->snd_cwnd */ - if ((tp->snd_cwnd_cnt++ * ca->alpha)>>7 >= tp->snd_cwnd) { + if ((tp->snd_cwnd_cnt * ca->alpha)>>7 >= tp->snd_cwnd) { if (tp->snd_cwnd < tp->snd_cwnd_clamp) tp->snd_cwnd++; tp->snd_cwnd_cnt = 0; - } + htcp_alpha_update(ca); + } else + tp->snd_cwnd_cnt += ca->pkts_acked; + + ca->pkts_acked = 1; } } @@ -249,11 +261,19 @@ static void htcp_init(struct sock *sk) memset(ca, 0, sizeof(struct htcp)); ca->alpha = ALPHA_BASE; ca->beta = BETA_MIN; + ca->pkts_acked = 1; + ca->last_cong = jiffies; } static void htcp_state(struct sock *sk, u8 new_state) { switch (new_state) { + case TCP_CA_Open: + { + struct htcp *ca = inet_csk_ca(sk); + ca->last_cong = jiffies; + } + break; case TCP_CA_CWR: case TCP_CA_Recovery: case TCP_CA_Loss: @@ -278,8 +298,6 @@ static int __init htcp_register(void) { BUG_ON(sizeof(struct htcp) > ICSK_CA_PRIV_SIZE); BUILD_BUG_ON(BETA_MIN >= BETA_MAX); - if (!use_bandwidth_switch) - htcp.pkts_acked = NULL; return tcp_register_congestion_control(&htcp); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e9a54ae7d690..195d83584558 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1891,6 +1891,34 @@ static void tcp_try_to_open(struct sock *sk, struct tcp_sock *tp, int flag) } } +static void tcp_mtup_probe_failed(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1; + icsk->icsk_mtup.probe_size = 0; +} + +static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + + /* FIXME: breaks with very large cwnd */ + tp->prior_ssthresh = tcp_current_ssthresh(sk); + tp->snd_cwnd = tp->snd_cwnd * + tcp_mss_to_mtu(sk, tp->mss_cache) / + icsk->icsk_mtup.probe_size; + tp->snd_cwnd_cnt = 0; + tp->snd_cwnd_stamp = tcp_time_stamp; + tp->rcv_ssthresh = tcp_current_ssthresh(sk); + + icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; + icsk->icsk_mtup.probe_size = 0; + tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); +} + + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2023,6 +2051,17 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una, return; } + /* MTU probe failure: don't reduce cwnd */ + if (icsk->icsk_ca_state < TCP_CA_CWR && + icsk->icsk_mtup.probe_size && + tp->snd_una == tp->mtu_probe.probe_seq_start) { + tcp_mtup_probe_failed(sk); + /* Restores the reduction we did in tcp_mtup_probe() */ + tp->snd_cwnd++; + tcp_simple_retransmit(sk); + return; + } + /* Otherwise enter Recovery state */ if (IsReno(tp)) @@ -2243,6 +2282,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p) tp->retrans_stamp = 0; } + /* MTU probing checks */ + if (icsk->icsk_mtup.probe_size) { + if (!after(tp->mtu_probe.probe_seq_end, TCP_SKB_CB(skb)->end_seq)) { + tcp_mtup_probe_success(sk, skb); + } + } + if (sacked) { if (sacked & TCPCB_RETRANS) { if(sacked & TCPCB_SACKED_RETRANS) @@ -4101,6 +4147,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.sack_ok && sysctl_tcp_fack) tp->rx_opt.sack_ok |= 2; + tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); @@ -4211,6 +4258,7 @@ discard: if (tp->ecn_flags&TCP_ECN_OK) sock_set_flag(sk, SOCK_NO_LARGESEND); + tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); @@ -4399,6 +4447,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, */ tp->lsndtime = tcp_time_stamp; + tcp_mtup_init(sk); tcp_initialize_rcv_mss(sk); tcp_init_buffer_space(sk); tcp_fast_path_on(tp); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 233bdf259965..9e85c0416109 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -900,6 +900,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen; newinet->id = newtp->write_seq ^ jiffies; + tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric(dst, RTAX_ADVMSS); tcp_initialize_rcv_mss(newsk); @@ -1216,17 +1217,21 @@ int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw) } struct inet_connection_sock_af_ops ipv4_specific = { - .queue_xmit = ip_queue_xmit, - .send_check = tcp_v4_send_check, - .rebuild_header = inet_sk_rebuild_header, - .conn_request = tcp_v4_conn_request, - .syn_recv_sock = tcp_v4_syn_recv_sock, - .remember_stamp = tcp_v4_remember_stamp, - .net_header_len = sizeof(struct iphdr), - .setsockopt = ip_setsockopt, - .getsockopt = ip_getsockopt, - .addr2sockaddr = inet_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in), + .queue_xmit = ip_queue_xmit, + .send_check = tcp_v4_send_check, + .rebuild_header = inet_sk_rebuild_header, + .conn_request = tcp_v4_conn_request, + .syn_recv_sock = tcp_v4_syn_recv_sock, + .remember_stamp = tcp_v4_remember_stamp, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ip_setsockopt, + .getsockopt = ip_getsockopt, + .addr2sockaddr = inet_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ip_setsockopt, + .compat_getsockopt = compat_ip_getsockopt, +#endif }; /* NOTE: A lot of things set to zero explicitly by call to @@ -1825,23 +1830,16 @@ struct proto tcp_prot = { .obj_size = sizeof(struct tcp_sock), .twsk_prot = &tcp_timewait_sock_ops, .rsk_prot = &tcp_request_sock_ops, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_tcp_setsockopt, + .compat_getsockopt = compat_tcp_getsockopt, +#endif }; - - void __init tcp_v4_init(struct net_proto_family *ops) { - int err = sock_create_kern(PF_INET, SOCK_RAW, IPPROTO_TCP, &tcp_socket); - if (err < 0) + if (inet_csk_ctl_sock_create(&tcp_socket, PF_INET, SOCK_RAW, IPPROTO_TCP) < 0) panic("Failed to create the TCP control socket.\n"); - tcp_socket->sk->sk_allocation = GFP_ATOMIC; - inet_sk(tcp_socket->sk)->uc_ttl = -1; - - /* Unhash it so that IP input processing does not even - * see it, we do not wish this socket to see incoming - * packets. - */ - tcp_socket->sk->sk_prot->unhash(tcp_socket->sk); } EXPORT_SYMBOL(ipv4_specific); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9f498a6c8895..9d79546d384e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -45,12 +45,23 @@ /* People can turn this off for buggy TCP's found in printers etc. */ int sysctl_tcp_retrans_collapse = 1; +/* People can turn this on to work with those rare, broken TCPs that + * interpret the window field as a signed quantity. + */ +int sysctl_tcp_workaround_signed_windows = 0; + /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. */ int sysctl_tcp_tso_win_divisor = 3; +int sysctl_tcp_mtu_probing = 0; +int sysctl_tcp_base_mss = 512; + +EXPORT_SYMBOL(sysctl_tcp_mtu_probing); +EXPORT_SYMBOL(sysctl_tcp_base_mss); + static void update_send_head(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb) { @@ -171,12 +182,18 @@ void tcp_select_initial_window(int __space, __u32 mss, space = (space / mss) * mss; /* NOTE: offering an initial window larger than 32767 - * will break some buggy TCP stacks. We try to be nice. - * If we are not window scaling, then this truncates - * our initial window offering to 32k. There should also - * be a sysctl option to stop being nice. + * will break some buggy TCP stacks. If the admin tells us + * it is likely we could be speaking with such a buggy stack + * we will truncate our initial window offering to 32K-1 + * unless the remote has sent us a window scaling option, + * which we interpret as a sign the remote TCP is not + * misinterpreting the window field as a signed quantity. */ - (*rcv_wnd) = min(space, MAX_TCP_WINDOW); + if (sysctl_tcp_workaround_signed_windows) + (*rcv_wnd) = min(space, MAX_TCP_WINDOW); + else + (*rcv_wnd) = space; + (*rcv_wscale) = 0; if (wscale_ok) { /* Set window scaling on max possible window @@ -235,7 +252,7 @@ static u16 tcp_select_window(struct sock *sk) /* Make sure we do not exceed the maximum possible * scaled window. */ - if (!tp->rx_opt.rcv_wscale) + if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); @@ -681,6 +698,62 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) return 0; } +/* Not accounting for SACKs here. */ +int tcp_mtu_to_mss(struct sock *sk, int pmtu) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + int mss_now; + + /* Calculate base mss without TCP options: + It is MMS_S - sizeof(tcphdr) of rfc1122 + */ + mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); + + /* Clamp it (mss_clamp does not include tcp options) */ + if (mss_now > tp->rx_opt.mss_clamp) + mss_now = tp->rx_opt.mss_clamp; + + /* Now subtract optional transport overhead */ + mss_now -= icsk->icsk_ext_hdr_len; + + /* Then reserve room for full set of TCP options and 8 bytes of data */ + if (mss_now < 48) + mss_now = 48; + + /* Now subtract TCP options size, not including SACKs */ + mss_now -= tp->tcp_header_len - sizeof(struct tcphdr); + + return mss_now; +} + +/* Inverse of above */ +int tcp_mss_to_mtu(struct sock *sk, int mss) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + int mtu; + + mtu = mss + + tp->tcp_header_len + + icsk->icsk_ext_hdr_len + + icsk->icsk_af_ops->net_header_len; + + return mtu; +} + +void tcp_mtup_init(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + + icsk->icsk_mtup.enabled = sysctl_tcp_mtu_probing > 1; + icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + + icsk->icsk_af_ops->net_header_len; + icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss); + icsk->icsk_mtup.probe_size = 0; +} + /* This function synchronize snd mss to current pmtu/exthdr set. tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts @@ -708,25 +781,12 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); - /* Calculate base mss without TCP options: - It is MMS_S - sizeof(tcphdr) of rfc1122 - */ - int mss_now = (pmtu - icsk->icsk_af_ops->net_header_len - - sizeof(struct tcphdr)); - - /* Clamp it (mss_clamp does not include tcp options) */ - if (mss_now > tp->rx_opt.mss_clamp) - mss_now = tp->rx_opt.mss_clamp; - - /* Now subtract optional transport overhead */ - mss_now -= icsk->icsk_ext_hdr_len; + int mss_now; - /* Then reserve room for full set of TCP options and 8 bytes of data */ - if (mss_now < 48) - mss_now = 48; + if (icsk->icsk_mtup.search_high > pmtu) + icsk->icsk_mtup.search_high = pmtu; - /* Now subtract TCP options size, not including SACKs */ - mss_now -= tp->tcp_header_len - sizeof(struct tcphdr); + mss_now = tcp_mtu_to_mss(sk, pmtu); /* Bound mss with half of window */ if (tp->max_window && mss_now > (tp->max_window>>1)) @@ -734,6 +794,8 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; + if (icsk->icsk_mtup.enabled) + mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)); tp->mss_cache = mss_now; return mss_now; @@ -1063,6 +1125,140 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_ return 1; } +/* Create a new MTU probe if we are ready. + * Returns 0 if we should wait to probe (no cwnd available), + * 1 if a probe was sent, + * -1 otherwise */ +static int tcp_mtu_probe(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb, *nskb, *next; + int len; + int probe_size; + unsigned int pif; + int copy; + int mss_now; + + /* Not currently probing/verifying, + * not in recovery, + * have enough cwnd, and + * not SACKing (the variable headers throw things off) */ + if (!icsk->icsk_mtup.enabled || + icsk->icsk_mtup.probe_size || + inet_csk(sk)->icsk_ca_state != TCP_CA_Open || + tp->snd_cwnd < 11 || + tp->rx_opt.eff_sacks) + return -1; + + /* Very simple search strategy: just double the MSS. */ + mss_now = tcp_current_mss(sk, 0); + probe_size = 2*tp->mss_cache; + if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) { + /* TODO: set timer for probe_converge_event */ + return -1; + } + + /* Have enough data in the send queue to probe? */ + len = 0; + if ((skb = sk->sk_send_head) == NULL) + return -1; + while ((len += skb->len) < probe_size && !tcp_skb_is_last(sk, skb)) + skb = skb->next; + if (len < probe_size) + return -1; + + /* Receive window check. */ + if (after(TCP_SKB_CB(skb)->seq + probe_size, tp->snd_una + tp->snd_wnd)) { + if (tp->snd_wnd < probe_size) + return -1; + else + return 0; + } + + /* Do we need to wait to drain cwnd? */ + pif = tcp_packets_in_flight(tp); + if (pif + 2 > tp->snd_cwnd) { + /* With no packets in flight, don't stall. */ + if (pif == 0) + return -1; + else + return 0; + } + + /* We're allowed to probe. Build it now. */ + if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL) + return -1; + sk_charge_skb(sk, nskb); + + skb = sk->sk_send_head; + __skb_insert(nskb, skb->prev, skb, &sk->sk_write_queue); + sk->sk_send_head = nskb; + + TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; + TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; + TCP_SKB_CB(nskb)->flags = TCPCB_FLAG_ACK; + TCP_SKB_CB(nskb)->sacked = 0; + nskb->csum = 0; + if (skb->ip_summed == CHECKSUM_HW) + nskb->ip_summed = CHECKSUM_HW; + + len = 0; + while (len < probe_size) { + next = skb->next; + + copy = min_t(int, skb->len, probe_size - len); + if (nskb->ip_summed) + skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); + else + nskb->csum = skb_copy_and_csum_bits(skb, 0, + skb_put(nskb, copy), copy, nskb->csum); + + if (skb->len <= copy) { + /* We've eaten all the data from this skb. + * Throw it away. */ + TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags; + __skb_unlink(skb, &sk->sk_write_queue); + sk_stream_free_skb(sk, skb); + } else { + TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags & + ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH); + if (!skb_shinfo(skb)->nr_frags) { + skb_pull(skb, copy); + if (skb->ip_summed != CHECKSUM_HW) + skb->csum = csum_partial(skb->data, skb->len, 0); + } else { + __pskb_trim_head(skb, copy); + tcp_set_skb_tso_segs(sk, skb, mss_now); + } + TCP_SKB_CB(skb)->seq += copy; + } + + len += copy; + skb = next; + } + tcp_init_tso_segs(sk, nskb, nskb->len); + + /* We're ready to send. If this fails, the probe will + * be resegmented into mss-sized pieces by tcp_write_xmit(). */ + TCP_SKB_CB(nskb)->when = tcp_time_stamp; + if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) { + /* Decrement cwnd here because we are sending + * effectively two packets. */ + tp->snd_cwnd--; + update_send_head(sk, tp, nskb); + + icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len); + tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq; + tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq; + + return 1; + } + + return -1; +} + + /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. @@ -1076,6 +1272,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) struct sk_buff *skb; unsigned int tso_segs, sent_pkts; int cwnd_quota; + int result; /* If we are closed, the bytes will have to remain here. * In time closedown will finish, we empty the write queue and all @@ -1085,6 +1282,14 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) return 0; sent_pkts = 0; + + /* Do MTU probing. */ + if ((result = tcp_mtu_probe(sk)) == 0) { + return 0; + } else if (result > 0) { + sent_pkts = 1; + } + while ((skb = sk->sk_send_head)) { unsigned int limit; @@ -1455,9 +1660,15 @@ void tcp_simple_retransmit(struct sock *sk) int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss = tcp_current_mss(sk, 0); int err; + /* Inconslusive MTU probe */ + if (icsk->icsk_mtup.probe_size) { + icsk->icsk_mtup.probe_size = 0; + } + /* Do not sent more than we queued. 1/4 is reserved for possible * copying overhead: fragmentation, tunneling, mangling etc. */ @@ -1883,6 +2094,7 @@ static void tcp_connect_init(struct sock *sk) if (tp->rx_opt.user_mss) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; tp->max_window = 0; + tcp_mtup_init(sk); tcp_sync_mss(sk, dst_mtu(dst)); if (!tp->window_clamp) @@ -2180,3 +2392,4 @@ EXPORT_SYMBOL(tcp_make_synack); EXPORT_SYMBOL(tcp_simple_retransmit); EXPORT_SYMBOL(tcp_sync_mss); EXPORT_SYMBOL(sysctl_tcp_tso_win_divisor); +EXPORT_SYMBOL(tcp_mtup_init); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index e1880959614a..7c1bde3cd6cb 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -119,8 +119,10 @@ static int tcp_orphan_retries(struct sock *sk, int alive) /* A write timeout has occurred. Process the after effects. */ static int tcp_write_timeout(struct sock *sk) { - const struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); int retry_until; + int mss; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) @@ -128,25 +130,19 @@ static int tcp_write_timeout(struct sock *sk) retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; } else { if (icsk->icsk_retransmits >= sysctl_tcp_retries1) { - /* NOTE. draft-ietf-tcpimpl-pmtud-01.txt requires pmtu black - hole detection. :-( - - It is place to make it. It is not made. I do not want - to make it. It is disgusting. It does not work in any - case. Let me to cite the same draft, which requires for - us to implement this: - - "The one security concern raised by this memo is that ICMP black holes - are often caused by over-zealous security administrators who block - all ICMP messages. It is vitally important that those who design and - deploy security systems understand the impact of strict filtering on - upper-layer protocols. The safest web site in the world is worthless - if most TCP implementations cannot transfer data from it. It would - be far nicer to have all of the black holes fixed rather than fixing - all of the TCP implementations." - - Golden words :-). - */ + /* Black hole detection */ + if (sysctl_tcp_mtu_probing) { + if (!icsk->icsk_mtup.enabled) { + icsk->icsk_mtup.enabled = 1; + tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); + } else { + mss = min(sysctl_tcp_base_mss, + tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)/2); + mss = max(mss, 68 - tp->tcp_header_len); + icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); + tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); + } + } dst_negative_advice(&sk->sk_dst_cache); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 00840474a449..3f93292b0ad8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1207,16 +1207,13 @@ static int udp_destroy_sock(struct sock *sk) /* * Socket option code for UDP */ -static int udp_setsockopt(struct sock *sk, int level, int optname, +static int do_udp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) { struct udp_sock *up = udp_sk(sk); int val; int err = 0; - if (level != SOL_UDP) - return ip_setsockopt(sk, level, optname, optval, optlen); - if(optlen<sizeof(int)) return -EINVAL; @@ -1256,15 +1253,30 @@ static int udp_setsockopt(struct sock *sk, int level, int optname, return err; } -static int udp_getsockopt(struct sock *sk, int level, int optname, +static int udp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level != SOL_UDP) + return ip_setsockopt(sk, level, optname, optval, optlen); + return do_udp_setsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +static int compat_udp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level != SOL_UDP) + return compat_ip_setsockopt(sk, level, optname, optval, optlen); + return do_udp_setsockopt(sk, level, optname, optval, optlen); +} +#endif + +static int do_udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct udp_sock *up = udp_sk(sk); int val, len; - if (level != SOL_UDP) - return ip_getsockopt(sk, level, optname, optval, optlen); - if(get_user(len,optlen)) return -EFAULT; @@ -1293,6 +1305,23 @@ static int udp_getsockopt(struct sock *sk, int level, int optname, return 0; } +static int udp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_UDP) + return ip_getsockopt(sk, level, optname, optval, optlen); + return do_udp_getsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +static int compat_udp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_UDP) + return compat_ip_getsockopt(sk, level, optname, optval, optlen); + return do_udp_getsockopt(sk, level, optname, optval, optlen); +} +#endif /** * udp_poll - wait for a UDP event. * @file - file struct @@ -1341,23 +1370,27 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) } struct proto udp_prot = { - .name = "UDP", - .owner = THIS_MODULE, - .close = udp_close, - .connect = ip4_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .destroy = udp_destroy_sock, - .setsockopt = udp_setsockopt, - .getsockopt = udp_getsockopt, - .sendmsg = udp_sendmsg, - .recvmsg = udp_recvmsg, - .sendpage = udp_sendpage, - .backlog_rcv = udp_queue_rcv_skb, - .hash = udp_v4_hash, - .unhash = udp_v4_unhash, - .get_port = udp_v4_get_port, - .obj_size = sizeof(struct udp_sock), + .name = "UDP", + .owner = THIS_MODULE, + .close = udp_close, + .connect = ip4_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .destroy = udp_destroy_sock, + .setsockopt = udp_setsockopt, + .getsockopt = udp_getsockopt, + .sendmsg = udp_sendmsg, + .recvmsg = udp_recvmsg, + .sendpage = udp_sendpage, + .backlog_rcv = udp_queue_rcv_skb, + .hash = udp_v4_hash, + .unhash = udp_v4_unhash, + .get_port = udp_v4_get_port, + .obj_size = sizeof(struct udp_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udp_setsockopt, + .compat_getsockopt = compat_udp_getsockopt, +#endif }; /* ------------------------------------------------------------------------ */ diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index afbb0d4cc305..b08d56b117f8 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -5,6 +5,7 @@ #include <linux/skbuff.h> #include <linux/module.h> +#include <linux/mutex.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/protocol.h> @@ -26,19 +27,19 @@ static int ipip_xfrm_rcv(struct xfrm_state *x, struct xfrm_decap_state *decap, s } static struct xfrm_tunnel *ipip_handler; -static DECLARE_MUTEX(xfrm4_tunnel_sem); +static DEFINE_MUTEX(xfrm4_tunnel_mutex); int xfrm4_tunnel_register(struct xfrm_tunnel *handler) { int ret; - down(&xfrm4_tunnel_sem); + mutex_lock(&xfrm4_tunnel_mutex); ret = 0; if (ipip_handler != NULL) ret = -EINVAL; if (!ret) ipip_handler = handler; - up(&xfrm4_tunnel_sem); + mutex_unlock(&xfrm4_tunnel_mutex); return ret; } @@ -49,13 +50,13 @@ int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler) { int ret; - down(&xfrm4_tunnel_sem); + mutex_lock(&xfrm4_tunnel_mutex); ret = 0; if (ipip_handler != handler) ret = -EINVAL; if (!ret) ipip_handler = NULL; - up(&xfrm4_tunnel_sem); + mutex_unlock(&xfrm4_tunnel_mutex); synchronize_net(); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ab7a9124f985..e6f83b6a2b76 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -6,8 +6,6 @@ config IPV6 tristate "The IPv6 protocol" default m - select CRYPTO if IPV6_PRIVACY - select CRYPTO_MD5 if IPV6_PRIVACY ---help--- This is complemental support for the IP version 6. You will still be able to do traditional IPv4 networking as well. @@ -22,7 +20,7 @@ config IPV6 module will be called ipv6. config IPV6_PRIVACY - bool "IPv6: Privacy Extensions (RFC 3041) support" + bool "IPv6: Privacy Extensions support" depends on IPV6 ---help--- Privacy Extensions for Stateless Address Autoconfiguration in IPv6 @@ -30,6 +28,9 @@ config IPV6_PRIVACY pseudo-random global-scope unicast address(es) will assigned to your interface(s). + We use our standard pseudo random algorithm to generate randomized + interface identifier, instead of one described in RFC 3041. + By default, kernel do not generate temporary addresses. To use temporary addresses, do @@ -37,6 +38,25 @@ config IPV6_PRIVACY See <file:Documentation/networking/ip-sysctl.txt> for details. +config IPV6_ROUTER_PREF + bool "IPv6: Router Preference (RFC 4191) support" + depends on IPV6 + ---help--- + Router Preference is an optional extension to the Router + Advertisement message to improve the ability of hosts + to pick more appropriate router, especially when the hosts + is placed in a multi-homed network. + + If unsure, say N. + +config IPV6_ROUTE_INFO + bool "IPv6: Route Information (RFC 4191) support (EXPERIMENTAL)" + depends on IPV6_ROUTER_PREF && EXPERIMENTAL + ---help--- + This is experimental support of Route Information. + + If unsure, say N. + config INET6_AH tristate "IPv6: AH transformation" depends on IPV6 diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 19727d941962..01c62a0d3742 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -78,8 +78,6 @@ #ifdef CONFIG_IPV6_PRIVACY #include <linux/random.h> -#include <linux/crypto.h> -#include <linux/scatterlist.h> #endif #include <asm/uaccess.h> @@ -110,8 +108,6 @@ static int __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad static void ipv6_regen_rndid(unsigned long data); static int desync_factor = MAX_DESYNC_FACTOR * HZ; -static struct crypto_tfm *md5_tfm; -static DEFINE_SPINLOCK(md5_tfm_lock); #endif static int ipv6_count_addresses(struct inet6_dev *idev); @@ -169,6 +165,15 @@ struct ipv6_devconf ipv6_devconf = { .max_desync_factor = MAX_DESYNC_FACTOR, #endif .max_addresses = IPV6_MAX_ADDRESSES, + .accept_ra_defrtr = 1, + .accept_ra_pinfo = 1, +#ifdef CONFIG_IPV6_ROUTER_PREF + .accept_ra_rtr_pref = 1, + .rtr_probe_interval = 60 * HZ, +#ifdef CONFIG_IPV6_ROUTE_INFO + .accept_ra_rt_info_max_plen = 0, +#endif +#endif }; static struct ipv6_devconf ipv6_devconf_dflt = { @@ -190,6 +195,15 @@ static struct ipv6_devconf ipv6_devconf_dflt = { .max_desync_factor = MAX_DESYNC_FACTOR, #endif .max_addresses = IPV6_MAX_ADDRESSES, + .accept_ra_defrtr = 1, + .accept_ra_pinfo = 1, +#ifdef CONFIG_IPV6_ROUTER_PREF + .accept_ra_rtr_pref = 1, + .rtr_probe_interval = 60 * HZ, +#ifdef CONFIG_IPV6_ROUTE_INFO + .accept_ra_rt_info_max_plen = 0, +#endif +#endif }; /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ @@ -327,86 +341,83 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) if (dev->mtu < IPV6_MIN_MTU) return NULL; - ndev = kmalloc(sizeof(struct inet6_dev), GFP_KERNEL); + ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL); - if (ndev) { - memset(ndev, 0, sizeof(struct inet6_dev)); + if (ndev == NULL) + return NULL; - rwlock_init(&ndev->lock); - ndev->dev = dev; - memcpy(&ndev->cnf, &ipv6_devconf_dflt, sizeof(ndev->cnf)); - ndev->cnf.mtu6 = dev->mtu; - ndev->cnf.sysctl = NULL; - ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); - if (ndev->nd_parms == NULL) { - kfree(ndev); - return NULL; - } - /* We refer to the device */ - dev_hold(dev); - - if (snmp6_alloc_dev(ndev) < 0) { - ADBG((KERN_WARNING - "%s(): cannot allocate memory for statistics; dev=%s.\n", - __FUNCTION__, dev->name)); - neigh_parms_release(&nd_tbl, ndev->nd_parms); - ndev->dead = 1; - in6_dev_finish_destroy(ndev); - return NULL; - } + rwlock_init(&ndev->lock); + ndev->dev = dev; + memcpy(&ndev->cnf, &ipv6_devconf_dflt, sizeof(ndev->cnf)); + ndev->cnf.mtu6 = dev->mtu; + ndev->cnf.sysctl = NULL; + ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); + if (ndev->nd_parms == NULL) { + kfree(ndev); + return NULL; + } + /* We refer to the device */ + dev_hold(dev); - if (snmp6_register_dev(ndev) < 0) { - ADBG((KERN_WARNING - "%s(): cannot create /proc/net/dev_snmp6/%s\n", - __FUNCTION__, dev->name)); - neigh_parms_release(&nd_tbl, ndev->nd_parms); - ndev->dead = 1; - in6_dev_finish_destroy(ndev); - return NULL; - } + if (snmp6_alloc_dev(ndev) < 0) { + ADBG((KERN_WARNING + "%s(): cannot allocate memory for statistics; dev=%s.\n", + __FUNCTION__, dev->name)); + neigh_parms_release(&nd_tbl, ndev->nd_parms); + ndev->dead = 1; + in6_dev_finish_destroy(ndev); + return NULL; + } - /* One reference from device. We must do this before - * we invoke __ipv6_regen_rndid(). - */ - in6_dev_hold(ndev); + if (snmp6_register_dev(ndev) < 0) { + ADBG((KERN_WARNING + "%s(): cannot create /proc/net/dev_snmp6/%s\n", + __FUNCTION__, dev->name)); + neigh_parms_release(&nd_tbl, ndev->nd_parms); + ndev->dead = 1; + in6_dev_finish_destroy(ndev); + return NULL; + } + + /* One reference from device. We must do this before + * we invoke __ipv6_regen_rndid(). + */ + in6_dev_hold(ndev); #ifdef CONFIG_IPV6_PRIVACY - get_random_bytes(ndev->rndid, sizeof(ndev->rndid)); - get_random_bytes(ndev->entropy, sizeof(ndev->entropy)); - init_timer(&ndev->regen_timer); - ndev->regen_timer.function = ipv6_regen_rndid; - ndev->regen_timer.data = (unsigned long) ndev; - if ((dev->flags&IFF_LOOPBACK) || - dev->type == ARPHRD_TUNNEL || - dev->type == ARPHRD_NONE || - dev->type == ARPHRD_SIT) { - printk(KERN_INFO - "%s: Disabled Privacy Extensions\n", - dev->name); - ndev->cnf.use_tempaddr = -1; - } else { - in6_dev_hold(ndev); - ipv6_regen_rndid((unsigned long) ndev); - } + init_timer(&ndev->regen_timer); + ndev->regen_timer.function = ipv6_regen_rndid; + ndev->regen_timer.data = (unsigned long) ndev; + if ((dev->flags&IFF_LOOPBACK) || + dev->type == ARPHRD_TUNNEL || + dev->type == ARPHRD_NONE || + dev->type == ARPHRD_SIT) { + printk(KERN_INFO + "%s: Disabled Privacy Extensions\n", + dev->name); + ndev->cnf.use_tempaddr = -1; + } else { + in6_dev_hold(ndev); + ipv6_regen_rndid((unsigned long) ndev); + } #endif - if (netif_carrier_ok(dev)) - ndev->if_flags |= IF_READY; + if (netif_carrier_ok(dev)) + ndev->if_flags |= IF_READY; - write_lock_bh(&addrconf_lock); - dev->ip6_ptr = ndev; - write_unlock_bh(&addrconf_lock); + write_lock_bh(&addrconf_lock); + dev->ip6_ptr = ndev; + write_unlock_bh(&addrconf_lock); - ipv6_mc_init_dev(ndev); - ndev->tstamp = jiffies; + ipv6_mc_init_dev(ndev); + ndev->tstamp = jiffies; #ifdef CONFIG_SYSCTL - neigh_sysctl_register(dev, ndev->nd_parms, NET_IPV6, - NET_IPV6_NEIGH, "ipv6", - &ndisc_ifinfo_sysctl_change, - NULL); - addrconf_sysctl_register(ndev, &ndev->cnf); + neigh_sysctl_register(dev, ndev->nd_parms, NET_IPV6, + NET_IPV6_NEIGH, "ipv6", + &ndisc_ifinfo_sysctl_change, + NULL); + addrconf_sysctl_register(ndev, &ndev->cnf); #endif - } return ndev; } @@ -524,7 +535,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, goto out; } - ifa = kmalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); + ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); if (ifa == NULL) { ADBG(("ipv6_add_addr: malloc failed\n")); @@ -538,7 +549,6 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, goto out; } - memset(ifa, 0, sizeof(struct inet6_ifaddr)); ipv6_addr_copy(&ifa->addr, addr); spin_lock_init(&ifa->lock); @@ -1305,52 +1315,67 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) __ipv6_dev_ac_dec(ifp->idev, &addr); } +static int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) +{ + if (dev->addr_len != ETH_ALEN) + return -1; + memcpy(eui, dev->dev_addr, 3); + memcpy(eui + 5, dev->dev_addr + 3, 3); + + /* + * The zSeries OSA network cards can be shared among various + * OS instances, but the OSA cards have only one MAC address. + * This leads to duplicate address conflicts in conjunction + * with IPv6 if more than one instance uses the same card. + * + * The driver for these cards can deliver a unique 16-bit + * identifier for each instance sharing the same card. It is + * placed instead of 0xFFFE in the interface identifier. The + * "u" bit of the interface identifier is not inverted in this + * case. Hence the resulting interface identifier has local + * scope according to RFC2373. + */ + if (dev->dev_id) { + eui[3] = (dev->dev_id >> 8) & 0xFF; + eui[4] = dev->dev_id & 0xFF; + } else { + eui[3] = 0xFF; + eui[4] = 0xFE; + eui[0] ^= 2; + } + return 0; +} + +static int addrconf_ifid_arcnet(u8 *eui, struct net_device *dev) +{ + /* XXX: inherit EUI-64 from other interface -- yoshfuji */ + if (dev->addr_len != ARCNET_ALEN) + return -1; + memset(eui, 0, 7); + eui[7] = *(u8*)dev->dev_addr; + return 0; +} + +static int addrconf_ifid_infiniband(u8 *eui, struct net_device *dev) +{ + if (dev->addr_len != INFINIBAND_ALEN) + return -1; + memcpy(eui, dev->dev_addr + 12, 8); + eui[0] |= 2; + return 0; +} + static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_FDDI: case ARPHRD_IEEE802_TR: - if (dev->addr_len != ETH_ALEN) - return -1; - memcpy(eui, dev->dev_addr, 3); - memcpy(eui + 5, dev->dev_addr + 3, 3); - - /* - * The zSeries OSA network cards can be shared among various - * OS instances, but the OSA cards have only one MAC address. - * This leads to duplicate address conflicts in conjunction - * with IPv6 if more than one instance uses the same card. - * - * The driver for these cards can deliver a unique 16-bit - * identifier for each instance sharing the same card. It is - * placed instead of 0xFFFE in the interface identifier. The - * "u" bit of the interface identifier is not inverted in this - * case. Hence the resulting interface identifier has local - * scope according to RFC2373. - */ - if (dev->dev_id) { - eui[3] = (dev->dev_id >> 8) & 0xFF; - eui[4] = dev->dev_id & 0xFF; - } else { - eui[3] = 0xFF; - eui[4] = 0xFE; - eui[0] ^= 2; - } - return 0; + return addrconf_ifid_eui48(eui, dev); case ARPHRD_ARCNET: - /* XXX: inherit EUI-64 from other interface -- yoshfuji */ - if (dev->addr_len != ARCNET_ALEN) - return -1; - memset(eui, 0, 7); - eui[7] = *(u8*)dev->dev_addr; - return 0; + return addrconf_ifid_arcnet(eui, dev); case ARPHRD_INFINIBAND: - if (dev->addr_len != INFINIBAND_ALEN) - return -1; - memcpy(eui, dev->dev_addr + 12, 8); - eui[0] |= 2; - return 0; + return addrconf_ifid_infiniband(eui, dev); } return -1; } @@ -1376,34 +1401,9 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) /* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */ static int __ipv6_regen_rndid(struct inet6_dev *idev) { - struct net_device *dev; - struct scatterlist sg[2]; - - sg_set_buf(&sg[0], idev->entropy, 8); - sg_set_buf(&sg[1], idev->work_eui64, 8); - - dev = idev->dev; - - if (ipv6_generate_eui64(idev->work_eui64, dev)) { - printk(KERN_INFO - "__ipv6_regen_rndid(idev=%p): cannot get EUI64 identifier; use random bytes.\n", - idev); - get_random_bytes(idev->work_eui64, sizeof(idev->work_eui64)); - } regen: - spin_lock(&md5_tfm_lock); - if (unlikely(md5_tfm == NULL)) { - spin_unlock(&md5_tfm_lock); - return -1; - } - crypto_digest_init(md5_tfm); - crypto_digest_update(md5_tfm, sg, 2); - crypto_digest_final(md5_tfm, idev->work_digest); - spin_unlock(&md5_tfm_lock); - - memcpy(idev->rndid, &idev->work_digest[0], 8); + get_random_bytes(idev->rndid, sizeof(idev->rndid)); idev->rndid[0] &= ~0x02; - memcpy(idev->entropy, &idev->work_digest[8], 8); /* * <draft-ietf-ipngwg-temp-addresses-v2-00.txt>: @@ -2143,7 +2143,6 @@ static void addrconf_ip6_tnl_config(struct net_device *dev) return; } ip6_tnl_add_linklocal(idev); - addrconf_add_mroute(dev); } static int addrconf_notify(struct notifier_block *this, unsigned long event, @@ -2668,11 +2667,10 @@ static int if6_seq_open(struct inode *inode, struct file *file) { struct seq_file *seq; int rc = -ENOMEM; - struct if6_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); + struct if6_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL); if (!s) goto out; - memset(s, 0, sizeof(*s)); rc = seq_open(file, &if6_seq_ops); if (rc) @@ -3133,6 +3131,15 @@ static void inline ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; #endif array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; + array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; + array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; +#ifdef CONFIG_IPV6_ROUTER_PREF + array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref; + array[DEVCONF_RTR_PROBE_INTERVAL] = cnf->rtr_probe_interval; +#ifdef CONFIV_IPV6_ROUTE_INFO + array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen; +#endif +#endif } static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, @@ -3586,6 +3593,51 @@ static struct addrconf_sysctl_table .proc_handler = &proc_dointvec, }, { + .ctl_name = NET_IPV6_ACCEPT_RA_DEFRTR, + .procname = "accept_ra_defrtr", + .data = &ipv6_devconf.accept_ra_defrtr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = NET_IPV6_ACCEPT_RA_PINFO, + .procname = "accept_ra_pinfo", + .data = &ipv6_devconf.accept_ra_pinfo, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#ifdef CONFIG_IPV6_ROUTER_PREF + { + .ctl_name = NET_IPV6_ACCEPT_RA_RTR_PREF, + .procname = "accept_ra_rtr_pref", + .data = &ipv6_devconf.accept_ra_rtr_pref, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = NET_IPV6_RTR_PROBE_INTERVAL, + .procname = "router_probe_interval", + .data = &ipv6_devconf.rtr_probe_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, + }, +#ifdef CONFIV_IPV6_ROUTE_INFO + { + .ctl_name = NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN, + .procname = "accept_ra_rt_info_max_plen", + .data = &ipv6_devconf.accept_ra_rt_info_max_plen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif +#endif + { .ctl_name = 0, /* sentinel */ } }, @@ -3760,13 +3812,6 @@ int __init addrconf_init(void) register_netdevice_notifier(&ipv6_dev_notf); -#ifdef CONFIG_IPV6_PRIVACY - md5_tfm = crypto_alloc_tfm("md5", 0); - if (unlikely(md5_tfm == NULL)) - printk(KERN_WARNING - "failed to load transform for md5\n"); -#endif - addrconf_verify(0); rtnetlink_links[PF_INET6] = inet6_rtnetlink_table; #ifdef CONFIG_SYSCTL @@ -3829,11 +3874,6 @@ void __exit addrconf_cleanup(void) rtnl_unlock(); -#ifdef CONFIG_IPV6_PRIVACY - crypto_free_tfm(md5_tfm); - md5_tfm = NULL; -#endif - #ifdef CONFIG_PROC_FS proc_net_remove("if_inet6"); #endif diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 6c9711ac1c03..e19457fe4f6e 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -456,45 +456,53 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } const struct proto_ops inet6_stream_ops = { - .family = PF_INET6, - .owner = THIS_MODULE, - .release = inet6_release, - .bind = inet6_bind, - .connect = inet_stream_connect, /* ok */ - .socketpair = sock_no_socketpair, /* a do nothing */ - .accept = inet_accept, /* ok */ - .getname = inet6_getname, - .poll = tcp_poll, /* ok */ - .ioctl = inet6_ioctl, /* must change */ - .listen = inet_listen, /* ok */ - .shutdown = inet_shutdown, /* ok */ - .setsockopt = sock_common_setsockopt, /* ok */ - .getsockopt = sock_common_getsockopt, /* ok */ - .sendmsg = inet_sendmsg, /* ok */ - .recvmsg = sock_common_recvmsg, /* ok */ - .mmap = sock_no_mmap, - .sendpage = tcp_sendpage + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_stream_connect, /* ok */ + .socketpair = sock_no_socketpair, /* a do nothing */ + .accept = inet_accept, /* ok */ + .getname = inet6_getname, + .poll = tcp_poll, /* ok */ + .ioctl = inet6_ioctl, /* must change */ + .listen = inet_listen, /* ok */ + .shutdown = inet_shutdown, /* ok */ + .setsockopt = sock_common_setsockopt, /* ok */ + .getsockopt = sock_common_getsockopt, /* ok */ + .sendmsg = inet_sendmsg, /* ok */ + .recvmsg = sock_common_recvmsg, /* ok */ + .mmap = sock_no_mmap, + .sendpage = tcp_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; const struct proto_ops inet6_dgram_ops = { - .family = PF_INET6, - .owner = THIS_MODULE, - .release = inet6_release, - .bind = inet6_bind, - .connect = inet_dgram_connect, /* ok */ - .socketpair = sock_no_socketpair, /* a do nothing */ - .accept = sock_no_accept, /* a do nothing */ - .getname = inet6_getname, - .poll = udp_poll, /* ok */ - .ioctl = inet6_ioctl, /* must change */ - .listen = sock_no_listen, /* ok */ - .shutdown = inet_shutdown, /* ok */ - .setsockopt = sock_common_setsockopt, /* ok */ - .getsockopt = sock_common_getsockopt, /* ok */ - .sendmsg = inet_sendmsg, /* ok */ - .recvmsg = sock_common_recvmsg, /* ok */ - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_dgram_connect, /* ok */ + .socketpair = sock_no_socketpair, /* a do nothing */ + .accept = sock_no_accept, /* a do nothing */ + .getname = inet6_getname, + .poll = udp_poll, /* ok */ + .ioctl = inet6_ioctl, /* must change */ + .listen = sock_no_listen, /* ok */ + .shutdown = inet_shutdown, /* ok */ + .setsockopt = sock_common_setsockopt, /* ok */ + .getsockopt = sock_common_getsockopt, /* ok */ + .sendmsg = inet_sendmsg, /* ok */ + .recvmsg = sock_common_recvmsg, /* ok */ + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; static struct net_proto_family inet6_family_ops = { @@ -505,24 +513,28 @@ static struct net_proto_family inet6_family_ops = { /* Same as inet6_dgram_ops, sans udp_poll. */ static const struct proto_ops inet6_sockraw_ops = { - .family = PF_INET6, - .owner = THIS_MODULE, - .release = inet6_release, - .bind = inet6_bind, - .connect = inet_dgram_connect, /* ok */ - .socketpair = sock_no_socketpair, /* a do nothing */ - .accept = sock_no_accept, /* a do nothing */ - .getname = inet6_getname, - .poll = datagram_poll, /* ok */ - .ioctl = inet6_ioctl, /* must change */ - .listen = sock_no_listen, /* ok */ - .shutdown = inet_shutdown, /* ok */ - .setsockopt = sock_common_setsockopt, /* ok */ - .getsockopt = sock_common_getsockopt, /* ok */ - .sendmsg = inet_sendmsg, /* ok */ - .recvmsg = sock_common_recvmsg, /* ok */ - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_dgram_connect, /* ok */ + .socketpair = sock_no_socketpair, /* a do nothing */ + .accept = sock_no_accept, /* a do nothing */ + .getname = inet6_getname, + .poll = datagram_poll, /* ok */ + .ioctl = inet6_ioctl, /* must change */ + .listen = sock_no_listen, /* ok */ + .shutdown = inet_shutdown, /* ok */ + .setsockopt = sock_common_setsockopt, /* ok */ + .getsockopt = sock_common_getsockopt, /* ok */ + .sendmsg = inet_sendmsg, /* ok */ + .recvmsg = sock_common_recvmsg, /* ok */ + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; static struct inet_protosw rawv6_protosw = { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 84963749ab77..cf58251df4b3 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -213,6 +213,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) ah->reserved = 0; ah->spi = x->id.spi; ah->seq_no = htonl(++x->replay.oseq); + xfrm_aevent_doreplay(x); ahp->icv(ahp, skb, ah->auth_data); err = 0; @@ -353,12 +354,10 @@ static int ah6_init_state(struct xfrm_state *x) if (x->encap) goto error; - ahp = kmalloc(sizeof(*ahp), GFP_KERNEL); + ahp = kzalloc(sizeof(*ahp), GFP_KERNEL); if (ahp == NULL) return -ENOMEM; - memset(ahp, 0, sizeof(*ahp)); - ahp->key = x->aalg->alg_key; ahp->key_len = (x->aalg->alg_key_len+7)/8; ahp->tfm = crypto_alloc_tfm(x->aalg->alg_name, 0); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 840a33d33296..39ec528923f6 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -308,7 +308,7 @@ int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) * not found: create a new one. */ - aca = kmalloc(sizeof(struct ifacaddr6), GFP_ATOMIC); + aca = kzalloc(sizeof(struct ifacaddr6), GFP_ATOMIC); if (aca == NULL) { err = -ENOMEM; @@ -322,8 +322,6 @@ int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) goto out; } - memset(aca, 0, sizeof(struct ifacaddr6)); - ipv6_addr_copy(&aca->aca_addr, addr); aca->aca_idev = idev; aca->aca_rt = rt; @@ -550,7 +548,7 @@ static int ac6_seq_open(struct inode *inode, struct file *file) { struct seq_file *seq; int rc = -ENOMEM; - struct ac6_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); + struct ac6_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL); if (!s) goto out; @@ -561,7 +559,6 @@ static int ac6_seq_open(struct inode *inode, struct file *file) seq = file->private_data; seq->private = s; - memset(s, 0, sizeof(*s)); out: return rc; out_kfree: diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 7b5b94f13902..3dcaac7a0972 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -94,6 +94,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) esph->spi = x->id.spi; esph->seq_no = htonl(++x->replay.oseq); + xfrm_aevent_doreplay(x); if (esp->conf.ivlen) crypto_cipher_set_iv(tfm, esp->conf.ivec, crypto_tfm_alg_ivsize(tfm)); @@ -304,12 +305,10 @@ static int esp6_init_state(struct xfrm_state *x) if (x->encap) goto error; - esp = kmalloc(sizeof(*esp), GFP_KERNEL); + esp = kzalloc(sizeof(*esp), GFP_KERNEL); if (esp == NULL) return -ENOMEM; - memset(esp, 0, sizeof(*esp)); - if (x->aalg) { struct xfrm_algo_desc *aalg_desc; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1bf6d9a769e6..2cb6149349bf 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1105,7 +1105,6 @@ static int fib6_age(struct rt6_info *rt, void *arg) if (rt->rt6i_flags&RTF_EXPIRES && rt->rt6i_expires) { if (time_after(now, rt->rt6i_expires)) { RT6_TRACE("expiring %p\n", rt); - rt6_reset_dflt_pointer(rt); return -1; } gc_args.more++; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 69cbe8a66d02..f9ca63912fbf 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -287,10 +287,9 @@ fl_create(struct in6_flowlabel_req *freq, char __user *optval, int optlen, int * int err; err = -ENOMEM; - fl = kmalloc(sizeof(*fl), GFP_KERNEL); + fl = kzalloc(sizeof(*fl), GFP_KERNEL); if (fl == NULL) goto done; - memset(fl, 0, sizeof(*fl)); olen = optlen - CMSG_ALIGN(sizeof(*freq)); if (olen > 0) { @@ -663,7 +662,7 @@ static int ip6fl_seq_open(struct inode *inode, struct file *file) { struct seq_file *seq; int rc = -ENOMEM; - struct ip6fl_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); + struct ip6fl_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL); if (!s) goto out; @@ -674,7 +673,6 @@ static int ip6fl_seq_open(struct inode *inode, struct file *file) seq = file->private_data; seq->private = s; - memset(s, 0, sizeof(*s)); out: return rc; out_kfree: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5bf70b1442ea..4fbc40b13f19 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -733,28 +733,29 @@ int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl) if (*dst) { struct rt6_info *rt = (struct rt6_info*)*dst; - /* Yes, checking route validity in not connected - case is not very simple. Take into account, - that we do not support routing by source, TOS, - and MSG_DONTROUTE --ANK (980726) - - 1. If route was host route, check that - cached destination is current. - If it is network route, we still may - check its validity using saved pointer - to the last used address: daddr_cache. - We do not want to save whole address now, - (because main consumer of this service - is tcp, which has not this problem), - so that the last trick works only on connected - sockets. - 2. oif also should be the same. - */ - + /* Yes, checking route validity in not connected + * case is not very simple. Take into account, + * that we do not support routing by source, TOS, + * and MSG_DONTROUTE --ANK (980726) + * + * 1. If route was host route, check that + * cached destination is current. + * If it is network route, we still may + * check its validity using saved pointer + * to the last used address: daddr_cache. + * We do not want to save whole address now, + * (because main consumer of this service + * is tcp, which has not this problem), + * so that the last trick works only on connected + * sockets. + * 2. oif also should be the same. + */ if (((rt->rt6i_dst.plen != 128 || - !ipv6_addr_equal(&fl->fl6_dst, &rt->rt6i_dst.addr)) + !ipv6_addr_equal(&fl->fl6_dst, + &rt->rt6i_dst.addr)) && (np->daddr_cache == NULL || - !ipv6_addr_equal(&fl->fl6_dst, np->daddr_cache))) + !ipv6_addr_equal(&fl->fl6_dst, + np->daddr_cache))) || (fl->oif && fl->oif != (*dst)->dev->ifindex)) { dst_release(*dst); *dst = NULL; @@ -889,7 +890,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, np->cork.hop_limit = hlimit; np->cork.tclass = tclass; mtu = dst_mtu(rt->u.dst.path); - if (np && np->frag_size < mtu) { + if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index d511a884dad0..028b636687ec 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -50,6 +50,7 @@ #include <net/protocol.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> +#include <linux/mutex.h> struct ipcomp6_tfms { struct list_head list; @@ -57,7 +58,7 @@ struct ipcomp6_tfms { int users; }; -static DECLARE_MUTEX(ipcomp6_resource_sem); +static DEFINE_MUTEX(ipcomp6_resource_mutex); static void **ipcomp6_scratches; static int ipcomp6_scratch_users; static LIST_HEAD(ipcomp6_tfms_list); @@ -286,8 +287,8 @@ static void ipcomp6_free_scratches(void) for_each_cpu(i) { void *scratch = *per_cpu_ptr(scratches, i); - if (scratch) - vfree(scratch); + + vfree(scratch); } free_percpu(scratches); @@ -405,9 +406,9 @@ static void ipcomp6_destroy(struct xfrm_state *x) if (!ipcd) return; xfrm_state_delete_tunnel(x); - down(&ipcomp6_resource_sem); + mutex_lock(&ipcomp6_resource_mutex); ipcomp6_free_data(ipcd); - up(&ipcomp6_resource_sem); + mutex_unlock(&ipcomp6_resource_mutex); kfree(ipcd); xfrm6_tunnel_free_spi((xfrm_address_t *)&x->props.saddr); @@ -427,23 +428,22 @@ static int ipcomp6_init_state(struct xfrm_state *x) goto out; err = -ENOMEM; - ipcd = kmalloc(sizeof(*ipcd), GFP_KERNEL); + ipcd = kzalloc(sizeof(*ipcd), GFP_KERNEL); if (!ipcd) goto out; - memset(ipcd, 0, sizeof(*ipcd)); x->props.header_len = 0; if (x->props.mode) x->props.header_len += sizeof(struct ipv6hdr); - down(&ipcomp6_resource_sem); + mutex_lock(&ipcomp6_resource_mutex); if (!ipcomp6_alloc_scratches()) goto error; ipcd->tfms = ipcomp6_alloc_tfms(x->calg->alg_name); if (!ipcd->tfms) goto error; - up(&ipcomp6_resource_sem); + mutex_unlock(&ipcomp6_resource_mutex); if (x->props.mode) { err = ipcomp6_tunnel_attach(x); @@ -459,10 +459,10 @@ static int ipcomp6_init_state(struct xfrm_state *x) out: return err; error_tunnel: - down(&ipcomp6_resource_sem); + mutex_lock(&ipcomp6_resource_mutex); error: ipcomp6_free_data(ipcd); - up(&ipcomp6_resource_sem); + mutex_unlock(&ipcomp6_resource_mutex); kfree(ipcd); goto out; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index f7142ba519ab..602feec47738 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -109,19 +109,13 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *)) return 0; } -int ipv6_setsockopt(struct sock *sk, int level, int optname, +static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); int val, valbool; int retv = -ENOPROTOOPT; - if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.setsockopt(sk, level, optname, optval, optlen); - - if(level!=SOL_IPV6) - goto out; - if (optval == NULL) val=0; else if (get_user(val, (int __user *) optval)) @@ -613,17 +607,9 @@ done: retv = xfrm_user_policy(sk, optname, optval, optlen); break; -#ifdef CONFIG_NETFILTER - default: - retv = nf_setsockopt(sk, PF_INET6, optname, optval, - optlen); - break; -#endif - } release_sock(sk); -out: return retv; e_inval: @@ -631,6 +617,65 @@ e_inval: return -EINVAL; } +int ipv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + int err; + + if (level == SOL_IP && sk->sk_type != SOCK_RAW) + return udp_prot.setsockopt(sk, level, optname, optval, optlen); + + if (level != SOL_IPV6) + return -ENOPROTOOPT; + + err = do_ipv6_setsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY && + optname != IPV6_XFRM_POLICY) { + lock_sock(sk); + err = nf_setsockopt(sk, PF_INET6, optname, optval, + optlen); + release_sock(sk); + } +#endif + return err; +} + + +#ifdef CONFIG_COMPAT +int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + int err; + + if (level == SOL_IP && sk->sk_type != SOCK_RAW) { + if (udp_prot.compat_setsockopt != NULL) + return udp_prot.compat_setsockopt(sk, level, optname, + optval, optlen); + return udp_prot.setsockopt(sk, level, optname, optval, optlen); + } + + if (level != SOL_IPV6) + return -ENOPROTOOPT; + + err = do_ipv6_setsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible ENOPROTOOPTs except default case */ + if (err == -ENOPROTOOPT && optname != IPV6_IPSEC_POLICY && + optname != IPV6_XFRM_POLICY) { + lock_sock(sk); + err = compat_nf_setsockopt(sk, PF_INET6, optname, + optval, optlen); + release_sock(sk); + } +#endif + return err; +} + +EXPORT_SYMBOL(compat_ipv6_setsockopt); +#endif + static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_opt_hdr *hdr, char __user *optval, int len) { @@ -642,17 +687,13 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_opt_hdr *hdr, return len; } -int ipv6_getsockopt(struct sock *sk, int level, int optname, +static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct ipv6_pinfo *np = inet6_sk(sk); int len; int val; - if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.getsockopt(sk, level, optname, optval, optlen); - if(level!=SOL_IPV6) - return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; switch (optname) { @@ -842,17 +883,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, break; default: -#ifdef CONFIG_NETFILTER - lock_sock(sk); - val = nf_getsockopt(sk, PF_INET6, optname, optval, - &len); - release_sock(sk); - if (val >= 0) - val = put_user(len, optlen); - return val; -#else return -EINVAL; -#endif } len = min_t(unsigned int, sizeof(int), len); if(put_user(len, optlen)) @@ -862,6 +893,78 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, return 0; } +int ipv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + int err; + + if (level == SOL_IP && sk->sk_type != SOCK_RAW) + return udp_prot.getsockopt(sk, level, optname, optval, optlen); + + if(level != SOL_IPV6) + return -ENOPROTOOPT; + + err = do_ipv6_getsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible EINVALs except default case */ + if (err == -ENOPROTOOPT && optname != IPV6_ADDRFORM && + optname != MCAST_MSFILTER) { + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + lock_sock(sk); + err = nf_getsockopt(sk, PF_INET6, optname, optval, + &len); + release_sock(sk); + if (err >= 0) + err = put_user(len, optlen); + } +#endif + return err; +} + +#ifdef CONFIG_COMPAT +int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + int err; + + if (level == SOL_IP && sk->sk_type != SOCK_RAW) { + if (udp_prot.compat_getsockopt != NULL) + return udp_prot.compat_getsockopt(sk, level, optname, + optval, optlen); + return udp_prot.getsockopt(sk, level, optname, optval, optlen); + } + + if (level != SOL_IPV6) + return -ENOPROTOOPT; + + err = do_ipv6_getsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_NETFILTER + /* we need to exclude all possible EINVALs except default case */ + if (err == -ENOPROTOOPT && optname != IPV6_ADDRFORM && + optname != MCAST_MSFILTER) { + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + lock_sock(sk); + err = compat_nf_getsockopt(sk, PF_INET6, + optname, optval, &len); + release_sock(sk); + if (err >= 0) + err = put_user(len, optlen); + } +#endif + return err; +} + +EXPORT_SYMBOL(compat_ipv6_getsockopt); +#endif + void __init ipv6_packet_init(void) { dev_add_pack(&ipv6_packet_type); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 807c021d64a2..6e871afbb2c7 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -767,10 +767,10 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ - pmc = kmalloc(sizeof(*pmc), GFP_ATOMIC); + pmc = kzalloc(sizeof(*pmc), GFP_ATOMIC); if (!pmc) return; - memset(pmc, 0, sizeof(*pmc)); + spin_lock_bh(&im->mca_lock); spin_lock_init(&pmc->mca_lock); pmc->idev = im->idev; @@ -893,7 +893,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, struct in6_addr *addr) * not found: create a new one. */ - mc = kmalloc(sizeof(struct ifmcaddr6), GFP_ATOMIC); + mc = kzalloc(sizeof(struct ifmcaddr6), GFP_ATOMIC); if (mc == NULL) { write_unlock_bh(&idev->lock); @@ -901,7 +901,6 @@ int ipv6_dev_mc_inc(struct net_device *dev, struct in6_addr *addr) return -ENOMEM; } - memset(mc, 0, sizeof(struct ifmcaddr6)); init_timer(&mc->mca_timer); mc->mca_timer.function = igmp6_timer_handler; mc->mca_timer.data = (unsigned long) mc; @@ -1934,10 +1933,10 @@ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, psf_prev = psf; } if (!psf) { - psf = kmalloc(sizeof(*psf), GFP_ATOMIC); + psf = kzalloc(sizeof(*psf), GFP_ATOMIC); if (!psf) return -ENOBUFS; - memset(psf, 0, sizeof(*psf)); + psf->sf_addr = *psfsrc; if (psf_prev) { psf_prev->sf_next = psf; @@ -2431,7 +2430,7 @@ static int igmp6_mc_seq_open(struct inode *inode, struct file *file) { struct seq_file *seq; int rc = -ENOMEM; - struct igmp6_mc_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); + struct igmp6_mc_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL); if (!s) goto out; @@ -2442,7 +2441,6 @@ static int igmp6_mc_seq_open(struct inode *inode, struct file *file) seq = file->private_data; seq->private = s; - memset(s, 0, sizeof(*s)); out: return rc; out_kfree: @@ -2606,7 +2604,7 @@ static int igmp6_mcf_seq_open(struct inode *inode, struct file *file) { struct seq_file *seq; int rc = -ENOMEM; - struct igmp6_mcf_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); + struct igmp6_mcf_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL); if (!s) goto out; @@ -2617,7 +2615,6 @@ static int igmp6_mcf_seq_open(struct inode *inode, struct file *file) seq = file->private_data; seq->private = s; - memset(s, 0, sizeof(*s)); out: return rc; out_kfree: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index cb8856b1d951..dfa20d3be9b6 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -156,7 +156,11 @@ struct neigh_table nd_tbl = { /* ND options */ struct ndisc_options { - struct nd_opt_hdr *nd_opt_array[__ND_OPT_MAX]; + struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX]; +#ifdef CONFIG_IPV6_ROUTE_INFO + struct nd_opt_hdr *nd_opts_ri; + struct nd_opt_hdr *nd_opts_ri_end; +#endif }; #define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] @@ -255,6 +259,13 @@ static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, if (ndopts->nd_opt_array[nd_opt->nd_opt_type] == 0) ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; break; +#ifdef CONFIG_IPV6_ROUTE_INFO + case ND_OPT_ROUTE_INFO: + ndopts->nd_opts_ri_end = nd_opt; + if (!ndopts->nd_opts_ri) + ndopts->nd_opts_ri = nd_opt; + break; +#endif default: /* * Unknown options must be silently ignored, @@ -1019,10 +1030,11 @@ static void ndisc_router_discovery(struct sk_buff *skb) struct ra_msg *ra_msg = (struct ra_msg *) skb->h.raw; struct neighbour *neigh = NULL; struct inet6_dev *in6_dev; - struct rt6_info *rt; + struct rt6_info *rt = NULL; int lifetime; struct ndisc_options ndopts; int optlen; + unsigned int pref = 0; __u8 * opt = (__u8 *)(ra_msg + 1); @@ -1081,8 +1093,19 @@ static void ndisc_router_discovery(struct sk_buff *skb) (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); + if (!in6_dev->cnf.accept_ra_defrtr) + goto skip_defrtr; + lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); +#ifdef CONFIG_IPV6_ROUTER_PREF + pref = ra_msg->icmph.icmp6_router_pref; + /* 10b is handled as if it were 00b (medium) */ + if (pref == ICMPV6_ROUTER_PREF_INVALID || + in6_dev->cnf.accept_ra_rtr_pref) + pref = ICMPV6_ROUTER_PREF_MEDIUM; +#endif + rt = rt6_get_dflt_router(&skb->nh.ipv6h->saddr, skb->dev); if (rt) @@ -1098,7 +1121,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) ND_PRINTK3(KERN_DEBUG "ICMPv6 RA: adding default router.\n"); - rt = rt6_add_dflt_router(&skb->nh.ipv6h->saddr, skb->dev); + rt = rt6_add_dflt_router(&skb->nh.ipv6h->saddr, skb->dev, pref); if (rt == NULL) { ND_PRINTK0(KERN_ERR "ICMPv6 RA: %s() failed to add default route.\n", @@ -1117,6 +1140,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } neigh->flags |= NTF_ROUTER; + } else if (rt) { + rt->rt6i_flags |= (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); } if (rt) @@ -1128,6 +1153,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) rt->u.dst.metrics[RTAX_HOPLIMIT-1] = ra_msg->icmph.icmp6_hop_limit; } +skip_defrtr: + /* * Update Reachable Time and Retrans Timer */ @@ -1186,7 +1213,21 @@ static void ndisc_router_discovery(struct sk_buff *skb) NEIGH_UPDATE_F_ISROUTER); } - if (ndopts.nd_opts_pi) { +#ifdef CONFIG_IPV6_ROUTE_INFO + if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { + struct nd_opt_hdr *p; + for (p = ndopts.nd_opts_ri; + p; + p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) { + if (((struct route_info *)p)->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) + continue; + rt6_route_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3, + &skb->nh.ipv6h->saddr); + } + } +#endif + + if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_pi; p; diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 2d6f8ecbc27b..98f78759f1ab 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -133,16 +133,6 @@ config IP6_NF_MATCH_EUI64 To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_MATCH_POLICY - tristate "IPsec policy match support" - depends on IP6_NF_IPTABLES && XFRM - help - Policy matching allows you to match packets based on the - IPsec policy that was used during decapsulation/will - be used during encapsulation. - - To compile it as a module, choose M here. If unsure, say N. - # The targets config IP6_NF_FILTER tristate "Packet filtering" diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index db6073c94163..8436a1a1731f 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -9,7 +9,6 @@ obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o ip6t_dst.o obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o obj-$(CONFIG_IP6_NF_MATCH_AHESP) += ip6t_esp.o ip6t_ah.o -obj-$(CONFIG_IP6_NF_MATCH_POLICY) += ip6t_policy.o obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o obj-$(CONFIG_IP6_NF_MATCH_MULTIPORT) += ip6t_multiport.o obj-$(CONFIG_IP6_NF_MATCH_OWNER) += ip6t_owner.o diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index af0635084df8..344eab3b5da8 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -35,6 +35,7 @@ #include <linux/spinlock.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> +#include <linux/mutex.h> #include <net/sock.h> #include <net/ipv6.h> #include <net/ip6_route.h> @@ -65,7 +66,7 @@ static unsigned int queue_dropped = 0; static unsigned int queue_user_dropped = 0; static struct sock *ipqnl; static LIST_HEAD(queue_list); -static DECLARE_MUTEX(ipqnl_sem); +static DEFINE_MUTEX(ipqnl_mutex); static void ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict) @@ -537,7 +538,7 @@ ipq_rcv_sk(struct sock *sk, int len) struct sk_buff *skb; unsigned int qlen; - down(&ipqnl_sem); + mutex_lock(&ipqnl_mutex); for (qlen = skb_queue_len(&sk->sk_receive_queue); qlen; qlen--) { skb = skb_dequeue(&sk->sk_receive_queue); @@ -545,7 +546,7 @@ ipq_rcv_sk(struct sock *sk, int len) kfree_skb(skb); } - up(&ipqnl_sem); + mutex_unlock(&ipqnl_mutex); } static int @@ -704,8 +705,8 @@ cleanup_sysctl: cleanup_ipqnl: sock_release(ipqnl->sk_socket); - down(&ipqnl_sem); - up(&ipqnl_sem); + mutex_lock(&ipqnl_mutex); + mutex_unlock(&ipqnl_mutex); cleanup_netlink_notifier: netlink_unregister_notifier(&ipq_nl_notifier); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 74ff56c322f4..5a2063bda676 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -29,7 +29,7 @@ #include <linux/icmpv6.h> #include <net/ipv6.h> #include <asm/uaccess.h> -#include <asm/semaphore.h> +#include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/cpumask.h> @@ -94,19 +94,6 @@ do { \ #define up(x) do { printk("UP:%u:" #x "\n", __LINE__); up(x); } while(0) #endif -int -ip6_masked_addrcmp(const struct in6_addr *addr1, const struct in6_addr *mask, - const struct in6_addr *addr2) -{ - int i; - for( i = 0; i < 16; i++){ - if((addr1->s6_addr[i] & mask->s6_addr[i]) != - (addr2->s6_addr[i] & mask->s6_addr[i])) - return 1; - } - return 0; -} - /* Check for an extension */ int ip6t_ext_hdr(u8 nexthdr) @@ -135,10 +122,10 @@ ip6_packet_match(const struct sk_buff *skb, #define FWINV(bool,invflg) ((bool) ^ !!(ip6info->invflags & invflg)) - if (FWINV(ip6_masked_addrcmp(&ipv6->saddr, &ip6info->smsk, - &ip6info->src), IP6T_INV_SRCIP) - || FWINV(ip6_masked_addrcmp(&ipv6->daddr, &ip6info->dmsk, - &ip6info->dst), IP6T_INV_DSTIP)) { + if (FWINV(ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, + &ip6info->src), IP6T_INV_SRCIP) + || FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, + &ip6info->dst), IP6T_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); /* dprintf("SRC: %u. Mask: %u. Target: %u.%s\n", ip->saddr, @@ -232,6 +219,7 @@ ip6t_error(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -251,7 +239,7 @@ int do_match(struct ip6t_entry_match *m, int *hotdrop) { /* Stop iteration if it doesn't match */ - if (!m->u.kernel.match->match(skb, in, out, m->data, + if (!m->u.kernel.match->match(skb, in, out, m->u.kernel.match, m->data, offset, protoff, hotdrop)) return 1; else @@ -373,6 +361,7 @@ ip6t_do_table(struct sk_buff **pskb, verdict = t->u.kernel.target->target(pskb, in, out, hook, + t->u.kernel.target, t->data, userdata); @@ -531,7 +520,7 @@ cleanup_match(struct ip6t_entry_match *m, unsigned int *i) return 1; if (m->u.kernel.match->destroy) - m->u.kernel.match->destroy(m->data, + m->u.kernel.match->destroy(m->u.kernel.match, m->data, m->u.match_size - sizeof(*m)); module_put(m->u.kernel.match->me); return 0; @@ -544,21 +533,12 @@ standard_check(const struct ip6t_entry_target *t, struct ip6t_standard_target *targ = (void *)t; /* Check standard info. */ - if (t->u.target_size - != IP6T_ALIGN(sizeof(struct ip6t_standard_target))) { - duprintf("standard_check: target size %u != %u\n", - t->u.target_size, - IP6T_ALIGN(sizeof(struct ip6t_standard_target))); - return 0; - } - if (targ->verdict >= 0 && targ->verdict > max_offset - sizeof(struct ip6t_entry)) { duprintf("ip6t_standard_check: bad verdict (%i)\n", targ->verdict); return 0; } - if (targ->verdict < -NF_MAX_VERDICT - 1) { duprintf("ip6t_standard_check: bad negative verdict (%i)\n", targ->verdict); @@ -575,6 +555,7 @@ check_match(struct ip6t_entry_match *m, unsigned int *i) { struct ip6t_match *match; + int ret; match = try_then_request_module(xt_find_match(AF_INET6, m->u.user.name, m->u.user.revision), @@ -585,18 +566,27 @@ check_match(struct ip6t_entry_match *m, } m->u.kernel.match = match; + ret = xt_check_match(match, AF_INET6, m->u.match_size - sizeof(*m), + name, hookmask, ipv6->proto, + ipv6->invflags & IP6T_INV_PROTO); + if (ret) + goto err; + if (m->u.kernel.match->checkentry - && !m->u.kernel.match->checkentry(name, ipv6, m->data, + && !m->u.kernel.match->checkentry(name, ipv6, match, m->data, m->u.match_size - sizeof(*m), hookmask)) { - module_put(m->u.kernel.match->me); duprintf("ip_tables: check failed for `%s'.\n", m->u.kernel.match->name); - return -EINVAL; + ret = -EINVAL; + goto err; } (*i)++; return 0; +err: + module_put(m->u.kernel.match->me); + return ret; } static struct ip6t_target ip6t_standard_target; @@ -632,26 +622,32 @@ check_entry(struct ip6t_entry *e, const char *name, unsigned int size, } t->u.kernel.target = target; + ret = xt_check_target(target, AF_INET6, t->u.target_size - sizeof(*t), + name, e->comefrom, e->ipv6.proto, + e->ipv6.invflags & IP6T_INV_PROTO); + if (ret) + goto err; + if (t->u.kernel.target == &ip6t_standard_target) { if (!standard_check(t, size)) { ret = -EINVAL; goto cleanup_matches; } } else if (t->u.kernel.target->checkentry - && !t->u.kernel.target->checkentry(name, e, t->data, + && !t->u.kernel.target->checkentry(name, e, target, t->data, t->u.target_size - sizeof(*t), e->comefrom)) { - module_put(t->u.kernel.target->me); duprintf("ip_tables: check failed for `%s'.\n", t->u.kernel.target->name); ret = -EINVAL; - goto cleanup_matches; + goto err; } (*i)++; return 0; - + err: + module_put(t->u.kernel.target->me); cleanup_matches: IP6T_MATCH_ITERATE(e, cleanup_match, &j); return ret; @@ -712,7 +708,7 @@ cleanup_entry(struct ip6t_entry *e, unsigned int *i) IP6T_MATCH_ITERATE(e, cleanup_match, NULL); t = ip6t_get_target(e); if (t->u.kernel.target->destroy) - t->u.kernel.target->destroy(t->data, + t->u.kernel.target->destroy(t->u.kernel.target, t->data, t->u.target_size - sizeof(*t)); module_put(t->u.kernel.target->me); return 0; @@ -1333,6 +1329,7 @@ static int icmp6_match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -1365,28 +1362,27 @@ icmp6_match(const struct sk_buff *skb, static int icmp6_checkentry(const char *tablename, const void *entry, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - const struct ip6t_ip6 *ipv6 = entry; const struct ip6t_icmp *icmpinfo = matchinfo; - /* Must specify proto == ICMP, and no unknown invflags */ - return ipv6->proto == IPPROTO_ICMPV6 - && !(ipv6->invflags & IP6T_INV_PROTO) - && matchsize == IP6T_ALIGN(sizeof(struct ip6t_icmp)) - && !(icmpinfo->invflags & ~IP6T_ICMP_INV); + /* Must specify no unknown invflags */ + return !(icmpinfo->invflags & ~IP6T_ICMP_INV); } /* The built-in targets: standard (NULL) and error. */ static struct ip6t_target ip6t_standard_target = { .name = IP6T_STANDARD_TARGET, + .targetsize = sizeof(int), }; static struct ip6t_target ip6t_error_target = { .name = IP6T_ERROR_TARGET, .target = ip6t_error, + .targetsize = IP6T_FUNCTION_MAXNAMELEN, }; static struct nf_sockopt_ops ip6t_sockopts = { @@ -1402,7 +1398,9 @@ static struct nf_sockopt_ops ip6t_sockopts = { static struct ip6t_match icmp6_matchstruct = { .name = "icmp6", .match = &icmp6_match, - .checkentry = &icmp6_checkentry, + .matchsize = sizeof(struct ip6t_icmp), + .checkentry = icmp6_checkentry, + .proto = IPPROTO_ICMPV6, }; static int __init init(void) @@ -1515,7 +1513,6 @@ EXPORT_SYMBOL(ip6t_unregister_table); EXPORT_SYMBOL(ip6t_do_table); EXPORT_SYMBOL(ip6t_ext_hdr); EXPORT_SYMBOL(ipv6_find_hdr); -EXPORT_SYMBOL(ip6_masked_addrcmp); module_init(init); module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_HL.c b/net/ipv6/netfilter/ip6t_HL.c index 306200c35057..da14c6d86bcc 100644 --- a/net/ipv6/netfilter/ip6t_HL.c +++ b/net/ipv6/netfilter/ip6t_HL.c @@ -21,6 +21,7 @@ static unsigned int ip6t_hl_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { struct ipv6hdr *ip6h; @@ -63,43 +64,31 @@ static unsigned int ip6t_hl_target(struct sk_buff **pskb, static int ip6t_hl_checkentry(const char *tablename, const void *entry, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { struct ip6t_HL_info *info = targinfo; - if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_HL_info))) { - printk(KERN_WARNING "ip6t_HL: targinfosize %u != %Zu\n", - targinfosize, - IP6T_ALIGN(sizeof(struct ip6t_HL_info))); - return 0; - } - - if (strcmp(tablename, "mangle")) { - printk(KERN_WARNING "ip6t_HL: can only be called from " - "\"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - if (info->mode > IP6T_HL_MAXMODE) { printk(KERN_WARNING "ip6t_HL: invalid or unknown Mode %u\n", info->mode); return 0; } - if ((info->mode != IP6T_HL_SET) && (info->hop_limit == 0)) { printk(KERN_WARNING "ip6t_HL: increment/decrement doesn't " "make sense with value 0\n"); return 0; } - return 1; } static struct ip6t_target ip6t_HL = { .name = "HL", .target = ip6t_hl_target, + .targetsize = sizeof(struct ip6t_HL_info), + .table = "mangle", .checkentry = ip6t_hl_checkentry, .me = THIS_MODULE }; diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 6b930efa9fb9..07c6bcbe4c5f 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -426,6 +426,7 @@ ip6t_log_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -449,35 +450,29 @@ ip6t_log_target(struct sk_buff **pskb, static int ip6t_log_checkentry(const char *tablename, const void *entry, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ip6t_log_info *loginfo = targinfo; - if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_log_info))) { - DEBUGP("LOG: targinfosize %u != %u\n", - targinfosize, IP6T_ALIGN(sizeof(struct ip6t_log_info))); - return 0; - } - if (loginfo->level >= 8) { DEBUGP("LOG: level %u >= 8\n", loginfo->level); return 0; } - if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { DEBUGP("LOG: prefix term %i\n", loginfo->prefix[sizeof(loginfo->prefix)-1]); return 0; } - return 1; } static struct ip6t_target ip6t_log_reg = { .name = "LOG", .target = ip6t_log_target, + .targetsize = sizeof(struct ip6t_log_info), .checkentry = ip6t_log_checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 0e6d1d4bbd5c..ddfa38575fe2 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -179,6 +179,7 @@ static unsigned int reject6_target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -221,6 +222,7 @@ static unsigned int reject6_target(struct sk_buff **pskb, static int check(const char *tablename, const void *entry, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -228,24 +230,6 @@ static int check(const char *tablename, const struct ip6t_reject_info *rejinfo = targinfo; const struct ip6t_entry *e = entry; - if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_reject_info))) { - DEBUGP("ip6t_REJECT: targinfosize %u != 0\n", targinfosize); - return 0; - } - - /* Only allow these for packet filtering. */ - if (strcmp(tablename, "filter") != 0) { - DEBUGP("ip6t_REJECT: bad table `%s'.\n", tablename); - return 0; - } - - if ((hook_mask & ~((1 << NF_IP6_LOCAL_IN) - | (1 << NF_IP6_FORWARD) - | (1 << NF_IP6_LOCAL_OUT))) != 0) { - DEBUGP("ip6t_REJECT: bad hook mask %X\n", hook_mask); - return 0; - } - if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) { printk("ip6t_REJECT: ECHOREPLY is not supported.\n"); return 0; @@ -257,13 +241,16 @@ static int check(const char *tablename, return 0; } } - return 1; } static struct ip6t_target ip6t_reject_reg = { .name = "REJECT", .target = reject6_target, + .targetsize = sizeof(struct ip6t_reject_info), + .table = "filter", + .hooks = (1 << NF_IP6_LOCAL_IN) | (1 << NF_IP6_FORWARD) | + (1 << NF_IP6_LOCAL_OUT), .checkentry = check, .me = THIS_MODULE }; diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 219a30365dff..178f6fb1e53d 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -44,6 +44,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -99,17 +100,13 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *entry, + const struct xt_match *match, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ip6t_ah *ahinfo = matchinfo; - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_ah))) { - DEBUGP("ip6t_ah: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_ah))); - return 0; - } if (ahinfo->invflags & ~IP6T_AH_INV_MASK) { DEBUGP("ip6t_ah: unknown flags %X\n", ahinfo->invflags); return 0; @@ -119,8 +116,9 @@ checkentry(const char *tablename, static struct ip6t_match ah_match = { .name = "ah", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ip6t_ah), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_dst.c b/net/ipv6/netfilter/ip6t_dst.c index b4c153a53500..e97a70226987 100644 --- a/net/ipv6/netfilter/ip6t_dst.c +++ b/net/ipv6/netfilter/ip6t_dst.c @@ -55,6 +55,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -179,22 +180,17 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *info, + const struct xt_match *match, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ip6t_opts *optsinfo = matchinfo; - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_opts))) { - DEBUGP("ip6t_opts: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_opts))); - return 0; - } if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) { DEBUGP("ip6t_opts: unknown flags %X\n", optsinfo->invflags); return 0; } - return 1; } @@ -204,8 +200,9 @@ static struct ip6t_match opts_match = { #else .name = "dst", #endif - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ip6t_opts), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_esp.c b/net/ipv6/netfilter/ip6t_esp.c index 724285df8711..540b8bfd5055 100644 --- a/net/ipv6/netfilter/ip6t_esp.c +++ b/net/ipv6/netfilter/ip6t_esp.c @@ -44,6 +44,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -77,17 +78,13 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ip6t_esp *espinfo = matchinfo; - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_esp))) { - DEBUGP("ip6t_esp: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_esp))); - return 0; - } if (espinfo->invflags & ~IP6T_ESP_INV_MASK) { DEBUGP("ip6t_esp: unknown flags %X\n", espinfo->invflags); @@ -98,8 +95,9 @@ checkentry(const char *tablename, static struct ip6t_match esp_match = { .name = "esp", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ip6t_esp), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_eui64.c b/net/ipv6/netfilter/ip6t_eui64.c index 27396ac0b9ed..d4b0bad52830 100644 --- a/net/ipv6/netfilter/ip6t_eui64.c +++ b/net/ipv6/netfilter/ip6t_eui64.c @@ -22,6 +22,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -60,30 +61,12 @@ match(const struct sk_buff *skb, return 0; } -static int -ip6t_eui64_checkentry(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (hook_mask - & ~((1 << NF_IP6_PRE_ROUTING) | (1 << NF_IP6_LOCAL_IN) | - (1 << NF_IP6_FORWARD))) { - printk("ip6t_eui64: only valid for PRE_ROUTING, LOCAL_IN or FORWARD.\n"); - return 0; - } - - if (matchsize != IP6T_ALIGN(sizeof(int))) - return 0; - - return 1; -} - static struct ip6t_match eui64_match = { .name = "eui64", - .match = &match, - .checkentry = &ip6t_eui64_checkentry, + .match = match, + .matchsize = sizeof(int), + .hooks = (1 << NF_IP6_PRE_ROUTING) | (1 << NF_IP6_LOCAL_IN) | + (1 << NF_IP6_FORWARD), .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index 4c14125a0e26..4c41e14823d5 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -43,6 +43,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -116,29 +117,25 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ip6t_frag *fraginfo = matchinfo; - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_frag))) { - DEBUGP("ip6t_frag: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_frag))); - return 0; - } if (fraginfo->invflags & ~IP6T_FRAG_INV_MASK) { DEBUGP("ip6t_frag: unknown flags %X\n", fraginfo->invflags); return 0; } - return 1; } static struct ip6t_match frag_match = { .name = "frag", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ip6t_frag), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index 37a8474a7e0c..b4a1fdfe6abc 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -55,6 +55,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -179,22 +180,17 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *entry, + const struct xt_match *match, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ip6t_opts *optsinfo = matchinfo; - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_opts))) { - DEBUGP("ip6t_opts: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_opts))); - return 0; - } if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) { DEBUGP("ip6t_opts: unknown flags %X\n", optsinfo->invflags); return 0; } - return 1; } @@ -204,8 +200,9 @@ static struct ip6t_match opts_match = { #else .name = "dst", #endif - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ip6t_opts), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_hl.c b/net/ipv6/netfilter/ip6t_hl.c index c5d9079f2d9d..374055733b26 100644 --- a/net/ipv6/netfilter/ip6t_hl.c +++ b/net/ipv6/netfilter/ip6t_hl.c @@ -18,10 +18,10 @@ MODULE_AUTHOR("Maciej Soltysiak <solt@dns.toxicfilms.tv>"); MODULE_DESCRIPTION("IP tables Hop Limit matching module"); MODULE_LICENSE("GPL"); -static int match(const struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, const void *matchinfo, - int offset, unsigned int protoff, - int *hotdrop) +static int match(const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, + int offset, unsigned int protoff, int *hotdrop) { const struct ip6t_hl_info *info = matchinfo; const struct ipv6hdr *ip6h = skb->nh.ipv6h; @@ -48,20 +48,10 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return 0; } -static int checkentry(const char *tablename, const void *entry, - void *matchinfo, unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_hl_info))) - return 0; - - return 1; -} - static struct ip6t_match hl_match = { .name = "hl", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ip6t_hl_info), .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c index 83ad6b272f7e..9375eeb1369f 100644 --- a/net/ipv6/netfilter/ip6t_ipv6header.c +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -29,6 +29,7 @@ static int ipv6header_match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -125,17 +126,13 @@ ipv6header_match(const struct sk_buff *skb, static int ipv6header_checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { const struct ip6t_ipv6header_info *info = matchinfo; - /* Check for obvious errors */ - /* This match is valid in all hooks! */ - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_ipv6header_info))) - return 0; - /* invflags is 0 or 0xff in hard mode */ if ((!info->modeflag) && info->invflags != 0x00 && info->invflags != 0xFF) @@ -147,6 +144,7 @@ ipv6header_checkentry(const char *tablename, static struct ip6t_match ip6t_ipv6header_match = { .name = "ipv6header", .match = &ipv6header_match, + .matchsize = sizeof(struct ip6t_ipv6header_info), .checkentry = &ipv6header_checkentry, .destroy = NULL, .me = THIS_MODULE, diff --git a/net/ipv6/netfilter/ip6t_multiport.c b/net/ipv6/netfilter/ip6t_multiport.c index 49f7829dfbc2..752b65d21c72 100644 --- a/net/ipv6/netfilter/ip6t_multiport.c +++ b/net/ipv6/netfilter/ip6t_multiport.c @@ -51,6 +51,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -85,6 +86,7 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *info, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) @@ -92,13 +94,9 @@ checkentry(const char *tablename, const struct ip6t_ip6 *ip = info; const struct ip6t_multiport *multiinfo = matchinfo; - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_multiport))) - return 0; - /* Must specify proto == TCP/UDP, no unknown flags or bad count */ return (ip->proto == IPPROTO_TCP || ip->proto == IPPROTO_UDP) && !(ip->invflags & IP6T_INV_PROTO) - && matchsize == IP6T_ALIGN(sizeof(struct ip6t_multiport)) && (multiinfo->flags == IP6T_MULTIPORT_SOURCE || multiinfo->flags == IP6T_MULTIPORT_DESTINATION || multiinfo->flags == IP6T_MULTIPORT_EITHER) @@ -107,8 +105,9 @@ checkentry(const char *tablename, static struct ip6t_match multiport_match = { .name = "multiport", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ip6t_multiport), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_owner.c b/net/ipv6/netfilter/ip6t_owner.c index 8c8a4c7ec934..e2cee3bcdef9 100644 --- a/net/ipv6/netfilter/ip6t_owner.c +++ b/net/ipv6/netfilter/ip6t_owner.c @@ -26,6 +26,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -54,34 +55,27 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { const struct ip6t_owner_info *info = matchinfo; - if (hook_mask - & ~((1 << NF_IP6_LOCAL_OUT) | (1 << NF_IP6_POST_ROUTING))) { - printk("ip6t_owner: only valid for LOCAL_OUT or POST_ROUTING.\n"); - return 0; - } - - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_owner_info))) - return 0; - if (info->match & (IP6T_OWNER_PID | IP6T_OWNER_SID)) { printk("ipt_owner: pid and sid matching " "not supported anymore\n"); return 0; } - return 1; } static struct ip6t_match owner_match = { .name = "owner", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ip6t_owner_info), + .hooks = (1 << NF_IP6_LOCAL_OUT) | (1 << NF_IP6_POST_ROUTING), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/ip6t_policy.c b/net/ipv6/netfilter/ip6t_policy.c deleted file mode 100644 index 3d39ec924041..000000000000 --- a/net/ipv6/netfilter/ip6t_policy.c +++ /dev/null @@ -1,176 +0,0 @@ -/* IP tables module for matching IPsec policy - * - * Copyright (c) 2004,2005 Patrick McHardy, <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/config.h> -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/init.h> -#include <net/xfrm.h> - -#include <linux/netfilter_ipv6.h> -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv6/ip6t_policy.h> - -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_DESCRIPTION("IPtables IPsec policy matching module"); -MODULE_LICENSE("GPL"); - - -static inline int -match_xfrm_state(struct xfrm_state *x, const struct ip6t_policy_elem *e) -{ -#define MATCH_ADDR(x,y,z) (!e->match.x || \ - ((!ip6_masked_addrcmp(&e->x.a6, &e->y.a6, z)) \ - ^ e->invert.x)) -#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) - - return MATCH_ADDR(saddr, smask, (struct in6_addr *)&x->props.saddr.a6) && - MATCH_ADDR(daddr, dmask, (struct in6_addr *)&x->id.daddr.a6) && - MATCH(proto, x->id.proto) && - MATCH(mode, x->props.mode) && - MATCH(spi, x->id.spi) && - MATCH(reqid, x->props.reqid); -} - -static int -match_policy_in(const struct sk_buff *skb, const struct ip6t_policy_info *info) -{ - const struct ip6t_policy_elem *e; - struct sec_path *sp = skb->sp; - int strict = info->flags & IP6T_POLICY_MATCH_STRICT; - int i, pos; - - if (sp == NULL) - return -1; - if (strict && info->len != sp->len) - return 0; - - for (i = sp->len - 1; i >= 0; i--) { - pos = strict ? i - sp->len + 1 : 0; - if (pos >= info->len) - return 0; - e = &info->pol[pos]; - - if (match_xfrm_state(sp->x[i].xvec, e)) { - if (!strict) - return 1; - } else if (strict) - return 0; - } - - return strict ? 1 : 0; -} - -static int -match_policy_out(const struct sk_buff *skb, const struct ip6t_policy_info *info) -{ - const struct ip6t_policy_elem *e; - struct dst_entry *dst = skb->dst; - int strict = info->flags & IP6T_POLICY_MATCH_STRICT; - int i, pos; - - if (dst->xfrm == NULL) - return -1; - - for (i = 0; dst && dst->xfrm; dst = dst->child, i++) { - pos = strict ? i : 0; - if (pos >= info->len) - return 0; - e = &info->pol[pos]; - - if (match_xfrm_state(dst->xfrm, e)) { - if (!strict) - return 1; - } else if (strict) - return 0; - } - - return strict ? i == info->len : 0; -} - -static int match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - const struct ip6t_policy_info *info = matchinfo; - int ret; - - if (info->flags & IP6T_POLICY_MATCH_IN) - ret = match_policy_in(skb, info); - else - ret = match_policy_out(skb, info); - - if (ret < 0) - ret = info->flags & IP6T_POLICY_MATCH_NONE ? 1 : 0; - else if (info->flags & IP6T_POLICY_MATCH_NONE) - ret = 0; - - return ret; -} - -static int checkentry(const char *tablename, const void *ip_void, - void *matchinfo, unsigned int matchsize, - unsigned int hook_mask) -{ - struct ip6t_policy_info *info = matchinfo; - - if (matchsize != IP6T_ALIGN(sizeof(*info))) { - printk(KERN_ERR "ip6t_policy: matchsize %u != %zu\n", - matchsize, IP6T_ALIGN(sizeof(*info))); - return 0; - } - if (!(info->flags & (IP6T_POLICY_MATCH_IN|IP6T_POLICY_MATCH_OUT))) { - printk(KERN_ERR "ip6t_policy: neither incoming nor " - "outgoing policy selected\n"); - return 0; - } - if (hook_mask & (1 << NF_IP6_PRE_ROUTING | 1 << NF_IP6_LOCAL_IN) - && info->flags & IP6T_POLICY_MATCH_OUT) { - printk(KERN_ERR "ip6t_policy: output policy not valid in " - "PRE_ROUTING and INPUT\n"); - return 0; - } - if (hook_mask & (1 << NF_IP6_POST_ROUTING | 1 << NF_IP6_LOCAL_OUT) - && info->flags & IP6T_POLICY_MATCH_IN) { - printk(KERN_ERR "ip6t_policy: input policy not valid in " - "POST_ROUTING and OUTPUT\n"); - return 0; - } - if (info->len > IP6T_POLICY_MAX_ELEM) { - printk(KERN_ERR "ip6t_policy: too many policy elements\n"); - return 0; - } - - return 1; -} - -static struct ip6t_match policy_match = { - .name = "policy", - .match = match, - .checkentry = checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&policy_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&policy_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index 8f82476dc89e..4c6b55bb225b 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -45,6 +45,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -194,17 +195,13 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *entry, + const struct xt_match *match, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ip6t_rt *rtinfo = matchinfo; - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_rt))) { - DEBUGP("ip6t_rt: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_rt))); - return 0; - } if (rtinfo->invflags & ~IP6T_RT_INV_MASK) { DEBUGP("ip6t_rt: unknown flags %X\n", rtinfo->invflags); return 0; @@ -222,8 +219,9 @@ checkentry(const char *tablename, static struct ip6t_match rt_match = { .name = "rt", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct ip6t_rt), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index ac702a29dd16..ac35f9526368 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -179,31 +179,36 @@ static unsigned int ipv6_confirm(unsigned int hooknum, int (*okfn)(struct sk_buff *)) { struct nf_conn *ct; + struct nf_conn_help *help; enum ip_conntrack_info ctinfo; + unsigned int ret, protoff; + unsigned int extoff = (u8*)((*pskb)->nh.ipv6h + 1) + - (*pskb)->data; + unsigned char pnum = (*pskb)->nh.ipv6h->nexthdr; + /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(*pskb, &ctinfo); - if (ct && ct->helper) { - unsigned int ret, protoff; - unsigned int extoff = (u8*)((*pskb)->nh.ipv6h + 1) - - (*pskb)->data; - unsigned char pnum = (*pskb)->nh.ipv6h->nexthdr; - - protoff = nf_ct_ipv6_skip_exthdr(*pskb, extoff, &pnum, - (*pskb)->len - extoff); - if (protoff < 0 || protoff > (*pskb)->len || - pnum == NEXTHDR_FRAGMENT) { - DEBUGP("proto header not found\n"); - return NF_ACCEPT; - } + if (!ct) + goto out; - ret = ct->helper->help(pskb, protoff, ct, ctinfo); - if (ret != NF_ACCEPT) - return ret; + help = nfct_help(ct); + if (!help || !help->helper) + goto out; + + protoff = nf_ct_ipv6_skip_exthdr(*pskb, extoff, &pnum, + (*pskb)->len - extoff); + if (protoff < 0 || protoff > (*pskb)->len || + pnum == NEXTHDR_FRAGMENT) { + DEBUGP("proto header not found\n"); + return NF_ACCEPT; } + ret = help->helper->help(pskb, protoff, ct, ctinfo); + if (ret != NF_ACCEPT) + return ret; +out: /* We've seen it coming out the other side: confirm it */ - return nf_conntrack_confirm(pskb); } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 84ef9a13108d..3e319035f82d 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -313,8 +313,8 @@ static struct nf_ct_frag6_queue *nf_ct_frag6_intern(unsigned int hash, #ifdef CONFIG_SMP hlist_for_each_entry(fq, n, &nf_ct_frag6_hash[hash], list) { if (fq->id == fq_in->id && - !ipv6_addr_cmp(&fq_in->saddr, &fq->saddr) && - !ipv6_addr_cmp(&fq_in->daddr, &fq->daddr)) { + ipv6_addr_equal(&fq_in->saddr, &fq->saddr) && + ipv6_addr_equal(&fq_in->daddr, &fq->daddr)) { atomic_inc(&fq->refcnt); write_unlock(&nf_ct_frag6_lock); fq_in->last_in |= COMPLETE; @@ -376,8 +376,8 @@ fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst) read_lock(&nf_ct_frag6_lock); hlist_for_each_entry(fq, n, &nf_ct_frag6_hash[hash], list) { if (fq->id == id && - !ipv6_addr_cmp(src, &fq->saddr) && - !ipv6_addr_cmp(dst, &fq->daddr)) { + ipv6_addr_equal(src, &fq->saddr) && + ipv6_addr_equal(dst, &fq->daddr)) { atomic_inc(&fq->refcnt); read_unlock(&nf_ct_frag6_lock); return fq; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ae20a0ec9bd8..fa1ce0ae123e 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -859,29 +859,12 @@ static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, } -static int rawv6_setsockopt(struct sock *sk, int level, int optname, +static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; - switch(level) { - case SOL_RAW: - break; - - case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) - return -EOPNOTSUPP; - return rawv6_seticmpfilter(sk, level, optname, optval, - optlen); - case SOL_IPV6: - if (optname == IPV6_CHECKSUM) - break; - default: - return ipv6_setsockopt(sk, level, optname, optval, - optlen); - }; - if (get_user(val, (int __user *)optval)) return -EFAULT; @@ -906,12 +889,9 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, } } -static int rawv6_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) +static int rawv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) { - struct raw6_sock *rp = raw6_sk(sk); - int val, len; - switch(level) { case SOL_RAW: break; @@ -919,15 +899,45 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, case SOL_ICMPV6: if (inet_sk(sk)->num != IPPROTO_ICMPV6) return -EOPNOTSUPP; - return rawv6_geticmpfilter(sk, level, optname, optval, + return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM) break; default: - return ipv6_getsockopt(sk, level, optname, optval, + return ipv6_setsockopt(sk, level, optname, optval, optlen); }; + return do_rawv6_setsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + switch (level) { + case SOL_RAW: + break; + case SOL_ICMPV6: + if (inet_sk(sk)->num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + return rawv6_seticmpfilter(sk, level, optname, optval, optlen); + case SOL_IPV6: + if (optname == IPV6_CHECKSUM) + break; + default: + return compat_ipv6_setsockopt(sk, level, optname, + optval, optlen); + }; + return do_rawv6_setsockopt(sk, level, optname, optval, optlen); +} +#endif + +static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct raw6_sock *rp = raw6_sk(sk); + int val, len; if (get_user(len,optlen)) return -EFAULT; @@ -953,6 +963,50 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, return 0; } +static int rawv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + switch(level) { + case SOL_RAW: + break; + + case SOL_ICMPV6: + if (inet_sk(sk)->num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + return rawv6_geticmpfilter(sk, level, optname, optval, + optlen); + case SOL_IPV6: + if (optname == IPV6_CHECKSUM) + break; + default: + return ipv6_getsockopt(sk, level, optname, optval, + optlen); + }; + return do_rawv6_getsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + switch (level) { + case SOL_RAW: + break; + case SOL_ICMPV6: + if (inet_sk(sk)->num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + return rawv6_geticmpfilter(sk, level, optname, optval, optlen); + case SOL_IPV6: + if (optname == IPV6_CHECKSUM) + break; + default: + return compat_ipv6_getsockopt(sk, level, optname, + optval, optlen); + }; + return do_rawv6_getsockopt(sk, level, optname, optval, optlen); +} +#endif + static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch(cmd) { @@ -998,23 +1052,27 @@ static int rawv6_init_sk(struct sock *sk) } struct proto rawv6_prot = { - .name = "RAWv6", - .owner = THIS_MODULE, - .close = rawv6_close, - .connect = ip6_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = rawv6_ioctl, - .init = rawv6_init_sk, - .destroy = inet6_destroy_sock, - .setsockopt = rawv6_setsockopt, - .getsockopt = rawv6_getsockopt, - .sendmsg = rawv6_sendmsg, - .recvmsg = rawv6_recvmsg, - .bind = rawv6_bind, - .backlog_rcv = rawv6_rcv_skb, - .hash = raw_v6_hash, - .unhash = raw_v6_unhash, - .obj_size = sizeof(struct raw6_sock), + .name = "RAWv6", + .owner = THIS_MODULE, + .close = rawv6_close, + .connect = ip6_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = rawv6_ioctl, + .init = rawv6_init_sk, + .destroy = inet6_destroy_sock, + .setsockopt = rawv6_setsockopt, + .getsockopt = rawv6_getsockopt, + .sendmsg = rawv6_sendmsg, + .recvmsg = rawv6_recvmsg, + .bind = rawv6_bind, + .backlog_rcv = rawv6_rcv_skb, + .hash = raw_v6_hash, + .unhash = raw_v6_unhash, + .obj_size = sizeof(struct raw6_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_rawv6_setsockopt, + .compat_getsockopt = compat_rawv6_getsockopt, +#endif }; #ifdef CONFIG_PROC_FS @@ -1140,7 +1198,7 @@ static int raw6_seq_open(struct inode *inode, struct file *file) { struct seq_file *seq; int rc = -ENOMEM; - struct raw6_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL); + struct raw6_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL); if (!s) goto out; rc = seq_open(file, &raw6_seq_ops); @@ -1148,7 +1206,6 @@ static int raw6_seq_open(struct inode *inode, struct file *file) goto out_kfree; seq = file->private_data; seq->private = s; - memset(s, 0, sizeof(*s)); out: return rc; out_kfree: diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 15e1456b3f18..b67a45fb93e9 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -203,7 +203,7 @@ static inline void frag_free_queue(struct frag_queue *fq, int *work) static inline struct frag_queue *frag_alloc_queue(void) { - struct frag_queue *fq = kmalloc(sizeof(struct frag_queue), GFP_ATOMIC); + struct frag_queue *fq = kzalloc(sizeof(struct frag_queue), GFP_ATOMIC); if(!fq) return NULL; @@ -288,6 +288,7 @@ static void ip6_evictor(void) static void ip6_frag_expire(unsigned long data) { struct frag_queue *fq = (struct frag_queue *) data; + struct net_device *dev; spin_lock(&fq->lock); @@ -299,22 +300,22 @@ static void ip6_frag_expire(unsigned long data) IP6_INC_STATS_BH(IPSTATS_MIB_REASMTIMEOUT); IP6_INC_STATS_BH(IPSTATS_MIB_REASMFAILS); - /* Send error only if the first segment arrived. */ - if (fq->last_in&FIRST_IN && fq->fragments) { - struct net_device *dev = dev_get_by_index(fq->iif); + /* Don't send error if the first segment did not arrive. */ + if (!(fq->last_in&FIRST_IN) || !fq->fragments) + goto out; - /* - But use as source device on which LAST ARRIVED - segment was received. And do not use fq->dev - pointer directly, device might already disappeared. - */ - if (dev) { - fq->fragments->dev = dev; - icmpv6_send(fq->fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, - dev); - dev_put(dev); - } - } + dev = dev_get_by_index(fq->iif); + if (!dev) + goto out; + + /* + But use as source device on which LAST ARRIVED + segment was received. And do not use fq->dev + pointer directly, device might already disappeared. + */ + fq->fragments->dev = dev; + icmpv6_send(fq->fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, dev); + dev_put(dev); out: spin_unlock(&fq->lock); fq_put(fq, NULL); @@ -368,8 +369,6 @@ ip6_frag_create(unsigned int hash, u32 id, struct in6_addr *src, struct in6_addr if ((fq = frag_alloc_queue()) == NULL) goto oom; - memset(fq, 0, sizeof(struct frag_queue)); - fq->id = id; ipv6_addr_copy(&fq->saddr, src); ipv6_addr_copy(&fq->daddr, dst); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e0d3ad02ffb5..79078747a646 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -72,6 +72,10 @@ #define RT6_TRACE(x...) do { ; } while (0) #endif +#define CLONE_OFFLINK_ROUTE 0 + +#define RT6_SELECT_F_IFACE 0x1 +#define RT6_SELECT_F_REACHABLE 0x2 static int ip6_rt_max_size = 4096; static int ip6_rt_gc_min_interval = HZ / 2; @@ -94,6 +98,14 @@ static int ip6_pkt_discard_out(struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu); +#ifdef CONFIG_IPV6_ROUTE_INFO +static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixlen, + struct in6_addr *gwaddr, int ifindex, + unsigned pref); +static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixlen, + struct in6_addr *gwaddr, int ifindex); +#endif + static struct dst_ops ip6_dst_ops = { .family = AF_INET6, .protocol = __constant_htons(ETH_P_IPV6), @@ -214,150 +226,211 @@ static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt, return rt; } +#ifdef CONFIG_IPV6_ROUTER_PREF +static void rt6_probe(struct rt6_info *rt) +{ + struct neighbour *neigh = rt ? rt->rt6i_nexthop : NULL; + /* + * Okay, this does not seem to be appropriate + * for now, however, we need to check if it + * is really so; aka Router Reachability Probing. + * + * Router Reachability Probe MUST be rate-limited + * to no more than one per minute. + */ + if (!neigh || (neigh->nud_state & NUD_VALID)) + return; + read_lock_bh(&neigh->lock); + if (!(neigh->nud_state & NUD_VALID) && + time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { + struct in6_addr mcaddr; + struct in6_addr *target; + + neigh->updated = jiffies; + read_unlock_bh(&neigh->lock); + + target = (struct in6_addr *)&neigh->primary_key; + addrconf_addr_solict_mult(target, &mcaddr); + ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL); + } else + read_unlock_bh(&neigh->lock); +} +#else +static inline void rt6_probe(struct rt6_info *rt) +{ + return; +} +#endif + /* - * pointer to the last default router chosen. BH is disabled locally. + * Default Router Selection (RFC 2461 6.3.6) */ -static struct rt6_info *rt6_dflt_pointer; -static DEFINE_SPINLOCK(rt6_dflt_lock); +static int inline rt6_check_dev(struct rt6_info *rt, int oif) +{ + struct net_device *dev = rt->rt6i_dev; + if (!oif || dev->ifindex == oif) + return 2; + if ((dev->flags & IFF_LOOPBACK) && + rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif) + return 1; + return 0; +} -void rt6_reset_dflt_pointer(struct rt6_info *rt) +static int inline rt6_check_neigh(struct rt6_info *rt) { - spin_lock_bh(&rt6_dflt_lock); - if (rt == NULL || rt == rt6_dflt_pointer) { - RT6_TRACE("reset default router: %p->NULL\n", rt6_dflt_pointer); - rt6_dflt_pointer = NULL; + struct neighbour *neigh = rt->rt6i_nexthop; + int m = 0; + if (neigh) { + read_lock_bh(&neigh->lock); + if (neigh->nud_state & NUD_VALID) + m = 1; + read_unlock_bh(&neigh->lock); } - spin_unlock_bh(&rt6_dflt_lock); + return m; } -/* Default Router Selection (RFC 2461 6.3.6) */ -static struct rt6_info *rt6_best_dflt(struct rt6_info *rt, int oif) +static int rt6_score_route(struct rt6_info *rt, int oif, + int strict) { - struct rt6_info *match = NULL; - struct rt6_info *sprt; - int mpri = 0; - - for (sprt = rt; sprt; sprt = sprt->u.next) { - struct neighbour *neigh; - int m = 0; - - if (!oif || - (sprt->rt6i_dev && - sprt->rt6i_dev->ifindex == oif)) - m += 8; + int m = rt6_check_dev(rt, oif); + if (!m && (strict & RT6_SELECT_F_IFACE)) + return -1; +#ifdef CONFIG_IPV6_ROUTER_PREF + m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; +#endif + if (rt6_check_neigh(rt)) + m |= 16; + else if (strict & RT6_SELECT_F_REACHABLE) + return -1; + return m; +} - if (rt6_check_expired(sprt)) - continue; +static struct rt6_info *rt6_select(struct rt6_info **head, int oif, + int strict) +{ + struct rt6_info *match = NULL, *last = NULL; + struct rt6_info *rt, *rt0 = *head; + u32 metric; + int mpri = -1; - if (sprt == rt6_dflt_pointer) - m += 4; + RT6_TRACE("%s(head=%p(*head=%p), oif=%d)\n", + __FUNCTION__, head, head ? *head : NULL, oif); - if ((neigh = sprt->rt6i_nexthop) != NULL) { - read_lock_bh(&neigh->lock); - switch (neigh->nud_state) { - case NUD_REACHABLE: - m += 3; - break; + for (rt = rt0, metric = rt0->rt6i_metric; + rt && rt->rt6i_metric == metric; + rt = rt->u.next) { + int m; - case NUD_STALE: - case NUD_DELAY: - case NUD_PROBE: - m += 2; - break; + if (rt6_check_expired(rt)) + continue; - case NUD_NOARP: - case NUD_PERMANENT: - m += 1; - break; + last = rt; - case NUD_INCOMPLETE: - default: - read_unlock_bh(&neigh->lock); - continue; - } - read_unlock_bh(&neigh->lock); - } else { + m = rt6_score_route(rt, oif, strict); + if (m < 0) continue; - } - if (m > mpri || m >= 12) { - match = sprt; + if (m > mpri) { + rt6_probe(match); + match = rt; mpri = m; - if (m >= 12) { - /* we choose the last default router if it - * is in (probably) reachable state. - * If route changed, we should do pmtu - * discovery. --yoshfuji - */ - break; - } + } else { + rt6_probe(rt); } } - spin_lock(&rt6_dflt_lock); - if (!match) { - /* - * No default routers are known to be reachable. - * SHOULD round robin - */ - if (rt6_dflt_pointer) { - for (sprt = rt6_dflt_pointer->u.next; - sprt; sprt = sprt->u.next) { - if (sprt->u.dst.obsolete <= 0 && - sprt->u.dst.error == 0 && - !rt6_check_expired(sprt)) { - match = sprt; - break; - } - } - for (sprt = rt; - !match && sprt; - sprt = sprt->u.next) { - if (sprt->u.dst.obsolete <= 0 && - sprt->u.dst.error == 0 && - !rt6_check_expired(sprt)) { - match = sprt; - break; - } - if (sprt == rt6_dflt_pointer) - break; - } - } + if (!match && + (strict & RT6_SELECT_F_REACHABLE) && + last && last != rt0) { + /* no entries matched; do round-robin */ + *head = rt0->u.next; + rt0->u.next = last->u.next; + last->u.next = rt0; } - if (match) { - if (rt6_dflt_pointer != match) - RT6_TRACE("changed default router: %p->%p\n", - rt6_dflt_pointer, match); - rt6_dflt_pointer = match; + RT6_TRACE("%s() => %p, score=%d\n", + __FUNCTION__, match, mpri); + + return (match ? match : &ip6_null_entry); +} + +#ifdef CONFIG_IPV6_ROUTE_INFO +int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, + struct in6_addr *gwaddr) +{ + struct route_info *rinfo = (struct route_info *) opt; + struct in6_addr prefix_buf, *prefix; + unsigned int pref; + u32 lifetime; + struct rt6_info *rt; + + if (len < sizeof(struct route_info)) { + return -EINVAL; } - spin_unlock(&rt6_dflt_lock); - if (!match) { - /* - * Last Resort: if no default routers found, - * use addrconf default route. - * We don't record this route. - */ - for (sprt = ip6_routing_table.leaf; - sprt; sprt = sprt->u.next) { - if (!rt6_check_expired(sprt) && - (sprt->rt6i_flags & RTF_DEFAULT) && - (!oif || - (sprt->rt6i_dev && - sprt->rt6i_dev->ifindex == oif))) { - match = sprt; - break; - } + /* Sanity check for prefix_len and length */ + if (rinfo->length > 3) { + return -EINVAL; + } else if (rinfo->prefix_len > 128) { + return -EINVAL; + } else if (rinfo->prefix_len > 64) { + if (rinfo->length < 2) { + return -EINVAL; } - if (!match) { - /* no default route. give up. */ - match = &ip6_null_entry; + } else if (rinfo->prefix_len > 0) { + if (rinfo->length < 1) { + return -EINVAL; } } - return match; + pref = rinfo->route_pref; + if (pref == ICMPV6_ROUTER_PREF_INVALID) + pref = ICMPV6_ROUTER_PREF_MEDIUM; + + lifetime = htonl(rinfo->lifetime); + if (lifetime == 0xffffffff) { + /* infinity */ + } else if (lifetime > 0x7fffffff/HZ) { + /* Avoid arithmetic overflow */ + lifetime = 0x7fffffff/HZ - 1; + } + + if (rinfo->length == 3) + prefix = (struct in6_addr *)rinfo->prefix; + else { + /* this function is safe */ + ipv6_addr_prefix(&prefix_buf, + (struct in6_addr *)rinfo->prefix, + rinfo->prefix_len); + prefix = &prefix_buf; + } + + rt = rt6_get_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex); + + if (rt && !lifetime) { + ip6_del_rt(rt, NULL, NULL, NULL); + rt = NULL; + } + + if (!rt && lifetime) + rt = rt6_add_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex, + pref); + else if (rt) + rt->rt6i_flags = RTF_ROUTEINFO | + (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); + + if (rt) { + if (lifetime == 0xffffffff) { + rt->rt6i_flags &= ~RTF_EXPIRES; + } else { + rt->rt6i_expires = jiffies + HZ * lifetime; + rt->rt6i_flags |= RTF_EXPIRES; + } + dst_release(&rt->u.dst); + } + return 0; } +#endif struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, int oif, int strict) @@ -397,14 +470,9 @@ int ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh, return err; } -/* No rt6_lock! If COW failed, the function returns dead route entry - with dst->error set to errno value. - */ - -static struct rt6_info *rt6_cow(struct rt6_info *ort, struct in6_addr *daddr, - struct in6_addr *saddr, struct netlink_skb_parms *req) +static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr, + struct in6_addr *saddr) { - int err; struct rt6_info *rt; /* @@ -435,25 +503,30 @@ static struct rt6_info *rt6_cow(struct rt6_info *ort, struct in6_addr *daddr, rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); - dst_hold(&rt->u.dst); - - err = ip6_ins_rt(rt, NULL, NULL, req); - if (err == 0) - return rt; + } - rt->u.dst.error = err; + return rt; +} - return rt; +static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *daddr) +{ + struct rt6_info *rt = ip6_rt_copy(ort); + if (rt) { + ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); + rt->rt6i_dst.plen = 128; + rt->rt6i_flags |= RTF_CACHE; + if (rt->rt6i_flags & RTF_REJECT) + rt->u.dst.error = ort->u.dst.error; + rt->u.dst.flags |= DST_HOST; + rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop); } - dst_hold(&ip6_null_entry.u.dst); - return &ip6_null_entry; + return rt; } #define BACKTRACK() \ -if (rt == &ip6_null_entry && strict) { \ +if (rt == &ip6_null_entry) { \ while ((fn = fn->parent) != NULL) { \ if (fn->fn_flags & RTN_ROOT) { \ - dst_hold(&rt->u.dst); \ goto out; \ } \ if (fn->fn_flags & RTN_RTINFO) \ @@ -465,115 +538,138 @@ if (rt == &ip6_null_entry && strict) { \ void ip6_route_input(struct sk_buff *skb) { struct fib6_node *fn; - struct rt6_info *rt; + struct rt6_info *rt, *nrt; int strict; int attempts = 3; + int err; + int reachable = RT6_SELECT_F_REACHABLE; - strict = ipv6_addr_type(&skb->nh.ipv6h->daddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL); + strict = ipv6_addr_type(&skb->nh.ipv6h->daddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0; relookup: read_lock_bh(&rt6_lock); +restart_2: fn = fib6_lookup(&ip6_routing_table, &skb->nh.ipv6h->daddr, &skb->nh.ipv6h->saddr); restart: - rt = fn->leaf; - - if ((rt->rt6i_flags & RTF_CACHE)) { - rt = rt6_device_match(rt, skb->dev->ifindex, strict); - BACKTRACK(); - dst_hold(&rt->u.dst); - goto out; - } - - rt = rt6_device_match(rt, skb->dev->ifindex, strict); + rt = rt6_select(&fn->leaf, skb->dev->ifindex, strict | reachable); BACKTRACK(); + if (rt == &ip6_null_entry || + rt->rt6i_flags & RTF_CACHE) + goto out; - if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) { - struct rt6_info *nrt; - dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + dst_hold(&rt->u.dst); + read_unlock_bh(&rt6_lock); - nrt = rt6_cow(rt, &skb->nh.ipv6h->daddr, - &skb->nh.ipv6h->saddr, - &NETLINK_CB(skb)); + if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) + nrt = rt6_alloc_cow(rt, &skb->nh.ipv6h->daddr, &skb->nh.ipv6h->saddr); + else { +#if CLONE_OFFLINK_ROUTE + nrt = rt6_alloc_clone(rt, &skb->nh.ipv6h->daddr); +#else + goto out2; +#endif + } - dst_release(&rt->u.dst); - rt = nrt; + dst_release(&rt->u.dst); + rt = nrt ? : &ip6_null_entry; - if (rt->u.dst.error != -EEXIST || --attempts <= 0) + dst_hold(&rt->u.dst); + if (nrt) { + err = ip6_ins_rt(nrt, NULL, NULL, &NETLINK_CB(skb)); + if (!err) goto out2; - - /* Race condition! In the gap, when rt6_lock was - released someone could insert this route. Relookup. - */ - dst_release(&rt->u.dst); - goto relookup; } - dst_hold(&rt->u.dst); + + if (--attempts <= 0) + goto out2; + + /* + * Race condition! In the gap, when rt6_lock was + * released someone could insert this route. Relookup. + */ + dst_release(&rt->u.dst); + goto relookup; out: + if (reachable) { + reachable = 0; + goto restart_2; + } + dst_hold(&rt->u.dst); read_unlock_bh(&rt6_lock); out2: rt->u.dst.lastuse = jiffies; rt->u.dst.__use++; skb->dst = (struct dst_entry *) rt; + return; } struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl) { struct fib6_node *fn; - struct rt6_info *rt; + struct rt6_info *rt, *nrt; int strict; int attempts = 3; + int err; + int reachable = RT6_SELECT_F_REACHABLE; - strict = ipv6_addr_type(&fl->fl6_dst) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL); + strict = ipv6_addr_type(&fl->fl6_dst) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0; relookup: read_lock_bh(&rt6_lock); +restart_2: fn = fib6_lookup(&ip6_routing_table, &fl->fl6_dst, &fl->fl6_src); restart: - rt = fn->leaf; - - if ((rt->rt6i_flags & RTF_CACHE)) { - rt = rt6_device_match(rt, fl->oif, strict); - BACKTRACK(); - dst_hold(&rt->u.dst); + rt = rt6_select(&fn->leaf, fl->oif, strict | reachable); + BACKTRACK(); + if (rt == &ip6_null_entry || + rt->rt6i_flags & RTF_CACHE) goto out; - } - if (rt->rt6i_flags & RTF_DEFAULT) { - if (rt->rt6i_metric >= IP6_RT_PRIO_ADDRCONF) - rt = rt6_best_dflt(rt, fl->oif); - } else { - rt = rt6_device_match(rt, fl->oif, strict); - BACKTRACK(); - } - if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) { - struct rt6_info *nrt; - dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + dst_hold(&rt->u.dst); + read_unlock_bh(&rt6_lock); - nrt = rt6_cow(rt, &fl->fl6_dst, &fl->fl6_src, NULL); + if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) + nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src); + else { +#if CLONE_OFFLINK_ROUTE + nrt = rt6_alloc_clone(rt, &fl->fl6_dst); +#else + goto out2; +#endif + } - dst_release(&rt->u.dst); - rt = nrt; + dst_release(&rt->u.dst); + rt = nrt ? : &ip6_null_entry; - if (rt->u.dst.error != -EEXIST || --attempts <= 0) + dst_hold(&rt->u.dst); + if (nrt) { + err = ip6_ins_rt(nrt, NULL, NULL, NULL); + if (!err) goto out2; - - /* Race condition! In the gap, when rt6_lock was - released someone could insert this route. Relookup. - */ - dst_release(&rt->u.dst); - goto relookup; } - dst_hold(&rt->u.dst); + + if (--attempts <= 0) + goto out2; + + /* + * Race condition! In the gap, when rt6_lock was + * released someone could insert this route. Relookup. + */ + dst_release(&rt->u.dst); + goto relookup; out: + if (reachable) { + reachable = 0; + goto restart_2; + } + dst_hold(&rt->u.dst); read_unlock_bh(&rt6_lock); out2: rt->u.dst.lastuse = jiffies; @@ -999,8 +1095,6 @@ int ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct write_lock_bh(&rt6_lock); - rt6_reset_dflt_pointer(NULL); - err = fib6_del(rt, nlh, _rtattr, req); dst_release(&rt->u.dst); @@ -1050,59 +1144,63 @@ static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_r void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr, struct neighbour *neigh, u8 *lladdr, int on_link) { - struct rt6_info *rt, *nrt; - - /* Locate old route to this destination. */ - rt = rt6_lookup(dest, NULL, neigh->dev->ifindex, 1); - - if (rt == NULL) - return; - - if (neigh->dev != rt->rt6i_dev) - goto out; + struct rt6_info *rt, *nrt = NULL; + int strict; + struct fib6_node *fn; /* - * Current route is on-link; redirect is always invalid. - * - * Seems, previous statement is not true. It could - * be node, which looks for us as on-link (f.e. proxy ndisc) - * But then router serving it might decide, that we should - * know truth 8)8) --ANK (980726). + * Get the "current" route for this destination and + * check if the redirect has come from approriate router. + * + * RFC 2461 specifies that redirects should only be + * accepted if they come from the nexthop to the target. + * Due to the way the routes are chosen, this notion + * is a bit fuzzy and one might need to check all possible + * routes. */ - if (!(rt->rt6i_flags&RTF_GATEWAY)) - goto out; + strict = ipv6_addr_type(dest) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL); - /* - * RFC 2461 specifies that redirects should only be - * accepted if they come from the nexthop to the target. - * Due to the way default routers are chosen, this notion - * is a bit fuzzy and one might need to check all default - * routers. - */ - if (!ipv6_addr_equal(saddr, &rt->rt6i_gateway)) { - if (rt->rt6i_flags & RTF_DEFAULT) { - struct rt6_info *rt1; - - read_lock(&rt6_lock); - for (rt1 = ip6_routing_table.leaf; rt1; rt1 = rt1->u.next) { - if (ipv6_addr_equal(saddr, &rt1->rt6i_gateway)) { - dst_hold(&rt1->u.dst); - dst_release(&rt->u.dst); - read_unlock(&rt6_lock); - rt = rt1; - goto source_ok; - } - } - read_unlock(&rt6_lock); + read_lock_bh(&rt6_lock); + fn = fib6_lookup(&ip6_routing_table, dest, NULL); +restart: + for (rt = fn->leaf; rt; rt = rt->u.next) { + /* + * Current route is on-link; redirect is always invalid. + * + * Seems, previous statement is not true. It could + * be node, which looks for us as on-link (f.e. proxy ndisc) + * But then router serving it might decide, that we should + * know truth 8)8) --ANK (980726). + */ + if (rt6_check_expired(rt)) + continue; + if (!(rt->rt6i_flags & RTF_GATEWAY)) + continue; + if (neigh->dev != rt->rt6i_dev) + continue; + if (!ipv6_addr_equal(saddr, &rt->rt6i_gateway)) + continue; + break; + } + if (rt) + dst_hold(&rt->u.dst); + else if (strict) { + while ((fn = fn->parent) != NULL) { + if (fn->fn_flags & RTN_ROOT) + break; + if (fn->fn_flags & RTN_RTINFO) + goto restart; } + } + read_unlock_bh(&rt6_lock); + + if (!rt) { if (net_ratelimit()) printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop " "for redirect target\n"); - goto out; + return; } -source_ok: - /* * We have finally decided to accept it. */ @@ -1210,38 +1308,27 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, 1. It is connected route. Action: COW 2. It is gatewayed route or NONEXTHOP route. Action: clone it. */ - if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) { - nrt = rt6_cow(rt, daddr, saddr, NULL); - if (!nrt->u.dst.error) { - nrt->u.dst.metrics[RTAX_MTU-1] = pmtu; - if (allfrag) - nrt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; - /* According to RFC 1981, detecting PMTU increase shouldn't be - happened within 5 mins, the recommended timer is 10 mins. - Here this route expiration time is set to ip6_rt_mtu_expires - which is 10 mins. After 10 mins the decreased pmtu is expired - and detecting PMTU increase will be automatically happened. - */ - dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires); - nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES; - } - dst_release(&nrt->u.dst); - } else { - nrt = ip6_rt_copy(rt); - if (nrt == NULL) - goto out; - ipv6_addr_copy(&nrt->rt6i_dst.addr, daddr); - nrt->rt6i_dst.plen = 128; - nrt->u.dst.flags |= DST_HOST; - nrt->rt6i_nexthop = neigh_clone(rt->rt6i_nexthop); - dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires); - nrt->rt6i_flags |= RTF_DYNAMIC|RTF_CACHE|RTF_EXPIRES; + if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) + nrt = rt6_alloc_cow(rt, daddr, saddr); + else + nrt = rt6_alloc_clone(rt, daddr); + + if (nrt) { nrt->u.dst.metrics[RTAX_MTU-1] = pmtu; if (allfrag) nrt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + + /* According to RFC 1981, detecting PMTU increase shouldn't be + * happened within 5 mins, the recommended timer is 10 mins. + * Here this route expiration time is set to ip6_rt_mtu_expires + * which is 10 mins. After 10 mins the decreased pmtu is expired + * and detecting PMTU increase will be automatically happened. + */ + dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires); + nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES; + ip6_ins_rt(nrt, NULL, NULL, NULL); } - out: dst_release(&rt->u.dst); } @@ -1280,6 +1367,57 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) return rt; } +#ifdef CONFIG_IPV6_ROUTE_INFO +static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixlen, + struct in6_addr *gwaddr, int ifindex) +{ + struct fib6_node *fn; + struct rt6_info *rt = NULL; + + write_lock_bh(&rt6_lock); + fn = fib6_locate(&ip6_routing_table, prefix ,prefixlen, NULL, 0); + if (!fn) + goto out; + + for (rt = fn->leaf; rt; rt = rt->u.next) { + if (rt->rt6i_dev->ifindex != ifindex) + continue; + if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) + continue; + if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) + continue; + dst_hold(&rt->u.dst); + break; + } +out: + write_unlock_bh(&rt6_lock); + return rt; +} + +static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixlen, + struct in6_addr *gwaddr, int ifindex, + unsigned pref) +{ + struct in6_rtmsg rtmsg; + + memset(&rtmsg, 0, sizeof(rtmsg)); + rtmsg.rtmsg_type = RTMSG_NEWROUTE; + ipv6_addr_copy(&rtmsg.rtmsg_dst, prefix); + rtmsg.rtmsg_dst_len = prefixlen; + ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr); + rtmsg.rtmsg_metric = 1024; + rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref); + /* We should treat it as a default route if prefix length is 0. */ + if (!prefixlen) + rtmsg.rtmsg_flags |= RTF_DEFAULT; + rtmsg.rtmsg_ifindex = ifindex; + + ip6_route_add(&rtmsg, NULL, NULL, NULL); + + return rt6_get_route_info(prefix, prefixlen, gwaddr, ifindex); +} +#endif + struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev) { struct rt6_info *rt; @@ -1290,6 +1428,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d write_lock_bh(&rt6_lock); for (rt = fn->leaf; rt; rt=rt->u.next) { if (dev == rt->rt6i_dev && + ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&rt->rt6i_gateway, addr)) break; } @@ -1300,7 +1439,8 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d } struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr, - struct net_device *dev) + struct net_device *dev, + unsigned int pref) { struct in6_rtmsg rtmsg; @@ -1308,7 +1448,8 @@ struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr, rtmsg.rtmsg_type = RTMSG_NEWROUTE; ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr); rtmsg.rtmsg_metric = 1024; - rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES; + rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | + RTF_PREF(pref); rtmsg.rtmsg_ifindex = dev->ifindex; @@ -1326,8 +1467,6 @@ restart: if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { dst_hold(&rt->u.dst); - rt6_reset_dflt_pointer(NULL); - read_unlock_bh(&rt6_lock); ip6_del_rt(rt, NULL, NULL, NULL); @@ -1738,11 +1877,10 @@ int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) /* * 2. allocate and initialize walker. */ - w = kmalloc(sizeof(*w), GFP_ATOMIC); + w = kzalloc(sizeof(*w), GFP_ATOMIC); if (w == NULL) return -ENOMEM; RT6_TRACE("dump<%p", w); - memset(w, 0, sizeof(*w)); w->root = &ip6_routing_table; w->func = fib6_dump_node; w->args = &arg; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ca9cf6853755..301eee726b0f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -987,6 +987,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + newnp->opt->opt_flen); + tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric(dst, RTAX_ADVMSS); tcp_initialize_rcv_mss(newsk); @@ -1297,18 +1298,21 @@ static int tcp_v6_remember_stamp(struct sock *sk) } static struct inet_connection_sock_af_ops ipv6_specific = { - .queue_xmit = inet6_csk_xmit, - .send_check = tcp_v6_send_check, - .rebuild_header = inet6_sk_rebuild_header, - .conn_request = tcp_v6_conn_request, - .syn_recv_sock = tcp_v6_syn_recv_sock, - .remember_stamp = tcp_v6_remember_stamp, - .net_header_len = sizeof(struct ipv6hdr), - - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .addr2sockaddr = inet6_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in6) + .queue_xmit = inet6_csk_xmit, + .send_check = tcp_v6_send_check, + .rebuild_header = inet6_sk_rebuild_header, + .conn_request = tcp_v6_conn_request, + .syn_recv_sock = tcp_v6_syn_recv_sock, + .remember_stamp = tcp_v6_remember_stamp, + .net_header_len = sizeof(struct ipv6hdr), + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .addr2sockaddr = inet6_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in6), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ipv6_setsockopt, + .compat_getsockopt = compat_ipv6_getsockopt, +#endif }; /* @@ -1316,22 +1320,23 @@ static struct inet_connection_sock_af_ops ipv6_specific = { */ static struct inet_connection_sock_af_ops ipv6_mapped = { - .queue_xmit = ip_queue_xmit, - .send_check = tcp_v4_send_check, - .rebuild_header = inet_sk_rebuild_header, - .conn_request = tcp_v6_conn_request, - .syn_recv_sock = tcp_v6_syn_recv_sock, - .remember_stamp = tcp_v4_remember_stamp, - .net_header_len = sizeof(struct iphdr), - - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .addr2sockaddr = inet6_csk_addr2sockaddr, - .sockaddr_len = sizeof(struct sockaddr_in6) + .queue_xmit = ip_queue_xmit, + .send_check = tcp_v4_send_check, + .rebuild_header = inet_sk_rebuild_header, + .conn_request = tcp_v6_conn_request, + .syn_recv_sock = tcp_v6_syn_recv_sock, + .remember_stamp = tcp_v4_remember_stamp, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .addr2sockaddr = inet6_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in6), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ipv6_setsockopt, + .compat_getsockopt = compat_ipv6_getsockopt, +#endif }; - - /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ @@ -1583,6 +1588,10 @@ struct proto tcpv6_prot = { .obj_size = sizeof(struct tcp6_sock), .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_tcp_setsockopt, + .compat_getsockopt = compat_tcp_getsockopt, +#endif }; static struct inet6_protocol tcpv6_protocol = { @@ -1604,21 +1613,12 @@ static struct inet_protosw tcpv6_protosw = { void __init tcpv6_init(void) { - int err; - /* register inet6 protocol */ if (inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP) < 0) printk(KERN_ERR "tcpv6_init: Could not register protocol\n"); inet6_register_protosw(&tcpv6_protosw); - err = sock_create_kern(PF_INET6, SOCK_RAW, IPPROTO_TCP, &tcp6_socket); - if (err < 0) + if (inet_csk_ctl_sock_create(&tcp6_socket, PF_INET6, SOCK_RAW, + IPPROTO_TCP) < 0) panic("Failed to create the TCPv6 control socket.\n"); - tcp6_socket->sk->sk_allocation = GFP_ATOMIC; - - /* Unhash it so that IP input processing does not even - * see it, we do not wish this socket to see incoming - * packets. - */ - tcp6_socket->sk->sk_prot->unhash(tcp6_socket->sk); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index c47648892c04..8d3432a70f3a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -880,16 +880,13 @@ static int udpv6_destroy_sock(struct sock *sk) /* * Socket option code for UDP */ -static int udpv6_setsockopt(struct sock *sk, int level, int optname, +static int do_udpv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) { struct udp_sock *up = udp_sk(sk); int val; int err = 0; - if (level != SOL_UDP) - return ipv6_setsockopt(sk, level, optname, optval, optlen); - if(optlen<sizeof(int)) return -EINVAL; @@ -927,15 +924,31 @@ static int udpv6_setsockopt(struct sock *sk, int level, int optname, return err; } -static int udpv6_getsockopt(struct sock *sk, int level, int optname, +static int udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level != SOL_UDP) + return ipv6_setsockopt(sk, level, optname, optval, optlen); + return do_udpv6_setsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +static int compat_udpv6_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, int optlen) +{ + if (level != SOL_UDP) + return compat_ipv6_setsockopt(sk, level, optname, + optval, optlen); + return do_udpv6_setsockopt(sk, level, optname, optval, optlen); +} +#endif + +static int do_udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct udp_sock *up = udp_sk(sk); int val, len; - if (level != SOL_UDP) - return ipv6_getsockopt(sk, level, optname, optval, optlen); - if(get_user(len,optlen)) return -EFAULT; @@ -964,6 +977,25 @@ static int udpv6_getsockopt(struct sock *sk, int level, int optname, return 0; } +static int udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_UDP) + return ipv6_getsockopt(sk, level, optname, optval, optlen); + return do_udpv6_getsockopt(sk, level, optname, optval, optlen); +} + +#ifdef CONFIG_COMPAT +static int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + if (level != SOL_UDP) + return compat_ipv6_getsockopt(sk, level, optname, + optval, optlen); + return do_udpv6_getsockopt(sk, level, optname, optval, optlen); +} +#endif + static struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, @@ -1037,22 +1069,26 @@ void udp6_proc_exit(void) { /* ------------------------------------------------------------------------ */ struct proto udpv6_prot = { - .name = "UDPv6", - .owner = THIS_MODULE, - .close = udpv6_close, - .connect = ip6_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .destroy = udpv6_destroy_sock, - .setsockopt = udpv6_setsockopt, - .getsockopt = udpv6_getsockopt, - .sendmsg = udpv6_sendmsg, - .recvmsg = udpv6_recvmsg, - .backlog_rcv = udpv6_queue_rcv_skb, - .hash = udp_v6_hash, - .unhash = udp_v6_unhash, - .get_port = udp_v6_get_port, - .obj_size = sizeof(struct udp6_sock), + .name = "UDPv6", + .owner = THIS_MODULE, + .close = udpv6_close, + .connect = ip6_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .destroy = udpv6_destroy_sock, + .setsockopt = udpv6_setsockopt, + .getsockopt = udpv6_getsockopt, + .sendmsg = udpv6_sendmsg, + .recvmsg = udpv6_recvmsg, + .backlog_rcv = udpv6_queue_rcv_skb, + .hash = udp_v6_hash, + .unhash = udp_v6_unhash, + .get_port = udp_v6_get_port, + .obj_size = sizeof(struct udp6_sock), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_udpv6_setsockopt, + .compat_getsockopt = compat_udpv6_getsockopt, +#endif }; static struct inet_protosw udpv6_protosw = { diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 8cfc58b96fc2..08f9abbdf1d7 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -31,6 +31,7 @@ #include <net/protocol.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> +#include <linux/mutex.h> #ifdef CONFIG_IPV6_XFRM6_TUNNEL_DEBUG # define X6TDEBUG 3 @@ -357,19 +358,19 @@ static int xfrm6_tunnel_input(struct xfrm_state *x, struct xfrm_decap_state *dec } static struct xfrm6_tunnel *xfrm6_tunnel_handler; -static DECLARE_MUTEX(xfrm6_tunnel_sem); +static DEFINE_MUTEX(xfrm6_tunnel_mutex); int xfrm6_tunnel_register(struct xfrm6_tunnel *handler) { int ret; - down(&xfrm6_tunnel_sem); + mutex_lock(&xfrm6_tunnel_mutex); ret = 0; if (xfrm6_tunnel_handler != NULL) ret = -EINVAL; if (!ret) xfrm6_tunnel_handler = handler; - up(&xfrm6_tunnel_sem); + mutex_unlock(&xfrm6_tunnel_mutex); return ret; } @@ -380,13 +381,13 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler) { int ret; - down(&xfrm6_tunnel_sem); + mutex_lock(&xfrm6_tunnel_mutex); ret = 0; if (xfrm6_tunnel_handler != handler) ret = -EINVAL; if (!ret) xfrm6_tunnel_handler = NULL; - up(&xfrm6_tunnel_sem); + mutex_unlock(&xfrm6_tunnel_mutex); synchronize_net(); diff --git a/net/key/af_key.c b/net/key/af_key.c index b2d4d1dd2116..859582275cab 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2651,6 +2651,8 @@ static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c) return key_notify_sa(x, c); case XFRM_MSG_FLUSHSA: return key_notify_sa_flush(c); + case XFRM_MSG_NEWAE: /* not yet supported */ + break; default: printk("pfkey: Unknown SA event %d\n", c->event); break; @@ -3078,9 +3080,9 @@ static int pfkey_sendmsg(struct kiocb *kiocb, if (!hdr) goto out; - down(&xfrm_cfg_sem); + mutex_lock(&xfrm_cfg_mutex); err = pfkey_process(sk, skb, hdr); - up(&xfrm_cfg_sem); + mutex_unlock(&xfrm_cfg_mutex); out: if (err && hdr && pfkey_error(hdr, err, sk) == 0) diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 8171c53bc0ed..5a04db745c8d 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -54,7 +54,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout); * * Return the next unused link number for a given sap. */ -static __inline__ u16 llc_ui_next_link_no(int sap) +static inline u16 llc_ui_next_link_no(int sap) { return llc_ui_sap_link_no_max[sap]++; } @@ -65,7 +65,7 @@ static __inline__ u16 llc_ui_next_link_no(int sap) * * Given an ARP header type return the corresponding ethernet protocol. */ -static __inline__ u16 llc_proto_type(u16 arphrd) +static inline u16 llc_proto_type(u16 arphrd) { return arphrd == ARPHRD_IEEE802_TR ? htons(ETH_P_TR_802_2) : htons(ETH_P_802_2); @@ -75,7 +75,7 @@ static __inline__ u16 llc_proto_type(u16 arphrd) * llc_ui_addr_null - determines if a address structure is null * @addr: Address to test if null. */ -static __inline__ u8 llc_ui_addr_null(struct sockaddr_llc *addr) +static inline u8 llc_ui_addr_null(struct sockaddr_llc *addr) { return !memcmp(addr, &llc_ui_addrnull, sizeof(*addr)); } @@ -89,8 +89,7 @@ static __inline__ u8 llc_ui_addr_null(struct sockaddr_llc *addr) * operation the user would like to perform and the type of socket. * Returns the correct llc header length. */ -static __inline__ u8 llc_ui_header_len(struct sock *sk, - struct sockaddr_llc *addr) +static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; @@ -138,7 +137,7 @@ static void llc_ui_sk_init(struct socket *sock, struct sock *sk) } static struct proto llc_proto = { - .name = "DDP", + .name = "LLC", .owner = THIS_MODULE, .obj_size = sizeof(struct llc_sock), }; @@ -188,8 +187,10 @@ static int llc_ui_release(struct socket *sock) llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); - if (!sock_flag(sk, SOCK_ZAPPED)) + if (!sock_flag(sk, SOCK_ZAPPED)) { + llc_sap_put(llc->sap); llc_sap_remove_socket(llc->sap, sk); + } release_sock(sk); if (llc->dev) dev_put(llc->dev); diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 8169f24ed33e..860140caa6e0 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -27,7 +27,6 @@ #include <net/llc_pdu.h> #include <net/llc.h> -#include "llc_output.h" static int llc_conn_ac_inc_vs_by_1(struct sock *sk, struct sk_buff *skb); static void llc_process_tmr_ev(struct sock *sk, struct sk_buff *skb); diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index ab0fcd32fd84..bd242a49514a 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -127,7 +127,6 @@ struct llc_sap *llc_sap_open(unsigned char lsap, goto out; sap->laddr.lsap = lsap; sap->rcv_func = func; - llc_sap_hold(sap); llc_add_sap(sap); out: write_unlock_bh(&llc_sap_list_lock); diff --git a/net/llc/llc_output.c b/net/llc/llc_output.c index b4d55b6abb67..b4e668e0e12c 100644 --- a/net/llc/llc_output.c +++ b/net/llc/llc_output.c @@ -30,7 +30,8 @@ * Fills MAC header fields, depending on MAC type. Returns 0, If MAC type * is a valid type and initialization completes correctly 1, otherwise. */ -int llc_mac_hdr_init(struct sk_buff *skb, unsigned char *sa, unsigned char *da) +int llc_mac_hdr_init(struct sk_buff *skb, + const unsigned char *sa, const unsigned char *da) { int rc = 0; diff --git a/net/llc/llc_output.h b/net/llc/llc_output.h deleted file mode 100644 index 179edf753f00..000000000000 --- a/net/llc/llc_output.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef LLC_OUTPUT_H -#define LLC_OUTPUT_H -/* - * Copyright (c) 1997 by Procom Technology, Inc. - * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> - * - * This program can be redistributed or modified under the terms of the - * GNU General Public License version 2 as published by the Free Software - * Foundation. - * This program is distributed without any warranty or implied warranty - * of merchantability or fitness for a particular purpose. - * - * See the GNU General Public License version 2 for more details. - */ - -struct sk_buff; - -int llc_mac_hdr_init(struct sk_buff *skb, unsigned char *sa, unsigned char *da); - -#endif /* LLC_OUTPUT_H */ diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index bb3580fb8cfe..ac3d93b210d2 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -24,7 +24,7 @@ #include <net/llc_s_ac.h> #include <net/llc_s_ev.h> #include <net/llc_sap.h> -#include "llc_output.h" + /** * llc_sap_action_unit_data_ind - forward UI PDU to network layer diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index a8e5544da93e..174027809148 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -279,6 +279,16 @@ config NETFILTER_XT_MATCH_MARK To compile it as a module, choose M here. If unsure, say N. +config NETFILTER_XT_MATCH_POLICY + tristate 'IPsec "policy" match support' + depends on NETFILTER_XTABLES && XFRM + help + Policy matching allows you to match packets based on the + IPsec policy that was used during decapsulation/will + be used during encapsulation. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_MATCH_PHYSDEV tristate '"physdev" match support' depends on NETFILTER_XTABLES && BRIDGE_NETFILTER diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 746172ebc91b..9558727f5e79 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -40,6 +40,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o obj-$(CONFIG_NETFILTER_XT_MATCH_MARK) += xt_mark.o +obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o obj-$(CONFIG_NETFILTER_XT_MATCH_REALM) += xt_realm.o obj-$(CONFIG_NETFILTER_XT_MATCH_SCTP) += xt_sctp.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d622ddf08bb0..f6498234e264 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -3,7 +3,7 @@ extension. */ /* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2005 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org> * * This program is free software; you can redistribute it and/or modify @@ -20,6 +20,9 @@ * - generalize L3 protocol denendent part. * 23 Mar 2004: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> * - add support various size of conntrack structures. + * 26 Jan 2006: Harald Welte <laforge@netfilter.org> + * - restructure nf_conn (introduce nf_conn_help) + * - redesign 'features' how they were originally intended * * Derived from net/ipv4/netfilter/ip_conntrack_core.c */ @@ -55,7 +58,7 @@ #include <net/netfilter/nf_conntrack_core.h> #include <linux/netfilter_ipv4/listhelp.h> -#define NF_CONNTRACK_VERSION "0.4.1" +#define NF_CONNTRACK_VERSION "0.5.0" #if 0 #define DEBUGP printk @@ -182,7 +185,7 @@ static struct { DEFINE_RWLOCK(nf_ct_cache_lock); /* This avoids calling kmem_cache_create() with same name simultaneously */ -DECLARE_MUTEX(nf_ct_cache_mutex); +static DEFINE_MUTEX(nf_ct_cache_mutex); extern struct nf_conntrack_protocol nf_conntrack_generic_protocol; struct nf_conntrack_protocol * @@ -259,21 +262,8 @@ static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple) nf_conntrack_hash_rnd); } -/* Initialize "struct nf_conn" which has spaces for helper */ -static int -init_conntrack_for_helper(struct nf_conn *conntrack, u_int32_t features) -{ - - conntrack->help = (union nf_conntrack_help *) - (((unsigned long)conntrack->data - + (__alignof__(union nf_conntrack_help) - 1)) - & (~((unsigned long)(__alignof__(union nf_conntrack_help) -1)))); - return 0; -} - int nf_conntrack_register_cache(u_int32_t features, const char *name, - size_t size, - int (*init)(struct nf_conn *, u_int32_t)) + size_t size) { int ret = 0; char *cache_name; @@ -288,7 +278,7 @@ int nf_conntrack_register_cache(u_int32_t features, const char *name, return -EINVAL; } - down(&nf_ct_cache_mutex); + mutex_lock(&nf_ct_cache_mutex); write_lock_bh(&nf_ct_cache_lock); /* e.g: multiple helpers are loaded */ @@ -296,8 +286,7 @@ int nf_conntrack_register_cache(u_int32_t features, const char *name, DEBUGP("nf_conntrack_register_cache: already resisterd.\n"); if ((!strncmp(nf_ct_cache[features].name, name, NF_CT_FEATURES_NAMELEN)) - && nf_ct_cache[features].size == size - && nf_ct_cache[features].init_conntrack == init) { + && nf_ct_cache[features].size == size) { DEBUGP("nf_conntrack_register_cache: reusing.\n"); nf_ct_cache[features].use++; ret = 0; @@ -305,7 +294,7 @@ int nf_conntrack_register_cache(u_int32_t features, const char *name, ret = -EBUSY; write_unlock_bh(&nf_ct_cache_lock); - up(&nf_ct_cache_mutex); + mutex_unlock(&nf_ct_cache_mutex); return ret; } write_unlock_bh(&nf_ct_cache_lock); @@ -340,7 +329,6 @@ int nf_conntrack_register_cache(u_int32_t features, const char *name, write_lock_bh(&nf_ct_cache_lock); nf_ct_cache[features].use = 1; nf_ct_cache[features].size = size; - nf_ct_cache[features].init_conntrack = init; nf_ct_cache[features].cachep = cachep; nf_ct_cache[features].name = cache_name; write_unlock_bh(&nf_ct_cache_lock); @@ -350,7 +338,7 @@ int nf_conntrack_register_cache(u_int32_t features, const char *name, out_free_name: kfree(cache_name); out_up_mutex: - up(&nf_ct_cache_mutex); + mutex_unlock(&nf_ct_cache_mutex); return ret; } @@ -365,19 +353,18 @@ void nf_conntrack_unregister_cache(u_int32_t features) * slab cache. */ DEBUGP("nf_conntrack_unregister_cache: 0x%04x\n", features); - down(&nf_ct_cache_mutex); + mutex_lock(&nf_ct_cache_mutex); write_lock_bh(&nf_ct_cache_lock); if (--nf_ct_cache[features].use > 0) { write_unlock_bh(&nf_ct_cache_lock); - up(&nf_ct_cache_mutex); + mutex_unlock(&nf_ct_cache_mutex); return; } cachep = nf_ct_cache[features].cachep; name = nf_ct_cache[features].name; nf_ct_cache[features].cachep = NULL; nf_ct_cache[features].name = NULL; - nf_ct_cache[features].init_conntrack = NULL; nf_ct_cache[features].size = 0; write_unlock_bh(&nf_ct_cache_lock); @@ -386,7 +373,7 @@ void nf_conntrack_unregister_cache(u_int32_t features) kmem_cache_destroy(cachep); kfree(name); - up(&nf_ct_cache_mutex); + mutex_unlock(&nf_ct_cache_mutex); } int @@ -432,11 +419,15 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, /* nf_conntrack_expect helper functions */ void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) { + struct nf_conn_help *master_help = nfct_help(exp->master); + + NF_CT_ASSERT(master_help); ASSERT_WRITE_LOCK(&nf_conntrack_lock); NF_CT_ASSERT(!timer_pending(&exp->timeout)); + list_del(&exp->list); NF_CT_STAT_INC(expect_delete); - exp->master->expecting--; + master_help->expecting--; nf_conntrack_expect_put(exp); } @@ -508,9 +499,10 @@ find_expectation(const struct nf_conntrack_tuple *tuple) void nf_ct_remove_expectations(struct nf_conn *ct) { struct nf_conntrack_expect *i, *tmp; + struct nf_conn_help *help = nfct_help(ct); /* Optimization: most connection never expect any others. */ - if (ct->expecting == 0) + if (!help || help->expecting == 0) return; list_for_each_entry_safe(i, tmp, &nf_conntrack_expect_list, list) { @@ -713,6 +705,7 @@ __nf_conntrack_confirm(struct sk_buff **pskb) conntrack_tuple_cmp, struct nf_conntrack_tuple_hash *, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, NULL)) { + struct nf_conn_help *help; /* Remove from unconfirmed list */ list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list); @@ -726,7 +719,8 @@ __nf_conntrack_confirm(struct sk_buff **pskb) set_bit(IPS_CONFIRMED_BIT, &ct->status); NF_CT_STAT_INC(insert); write_unlock_bh(&nf_conntrack_lock); - if (ct->helper) + help = nfct_help(ct); + if (help && help->helper) nf_conntrack_event_cache(IPCT_HELPER, *pskb); #ifdef CONFIG_NF_NAT_NEEDED if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) || @@ -842,8 +836,9 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, { struct nf_conn *conntrack = NULL; u_int32_t features = 0; + struct nf_conntrack_helper *helper; - if (!nf_conntrack_hash_rnd_initted) { + if (unlikely(!nf_conntrack_hash_rnd_initted)) { get_random_bytes(&nf_conntrack_hash_rnd, 4); nf_conntrack_hash_rnd_initted = 1; } @@ -863,8 +858,11 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, /* find features needed by this conntrack. */ features = l3proto->get_features(orig); + + /* FIXME: protect helper list per RCU */ read_lock_bh(&nf_conntrack_lock); - if (__nf_ct_helper_find(repl) != NULL) + helper = __nf_ct_helper_find(repl); + if (helper) features |= NF_CT_F_HELP; read_unlock_bh(&nf_conntrack_lock); @@ -872,7 +870,7 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, read_lock_bh(&nf_ct_cache_lock); - if (!nf_ct_cache[features].use) { + if (unlikely(!nf_ct_cache[features].use)) { DEBUGP("nf_conntrack_alloc: not supported features = 0x%x\n", features); goto out; @@ -886,12 +884,10 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, memset(conntrack, 0, nf_ct_cache[features].size); conntrack->features = features; - if (nf_ct_cache[features].init_conntrack && - nf_ct_cache[features].init_conntrack(conntrack, features) < 0) { - DEBUGP("nf_conntrack_alloc: failed to init\n"); - kmem_cache_free(nf_ct_cache[features].cachep, conntrack); - conntrack = NULL; - goto out; + if (helper) { + struct nf_conn_help *help = nfct_help(conntrack); + NF_CT_ASSERT(help); + help->helper = helper; } atomic_set(&conntrack->ct_general.use, 1); @@ -972,11 +968,8 @@ init_conntrack(const struct nf_conntrack_tuple *tuple, #endif nf_conntrack_get(&conntrack->master->ct_general); NF_CT_STAT_INC(expect_new); - } else { - conntrack->helper = __nf_ct_helper_find(&repl_tuple); - + } else NF_CT_STAT_INC(new); - } /* Overload tuple linked list to put us in unconfirmed list. */ list_add(&conntrack->tuplehash[IP_CT_DIR_ORIGINAL].list, &unconfirmed); @@ -1206,14 +1199,16 @@ void nf_conntrack_expect_put(struct nf_conntrack_expect *exp) static void nf_conntrack_expect_insert(struct nf_conntrack_expect *exp) { + struct nf_conn_help *master_help = nfct_help(exp->master); + atomic_inc(&exp->use); - exp->master->expecting++; + master_help->expecting++; list_add(&exp->list, &nf_conntrack_expect_list); init_timer(&exp->timeout); exp->timeout.data = (unsigned long)exp; exp->timeout.function = expectation_timed_out; - exp->timeout.expires = jiffies + exp->master->helper->timeout * HZ; + exp->timeout.expires = jiffies + master_help->helper->timeout * HZ; add_timer(&exp->timeout); exp->id = ++nf_conntrack_expect_next_id; @@ -1239,10 +1234,12 @@ static void evict_oldest_expect(struct nf_conn *master) static inline int refresh_timer(struct nf_conntrack_expect *i) { + struct nf_conn_help *master_help = nfct_help(i->master); + if (!del_timer(&i->timeout)) return 0; - i->timeout.expires = jiffies + i->master->helper->timeout*HZ; + i->timeout.expires = jiffies + master_help->helper->timeout*HZ; add_timer(&i->timeout); return 1; } @@ -1251,8 +1248,11 @@ int nf_conntrack_expect_related(struct nf_conntrack_expect *expect) { struct nf_conntrack_expect *i; struct nf_conn *master = expect->master; + struct nf_conn_help *master_help = nfct_help(master); int ret; + NF_CT_ASSERT(master_help); + DEBUGP("nf_conntrack_expect_related %p\n", related_to); DEBUGP("tuple: "); NF_CT_DUMP_TUPLE(&expect->tuple); DEBUGP("mask: "); NF_CT_DUMP_TUPLE(&expect->mask); @@ -1271,8 +1271,8 @@ int nf_conntrack_expect_related(struct nf_conntrack_expect *expect) } } /* Will be over limit? */ - if (master->helper->max_expected && - master->expecting >= master->helper->max_expected) + if (master_help->helper->max_expected && + master_help->expecting >= master_help->helper->max_expected) evict_oldest_expect(master); nf_conntrack_expect_insert(expect); @@ -1283,24 +1283,6 @@ out: return ret; } -/* Alter reply tuple (maybe alter helper). This is for NAT, and is - implicitly racy: see __nf_conntrack_confirm */ -void nf_conntrack_alter_reply(struct nf_conn *conntrack, - const struct nf_conntrack_tuple *newreply) -{ - write_lock_bh(&nf_conntrack_lock); - /* Should be unconfirmed, so not in hash table yet */ - NF_CT_ASSERT(!nf_ct_is_confirmed(conntrack)); - - DEBUGP("Altering reply tuple of %p to ", conntrack); - NF_CT_DUMP_TUPLE(newreply); - - conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply; - if (!conntrack->master && conntrack->expecting == 0) - conntrack->helper = __nf_ct_helper_find(newreply); - write_unlock_bh(&nf_conntrack_lock); -} - int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { int ret; @@ -1308,9 +1290,8 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) ret = nf_conntrack_register_cache(NF_CT_F_HELP, "nf_conntrack:help", sizeof(struct nf_conn) - + sizeof(union nf_conntrack_help) - + __alignof__(union nf_conntrack_help), - init_conntrack_for_helper); + + sizeof(struct nf_conn_help) + + __alignof__(struct nf_conn_help)); if (ret < 0) { printk(KERN_ERR "nf_conntrack_helper_reigster: Unable to create slab cache for conntracks\n"); return ret; @@ -1338,9 +1319,12 @@ __nf_conntrack_helper_find_byname(const char *name) static inline int unhelp(struct nf_conntrack_tuple_hash *i, const struct nf_conntrack_helper *me) { - if (nf_ct_tuplehash_to_ctrack(i)->helper == me) { - nf_conntrack_event(IPCT_HELPER, nf_ct_tuplehash_to_ctrack(i)); - nf_ct_tuplehash_to_ctrack(i)->helper = NULL; + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); + struct nf_conn_help *help = nfct_help(ct); + + if (help && help->helper == me) { + nf_conntrack_event(IPCT_HELPER, ct); + help->helper = NULL; } return 0; } @@ -1356,7 +1340,8 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) /* Get rid of expectations */ list_for_each_entry_safe(exp, tmp, &nf_conntrack_expect_list, list) { - if (exp->master->helper == me && del_timer(&exp->timeout)) { + struct nf_conn_help *help = nfct_help(exp->master); + if (help->helper == me && del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_conntrack_expect_put(exp); } @@ -1423,6 +1408,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> +#include <linux/mutex.h> + /* Generic function for tcp/udp/sctp/dccp and alike. This needs to be * in ip_conntrack_core, since we don't want the protocols to autoload @@ -1697,7 +1684,7 @@ int __init nf_conntrack_init(void) } ret = nf_conntrack_register_cache(NF_CT_F_BASIC, "nf_conntrack:basic", - sizeof(struct nf_conn), NULL); + sizeof(struct nf_conn)); if (ret < 0) { printk(KERN_ERR "Unable to create nf_conn slab cache\n"); goto err_free_hash; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 6f210f399762..cd191b0d4ac7 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -440,7 +440,7 @@ static int help(struct sk_buff **pskb, u32 seq; int dir = CTINFO2DIR(ctinfo); unsigned int matchlen, matchoff; - struct ip_ct_ftp_master *ct_ftp_info = &ct->help->ct_ftp_info; + struct ip_ct_ftp_master *ct_ftp_info = &nfct_help(ct)->help.ct_ftp_info; struct nf_conntrack_expect *exp; struct nf_conntrack_man cmd = {}; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9ff3463037e1..5eadf009bb15 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2,7 +2,7 @@ * protocol helpers and general trouble making from userspace. * * (C) 2001 by Jay Schulist <jschlst@samba.org> - * (C) 2002-2005 by Harald Welte <laforge@gnumonks.org> + * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> * (C) 2005 by Pablo Neira Ayuso <pablo@eurodev.net> * @@ -44,7 +44,7 @@ MODULE_LICENSE("GPL"); -static char __initdata version[] = "0.92"; +static char __initdata version[] = "0.93"; #if 0 #define DEBUGP printk @@ -165,15 +165,16 @@ static inline int ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct) { struct nfattr *nest_helper; + const struct nf_conn_help *help = nfct_help(ct); - if (!ct->helper) + if (!help || !help->helper) return 0; nest_helper = NFA_NEST(skb, CTA_HELP); - NFA_PUT(skb, CTA_HELP_NAME, strlen(ct->helper->name), ct->helper->name); + NFA_PUT(skb, CTA_HELP_NAME, strlen(help->helper->name), help->helper->name); - if (ct->helper->to_nfattr) - ct->helper->to_nfattr(skb, ct); + if (help->helper->to_nfattr) + help->helper->to_nfattr(skb, ct); NFA_NEST_END(skb, nest_helper); @@ -337,9 +338,10 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, group = NFNLGRP_CONNTRACK_UPDATE; } else return NOTIFY_DONE; - - /* FIXME: Check if there are any listeners before, don't hurt performance */ - + + if (!nfnetlink_has_listeners(group)) + return NOTIFY_DONE; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb) return NOTIFY_DONE; @@ -903,11 +905,17 @@ static inline int ctnetlink_change_helper(struct nf_conn *ct, struct nfattr *cda[]) { struct nf_conntrack_helper *helper; + struct nf_conn_help *help = nfct_help(ct); char *helpname; int err; DEBUGP("entered %s\n", __FUNCTION__); + if (!help) { + /* FIXME: we need to reallocate and rehash */ + return -EBUSY; + } + /* don't change helper of sibling connections */ if (ct->master) return -EINVAL; @@ -924,18 +932,18 @@ ctnetlink_change_helper(struct nf_conn *ct, struct nfattr *cda[]) return -EINVAL; } - if (ct->helper) { + if (help->helper) { if (!helper) { /* we had a helper before ... */ nf_ct_remove_expectations(ct); - ct->helper = NULL; + help->helper = NULL; } else { /* need to zero data of old helper */ - memset(&ct->help, 0, sizeof(ct->help)); + memset(&help->help, 0, sizeof(help->help)); } } - ct->helper = helper; + help->helper = helper; return 0; } @@ -1050,14 +1058,9 @@ ctnetlink_create_conntrack(struct nfattr *cda[], ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1])); #endif - ct->helper = nf_ct_helper_find_get(rtuple); - add_timer(&ct->timeout); nf_conntrack_hash_insert(ct); - if (ct->helper) - nf_ct_helper_put(ct->helper); - DEBUGP("conntrack with id %u inserted\n", ct->id); return 0; @@ -1417,7 +1420,8 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, } list_for_each_entry_safe(exp, tmp, &nf_conntrack_expect_list, list) { - if (exp->master->helper == h + struct nf_conn_help *m_help = nfct_help(exp->master); + if (m_help->helper == h && del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_conntrack_expect_put(exp); @@ -1452,6 +1456,7 @@ ctnetlink_create_expect(struct nfattr *cda[], u_int8_t u3) struct nf_conntrack_tuple_hash *h = NULL; struct nf_conntrack_expect *exp; struct nf_conn *ct; + struct nf_conn_help *help; int err = 0; DEBUGP("entered %s\n", __FUNCTION__); @@ -1472,8 +1477,9 @@ ctnetlink_create_expect(struct nfattr *cda[], u_int8_t u3) if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); + help = nfct_help(ct); - if (!ct->helper) { + if (!help || !help->helper) { /* such conntrack hasn't got any helper, abort */ err = -EINVAL; goto out; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 617599aeeead..290d5a0c559b 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -839,7 +839,6 @@ EXPORT_SYMBOL(nf_conntrack_l3proto_unregister); EXPORT_SYMBOL(nf_conntrack_protocol_register); EXPORT_SYMBOL(nf_conntrack_protocol_unregister); EXPORT_SYMBOL(nf_ct_invert_tuplepr); -EXPORT_SYMBOL(nf_conntrack_alter_reply); EXPORT_SYMBOL(nf_conntrack_destroyed); EXPORT_SYMBOL(need_conntrack); EXPORT_SYMBOL(nf_conntrack_helper_register); diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c index 61a833a9caa6..0a63d7dac7be 100644 --- a/net/netfilter/nf_sockopt.c +++ b/net/netfilter/nf_sockopt.c @@ -4,6 +4,7 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter.h> +#include <linux/mutex.h> #include <net/sock.h> #include "nf_internals.h" @@ -11,7 +12,7 @@ /* Sockopts only registered and called from user context, so net locking would be overkill. Also, [gs]etsockopt calls may sleep. */ -static DECLARE_MUTEX(nf_sockopt_mutex); +static DEFINE_MUTEX(nf_sockopt_mutex); static LIST_HEAD(nf_sockopts); /* Do exclusive ranges overlap? */ @@ -26,7 +27,7 @@ int nf_register_sockopt(struct nf_sockopt_ops *reg) struct list_head *i; int ret = 0; - if (down_interruptible(&nf_sockopt_mutex) != 0) + if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) return -EINTR; list_for_each(i, &nf_sockopts) { @@ -48,7 +49,7 @@ int nf_register_sockopt(struct nf_sockopt_ops *reg) list_add(®->list, &nf_sockopts); out: - up(&nf_sockopt_mutex); + mutex_unlock(&nf_sockopt_mutex); return ret; } EXPORT_SYMBOL(nf_register_sockopt); @@ -57,18 +58,18 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg) { /* No point being interruptible: we're probably in cleanup_module() */ restart: - down(&nf_sockopt_mutex); + mutex_lock(&nf_sockopt_mutex); if (reg->use != 0) { /* To be woken by nf_sockopt call... */ /* FIXME: Stuart Young's name appears gratuitously. */ set_current_state(TASK_UNINTERRUPTIBLE); reg->cleanup_task = current; - up(&nf_sockopt_mutex); + mutex_unlock(&nf_sockopt_mutex); schedule(); goto restart; } list_del(®->list); - up(&nf_sockopt_mutex); + mutex_unlock(&nf_sockopt_mutex); } EXPORT_SYMBOL(nf_unregister_sockopt); @@ -80,7 +81,7 @@ static int nf_sockopt(struct sock *sk, int pf, int val, struct nf_sockopt_ops *ops; int ret; - if (down_interruptible(&nf_sockopt_mutex) != 0) + if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) return -EINTR; list_for_each(i, &nf_sockopts) { @@ -90,7 +91,7 @@ static int nf_sockopt(struct sock *sk, int pf, int val, if (val >= ops->get_optmin && val < ops->get_optmax) { ops->use++; - up(&nf_sockopt_mutex); + mutex_unlock(&nf_sockopt_mutex); ret = ops->get(sk, val, opt, len); goto out; } @@ -98,22 +99,22 @@ static int nf_sockopt(struct sock *sk, int pf, int val, if (val >= ops->set_optmin && val < ops->set_optmax) { ops->use++; - up(&nf_sockopt_mutex); + mutex_unlock(&nf_sockopt_mutex); ret = ops->set(sk, val, opt, *len); goto out; } } } } - up(&nf_sockopt_mutex); + mutex_unlock(&nf_sockopt_mutex); return -ENOPROTOOPT; out: - down(&nf_sockopt_mutex); + mutex_lock(&nf_sockopt_mutex); ops->use--; if (ops->cleanup_task) wake_up_process(ops->cleanup_task); - up(&nf_sockopt_mutex); + mutex_unlock(&nf_sockopt_mutex); return ret; } @@ -130,3 +131,72 @@ int nf_getsockopt(struct sock *sk, int pf, int val, char __user *opt, int *len) } EXPORT_SYMBOL(nf_getsockopt); +#ifdef CONFIG_COMPAT +static int compat_nf_sockopt(struct sock *sk, int pf, int val, + char __user *opt, int *len, int get) +{ + struct list_head *i; + struct nf_sockopt_ops *ops; + int ret; + + if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) + return -EINTR; + + list_for_each(i, &nf_sockopts) { + ops = (struct nf_sockopt_ops *)i; + if (ops->pf == pf) { + if (get) { + if (val >= ops->get_optmin + && val < ops->get_optmax) { + ops->use++; + mutex_unlock(&nf_sockopt_mutex); + if (ops->compat_get) + ret = ops->compat_get(sk, + val, opt, len); + else + ret = ops->get(sk, + val, opt, len); + goto out; + } + } else { + if (val >= ops->set_optmin + && val < ops->set_optmax) { + ops->use++; + mutex_unlock(&nf_sockopt_mutex); + if (ops->compat_set) + ret = ops->compat_set(sk, + val, opt, *len); + else + ret = ops->set(sk, + val, opt, *len); + goto out; + } + } + } + } + mutex_unlock(&nf_sockopt_mutex); + return -ENOPROTOOPT; + + out: + mutex_lock(&nf_sockopt_mutex); + ops->use--; + if (ops->cleanup_task) + wake_up_process(ops->cleanup_task); + mutex_unlock(&nf_sockopt_mutex); + return ret; +} + +int compat_nf_setsockopt(struct sock *sk, int pf, + int val, char __user *opt, int len) +{ + return compat_nf_sockopt(sk, pf, val, opt, &len, 0); +} +EXPORT_SYMBOL(compat_nf_setsockopt); + +int compat_nf_getsockopt(struct sock *sk, int pf, + int val, char __user *opt, int *len) +{ + return compat_nf_sockopt(sk, pf, val, opt, len, 1); +} +EXPORT_SYMBOL(compat_nf_getsockopt); +#endif diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index f6063e8f0050..b88e82a1a987 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -191,6 +191,12 @@ nfnetlink_check_attributes(struct nfnetlink_subsystem *subsys, return 0; } +int nfnetlink_has_listeners(unsigned int group) +{ + return netlink_has_listeners(nfnl, group); +} +EXPORT_SYMBOL_GPL(nfnetlink_has_listeners); + int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo) { gfp_t allocation = in_interrupt() ? GFP_ATOMIC : GFP_KERNEL; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 3b3c781b40c0..54cbbaa712dc 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -11,6 +11,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. * + * 2006-01-26 Harald Welte <laforge@netfilter.org> + * - Add optional local and global sequence number to detect lost + * events from userspace + * */ #include <linux/module.h> #include <linux/skbuff.h> @@ -68,11 +72,14 @@ struct nfulnl_instance { unsigned int nlbufsiz; /* netlink buffer allocation size */ unsigned int qthreshold; /* threshold of the queue */ u_int32_t copy_range; + u_int32_t seq; /* instance-local sequential counter */ u_int16_t group_num; /* number of this queue */ + u_int16_t flags; u_int8_t copy_mode; }; static DEFINE_RWLOCK(instances_lock); +static atomic_t global_seq; #define INSTANCE_BUCKETS 16 static struct hlist_head instance_table[INSTANCE_BUCKETS]; @@ -310,6 +317,16 @@ nfulnl_set_qthresh(struct nfulnl_instance *inst, u_int32_t qthresh) return 0; } +static int +nfulnl_set_flags(struct nfulnl_instance *inst, u_int16_t flags) +{ + spin_lock_bh(&inst->lock); + inst->flags = ntohs(flags); + spin_unlock_bh(&inst->lock); + + return 0; +} + static struct sk_buff *nfulnl_alloc_skb(unsigned int inst_size, unsigned int pkt_size) { @@ -377,6 +394,8 @@ static void nfulnl_timer(unsigned long data) spin_unlock_bh(&inst->lock); } +/* This is an inline function, we don't really care about a long + * list of arguments */ static inline int __build_packet_message(struct nfulnl_instance *inst, const struct sk_buff *skb, @@ -515,6 +534,17 @@ __build_packet_message(struct nfulnl_instance *inst, read_unlock_bh(&skb->sk->sk_callback_lock); } + /* local sequence number */ + if (inst->flags & NFULNL_CFG_F_SEQ) { + tmp_uint = htonl(inst->seq++); + NFA_PUT(inst->skb, NFULA_SEQ, sizeof(tmp_uint), &tmp_uint); + } + /* global sequence number */ + if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) { + tmp_uint = atomic_inc_return(&global_seq); + NFA_PUT(inst->skb, NFULA_SEQ_GLOBAL, sizeof(tmp_uint), &tmp_uint); + } + if (data_len) { struct nfattr *nfa; int size = NFA_LENGTH(data_len); @@ -607,6 +637,11 @@ nfulnl_log_packet(unsigned int pf, spin_lock_bh(&inst->lock); + if (inst->flags & NFULNL_CFG_F_SEQ) + size += NFA_SPACE(sizeof(u_int32_t)); + if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) + size += NFA_SPACE(sizeof(u_int32_t)); + qthreshold = inst->qthreshold; /* per-rule qthreshold overrides per-instance */ if (qthreshold > li->u.ulog.qthreshold) @@ -736,10 +771,14 @@ static const int nfula_min[NFULA_MAX] = { [NFULA_TIMESTAMP-1] = sizeof(struct nfulnl_msg_packet_timestamp), [NFULA_IFINDEX_INDEV-1] = sizeof(u_int32_t), [NFULA_IFINDEX_OUTDEV-1]= sizeof(u_int32_t), + [NFULA_IFINDEX_PHYSINDEV-1] = sizeof(u_int32_t), + [NFULA_IFINDEX_PHYSOUTDEV-1] = sizeof(u_int32_t), [NFULA_HWADDR-1] = sizeof(struct nfulnl_msg_packet_hw), [NFULA_PAYLOAD-1] = 0, [NFULA_PREFIX-1] = 0, [NFULA_UID-1] = sizeof(u_int32_t), + [NFULA_SEQ-1] = sizeof(u_int32_t), + [NFULA_SEQ_GLOBAL-1] = sizeof(u_int32_t), }; static const int nfula_cfg_min[NFULA_CFG_MAX] = { @@ -748,6 +787,7 @@ static const int nfula_cfg_min[NFULA_CFG_MAX] = { [NFULA_CFG_TIMEOUT-1] = sizeof(u_int32_t), [NFULA_CFG_QTHRESH-1] = sizeof(u_int32_t), [NFULA_CFG_NLBUFSIZ-1] = sizeof(u_int32_t), + [NFULA_CFG_FLAGS-1] = sizeof(u_int16_t), }; static int @@ -859,6 +899,12 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, nfulnl_set_qthresh(inst, ntohl(qthresh)); } + if (nfula[NFULA_CFG_FLAGS-1]) { + u_int16_t flags = + *(u_int16_t *)NFA_DATA(nfula[NFULA_CFG_FLAGS-1]); + nfulnl_set_flags(inst, ntohl(flags)); + } + out_put: instance_put(inst); return ret; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index d7817afc6b96..750b92829766 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -52,6 +52,12 @@ enum { MATCH, }; +static const char *xt_prefix[NPROTO] = { + [AF_INET] = "ip", + [AF_INET6] = "ip6", + [NF_ARP] = "arp", +}; + /* Registration hooks for targets. */ int xt_register_target(int af, struct xt_target *target) @@ -158,18 +164,12 @@ struct xt_target *xt_find_target(int af, const char *name, u8 revision) } EXPORT_SYMBOL(xt_find_target); -static const char *xt_prefix[NPROTO] = { - [AF_INET] = "ipt_%s", - [AF_INET6] = "ip6t_%s", - [NF_ARP] = "arpt_%s", -}; - struct xt_target *xt_request_find_target(int af, const char *name, u8 revision) { struct xt_target *target; target = try_then_request_module(xt_find_target(af, name, revision), - xt_prefix[af], name); + "%st_%s", xt_prefix[af], name); if (IS_ERR(target) || !target) return NULL; return target; @@ -237,6 +237,64 @@ int xt_find_revision(int af, const char *name, u8 revision, int target, } EXPORT_SYMBOL_GPL(xt_find_revision); +int xt_check_match(const struct xt_match *match, unsigned short family, + unsigned int size, const char *table, unsigned int hook_mask, + unsigned short proto, int inv_proto) +{ + if (XT_ALIGN(match->matchsize) != size) { + printk("%s_tables: %s match: invalid size %Zu != %u\n", + xt_prefix[family], match->name, + XT_ALIGN(match->matchsize), size); + return -EINVAL; + } + if (match->table && strcmp(match->table, table)) { + printk("%s_tables: %s match: only valid in %s table, not %s\n", + xt_prefix[family], match->name, match->table, table); + return -EINVAL; + } + if (match->hooks && (hook_mask & ~match->hooks) != 0) { + printk("%s_tables: %s match: bad hook_mask %u\n", + xt_prefix[family], match->name, hook_mask); + return -EINVAL; + } + if (match->proto && (match->proto != proto || inv_proto)) { + printk("%s_tables: %s match: only valid for protocol %u\n", + xt_prefix[family], match->name, match->proto); + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL_GPL(xt_check_match); + +int xt_check_target(const struct xt_target *target, unsigned short family, + unsigned int size, const char *table, unsigned int hook_mask, + unsigned short proto, int inv_proto) +{ + if (XT_ALIGN(target->targetsize) != size) { + printk("%s_tables: %s target: invalid size %Zu != %u\n", + xt_prefix[family], target->name, + XT_ALIGN(target->targetsize), size); + return -EINVAL; + } + if (target->table && strcmp(target->table, table)) { + printk("%s_tables: %s target: only valid in %s table, not %s\n", + xt_prefix[family], target->name, target->table, table); + return -EINVAL; + } + if (target->hooks && (hook_mask & ~target->hooks) != 0) { + printk("%s_tables: %s target: bad hook_mask %u\n", + xt_prefix[family], target->name, hook_mask); + return -EINVAL; + } + if (target->proto && (target->proto != proto || inv_proto)) { + printk("%s_tables: %s target: only valid for protocol %u\n", + xt_prefix[family], target->name, target->proto); + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL_GPL(xt_check_target); + struct xt_table_info *xt_alloc_table_info(unsigned int size) { struct xt_table_info *newinfo; diff --git a/net/netfilter/xt_CLASSIFY.c b/net/netfilter/xt_CLASSIFY.c index 78ee266a12ee..3224ed87d4c7 100644 --- a/net/netfilter/xt_CLASSIFY.c +++ b/net/netfilter/xt_CLASSIFY.c @@ -28,6 +28,7 @@ target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -39,47 +40,22 @@ target(struct sk_buff **pskb, return XT_CONTINUE; } -static int -checkentry(const char *tablename, - const void *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != XT_ALIGN(sizeof(struct xt_classify_target_info))){ - printk(KERN_ERR "CLASSIFY: invalid size (%u != %Zu).\n", - targinfosize, - XT_ALIGN(sizeof(struct xt_classify_target_info))); - return 0; - } - - if (hook_mask & ~((1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_FORWARD) | - (1 << NF_IP_POST_ROUTING))) { - printk(KERN_ERR "CLASSIFY: only valid in LOCAL_OUT, FORWARD " - "and POST_ROUTING.\n"); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_ERR "CLASSIFY: can only be called from " - "\"mangle\" table, not \"%s\".\n", - tablename); - return 0; - } - - return 1; -} - static struct xt_target classify_reg = { .name = "CLASSIFY", .target = target, - .checkentry = checkentry, + .targetsize = sizeof(struct xt_classify_target_info), + .table = "mangle", + .hooks = (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_FORWARD) | + (1 << NF_IP_POST_ROUTING), .me = THIS_MODULE, }; static struct xt_target classify6_reg = { .name = "CLASSIFY", .target = target, - .checkentry = checkentry, + .targetsize = sizeof(struct xt_classify_target_info), + .table = "mangle", + .hooks = (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_FORWARD) | + (1 << NF_IP_POST_ROUTING), .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_CONNMARK.c b/net/netfilter/xt_CONNMARK.c index 22506e376be5..df2486a3efd5 100644 --- a/net/netfilter/xt_CONNMARK.c +++ b/net/netfilter/xt_CONNMARK.c @@ -37,6 +37,7 @@ target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -74,17 +75,12 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, const void *entry, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { struct xt_connmark_target_info *matchinfo = targinfo; - if (targinfosize != XT_ALIGN(sizeof(struct xt_connmark_target_info))) { - printk(KERN_WARNING "CONNMARK: targinfosize %u != %Zu\n", - targinfosize, - XT_ALIGN(sizeof(struct xt_connmark_target_info))); - return 0; - } if (matchinfo->mode == XT_CONNMARK_RESTORE) { if (strcmp(tablename, "mangle") != 0) { @@ -102,16 +98,19 @@ checkentry(const char *tablename, } static struct xt_target connmark_reg = { - .name = "CONNMARK", - .target = &target, - .checkentry = &checkentry, - .me = THIS_MODULE + .name = "CONNMARK", + .target = target, + .targetsize = sizeof(struct xt_connmark_target_info), + .checkentry = checkentry, + .me = THIS_MODULE }; + static struct xt_target connmark6_reg = { - .name = "CONNMARK", - .target = &target, - .checkentry = &checkentry, - .me = THIS_MODULE + .name = "CONNMARK", + .target = target, + .targetsize = sizeof(struct xt_connmark_target_info), + .checkentry = checkentry, + .me = THIS_MODULE }; static int __init init(void) diff --git a/net/netfilter/xt_MARK.c b/net/netfilter/xt_MARK.c index 0c11ee9550f3..dcb5266efae0 100644 --- a/net/netfilter/xt_MARK.c +++ b/net/netfilter/xt_MARK.c @@ -26,6 +26,7 @@ target_v0(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -42,6 +43,7 @@ target_v1(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -72,53 +74,30 @@ target_v1(struct sk_buff **pskb, static int checkentry_v0(const char *tablename, const void *entry, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { struct xt_mark_target_info *markinfo = targinfo; - if (targinfosize != XT_ALIGN(sizeof(struct xt_mark_target_info))) { - printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n", - targinfosize, - XT_ALIGN(sizeof(struct xt_mark_target_info))); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "MARK: can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - if (markinfo->mark > 0xffffffff) { printk(KERN_WARNING "MARK: Only supports 32bit wide mark\n"); return 0; } - return 1; } static int checkentry_v1(const char *tablename, const void *entry, + const struct xt_target *target, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { struct xt_mark_target_info_v1 *markinfo = targinfo; - if (targinfosize != XT_ALIGN(sizeof(struct xt_mark_target_info_v1))){ - printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n", - targinfosize, - XT_ALIGN(sizeof(struct xt_mark_target_info_v1))); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "MARK: can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - if (markinfo->mode != XT_MARK_SET && markinfo->mode != XT_MARK_AND && markinfo->mode != XT_MARK_OR) { @@ -126,18 +105,18 @@ checkentry_v1(const char *tablename, markinfo->mode); return 0; } - if (markinfo->mark > 0xffffffff) { printk(KERN_WARNING "MARK: Only supports 32bit wide mark\n"); return 0; } - return 1; } static struct xt_target ipt_mark_reg_v0 = { .name = "MARK", .target = target_v0, + .targetsize = sizeof(struct xt_mark_target_info), + .table = "mangle", .checkentry = checkentry_v0, .me = THIS_MODULE, .revision = 0, @@ -146,6 +125,8 @@ static struct xt_target ipt_mark_reg_v0 = { static struct xt_target ipt_mark_reg_v1 = { .name = "MARK", .target = target_v1, + .targetsize = sizeof(struct xt_mark_target_info_v1), + .table = "mangle", .checkentry = checkentry_v1, .me = THIS_MODULE, .revision = 1, @@ -154,6 +135,8 @@ static struct xt_target ipt_mark_reg_v1 = { static struct xt_target ip6t_mark_reg_v0 = { .name = "MARK", .target = target_v0, + .targetsize = sizeof(struct xt_mark_target_info), + .table = "mangle", .checkentry = checkentry_v0, .me = THIS_MODULE, .revision = 0, diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 8b76b6f8d1e4..39a963edf16b 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -28,6 +28,7 @@ target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -36,41 +37,24 @@ target(struct sk_buff **pskb, return NF_QUEUE_NR(tinfo->queuenum); } -static int -checkentry(const char *tablename, - const void *entry, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != XT_ALIGN(sizeof(struct xt_NFQ_info))) { - printk(KERN_WARNING "NFQUEUE: targinfosize %u != %Zu\n", - targinfosize, - XT_ALIGN(sizeof(struct xt_NFQ_info))); - return 0; - } - - return 1; -} - static struct xt_target ipt_NFQ_reg = { .name = "NFQUEUE", .target = target, - .checkentry = checkentry, + .targetsize = sizeof(struct xt_NFQ_info), .me = THIS_MODULE, }; static struct xt_target ip6t_NFQ_reg = { .name = "NFQUEUE", .target = target, - .checkentry = checkentry, + .targetsize = sizeof(struct xt_NFQ_info), .me = THIS_MODULE, }; static struct xt_target arpt_NFQ_reg = { .name = "NFQUEUE", .target = target, - .checkentry = checkentry, + .targetsize = sizeof(struct xt_NFQ_info), .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_NOTRACK.c b/net/netfilter/xt_NOTRACK.c index 24d477afa939..b8634e3f6169 100644 --- a/net/netfilter/xt_NOTRACK.c +++ b/net/netfilter/xt_NOTRACK.c @@ -15,6 +15,7 @@ target(struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, + const struct xt_target *target, const void *targinfo, void *userinfo) { @@ -33,38 +34,20 @@ target(struct sk_buff **pskb, return XT_CONTINUE; } -static int -checkentry(const char *tablename, - const void *entry, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != 0) { - printk(KERN_WARNING "NOTRACK: targinfosize %u != 0\n", - targinfosize); - return 0; - } - - if (strcmp(tablename, "raw") != 0) { - printk(KERN_WARNING "NOTRACK: can only be called from \"raw\" table, not \"%s\"\n", tablename); - return 0; - } - - return 1; -} - -static struct xt_target notrack_reg = { - .name = "NOTRACK", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE, +static struct xt_target notrack_reg = { + .name = "NOTRACK", + .target = target, + .targetsize = 0, + .table = "raw", + .me = THIS_MODULE, }; -static struct xt_target notrack6_reg = { - .name = "NOTRACK", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE, + +static struct xt_target notrack6_reg = { + .name = "NOTRACK", + .target = target, + .targetsize = 0, + .table = "raw", + .me = THIS_MODULE, }; static int __init init(void) diff --git a/net/netfilter/xt_comment.c b/net/netfilter/xt_comment.c index 4ba6fd65c6e9..03d9d741231c 100644 --- a/net/netfilter/xt_comment.c +++ b/net/netfilter/xt_comment.c @@ -19,6 +19,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protooff, @@ -28,30 +29,17 @@ match(const struct sk_buff *skb, return 1; } -static int -checkentry(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - /* Check the size */ - if (matchsize != XT_ALIGN(sizeof(struct xt_comment_info))) - return 0; - return 1; -} - static struct xt_match comment_match = { .name = "comment", .match = match, - .checkentry = checkentry, + .matchsize = sizeof(struct xt_comment_info), .me = THIS_MODULE }; static struct xt_match comment6_match = { .name = "comment", .match = match, - .checkentry = checkentry, + .matchsize = sizeof(struct xt_comment_info), .me = THIS_MODULE }; diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c index 150d2a4b0f71..f34ecb9485c7 100644 --- a/net/netfilter/xt_connbytes.c +++ b/net/netfilter/xt_connbytes.c @@ -44,6 +44,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -122,15 +123,13 @@ match(const struct sk_buff *skb, static int check(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { const struct xt_connbytes_info *sinfo = matchinfo; - if (matchsize != XT_ALIGN(sizeof(struct xt_connbytes_info))) - return 0; - if (sinfo->what != XT_CONNBYTES_PKTS && sinfo->what != XT_CONNBYTES_BYTES && sinfo->what != XT_CONNBYTES_AVGPKT) @@ -146,14 +145,16 @@ static int check(const char *tablename, static struct xt_match connbytes_match = { .name = "connbytes", - .match = &match, - .checkentry = &check, + .match = match, + .checkentry = check, + .matchsize = sizeof(struct xt_connbytes_info), .me = THIS_MODULE }; static struct xt_match connbytes6_match = { .name = "connbytes", - .match = &match, - .checkentry = &check, + .match = match, + .checkentry = check, + .matchsize = sizeof(struct xt_connbytes_info), .me = THIS_MODULE }; diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index d06e925032da..51822471e919 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -35,6 +35,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -52,37 +53,36 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - struct xt_connmark_info *cm = - (struct xt_connmark_info *)matchinfo; - if (matchsize != XT_ALIGN(sizeof(struct xt_connmark_info))) - return 0; + struct xt_connmark_info *cm = (struct xt_connmark_info *)matchinfo; if (cm->mark > 0xffffffff || cm->mask > 0xffffffff) { printk(KERN_WARNING "connmark: only support 32bit mark\n"); return 0; } - return 1; } static struct xt_match connmark_match = { - .name = "connmark", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE + .name = "connmark", + .match = match, + .matchsize = sizeof(struct xt_connmark_info), + .checkentry = checkentry, + .me = THIS_MODULE }; + static struct xt_match connmark6_match = { - .name = "connmark", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE + .name = "connmark", + .match = match, + .matchsize = sizeof(struct xt_connmark_info), + .checkentry = checkentry, + .me = THIS_MODULE }; - static int __init init(void) { int ret; diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index ffdebc95eb95..39fc29496e00 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -32,6 +32,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -118,6 +119,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -201,22 +203,10 @@ match(const struct sk_buff *skb, #endif /* CONFIG_NF_IP_CONNTRACK */ -static int check(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != XT_ALIGN(sizeof(struct xt_conntrack_info))) - return 0; - - return 1; -} - static struct xt_match conntrack_match = { .name = "conntrack", - .match = &match, - .checkentry = &check, + .match = match, + .matchsize = sizeof(struct xt_conntrack_info), .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_dccp.c b/net/netfilter/xt_dccp.c index 779f42fc9524..db6b70cdc770 100644 --- a/net/netfilter/xt_dccp.c +++ b/net/netfilter/xt_dccp.c @@ -95,6 +95,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -129,56 +130,34 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *inf, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - const struct ipt_ip *ip = inf; - const struct xt_dccp_info *info; + const struct xt_dccp_info *info = matchinfo; - info = (const struct xt_dccp_info *)matchinfo; - - return ip->proto == IPPROTO_DCCP - && !(ip->invflags & XT_INV_PROTO) - && matchsize == XT_ALIGN(sizeof(struct xt_dccp_info)) - && !(info->flags & ~XT_DCCP_VALID_FLAGS) - && !(info->invflags & ~XT_DCCP_VALID_FLAGS) - && !(info->invflags & ~info->flags); -} - -static int -checkentry6(const char *tablename, - const void *inf, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ip6t_ip6 *ip = inf; - const struct xt_dccp_info *info; - - info = (const struct xt_dccp_info *)matchinfo; - - return ip->proto == IPPROTO_DCCP - && !(ip->invflags & XT_INV_PROTO) - && matchsize == XT_ALIGN(sizeof(struct xt_dccp_info)) - && !(info->flags & ~XT_DCCP_VALID_FLAGS) + return !(info->flags & ~XT_DCCP_VALID_FLAGS) && !(info->invflags & ~XT_DCCP_VALID_FLAGS) && !(info->invflags & ~info->flags); } - static struct xt_match dccp_match = { .name = "dccp", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct xt_dccp_info), + .proto = IPPROTO_DCCP, + .checkentry = checkentry, .me = THIS_MODULE, }; static struct xt_match dccp6_match = { .name = "dccp", - .match = &match, - .checkentry = &checkentry6, + .match = match, + .matchsize = sizeof(struct xt_dccp_info), + .proto = IPPROTO_DCCP, + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_helper.c b/net/netfilter/xt_helper.c index 38b6715e1db4..ef8e54d40c92 100644 --- a/net/netfilter/xt_helper.c +++ b/net/netfilter/xt_helper.c @@ -42,6 +42,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -89,6 +90,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -96,6 +98,7 @@ match(const struct sk_buff *skb, { const struct xt_helper_info *info = matchinfo; struct nf_conn *ct; + struct nf_conn_help *master_help; enum ip_conntrack_info ctinfo; int ret = info->invert; @@ -111,7 +114,8 @@ match(const struct sk_buff *skb, } read_lock_bh(&nf_conntrack_lock); - if (!ct->master->helper) { + master_help = nfct_help(ct->master); + if (!master_help || !master_help->helper) { DEBUGP("xt_helper: master ct %p has no helper\n", exp->expectant); goto out_unlock; @@ -123,8 +127,8 @@ match(const struct sk_buff *skb, if (info->name[0] == '\0') ret ^= 1; else - ret ^= !strncmp(ct->master->helper->name, info->name, - strlen(ct->master->helper->name)); + ret ^= !strncmp(master_help->helper->name, info->name, + strlen(master_help->helper->name)); out_unlock: read_unlock_bh(&nf_conntrack_lock); return ret; @@ -133,6 +137,7 @@ out_unlock: static int check(const char *tablename, const void *inf, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) @@ -140,24 +145,21 @@ static int check(const char *tablename, struct xt_helper_info *info = matchinfo; info->name[29] = '\0'; - - /* verify size */ - if (matchsize != XT_ALIGN(sizeof(struct xt_helper_info))) - return 0; - return 1; } static struct xt_match helper_match = { .name = "helper", - .match = &match, - .checkentry = &check, + .match = match, + .matchsize = sizeof(struct xt_helper_info), + .checkentry = check, .me = THIS_MODULE, }; static struct xt_match helper6_match = { .name = "helper", - .match = &match, - .checkentry = &check, + .match = match, + .matchsize = sizeof(struct xt_helper_info), + .checkentry = check, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_length.c b/net/netfilter/xt_length.c index 39c8faea63de..b9e60f041a64 100644 --- a/net/netfilter/xt_length.c +++ b/net/netfilter/xt_length.c @@ -24,6 +24,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -39,6 +40,7 @@ static int match6(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -50,29 +52,17 @@ match6(const struct sk_buff *skb, return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } -static int -checkentry(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != XT_ALIGN(sizeof(struct xt_length_info))) - return 0; - - return 1; -} - static struct xt_match length_match = { .name = "length", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct xt_length_info), .me = THIS_MODULE, }; + static struct xt_match length6_match = { .name = "length", - .match = &match6, - .checkentry = &checkentry, + .match = match6, + .matchsize = sizeof(struct xt_length_info), .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 15e40506bc3a..3049e6f8889e 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -68,6 +68,7 @@ static int ipt_limit_match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -107,15 +108,13 @@ user2credits(u_int32_t user) static int ipt_limit_checkentry(const char *tablename, const void *inf, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { struct xt_rateinfo *r = matchinfo; - if (matchsize != XT_ALIGN(sizeof(struct xt_rateinfo))) - return 0; - /* Check for overflow. */ if (r->burst == 0 || user2credits(r->avg * r->burst) < user2credits(r->avg)) { @@ -140,12 +139,14 @@ ipt_limit_checkentry(const char *tablename, static struct xt_match ipt_limit_reg = { .name = "limit", .match = ipt_limit_match, + .matchsize = sizeof(struct xt_rateinfo), .checkentry = ipt_limit_checkentry, .me = THIS_MODULE, }; static struct xt_match limit6_reg = { .name = "limit", .match = ipt_limit_match, + .matchsize = sizeof(struct xt_rateinfo), .checkentry = ipt_limit_checkentry, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_mac.c b/net/netfilter/xt_mac.c index 0461dcb5fc7a..b4559a46dce8 100644 --- a/net/netfilter/xt_mac.c +++ b/net/netfilter/xt_mac.c @@ -27,6 +27,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -42,37 +43,20 @@ match(const struct sk_buff *skb, ^ info->invert)); } -static int -ipt_mac_checkentry(const char *tablename, - const void *inf, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - /* FORWARD isn't always valid, but it's nice to be able to do --RR */ - if (hook_mask - & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_IN) - | (1 << NF_IP_FORWARD))) { - printk("xt_mac: only valid for PRE_ROUTING, LOCAL_IN or FORWARD.\n"); - return 0; - } - - if (matchsize != XT_ALIGN(sizeof(struct xt_mac_info))) - return 0; - - return 1; -} - static struct xt_match mac_match = { .name = "mac", - .match = &match, - .checkentry = &ipt_mac_checkentry, + .match = match, + .matchsize = sizeof(struct xt_mac_info), + .hooks = (1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_IN) | + (1 << NF_IP_FORWARD), .me = THIS_MODULE, }; static struct xt_match mac6_match = { .name = "mac", - .match = &match, - .checkentry = &ipt_mac_checkentry, + .match = match, + .matchsize = sizeof(struct xt_mac_info), + .hooks = (1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_IN) | + (1 << NF_IP_FORWARD), .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_mark.c b/net/netfilter/xt_mark.c index 2a0ac62b72c8..c1a8f0f587f0 100644 --- a/net/netfilter/xt_mark.c +++ b/net/netfilter/xt_mark.c @@ -23,6 +23,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -36,34 +37,33 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *entry, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { struct xt_mark_info *minfo = (struct xt_mark_info *) matchinfo; - if (matchsize != XT_ALIGN(sizeof(struct xt_mark_info))) - return 0; - if (minfo->mark > 0xffffffff || minfo->mask > 0xffffffff) { printk(KERN_WARNING "mark: only supports 32bit mark\n"); return 0; } - return 1; } static struct xt_match mark_match = { .name = "mark", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct xt_mark_info), + .checkentry = checkentry, .me = THIS_MODULE, }; static struct xt_match mark6_match = { .name = "mark", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct xt_mark_info), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index 19bb57c14dfe..f788e8e76254 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -26,6 +26,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -102,14 +103,13 @@ match_outdev: static int checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { const struct xt_physdev_info *info = matchinfo; - if (matchsize != XT_ALIGN(sizeof(struct xt_physdev_info))) - return 0; if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || info->bitmask & ~XT_PHYSDEV_OP_MASK) return 0; @@ -118,15 +118,17 @@ checkentry(const char *tablename, static struct xt_match physdev_match = { .name = "physdev", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct xt_physdev_info), + .checkentry = checkentry, .me = THIS_MODULE, }; static struct xt_match physdev6_match = { .name = "physdev", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct xt_physdev_info), + .checkentry = checkentry, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_pkttype.c b/net/netfilter/xt_pkttype.c index ab1b2630f97d..f38638dfd139 100644 --- a/net/netfilter/xt_pkttype.c +++ b/net/netfilter/xt_pkttype.c @@ -22,6 +22,7 @@ MODULE_ALIAS("ip6t_pkttype"); static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -32,32 +33,20 @@ static int match(const struct sk_buff *skb, return (skb->pkt_type == info->pkttype) ^ info->invert; } -static int checkentry(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != XT_ALIGN(sizeof(struct xt_pkttype_info))) - return 0; - - return 1; -} - static struct xt_match pkttype_match = { .name = "pkttype", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct xt_pkttype_info), .me = THIS_MODULE, }; + static struct xt_match pkttype6_match = { .name = "pkttype", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct xt_pkttype_info), .me = THIS_MODULE, }; - static int __init init(void) { int ret; diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c new file mode 100644 index 000000000000..1ec22082f04d --- /dev/null +++ b/net/netfilter/xt_policy.c @@ -0,0 +1,209 @@ +/* IP tables module for matching IPsec policy + * + * Copyright (c) 2004,2005 Patrick McHardy, <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/config.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/init.h> +#include <net/xfrm.h> + +#include <linux/netfilter/xt_policy.h> +#include <linux/netfilter/x_tables.h> + +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Xtables IPsec policy matching module"); +MODULE_LICENSE("GPL"); + +static inline int +xt_addr_cmp(const union xt_policy_addr *a1, const union xt_policy_addr *m, + const union xt_policy_addr *a2, unsigned short family) +{ + switch (family) { + case AF_INET: + return (a1->a4.s_addr ^ a2->a4.s_addr) & m->a4.s_addr; + case AF_INET6: + return ipv6_masked_addr_cmp(&a1->a6, &m->a6, &a2->a6); + } + return 0; +} + +static inline int +match_xfrm_state(struct xfrm_state *x, const struct xt_policy_elem *e, + unsigned short family) +{ +#define MATCH_ADDR(x,y,z) (!e->match.x || \ + (xt_addr_cmp(&e->x, &e->y, z, family) \ + ^ e->invert.x)) +#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) + + return MATCH_ADDR(saddr, smask, (union xt_policy_addr *)&x->props.saddr) && + MATCH_ADDR(daddr, dmask, (union xt_policy_addr *)&x->id.daddr.a4) && + MATCH(proto, x->id.proto) && + MATCH(mode, x->props.mode) && + MATCH(spi, x->id.spi) && + MATCH(reqid, x->props.reqid); +} + +static int +match_policy_in(const struct sk_buff *skb, const struct xt_policy_info *info, + unsigned short family) +{ + const struct xt_policy_elem *e; + struct sec_path *sp = skb->sp; + int strict = info->flags & XT_POLICY_MATCH_STRICT; + int i, pos; + + if (sp == NULL) + return -1; + if (strict && info->len != sp->len) + return 0; + + for (i = sp->len - 1; i >= 0; i--) { + pos = strict ? i - sp->len + 1 : 0; + if (pos >= info->len) + return 0; + e = &info->pol[pos]; + + if (match_xfrm_state(sp->x[i].xvec, e, family)) { + if (!strict) + return 1; + } else if (strict) + return 0; + } + + return strict ? 1 : 0; +} + +static int +match_policy_out(const struct sk_buff *skb, const struct xt_policy_info *info, + unsigned short family) +{ + const struct xt_policy_elem *e; + struct dst_entry *dst = skb->dst; + int strict = info->flags & XT_POLICY_MATCH_STRICT; + int i, pos; + + if (dst->xfrm == NULL) + return -1; + + for (i = 0; dst && dst->xfrm; dst = dst->child, i++) { + pos = strict ? i : 0; + if (pos >= info->len) + return 0; + e = &info->pol[pos]; + + if (match_xfrm_state(dst->xfrm, e, family)) { + if (!strict) + return 1; + } else if (strict) + return 0; + } + + return strict ? i == info->len : 0; +} + +static int match(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct xt_match *match, + const void *matchinfo, + int offset, + unsigned int protoff, + int *hotdrop) +{ + const struct xt_policy_info *info = matchinfo; + int ret; + + if (info->flags & XT_POLICY_MATCH_IN) + ret = match_policy_in(skb, info, match->family); + else + ret = match_policy_out(skb, info, match->family); + + if (ret < 0) + ret = info->flags & XT_POLICY_MATCH_NONE ? 1 : 0; + else if (info->flags & XT_POLICY_MATCH_NONE) + ret = 0; + + return ret; +} + +static int checkentry(const char *tablename, const void *ip_void, + const struct xt_match *match, + void *matchinfo, unsigned int matchsize, + unsigned int hook_mask) +{ + struct xt_policy_info *info = matchinfo; + + if (!(info->flags & (XT_POLICY_MATCH_IN|XT_POLICY_MATCH_OUT))) { + printk(KERN_ERR "xt_policy: neither incoming nor " + "outgoing policy selected\n"); + return 0; + } + /* hook values are equal for IPv4 and IPv6 */ + if (hook_mask & (1 << NF_IP_PRE_ROUTING | 1 << NF_IP_LOCAL_IN) + && info->flags & XT_POLICY_MATCH_OUT) { + printk(KERN_ERR "xt_policy: output policy not valid in " + "PRE_ROUTING and INPUT\n"); + return 0; + } + if (hook_mask & (1 << NF_IP_POST_ROUTING | 1 << NF_IP_LOCAL_OUT) + && info->flags & XT_POLICY_MATCH_IN) { + printk(KERN_ERR "xt_policy: input policy not valid in " + "POST_ROUTING and OUTPUT\n"); + return 0; + } + if (info->len > XT_POLICY_MAX_ELEM) { + printk(KERN_ERR "xt_policy: too many policy elements\n"); + return 0; + } + return 1; +} + +static struct xt_match policy_match = { + .name = "policy", + .family = AF_INET, + .match = match, + .matchsize = sizeof(struct xt_policy_info), + .checkentry = checkentry, + .me = THIS_MODULE, +}; + +static struct xt_match policy6_match = { + .name = "policy", + .family = AF_INET6, + .match = match, + .matchsize = sizeof(struct xt_policy_info), + .checkentry = checkentry, + .me = THIS_MODULE, +}; + +static int __init init(void) +{ + int ret; + + ret = xt_register_match(AF_INET, &policy_match); + if (ret) + return ret; + ret = xt_register_match(AF_INET6, &policy6_match); + if (ret) + xt_unregister_match(AF_INET, &policy_match); + return ret; +} + +static void __exit fini(void) +{ + xt_unregister_match(AF_INET6, &policy6_match); + xt_unregister_match(AF_INET, &policy_match); +} + +module_init(init); +module_exit(fini); +MODULE_ALIAS("ipt_policy"); +MODULE_ALIAS("ip6t_policy"); diff --git a/net/netfilter/xt_realm.c b/net/netfilter/xt_realm.c index 2b7e1781d34d..57815a07db67 100644 --- a/net/netfilter/xt_realm.c +++ b/net/netfilter/xt_realm.c @@ -27,6 +27,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -38,30 +39,12 @@ match(const struct sk_buff *skb, return (info->id == (dst->tclassid & info->mask)) ^ info->invert; } -static int check(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (hook_mask - & ~((1 << NF_IP_POST_ROUTING) | (1 << NF_IP_FORWARD) | - (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_LOCAL_IN))) { - printk("xt_realm: only valid for POST_ROUTING, LOCAL_OUT, " - "LOCAL_IN or FORWARD.\n"); - return 0; - } - if (matchsize != XT_ALIGN(sizeof(struct xt_realm_info))) { - printk("xt_realm: invalid matchsize.\n"); - return 0; - } - return 1; -} - static struct xt_match realm_match = { .name = "realm", - .match = match, - .checkentry = check, + .match = match, + .matchsize = sizeof(struct xt_realm_info), + .hooks = (1 << NF_IP_POST_ROUTING) | (1 << NF_IP_FORWARD) | + (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_LOCAL_IN), .me = THIS_MODULE }; diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index 10fbfc5ba758..f5d698ba03ca 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -123,6 +123,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -162,19 +163,14 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *inf, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - const struct xt_sctp_info *info; - const struct ipt_ip *ip = inf; - - info = (const struct xt_sctp_info *)matchinfo; + const struct xt_sctp_info *info = matchinfo; - return ip->proto == IPPROTO_SCTP - && !(ip->invflags & XT_INV_PROTO) - && matchsize == XT_ALIGN(sizeof(struct xt_sctp_info)) - && !(info->flags & ~XT_SCTP_VALID_FLAGS) + return !(info->flags & ~XT_SCTP_VALID_FLAGS) && !(info->invflags & ~XT_SCTP_VALID_FLAGS) && !(info->invflags & ~info->flags) && ((!(info->flags & XT_SCTP_CHUNK_TYPES)) || @@ -184,47 +180,23 @@ checkentry(const char *tablename, | SCTP_CHUNK_MATCH_ONLY))); } -static int -checkentry6(const char *tablename, - const void *inf, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct xt_sctp_info *info; - const struct ip6t_ip6 *ip = inf; - - info = (const struct xt_sctp_info *)matchinfo; - - return ip->proto == IPPROTO_SCTP - && !(ip->invflags & XT_INV_PROTO) - && matchsize == XT_ALIGN(sizeof(struct xt_sctp_info)) - && !(info->flags & ~XT_SCTP_VALID_FLAGS) - && !(info->invflags & ~XT_SCTP_VALID_FLAGS) - && !(info->invflags & ~info->flags) - && ((!(info->flags & XT_SCTP_CHUNK_TYPES)) || - (info->chunk_match_type & - (SCTP_CHUNK_MATCH_ALL - | SCTP_CHUNK_MATCH_ANY - | SCTP_CHUNK_MATCH_ONLY))); -} - - -static struct xt_match sctp_match = -{ - .name = "sctp", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE -}; -static struct xt_match sctp6_match = -{ - .name = "sctp", - .match = &match, - .checkentry = &checkentry6, - .me = THIS_MODULE +static struct xt_match sctp_match = { + .name = "sctp", + .match = match, + .matchsize = sizeof(struct xt_sctp_info), + .proto = IPPROTO_SCTP, + .checkentry = checkentry, + .me = THIS_MODULE }; +static struct xt_match sctp6_match = { + .name = "sctp", + .match = match, + .matchsize = sizeof(struct xt_sctp_info), + .proto = IPPROTO_SCTP, + .checkentry = checkentry, + .me = THIS_MODULE +}; static int __init init(void) { diff --git a/net/netfilter/xt_state.c b/net/netfilter/xt_state.c index 39ce808d40ef..b8ec00cd51fc 100644 --- a/net/netfilter/xt_state.c +++ b/net/netfilter/xt_state.c @@ -24,6 +24,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -43,29 +44,17 @@ match(const struct sk_buff *skb, return (sinfo->statemask & statebit); } -static int check(const char *tablename, - const void *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != XT_ALIGN(sizeof(struct xt_state_info))) - return 0; - - return 1; -} - static struct xt_match state_match = { .name = "state", - .match = &match, - .checkentry = &check, + .match = match, + .matchsize = sizeof(struct xt_state_info), .me = THIS_MODULE, }; static struct xt_match state6_match = { .name = "state", - .match = &match, - .checkentry = &check, + .match = match, + .matchsize = sizeof(struct xt_state_info), .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c index 7c7d5c8807d6..fccbad6a7f40 100644 --- a/net/netfilter/xt_string.c +++ b/net/netfilter/xt_string.c @@ -24,6 +24,7 @@ MODULE_ALIAS("ip6t_string"); static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -43,6 +44,7 @@ static int match(const struct sk_buff *skb, static int checkentry(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) @@ -50,9 +52,6 @@ static int checkentry(const char *tablename, struct xt_string_info *conf = matchinfo; struct ts_config *ts_conf; - if (matchsize != XT_ALIGN(sizeof(struct xt_string_info))) - return 0; - /* Damn, can't handle this case properly with iptables... */ if (conf->from_offset > conf->to_offset) return 0; @@ -67,7 +66,8 @@ static int checkentry(const char *tablename, return 1; } -static void destroy(void *matchinfo, unsigned int matchsize) +static void destroy(const struct xt_match *match, void *matchinfo, + unsigned int matchsize) { textsearch_destroy(STRING_TEXT_PRIV(matchinfo)->config); } @@ -75,6 +75,7 @@ static void destroy(void *matchinfo, unsigned int matchsize) static struct xt_match string_match = { .name = "string", .match = match, + .matchsize = sizeof(struct xt_string_info), .checkentry = checkentry, .destroy = destroy, .me = THIS_MODULE @@ -82,6 +83,7 @@ static struct xt_match string_match = { static struct xt_match string6_match = { .name = "string", .match = match, + .matchsize = sizeof(struct xt_string_info), .checkentry = checkentry, .destroy = destroy, .me = THIS_MODULE diff --git a/net/netfilter/xt_tcpmss.c b/net/netfilter/xt_tcpmss.c index acf7f533e9f1..4925fc98f4ae 100644 --- a/net/netfilter/xt_tcpmss.c +++ b/net/netfilter/xt_tcpmss.c @@ -81,6 +81,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -92,58 +93,19 @@ match(const struct sk_buff *skb, info->invert, hotdrop); } -static int -checkentry(const char *tablename, - const void *ipinfo, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ipt_ip *ip = ipinfo; - if (matchsize != XT_ALIGN(sizeof(struct xt_tcpmss_match_info))) - return 0; - - /* Must specify -p tcp */ - if (ip->proto != IPPROTO_TCP || (ip->invflags & IPT_INV_PROTO)) { - printk("tcpmss: Only works on TCP packets\n"); - return 0; - } - - return 1; -} - -static int -checkentry6(const char *tablename, - const void *ipinfo, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ip6t_ip6 *ip = ipinfo; - - if (matchsize != XT_ALIGN(sizeof(struct xt_tcpmss_match_info))) - return 0; - - /* Must specify -p tcp */ - if (ip->proto != IPPROTO_TCP || (ip->invflags & XT_INV_PROTO)) { - printk("tcpmss: Only works on TCP packets\n"); - return 0; - } - - return 1; -} - static struct xt_match tcpmss_match = { .name = "tcpmss", - .match = &match, - .checkentry = &checkentry, + .match = match, + .matchsize = sizeof(struct xt_tcpmss_match_info), + .proto = IPPROTO_TCP, .me = THIS_MODULE, }; static struct xt_match tcpmss6_match = { .name = "tcpmss", - .match = &match, - .checkentry = &checkentry6, + .match = match, + .matchsize = sizeof(struct xt_tcpmss_match_info), + .proto = IPPROTO_TCP, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c index 669c8113cc60..b5cd0dd4e41f 100644 --- a/net/netfilter/xt_tcpudp.c +++ b/net/netfilter/xt_tcpudp.c @@ -74,6 +74,7 @@ static int tcp_match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -138,43 +139,22 @@ tcp_match(const struct sk_buff *skb, static int tcp_checkentry(const char *tablename, const void *info, + const struct xt_match *match, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - const struct ipt_ip *ip = info; const struct xt_tcp *tcpinfo = matchinfo; - /* Must specify proto == TCP, and no unknown invflags */ - return ip->proto == IPPROTO_TCP - && !(ip->invflags & XT_INV_PROTO) - && matchsize == XT_ALIGN(sizeof(struct xt_tcp)) - && !(tcpinfo->invflags & ~XT_TCP_INV_MASK); + /* Must specify no unknown invflags */ + return !(tcpinfo->invflags & ~XT_TCP_INV_MASK); } -/* Called when user tries to insert an entry of this type. */ -static int -tcp6_checkentry(const char *tablename, - const void *entry, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ip6t_ip6 *ipv6 = entry; - const struct xt_tcp *tcpinfo = matchinfo; - - /* Must specify proto == TCP, and no unknown invflags */ - return ipv6->proto == IPPROTO_TCP - && !(ipv6->invflags & XT_INV_PROTO) - && matchsize == XT_ALIGN(sizeof(struct xt_tcp)) - && !(tcpinfo->invflags & ~XT_TCP_INV_MASK); -} - - static int udp_match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, int offset, unsigned int protoff, @@ -208,87 +188,49 @@ udp_match(const struct sk_buff *skb, static int udp_checkentry(const char *tablename, const void *info, + const struct xt_match *match, void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) -{ - const struct ipt_ip *ip = info; - const struct xt_udp *udpinfo = matchinfo; - - /* Must specify proto == UDP, and no unknown invflags */ - if (ip->proto != IPPROTO_UDP || (ip->invflags & XT_INV_PROTO)) { - duprintf("ipt_udp: Protocol %u != %u\n", ip->proto, - IPPROTO_UDP); - return 0; - } - if (matchinfosize != XT_ALIGN(sizeof(struct xt_udp))) { - duprintf("ipt_udp: matchsize %u != %u\n", - matchinfosize, XT_ALIGN(sizeof(struct xt_udp))); - return 0; - } - if (udpinfo->invflags & ~XT_UDP_INV_MASK) { - duprintf("ipt_udp: unknown flags %X\n", - udpinfo->invflags); - return 0; - } - - return 1; -} - -/* Called when user tries to insert an entry of this type. */ -static int -udp6_checkentry(const char *tablename, - const void *entry, - void *matchinfo, - unsigned int matchinfosize, + unsigned int matchsize, unsigned int hook_mask) { - const struct ip6t_ip6 *ipv6 = entry; - const struct xt_udp *udpinfo = matchinfo; + const struct xt_tcp *udpinfo = matchinfo; - /* Must specify proto == UDP, and no unknown invflags */ - if (ipv6->proto != IPPROTO_UDP || (ipv6->invflags & XT_INV_PROTO)) { - duprintf("ip6t_udp: Protocol %u != %u\n", ipv6->proto, - IPPROTO_UDP); - return 0; - } - if (matchinfosize != XT_ALIGN(sizeof(struct xt_udp))) { - duprintf("ip6t_udp: matchsize %u != %u\n", - matchinfosize, XT_ALIGN(sizeof(struct xt_udp))); - return 0; - } - if (udpinfo->invflags & ~XT_UDP_INV_MASK) { - duprintf("ip6t_udp: unknown flags %X\n", - udpinfo->invflags); - return 0; - } - - return 1; + /* Must specify no unknown invflags */ + return !(udpinfo->invflags & ~XT_UDP_INV_MASK); } static struct xt_match tcp_matchstruct = { .name = "tcp", - .match = &tcp_match, - .checkentry = &tcp_checkentry, + .match = tcp_match, + .matchsize = sizeof(struct xt_tcp), + .proto = IPPROTO_TCP, + .checkentry = tcp_checkentry, .me = THIS_MODULE, }; + static struct xt_match tcp6_matchstruct = { .name = "tcp", - .match = &tcp_match, - .checkentry = &tcp6_checkentry, + .match = tcp_match, + .matchsize = sizeof(struct xt_tcp), + .proto = IPPROTO_TCP, + .checkentry = tcp_checkentry, .me = THIS_MODULE, }; static struct xt_match udp_matchstruct = { .name = "udp", - .match = &udp_match, - .checkentry = &udp_checkentry, + .match = udp_match, + .matchsize = sizeof(struct xt_udp), + .proto = IPPROTO_UDP, + .checkentry = udp_checkentry, .me = THIS_MODULE, }; static struct xt_match udp6_matchstruct = { .name = "udp", - .match = &udp_match, - .checkentry = &udp6_checkentry, + .match = udp_match, + .matchsize = sizeof(struct xt_udp), + .proto = IPPROTO_UDP, + .checkentry = udp_checkentry, .me = THIS_MODULE, }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 59dc7d140600..d00a9034cb5f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -106,6 +106,7 @@ struct nl_pid_hash { struct netlink_table { struct nl_pid_hash hash; struct hlist_head mc_list; + unsigned long *listeners; unsigned int nl_nonroot; unsigned int groups; struct module *module; @@ -296,6 +297,24 @@ static inline int nl_pid_hash_dilute(struct nl_pid_hash *hash, int len) static const struct proto_ops netlink_ops; +static void +netlink_update_listeners(struct sock *sk) +{ + struct netlink_table *tbl = &nl_table[sk->sk_protocol]; + struct hlist_node *node; + unsigned long mask; + unsigned int i; + + for (i = 0; i < NLGRPSZ(tbl->groups)/sizeof(unsigned long); i++) { + mask = 0; + sk_for_each_bound(sk, node, &tbl->mc_list) + mask |= nlk_sk(sk)->groups[i]; + tbl->listeners[i] = mask; + } + /* this function is only called with the netlink table "grabbed", which + * makes sure updates are visible before bind or setsockopt return. */ +} + static int netlink_insert(struct sock *sk, u32 pid) { struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash; @@ -456,12 +475,14 @@ static int netlink_release(struct socket *sock) if (nlk->module) module_put(nlk->module); + netlink_table_grab(); if (nlk->flags & NETLINK_KERNEL_SOCKET) { - netlink_table_grab(); + kfree(nl_table[sk->sk_protocol].listeners); nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].registered = 0; - netlink_table_ungrab(); - } + } else if (nlk->subscriptions) + netlink_update_listeners(sk); + netlink_table_ungrab(); kfree(nlk->groups); nlk->groups = NULL; @@ -589,6 +610,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len hweight32(nladdr->nl_groups) - hweight32(nlk->groups[0])); nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups; + netlink_update_listeners(sk); netlink_table_ungrab(); return 0; @@ -807,6 +829,17 @@ retry: return netlink_sendskb(sk, skb, ssk->sk_protocol); } +int netlink_has_listeners(struct sock *sk, unsigned int group) +{ + int res = 0; + + BUG_ON(!(nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET)); + if (group - 1 < nl_table[sk->sk_protocol].groups) + res = test_bit(group - 1, nl_table[sk->sk_protocol].listeners); + return res; +} +EXPORT_SYMBOL_GPL(netlink_has_listeners); + static __inline__ int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); @@ -1011,6 +1044,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, else __clear_bit(val - 1, nlk->groups); netlink_update_subscriptions(sk, subscriptions); + netlink_update_listeners(sk); netlink_table_ungrab(); err = 0; break; @@ -1237,6 +1271,7 @@ netlink_kernel_create(int unit, unsigned int groups, struct socket *sock; struct sock *sk; struct netlink_sock *nlk; + unsigned long *listeners = NULL; if (!nl_table) return NULL; @@ -1250,6 +1285,13 @@ netlink_kernel_create(int unit, unsigned int groups, if (__netlink_create(sock, unit) < 0) goto out_sock_release; + if (groups < 32) + groups = 32; + + listeners = kzalloc(NLGRPSZ(groups), GFP_KERNEL); + if (!listeners) + goto out_sock_release; + sk = sock->sk; sk->sk_data_ready = netlink_data_ready; if (input) @@ -1262,7 +1304,8 @@ netlink_kernel_create(int unit, unsigned int groups, nlk->flags |= NETLINK_KERNEL_SOCKET; netlink_table_grab(); - nl_table[unit].groups = groups < 32 ? 32 : groups; + nl_table[unit].groups = groups; + nl_table[unit].listeners = listeners; nl_table[unit].module = module; nl_table[unit].registered = 1; netlink_table_ungrab(); @@ -1270,6 +1313,7 @@ netlink_kernel_create(int unit, unsigned int groups, return sk; out_sock_release: + kfree(listeners); sock_release(sock); return NULL; } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 778b1e5a4b50..13eeee582886 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -434,7 +434,6 @@ config NET_EMATCH_TEXT config NET_CLS_ACT bool "Actions" - depends on EXPERIMENTAL select NET_ESTIMATOR ---help--- Say Y here if you want to use traffic control actions. Actions diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 39a22a3ffe78..6056d20ef429 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -70,7 +70,8 @@ ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook) t->u.kernel.target = target; if (t->u.kernel.target->checkentry - && !t->u.kernel.target->checkentry(table, NULL, t->data, + && !t->u.kernel.target->checkentry(table, NULL, + t->u.kernel.target, t->data, t->u.target_size - sizeof(*t), hook)) { DPRINTK("ipt_init_target: check failed for `%s'.\n", @@ -86,7 +87,7 @@ static void ipt_destroy_target(struct ipt_entry_target *t) { if (t->u.kernel.target->destroy) - t->u.kernel.target->destroy(t->data, + t->u.kernel.target->destroy(t->u.kernel.target, t->data, t->u.target_size - sizeof(*t)); module_put(t->u.kernel.target->me); } @@ -224,8 +225,9 @@ tcf_ipt(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) /* iptables targets take a double skb pointer in case the skb * needs to be replaced. We don't own the skb, so this must not * happen. The pskb_expand_head above should make sure of this */ - ret = p->t->u.kernel.target->target(&skb, skb->dev, NULL, - p->hook, p->t->data, NULL); + ret = p->t->u.kernel.target->target(&skb, skb->dev, NULL, p->hook, + p->t->u.kernel.target, p->t->data, + NULL); switch (ret) { case NF_ACCEPT: result = TC_ACT_OK; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 93ebce40acac..ac7cb60d1e25 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -638,6 +638,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, sch,p,flow,skb,tcm); if (!find_flow(p,flow)) return -EINVAL; tcm->tcm_handle = flow->classid; + tcm->tcm_info = flow->q->handle; rta = (struct rtattr *) b; RTA_PUT(skb,TCA_OPTIONS,0,NULL); RTA_PUT(skb,TCA_ATM_HDR,flow->hdr_len,flow->hdr); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 13e0e7b3856b..f6320ca70493 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -438,6 +438,7 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, return -EINVAL; tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl-1); + tcm->tcm_info = p->q->handle; opts = RTA_NEST(skb, TCA_OPTIONS); RTA_PUT_U8(skb,TCA_DSMARK_MASK, p->mask[cl-1]); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 99ceb91f0150..31eb83717c26 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -234,7 +234,7 @@ static void dev_watchdog_down(struct net_device *dev) { spin_lock_bh(&dev->xmit_lock); if (del_timer(&dev->watchdog_timer)) - __dev_put(dev); + dev_put(dev); spin_unlock_bh(&dev->xmit_lock); } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index ba5283204837..7228d30512c7 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -252,9 +252,9 @@ static int netem_requeue(struct sk_buff *skb, struct Qdisc *sch) static unsigned int netem_drop(struct Qdisc* sch) { struct netem_sched_data *q = qdisc_priv(sch); - unsigned int len; + unsigned int len = 0; - if ((len = q->qdisc->ops->drop(q->qdisc)) != 0) { + if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) { sch->q.qlen--; sch->qstats.drops++; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 1641db33a994..3395ca7bcadf 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -165,7 +165,7 @@ static unsigned int prio_drop(struct Qdisc* sch) for (prio = q->bands-1; prio >= 0; prio--) { qdisc = q->queues[prio]; - if ((len = qdisc->ops->drop(qdisc)) != 0) { + if (qdisc->ops->drop && (len = qdisc->ops->drop(qdisc)) != 0) { sch->q.qlen--; return len; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index dccfa44c2d71..2be563cba72b 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -44,6 +44,7 @@ struct red_sched_data unsigned char flags; struct red_parms parms; struct red_stats stats; + struct Qdisc *qdisc; }; static inline int red_use_ecn(struct red_sched_data *q) @@ -59,8 +60,10 @@ static inline int red_use_harddrop(struct red_sched_data *q) static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) { struct red_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; + int ret; - q->parms.qavg = red_calc_qavg(&q->parms, sch->qstats.backlog); + q->parms.qavg = red_calc_qavg(&q->parms, child->qstats.backlog); if (red_is_idling(&q->parms)) red_end_of_idle_period(&q->parms); @@ -91,11 +94,16 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) break; } - if (sch->qstats.backlog + skb->len <= q->limit) - return qdisc_enqueue_tail(skb, sch); - - q->stats.pdrop++; - return qdisc_drop(skb, sch); + ret = child->enqueue(skb, child); + if (likely(ret == NET_XMIT_SUCCESS)) { + sch->bstats.bytes += skb->len; + sch->bstats.packets++; + sch->q.qlen++; + } else { + q->stats.pdrop++; + sch->qstats.drops++; + } + return ret; congestion_drop: qdisc_drop(skb, sch); @@ -105,21 +113,30 @@ congestion_drop: static int red_requeue(struct sk_buff *skb, struct Qdisc* sch) { struct red_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; + int ret; if (red_is_idling(&q->parms)) red_end_of_idle_period(&q->parms); - return qdisc_requeue(skb, sch); + ret = child->ops->requeue(skb, child); + if (likely(ret == NET_XMIT_SUCCESS)) { + sch->qstats.requeues++; + sch->q.qlen++; + } + return ret; } static struct sk_buff * red_dequeue(struct Qdisc* sch) { struct sk_buff *skb; struct red_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; - skb = qdisc_dequeue_head(sch); - - if (skb == NULL && !red_is_idling(&q->parms)) + skb = child->dequeue(child); + if (skb) + sch->q.qlen--; + else if (!red_is_idling(&q->parms)) red_start_of_idle_period(&q->parms); return skb; @@ -127,14 +144,14 @@ static struct sk_buff * red_dequeue(struct Qdisc* sch) static unsigned int red_drop(struct Qdisc* sch) { - struct sk_buff *skb; struct red_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; + unsigned int len; - skb = qdisc_dequeue_tail(sch); - if (skb) { - unsigned int len = skb->len; + if (child->ops->drop && (len = child->ops->drop(child)) > 0) { q->stats.other++; - qdisc_drop(skb, sch); + sch->qstats.drops++; + sch->q.qlen--; return len; } @@ -148,15 +165,48 @@ static void red_reset(struct Qdisc* sch) { struct red_sched_data *q = qdisc_priv(sch); - qdisc_reset_queue(sch); + qdisc_reset(q->qdisc); + sch->q.qlen = 0; red_restart(&q->parms); } +static void red_destroy(struct Qdisc *sch) +{ + struct red_sched_data *q = qdisc_priv(sch); + qdisc_destroy(q->qdisc); +} + +static struct Qdisc *red_create_dflt(struct net_device *dev, u32 limit) +{ + struct Qdisc *q = qdisc_create_dflt(dev, &bfifo_qdisc_ops); + struct rtattr *rta; + int ret; + + if (q) { + rta = kmalloc(RTA_LENGTH(sizeof(struct tc_fifo_qopt)), + GFP_KERNEL); + if (rta) { + rta->rta_type = RTM_NEWQDISC; + rta->rta_len = RTA_LENGTH(sizeof(struct tc_fifo_qopt)); + ((struct tc_fifo_qopt *)RTA_DATA(rta))->limit = limit; + + ret = q->ops->change(q, rta); + kfree(rta); + + if (ret == 0) + return q; + } + qdisc_destroy(q); + } + return NULL; +} + static int red_change(struct Qdisc *sch, struct rtattr *opt) { struct red_sched_data *q = qdisc_priv(sch); struct rtattr *tb[TCA_RED_MAX]; struct tc_red_qopt *ctl; + struct Qdisc *child = NULL; if (opt == NULL || rtattr_parse_nested(tb, TCA_RED_MAX, opt)) return -EINVAL; @@ -169,9 +219,17 @@ static int red_change(struct Qdisc *sch, struct rtattr *opt) ctl = RTA_DATA(tb[TCA_RED_PARMS-1]); + if (ctl->limit > 0) { + child = red_create_dflt(sch->dev, ctl->limit); + if (child == NULL) + return -ENOMEM; + } + sch_tree_lock(sch); q->flags = ctl->flags; q->limit = ctl->limit; + if (child) + qdisc_destroy(xchg(&q->qdisc, child)); red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, @@ -186,6 +244,9 @@ static int red_change(struct Qdisc *sch, struct rtattr *opt) static int red_init(struct Qdisc* sch, struct rtattr *opt) { + struct red_sched_data *q = qdisc_priv(sch); + + q->qdisc = &noop_qdisc; return red_change(sch, opt); } @@ -224,15 +285,101 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) return gnet_stats_copy_app(d, &st, sizeof(st)); } +static int red_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct red_sched_data *q = qdisc_priv(sch); + + if (cl != 1) + return -ENOENT; + tcm->tcm_handle |= TC_H_MIN(1); + tcm->tcm_info = q->qdisc->handle; + return 0; +} + +static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, + struct Qdisc **old) +{ + struct red_sched_data *q = qdisc_priv(sch); + + if (new == NULL) + new = &noop_qdisc; + + sch_tree_lock(sch); + *old = xchg(&q->qdisc, new); + qdisc_reset(*old); + sch->q.qlen = 0; + sch_tree_unlock(sch); + return 0; +} + +static struct Qdisc *red_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct red_sched_data *q = qdisc_priv(sch); + return q->qdisc; +} + +static unsigned long red_get(struct Qdisc *sch, u32 classid) +{ + return 1; +} + +static void red_put(struct Qdisc *sch, unsigned long arg) +{ + return; +} + +static int red_change_class(struct Qdisc *sch, u32 classid, u32 parentid, + struct rtattr **tca, unsigned long *arg) +{ + return -ENOSYS; +} + +static int red_delete(struct Qdisc *sch, unsigned long cl) +{ + return -ENOSYS; +} + +static void red_walk(struct Qdisc *sch, struct qdisc_walker *walker) +{ + if (!walker->stop) { + if (walker->count >= walker->skip) + if (walker->fn(sch, 1, walker) < 0) { + walker->stop = 1; + return; + } + walker->count++; + } +} + +static struct tcf_proto **red_find_tcf(struct Qdisc *sch, unsigned long cl) +{ + return NULL; +} + +static struct Qdisc_class_ops red_class_ops = { + .graft = red_graft, + .leaf = red_leaf, + .get = red_get, + .put = red_put, + .change = red_change_class, + .delete = red_delete, + .walk = red_walk, + .tcf_chain = red_find_tcf, + .dump = red_dump_class, +}; + static struct Qdisc_ops red_qdisc_ops = { .id = "red", .priv_size = sizeof(struct red_sched_data), + .cl_ops = &red_class_ops, .enqueue = red_enqueue, .dequeue = red_dequeue, .requeue = red_requeue, .drop = red_drop, .init = red_init, .reset = red_reset, + .destroy = red_destroy, .change = red_change, .dump = red_dump, .dump_stats = red_dump_stats, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 86d8da0cbd02..e057768f68b4 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -232,6 +232,7 @@ static unsigned int sfq_drop(struct Qdisc *sch) sfq_dec(q, x); sch->q.qlen--; sch->qstats.drops++; + sch->qstats.backlog -= len; return len; } @@ -248,6 +249,7 @@ static unsigned int sfq_drop(struct Qdisc *sch) sch->q.qlen--; q->ht[q->hash[d]] = SFQ_DEPTH; sch->qstats.drops++; + sch->qstats.backlog -= len; return len; } @@ -266,6 +268,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc* sch) q->ht[hash] = x = q->dep[SFQ_DEPTH].next; q->hash[x] = hash; } + sch->qstats.backlog += skb->len; __skb_queue_tail(&q->qs[x], skb); sfq_inc(q, x); if (q->qs[x].qlen == 1) { /* The flow is new */ @@ -301,6 +304,7 @@ sfq_requeue(struct sk_buff *skb, struct Qdisc* sch) q->ht[hash] = x = q->dep[SFQ_DEPTH].next; q->hash[x] = hash; } + sch->qstats.backlog += skb->len; __skb_queue_head(&q->qs[x], skb); sfq_inc(q, x); if (q->qs[x].qlen == 1) { /* The flow is new */ @@ -344,6 +348,7 @@ sfq_dequeue(struct Qdisc* sch) skb = __skb_dequeue(&q->qs[a]); sfq_dec(q, a); sch->q.qlen--; + sch->qstats.backlog -= skb->len; /* Is the slot empty? */ if (q->qs[a].qlen == 0) { diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index cb9711ea8c6c..d8e03c74ca76 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -177,9 +177,9 @@ static int tbf_requeue(struct sk_buff *skb, struct Qdisc* sch) static unsigned int tbf_drop(struct Qdisc* sch) { struct tbf_sched_data *q = qdisc_priv(sch); - unsigned int len; + unsigned int len = 0; - if ((len = q->qdisc->ops->drop(q->qdisc)) != 0) { + if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) { sch->q.qlen--; sch->qstats.drops++; } @@ -341,13 +341,14 @@ static int tbf_change(struct Qdisc* sch, struct rtattr *opt) if (max_size < 0) goto done; - if (q->qdisc == &noop_qdisc) { + if (qopt->limit > 0) { if ((child = tbf_create_dflt_qdisc(sch->dev, qopt->limit)) == NULL) goto done; } sch_tree_lock(sch); - if (child) q->qdisc = child; + if (child) + qdisc_destroy(xchg(&q->qdisc, child)); q->limit = qopt->limit; q->mtu = qopt->mtu; q->max_size = max_size; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 2e266129a764..c20d282fac06 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -861,23 +861,27 @@ static int sctp_inet6_supported_addrs(const struct sctp_sock *opt, } static const struct proto_ops inet6_seqpacket_ops = { - .family = PF_INET6, - .owner = THIS_MODULE, - .release = inet6_release, - .bind = inet6_bind, - .connect = inet_dgram_connect, - .socketpair = sock_no_socketpair, - .accept = inet_accept, - .getname = inet6_getname, - .poll = sctp_poll, - .ioctl = inet6_ioctl, - .listen = sctp_inet_listen, - .shutdown = inet_shutdown, - .setsockopt = sock_common_setsockopt, - .getsockopt = sock_common_getsockopt, - .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, - .mmap = sock_no_mmap, + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_dgram_connect, + .socketpair = sock_no_socketpair, + .accept = inet_accept, + .getname = inet6_getname, + .poll = sctp_poll, + .ioctl = inet6_ioctl, + .listen = sctp_inet_listen, + .shutdown = inet_shutdown, + .setsockopt = sock_common_setsockopt, + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; static struct inet_protosw sctpv6_seqpacket_protosw = { @@ -911,31 +915,35 @@ static struct inet6_protocol sctpv6_protocol = { }; static struct sctp_af sctp_ipv6_specific = { - .sctp_xmit = sctp_v6_xmit, - .setsockopt = ipv6_setsockopt, - .getsockopt = ipv6_getsockopt, - .get_dst = sctp_v6_get_dst, - .get_saddr = sctp_v6_get_saddr, - .copy_addrlist = sctp_v6_copy_addrlist, - .from_skb = sctp_v6_from_skb, - .from_sk = sctp_v6_from_sk, - .to_sk_saddr = sctp_v6_to_sk_saddr, - .to_sk_daddr = sctp_v6_to_sk_daddr, - .from_addr_param = sctp_v6_from_addr_param, - .to_addr_param = sctp_v6_to_addr_param, - .dst_saddr = sctp_v6_dst_saddr, - .cmp_addr = sctp_v6_cmp_addr, - .scope = sctp_v6_scope, - .addr_valid = sctp_v6_addr_valid, - .inaddr_any = sctp_v6_inaddr_any, - .is_any = sctp_v6_is_any, - .available = sctp_v6_available, - .skb_iif = sctp_v6_skb_iif, - .is_ce = sctp_v6_is_ce, - .seq_dump_addr = sctp_v6_seq_dump_addr, - .net_header_len = sizeof(struct ipv6hdr), - .sockaddr_len = sizeof(struct sockaddr_in6), - .sa_family = AF_INET6, + .sa_family = AF_INET6, + .sctp_xmit = sctp_v6_xmit, + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .get_dst = sctp_v6_get_dst, + .get_saddr = sctp_v6_get_saddr, + .copy_addrlist = sctp_v6_copy_addrlist, + .from_skb = sctp_v6_from_skb, + .from_sk = sctp_v6_from_sk, + .to_sk_saddr = sctp_v6_to_sk_saddr, + .to_sk_daddr = sctp_v6_to_sk_daddr, + .from_addr_param = sctp_v6_from_addr_param, + .to_addr_param = sctp_v6_to_addr_param, + .dst_saddr = sctp_v6_dst_saddr, + .cmp_addr = sctp_v6_cmp_addr, + .scope = sctp_v6_scope, + .addr_valid = sctp_v6_addr_valid, + .inaddr_any = sctp_v6_inaddr_any, + .is_any = sctp_v6_is_any, + .available = sctp_v6_available, + .skb_iif = sctp_v6_skb_iif, + .is_ce = sctp_v6_is_ce, + .seq_dump_addr = sctp_v6_seq_dump_addr, + .net_header_len = sizeof(struct ipv6hdr), + .sockaddr_len = sizeof(struct sockaddr_in6), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ipv6_setsockopt, + .compat_getsockopt = compat_ipv6_getsockopt, +#endif }; static struct sctp_pf sctp_pf_inet6_specific = { diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index de693b43c8ea..2088aa992b7a 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -831,24 +831,28 @@ static struct notifier_block sctp_inetaddr_notifier = { /* Socket operations. */ static const struct proto_ops inet_seqpacket_ops = { - .family = PF_INET, - .owner = THIS_MODULE, - .release = inet_release, /* Needs to be wrapped... */ - .bind = inet_bind, - .connect = inet_dgram_connect, - .socketpair = sock_no_socketpair, - .accept = inet_accept, - .getname = inet_getname, /* Semantics are different. */ - .poll = sctp_poll, - .ioctl = inet_ioctl, - .listen = sctp_inet_listen, - .shutdown = inet_shutdown, /* Looks harmless. */ - .setsockopt = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem. */ - .getsockopt = sock_common_getsockopt, - .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, + .family = PF_INET, + .owner = THIS_MODULE, + .release = inet_release, /* Needs to be wrapped... */ + .bind = inet_bind, + .connect = inet_dgram_connect, + .socketpair = sock_no_socketpair, + .accept = inet_accept, + .getname = inet_getname, /* Semantics are different. */ + .poll = sctp_poll, + .ioctl = inet_ioctl, + .listen = sctp_inet_listen, + .shutdown = inet_shutdown, /* Looks harmless. */ + .setsockopt = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */ + .getsockopt = sock_common_getsockopt, + .sendmsg = inet_sendmsg, + .recvmsg = sock_common_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_sock_common_setsockopt, + .compat_getsockopt = compat_sock_common_getsockopt, +#endif }; /* Registration with AF_INET family. */ @@ -880,31 +884,35 @@ static struct net_protocol sctp_protocol = { /* IPv4 address related functions. */ static struct sctp_af sctp_ipv4_specific = { - .sctp_xmit = sctp_v4_xmit, - .setsockopt = ip_setsockopt, - .getsockopt = ip_getsockopt, - .get_dst = sctp_v4_get_dst, - .get_saddr = sctp_v4_get_saddr, - .copy_addrlist = sctp_v4_copy_addrlist, - .from_skb = sctp_v4_from_skb, - .from_sk = sctp_v4_from_sk, - .to_sk_saddr = sctp_v4_to_sk_saddr, - .to_sk_daddr = sctp_v4_to_sk_daddr, - .from_addr_param= sctp_v4_from_addr_param, - .to_addr_param = sctp_v4_to_addr_param, - .dst_saddr = sctp_v4_dst_saddr, - .cmp_addr = sctp_v4_cmp_addr, - .addr_valid = sctp_v4_addr_valid, - .inaddr_any = sctp_v4_inaddr_any, - .is_any = sctp_v4_is_any, - .available = sctp_v4_available, - .scope = sctp_v4_scope, - .skb_iif = sctp_v4_skb_iif, - .is_ce = sctp_v4_is_ce, - .seq_dump_addr = sctp_v4_seq_dump_addr, - .net_header_len = sizeof(struct iphdr), - .sockaddr_len = sizeof(struct sockaddr_in), - .sa_family = AF_INET, + .sa_family = AF_INET, + .sctp_xmit = sctp_v4_xmit, + .setsockopt = ip_setsockopt, + .getsockopt = ip_getsockopt, + .get_dst = sctp_v4_get_dst, + .get_saddr = sctp_v4_get_saddr, + .copy_addrlist = sctp_v4_copy_addrlist, + .from_skb = sctp_v4_from_skb, + .from_sk = sctp_v4_from_sk, + .to_sk_saddr = sctp_v4_to_sk_saddr, + .to_sk_daddr = sctp_v4_to_sk_daddr, + .from_addr_param = sctp_v4_from_addr_param, + .to_addr_param = sctp_v4_to_addr_param, + .dst_saddr = sctp_v4_dst_saddr, + .cmp_addr = sctp_v4_cmp_addr, + .addr_valid = sctp_v4_addr_valid, + .inaddr_any = sctp_v4_inaddr_any, + .is_any = sctp_v4_is_any, + .available = sctp_v4_available, + .scope = sctp_v4_scope, + .skb_iif = sctp_v4_skb_iif, + .is_ce = sctp_v4_is_ce, + .seq_dump_addr = sctp_v4_seq_dump_addr, + .net_header_len = sizeof(struct iphdr), + .sockaddr_len = sizeof(struct sockaddr_in), +#ifdef CONFIG_COMPAT + .compat_setsockopt = compat_ip_setsockopt, + .compat_getsockopt = compat_ip_getsockopt, +#endif }; struct sctp_pf *sctp_get_pf_specific(sa_family_t family) { diff --git a/net/socket.c b/net/socket.c index 7e1bdef8b09e..e3c21d5ec288 100644 --- a/net/socket.c +++ b/net/socket.c @@ -68,6 +68,7 @@ #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/mutex.h> #include <linux/wanrouter.h> #include <linux/if_bridge.h> #include <linux/if_frad.h> @@ -348,8 +349,8 @@ static struct dentry_operations sockfs_dentry_operations = { /* * Obtains the first available file descriptor and sets it up for use. * - * This function creates file structure and maps it to fd space - * of current process. On success it returns file descriptor + * These functions create file structures and maps them to fd space + * of the current process. On success it returns file descriptor * and file struct implicitly stored in sock->file. * Note that another thread may close file descriptor before we return * from this function. We use the fact that now we do not refer @@ -362,53 +363,90 @@ static struct dentry_operations sockfs_dentry_operations = { * but we take care of internal coherence yet. */ -int sock_map_fd(struct socket *sock) +static int sock_alloc_fd(struct file **filep) { int fd; - struct qstr this; - char name[32]; - - /* - * Find a file descriptor suitable for return to the user. - */ fd = get_unused_fd(); - if (fd >= 0) { + if (likely(fd >= 0)) { struct file *file = get_empty_filp(); - if (!file) { + *filep = file; + if (unlikely(!file)) { put_unused_fd(fd); - fd = -ENFILE; - goto out; + return -ENFILE; } + } else + *filep = NULL; + return fd; +} + +static int sock_attach_fd(struct socket *sock, struct file *file) +{ + struct qstr this; + char name[32]; + + this.len = sprintf(name, "[%lu]", SOCK_INODE(sock)->i_ino); + this.name = name; + this.hash = SOCK_INODE(sock)->i_ino; - this.len = sprintf(name, "[%lu]", SOCK_INODE(sock)->i_ino); - this.name = name; - this.hash = SOCK_INODE(sock)->i_ino; + file->f_dentry = d_alloc(sock_mnt->mnt_sb->s_root, &this); + if (unlikely(!file->f_dentry)) + return -ENOMEM; + + file->f_dentry->d_op = &sockfs_dentry_operations; + d_add(file->f_dentry, SOCK_INODE(sock)); + file->f_vfsmnt = mntget(sock_mnt); + file->f_mapping = file->f_dentry->d_inode->i_mapping; + + sock->file = file; + file->f_op = SOCK_INODE(sock)->i_fop = &socket_file_ops; + file->f_mode = FMODE_READ | FMODE_WRITE; + file->f_flags = O_RDWR; + file->f_pos = 0; + file->private_data = sock; + + return 0; +} - file->f_dentry = d_alloc(sock_mnt->mnt_sb->s_root, &this); - if (!file->f_dentry) { - put_filp(file); +int sock_map_fd(struct socket *sock) +{ + struct file *newfile; + int fd = sock_alloc_fd(&newfile); + + if (likely(fd >= 0)) { + int err = sock_attach_fd(sock, newfile); + + if (unlikely(err < 0)) { + put_filp(newfile); put_unused_fd(fd); - fd = -ENOMEM; - goto out; + return err; } - file->f_dentry->d_op = &sockfs_dentry_operations; - d_add(file->f_dentry, SOCK_INODE(sock)); - file->f_vfsmnt = mntget(sock_mnt); - file->f_mapping = file->f_dentry->d_inode->i_mapping; + fd_install(fd, newfile); + } + return fd; +} - sock->file = file; - file->f_op = SOCK_INODE(sock)->i_fop = &socket_file_ops; - file->f_mode = FMODE_READ | FMODE_WRITE; - file->f_flags = O_RDWR; - file->f_pos = 0; - file->private_data = sock; - fd_install(fd, file); +static struct socket *sock_from_file(struct file *file, int *err) +{ + struct inode *inode; + struct socket *sock; + + if (file->f_op == &socket_file_ops) + return file->private_data; /* set in sock_map_fd */ + + inode = file->f_dentry->d_inode; + if (!S_ISSOCK(inode->i_mode)) { + *err = -ENOTSOCK; + return NULL; } -out: - return fd; + sock = SOCKET_I(inode); + if (sock->file != file) { + printk(KERN_ERR "socki_lookup: socket file changed!\n"); + sock->file = file; + } + return sock; } /** @@ -427,31 +465,31 @@ out: struct socket *sockfd_lookup(int fd, int *err) { struct file *file; - struct inode *inode; struct socket *sock; - if (!(file = fget(fd))) - { + if (!(file = fget(fd))) { *err = -EBADF; return NULL; } - - if (file->f_op == &socket_file_ops) - return file->private_data; /* set in sock_map_fd */ - - inode = file->f_dentry->d_inode; - if (!S_ISSOCK(inode->i_mode)) { - *err = -ENOTSOCK; + sock = sock_from_file(file, err); + if (!sock) fput(file); - return NULL; - } + return sock; +} - sock = SOCKET_I(inode); - if (sock->file != file) { - printk(KERN_ERR "socki_lookup: socket file changed!\n"); - sock->file = file; +static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) +{ + struct file *file; + struct socket *sock; + + file = fget_light(fd, fput_needed); + if (file) { + sock = sock_from_file(file, err); + if (sock) + return sock; + fput_light(file, *fput_needed); } - return sock; + return NULL; } /** @@ -789,36 +827,36 @@ static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *ubuf, * with module unload. */ -static DECLARE_MUTEX(br_ioctl_mutex); +static DEFINE_MUTEX(br_ioctl_mutex); static int (*br_ioctl_hook)(unsigned int cmd, void __user *arg) = NULL; void brioctl_set(int (*hook)(unsigned int, void __user *)) { - down(&br_ioctl_mutex); + mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; - up(&br_ioctl_mutex); + mutex_unlock(&br_ioctl_mutex); } EXPORT_SYMBOL(brioctl_set); -static DECLARE_MUTEX(vlan_ioctl_mutex); +static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook)(void __user *arg); void vlan_ioctl_set(int (*hook)(void __user *)) { - down(&vlan_ioctl_mutex); + mutex_lock(&vlan_ioctl_mutex); vlan_ioctl_hook = hook; - up(&vlan_ioctl_mutex); + mutex_unlock(&vlan_ioctl_mutex); } EXPORT_SYMBOL(vlan_ioctl_set); -static DECLARE_MUTEX(dlci_ioctl_mutex); +static DEFINE_MUTEX(dlci_ioctl_mutex); static int (*dlci_ioctl_hook)(unsigned int, void __user *); void dlci_ioctl_set(int (*hook)(unsigned int, void __user *)) { - down(&dlci_ioctl_mutex); + mutex_lock(&dlci_ioctl_mutex); dlci_ioctl_hook = hook; - up(&dlci_ioctl_mutex); + mutex_unlock(&dlci_ioctl_mutex); } EXPORT_SYMBOL(dlci_ioctl_set); @@ -862,10 +900,10 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (!br_ioctl_hook) request_module("bridge"); - down(&br_ioctl_mutex); + mutex_lock(&br_ioctl_mutex); if (br_ioctl_hook) err = br_ioctl_hook(cmd, argp); - up(&br_ioctl_mutex); + mutex_unlock(&br_ioctl_mutex); break; case SIOCGIFVLAN: case SIOCSIFVLAN: @@ -873,10 +911,10 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (!vlan_ioctl_hook) request_module("8021q"); - down(&vlan_ioctl_mutex); + mutex_lock(&vlan_ioctl_mutex); if (vlan_ioctl_hook) err = vlan_ioctl_hook(argp); - up(&vlan_ioctl_mutex); + mutex_unlock(&vlan_ioctl_mutex); break; case SIOCGIFDIVERT: case SIOCSIFDIVERT: @@ -890,9 +928,9 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) request_module("dlci"); if (dlci_ioctl_hook) { - down(&dlci_ioctl_mutex); + mutex_lock(&dlci_ioctl_mutex); err = dlci_ioctl_hook(cmd, argp); - up(&dlci_ioctl_mutex); + mutex_unlock(&dlci_ioctl_mutex); } break; default: @@ -1286,19 +1324,17 @@ asmlinkage long sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) { struct socket *sock; char address[MAX_SOCK_ADDR]; - int err; + int err, fput_needed; - if((sock = sockfd_lookup(fd,&err))!=NULL) + if((sock = sockfd_lookup_light(fd, &err, &fput_needed))!=NULL) { if((err=move_addr_to_kernel(umyaddr,addrlen,address))>=0) { err = security_socket_bind(sock, (struct sockaddr *)address, addrlen); - if (err) { - sockfd_put(sock); - return err; - } - err = sock->ops->bind(sock, (struct sockaddr *)address, addrlen); + if (!err) + err = sock->ops->bind(sock, + (struct sockaddr *)address, addrlen); } - sockfd_put(sock); + fput_light(sock->file, fput_needed); } return err; } @@ -1315,20 +1351,17 @@ int sysctl_somaxconn = SOMAXCONN; asmlinkage long sys_listen(int fd, int backlog) { struct socket *sock; - int err; + int err, fput_needed; - if ((sock = sockfd_lookup(fd, &err)) != NULL) { + if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) { if ((unsigned) backlog > sysctl_somaxconn) backlog = sysctl_somaxconn; err = security_socket_listen(sock, backlog); - if (err) { - sockfd_put(sock); - return err; - } + if (!err) + err = sock->ops->listen(sock, backlog); - err=sock->ops->listen(sock, backlog); - sockfd_put(sock); + fput_light(sock->file, fput_needed); } return err; } @@ -1349,10 +1382,11 @@ asmlinkage long sys_listen(int fd, int backlog) asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen) { struct socket *sock, *newsock; - int err, len; + struct file *newfile; + int err, len, newfd, fput_needed; char address[MAX_SOCK_ADDR]; - sock = sockfd_lookup(fd, &err); + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1369,35 +1403,48 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, int _ */ __module_get(newsock->ops->owner); + newfd = sock_alloc_fd(&newfile); + if (unlikely(newfd < 0)) { + err = newfd; + goto out_release; + } + + err = sock_attach_fd(newsock, newfile); + if (err < 0) + goto out_fd; + err = security_socket_accept(sock, newsock); if (err) - goto out_release; + goto out_fd; err = sock->ops->accept(sock, newsock, sock->file->f_flags); if (err < 0) - goto out_release; + goto out_fd; if (upeer_sockaddr) { if(newsock->ops->getname(newsock, (struct sockaddr *)address, &len, 2)<0) { err = -ECONNABORTED; - goto out_release; + goto out_fd; } err = move_addr_to_user(address, len, upeer_sockaddr, upeer_addrlen); if (err < 0) - goto out_release; + goto out_fd; } /* File flags are not inherited via accept() unlike another OSes. */ - if ((err = sock_map_fd(newsock)) < 0) - goto out_release; + fd_install(newfd, newfile); + err = newfd; security_socket_post_accept(sock, newsock); out_put: - sockfd_put(sock); + fput_light(sock->file, fput_needed); out: return err; +out_fd: + put_filp(newfile); + put_unused_fd(newfd); out_release: sock_release(newsock); goto out_put; @@ -1420,9 +1467,9 @@ asmlinkage long sys_connect(int fd, struct sockaddr __user *uservaddr, int addrl { struct socket *sock; char address[MAX_SOCK_ADDR]; - int err; + int err, fput_needed; - sock = sockfd_lookup(fd, &err); + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = move_addr_to_kernel(uservaddr, addrlen, address); @@ -1436,7 +1483,7 @@ asmlinkage long sys_connect(int fd, struct sockaddr __user *uservaddr, int addrl err = sock->ops->connect(sock, (struct sockaddr *) address, addrlen, sock->file->f_flags); out_put: - sockfd_put(sock); + fput_light(sock->file, fput_needed); out: return err; } @@ -1450,9 +1497,9 @@ asmlinkage long sys_getsockname(int fd, struct sockaddr __user *usockaddr, int _ { struct socket *sock; char address[MAX_SOCK_ADDR]; - int len, err; + int len, err, fput_needed; - sock = sockfd_lookup(fd, &err); + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1466,7 +1513,7 @@ asmlinkage long sys_getsockname(int fd, struct sockaddr __user *usockaddr, int _ err = move_addr_to_user(address, len, usockaddr, usockaddr_len); out_put: - sockfd_put(sock); + fput_light(sock->file, fput_needed); out: return err; } @@ -1480,20 +1527,19 @@ asmlinkage long sys_getpeername(int fd, struct sockaddr __user *usockaddr, int _ { struct socket *sock; char address[MAX_SOCK_ADDR]; - int len, err; + int len, err, fput_needed; - if ((sock = sockfd_lookup(fd, &err))!=NULL) - { + if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) { err = security_socket_getpeername(sock); if (err) { - sockfd_put(sock); + fput_light(sock->file, fput_needed); return err; } err = sock->ops->getname(sock, (struct sockaddr *)address, &len, 1); if (!err) err=move_addr_to_user(address,len, usockaddr, usockaddr_len); - sockfd_put(sock); + fput_light(sock->file, fput_needed); } return err; } @@ -1512,10 +1558,16 @@ asmlinkage long sys_sendto(int fd, void __user * buff, size_t len, unsigned flag int err; struct msghdr msg; struct iovec iov; - - sock = sockfd_lookup(fd, &err); + int fput_needed; + struct file *sock_file; + + sock_file = fget_light(fd, &fput_needed); + if (!sock_file) + return -EBADF; + + sock = sock_from_file(sock_file, &err); if (!sock) - goto out; + goto out_put; iov.iov_base=buff; iov.iov_len=len; msg.msg_name=NULL; @@ -1524,8 +1576,7 @@ asmlinkage long sys_sendto(int fd, void __user * buff, size_t len, unsigned flag msg.msg_control=NULL; msg.msg_controllen=0; msg.msg_namelen=0; - if(addr) - { + if (addr) { err = move_addr_to_kernel(addr, addr_len, address); if (err < 0) goto out_put; @@ -1538,8 +1589,7 @@ asmlinkage long sys_sendto(int fd, void __user * buff, size_t len, unsigned flag err = sock_sendmsg(sock, &msg, len); out_put: - sockfd_put(sock); -out: + fput_light(sock_file, fput_needed); return err; } @@ -1566,8 +1616,14 @@ asmlinkage long sys_recvfrom(int fd, void __user * ubuf, size_t size, unsigned f struct msghdr msg; char address[MAX_SOCK_ADDR]; int err,err2; + struct file *sock_file; + int fput_needed; - sock = sockfd_lookup(fd, &err); + sock_file = fget_light(fd, &fput_needed); + if (!sock_file) + return -EBADF; + + sock = sock_from_file(sock_file, &err); if (!sock) goto out; @@ -1589,8 +1645,8 @@ asmlinkage long sys_recvfrom(int fd, void __user * ubuf, size_t size, unsigned f if(err2<0) err=err2; } - sockfd_put(sock); out: + fput_light(sock_file, fput_needed); return err; } @@ -1610,25 +1666,24 @@ asmlinkage long sys_recv(int fd, void __user * ubuf, size_t size, unsigned flags asmlinkage long sys_setsockopt(int fd, int level, int optname, char __user *optval, int optlen) { - int err; + int err, fput_needed; struct socket *sock; if (optlen < 0) return -EINVAL; - if ((sock = sockfd_lookup(fd, &err))!=NULL) + if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) { err = security_socket_setsockopt(sock,level,optname); - if (err) { - sockfd_put(sock); - return err; - } + if (err) + goto out_put; if (level == SOL_SOCKET) err=sock_setsockopt(sock,level,optname,optval,optlen); else err=sock->ops->setsockopt(sock, level, optname, optval, optlen); - sockfd_put(sock); +out_put: + fput_light(sock->file, fput_needed); } return err; } @@ -1640,23 +1695,20 @@ asmlinkage long sys_setsockopt(int fd, int level, int optname, char __user *optv asmlinkage long sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) { - int err; + int err, fput_needed; struct socket *sock; - if ((sock = sockfd_lookup(fd, &err))!=NULL) - { - err = security_socket_getsockopt(sock, level, - optname); - if (err) { - sockfd_put(sock); - return err; - } + if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) { + err = security_socket_getsockopt(sock, level, optname); + if (err) + goto out_put; if (level == SOL_SOCKET) err=sock_getsockopt(sock,level,optname,optval,optlen); else err=sock->ops->getsockopt(sock, level, optname, optval, optlen); - sockfd_put(sock); +out_put: + fput_light(sock->file, fput_needed); } return err; } @@ -1668,19 +1720,15 @@ asmlinkage long sys_getsockopt(int fd, int level, int optname, char __user *optv asmlinkage long sys_shutdown(int fd, int how) { - int err; + int err, fput_needed; struct socket *sock; - if ((sock = sockfd_lookup(fd, &err))!=NULL) + if ((sock = sockfd_lookup_light(fd, &err, &fput_needed))!=NULL) { err = security_socket_shutdown(sock, how); - if (err) { - sockfd_put(sock); - return err; - } - - err=sock->ops->shutdown(sock, how); - sockfd_put(sock); + if (!err) + err = sock->ops->shutdown(sock, how); + fput_light(sock->file, fput_needed); } return err; } @@ -1709,6 +1757,7 @@ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) unsigned char *ctl_buf = ctl; struct msghdr msg_sys; int err, ctl_len, iov_size, total_len; + int fput_needed; err = -EFAULT; if (MSG_CMSG_COMPAT & flags) { @@ -1717,7 +1766,7 @@ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) } else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr))) return -EFAULT; - sock = sockfd_lookup(fd, &err); + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1785,7 +1834,7 @@ out_freeiov: if (iov != iovstack) sock_kfree_s(sock->sk, iov, iov_size); out_put: - sockfd_put(sock); + fput_light(sock->file, fput_needed); out: return err; } @@ -1803,6 +1852,7 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flag struct msghdr msg_sys; unsigned long cmsg_ptr; int err, iov_size, total_len, len; + int fput_needed; /* kernel mode address */ char addr[MAX_SOCK_ADDR]; @@ -1818,7 +1868,7 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flag if (copy_from_user(&msg_sys,msg,sizeof(struct msghdr))) return -EFAULT; - sock = sockfd_lookup(fd, &err); + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1885,7 +1935,7 @@ out_freeiov: if (iov != iovstack) sock_kfree_s(sock->sk, iov, iov_size); out_put: - sockfd_put(sock); + fput_light(sock->file, fput_needed); out: return err; } diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index dcaa0c4453ff..0acccfeeb284 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -26,6 +26,7 @@ #include <linux/proc_fs.h> #include <linux/net.h> #include <linux/workqueue.h> +#include <linux/mutex.h> #include <asm/ioctls.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/cache.h> @@ -532,7 +533,7 @@ void cache_clean_deferred(void *owner) */ static DEFINE_SPINLOCK(queue_lock); -static DECLARE_MUTEX(queue_io_sem); +static DEFINE_MUTEX(queue_io_mutex); struct cache_queue { struct list_head list; @@ -561,7 +562,7 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) if (count == 0) return 0; - down(&queue_io_sem); /* protect against multiple concurrent + mutex_lock(&queue_io_mutex); /* protect against multiple concurrent * readers on this file */ again: spin_lock(&queue_lock); @@ -574,7 +575,7 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (rp->q.list.next == &cd->queue) { spin_unlock(&queue_lock); - up(&queue_io_sem); + mutex_unlock(&queue_io_mutex); BUG_ON(rp->offset); return 0; } @@ -621,11 +622,11 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (err == -EAGAIN) goto again; - up(&queue_io_sem); + mutex_unlock(&queue_io_mutex); return err ? err : count; } -static char write_buf[8192]; /* protected by queue_io_sem */ +static char write_buf[8192]; /* protected by queue_io_mutex */ static ssize_t cache_write(struct file *filp, const char __user *buf, size_t count, @@ -639,10 +640,10 @@ cache_write(struct file *filp, const char __user *buf, size_t count, if (count >= sizeof(write_buf)) return -EINVAL; - down(&queue_io_sem); + mutex_lock(&queue_io_mutex); if (copy_from_user(write_buf, buf, count)) { - up(&queue_io_sem); + mutex_unlock(&queue_io_mutex); return -EFAULT; } write_buf[count] = '\0'; @@ -651,7 +652,7 @@ cache_write(struct file *filp, const char __user *buf, size_t count, else err = -EINVAL; - up(&queue_io_sem); + mutex_unlock(&queue_io_mutex); return err ? err : count; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index e838d042f7f5..dff07795bd16 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -18,6 +18,7 @@ #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/spinlock.h> +#include <linux/mutex.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/xprt.h> @@ -62,7 +63,7 @@ static LIST_HEAD(all_tasks); /* * rpciod-related stuff */ -static DECLARE_MUTEX(rpciod_sema); +static DEFINE_MUTEX(rpciod_mutex); static unsigned int rpciod_users; static struct workqueue_struct *rpciod_workqueue; @@ -1047,7 +1048,7 @@ rpciod_up(void) struct workqueue_struct *wq; int error = 0; - down(&rpciod_sema); + mutex_lock(&rpciod_mutex); dprintk("rpciod_up: users %d\n", rpciod_users); rpciod_users++; if (rpciod_workqueue) @@ -1070,14 +1071,14 @@ rpciod_up(void) rpciod_workqueue = wq; error = 0; out: - up(&rpciod_sema); + mutex_unlock(&rpciod_mutex); return error; } void rpciod_down(void) { - down(&rpciod_sema); + mutex_lock(&rpciod_mutex); dprintk("rpciod_down sema %d\n", rpciod_users); if (rpciod_users) { if (--rpciod_users) @@ -1094,7 +1095,7 @@ rpciod_down(void) destroy_workqueue(rpciod_workqueue); rpciod_workqueue = NULL; out: - up(&rpciod_sema); + mutex_unlock(&rpciod_mutex); } #ifdef RPC_DEBUG diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 50580620e897..a27905a0ad27 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1296,13 +1296,13 @@ svc_send(struct svc_rqst *rqstp) xb->page_len + xb->tail[0].iov_len; - /* Grab svsk->sk_sem to serialize outgoing data. */ - down(&svsk->sk_sem); + /* Grab svsk->sk_mutex to serialize outgoing data. */ + mutex_lock(&svsk->sk_mutex); if (test_bit(SK_DEAD, &svsk->sk_flags)) len = -ENOTCONN; else len = svsk->sk_sendto(rqstp); - up(&svsk->sk_sem); + mutex_unlock(&svsk->sk_mutex); svc_sock_release(rqstp); if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN) @@ -1351,7 +1351,7 @@ svc_setup_socket(struct svc_serv *serv, struct socket *sock, svsk->sk_lastrecv = get_seconds(); INIT_LIST_HEAD(&svsk->sk_deferred); INIT_LIST_HEAD(&svsk->sk_ready); - sema_init(&svsk->sk_sem, 1); + mutex_init(&svsk->sk_mutex); /* Initialize the socket */ if (sock->type == SOCK_DGRAM) diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index a7b04f397c12..2c4ecbe50082 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -107,22 +107,22 @@ static spinlock_t bc_lock = SPIN_LOCK_UNLOCKED; char tipc_bclink_name[] = "multicast-link"; -static inline u32 buf_seqno(struct sk_buff *buf) +static u32 buf_seqno(struct sk_buff *buf) { return msg_seqno(buf_msg(buf)); } -static inline u32 bcbuf_acks(struct sk_buff *buf) +static u32 bcbuf_acks(struct sk_buff *buf) { return (u32)(unsigned long)TIPC_SKB_CB(buf)->handle; } -static inline void bcbuf_set_acks(struct sk_buff *buf, u32 acks) +static void bcbuf_set_acks(struct sk_buff *buf, u32 acks) { TIPC_SKB_CB(buf)->handle = (void *)(unsigned long)acks; } -static inline void bcbuf_decr_acks(struct sk_buff *buf) +static void bcbuf_decr_acks(struct sk_buff *buf) { bcbuf_set_acks(buf, bcbuf_acks(buf) - 1); } @@ -134,7 +134,7 @@ static inline void bcbuf_decr_acks(struct sk_buff *buf) * Called with 'node' locked, bc_lock unlocked */ -static inline void bclink_set_gap(struct node *n_ptr) +static void bclink_set_gap(struct node *n_ptr) { struct sk_buff *buf = n_ptr->bclink.deferred_head; @@ -154,7 +154,7 @@ static inline void bclink_set_gap(struct node *n_ptr) * distribute NACKs, but tries to use the same spacing (divide by 16). */ -static inline int bclink_ack_allowed(u32 n) +static int bclink_ack_allowed(u32 n) { return((n % TIPC_MIN_LINK_WIN) == tipc_own_tag); } @@ -271,7 +271,7 @@ static void bclink_send_nack(struct node *n_ptr) msg_set_bcgap_to(msg, n_ptr->bclink.gap_to); msg_set_bcast_tag(msg, tipc_own_tag); - if (tipc_bearer_send(&bcbearer->bearer, buf, 0)) { + if (tipc_bearer_send(&bcbearer->bearer, buf, NULL)) { bcl->stats.sent_nacks++; buf_discard(buf); } else { @@ -314,7 +314,7 @@ void tipc_bclink_check_gap(struct node *n_ptr, u32 last_sent) * Only tipc_net_lock set. */ -void tipc_bclink_peek_nack(u32 dest, u32 sender_tag, u32 gap_after, u32 gap_to) +static void tipc_bclink_peek_nack(u32 dest, u32 sender_tag, u32 gap_after, u32 gap_to) { struct node *n_ptr = tipc_node_find(dest); u32 my_after, my_to; @@ -425,9 +425,9 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf) msg_bcgap_to(msg)); } else { tipc_bclink_peek_nack(msg_destnode(msg), - msg_bcast_tag(msg), - msg_bcgap_after(msg), - msg_bcgap_to(msg)); + msg_bcast_tag(msg), + msg_bcgap_after(msg), + msg_bcgap_to(msg)); } buf_discard(buf); return; @@ -525,16 +525,18 @@ u32 tipc_bclink_acks_missing(struct node *n_ptr) * Returns 0 if packet sent successfully, non-zero if not */ -int tipc_bcbearer_send(struct sk_buff *buf, - struct tipc_bearer *unused1, - struct tipc_media_addr *unused2) +static int tipc_bcbearer_send(struct sk_buff *buf, + struct tipc_bearer *unused1, + struct tipc_media_addr *unused2) { static int send_count = 0; - struct node_map remains; - struct node_map remains_new; + struct node_map *remains; + struct node_map *remains_new; + struct node_map *remains_tmp; int bp_index; int swap_time; + int err; /* Prepare buffer for broadcasting (if first time trying to send it) */ @@ -555,7 +557,9 @@ int tipc_bcbearer_send(struct sk_buff *buf, /* Send buffer over bearers until all targets reached */ - remains = tipc_cltr_bcast_nodes; + remains = kmalloc(sizeof(struct node_map), GFP_ATOMIC); + remains_new = kmalloc(sizeof(struct node_map), GFP_ATOMIC); + *remains = tipc_cltr_bcast_nodes; for (bp_index = 0; bp_index < MAX_BEARERS; bp_index++) { struct bearer *p = bcbearer->bpairs[bp_index].primary; @@ -564,8 +568,8 @@ int tipc_bcbearer_send(struct sk_buff *buf, if (!p) break; /* no more bearers to try */ - tipc_nmap_diff(&remains, &p->nodes, &remains_new); - if (remains_new.count == remains.count) + tipc_nmap_diff(remains, &p->nodes, remains_new); + if (remains_new->count == remains->count) continue; /* bearer pair doesn't add anything */ if (!p->publ.blocked && @@ -583,17 +587,27 @@ swap: bcbearer->bpairs[bp_index].primary = s; bcbearer->bpairs[bp_index].secondary = p; update: - if (remains_new.count == 0) - return TIPC_OK; + if (remains_new->count == 0) { + err = TIPC_OK; + goto out; + } + /* swap map */ + remains_tmp = remains; remains = remains_new; + remains_new = remains_tmp; } /* Unable to reach all targets */ bcbearer->bearer.publ.blocked = 1; bcl->stats.bearer_congs++; - return ~TIPC_OK; + err = ~TIPC_OK; + + out: + kfree(remains_new); + kfree(remains); + return err; } /** diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 64dcb0f3a8b2..e213a8e54855 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -45,10 +45,10 @@ #define MAX_ADDR_STR 32 -static struct media *media_list = 0; +static struct media *media_list = NULL; static u32 media_count = 0; -struct bearer *tipc_bearers = 0; +struct bearer *tipc_bearers = NULL; /** * media_name_valid - validate media name @@ -79,7 +79,7 @@ static struct media *media_find(const char *name) if (!strcmp(m_ptr->name, name)) return m_ptr; } - return 0; + return NULL; } /** @@ -287,7 +287,7 @@ static struct bearer *bearer_find(const char *name) if (b_ptr->active && (!strcmp(b_ptr->publ.name, name))) return b_ptr; } - return 0; + return NULL; } /** @@ -307,7 +307,7 @@ struct bearer *tipc_bearer_find_interface(const char *if_name) if (!strcmp(b_if_name, if_name)) return b_ptr; } - return 0; + return NULL; } /** @@ -569,7 +569,7 @@ failed: int tipc_block_bearer(const char *name) { - struct bearer *b_ptr = 0; + struct bearer *b_ptr = NULL; struct link *l_ptr; struct link *temp_l_ptr; @@ -666,8 +666,8 @@ int tipc_bearer_init(void) } else { kfree(tipc_bearers); kfree(media_list); - tipc_bearers = 0; - media_list = 0; + tipc_bearers = NULL; + media_list = NULL; res = -ENOMEM; } write_unlock_bh(&tipc_net_lock); @@ -691,8 +691,8 @@ void tipc_bearer_stop(void) } kfree(tipc_bearers); kfree(media_list); - tipc_bearers = 0; - media_list = 0; + tipc_bearers = NULL; + media_list = NULL; media_count = 0; } diff --git a/net/tipc/cluster.c b/net/tipc/cluster.c index ab974ca19371..1aed81584e96 100644 --- a/net/tipc/cluster.c +++ b/net/tipc/cluster.c @@ -44,11 +44,11 @@ #include "msg.h" #include "bearer.h" -void tipc_cltr_multicast(struct cluster *c_ptr, struct sk_buff *buf, - u32 lower, u32 upper); -struct sk_buff *tipc_cltr_prepare_routing_msg(u32 data_size, u32 dest); +static void tipc_cltr_multicast(struct cluster *c_ptr, struct sk_buff *buf, + u32 lower, u32 upper); +static struct sk_buff *tipc_cltr_prepare_routing_msg(u32 data_size, u32 dest); -struct node **tipc_local_nodes = 0; +struct node **tipc_local_nodes = NULL; struct node_map tipc_cltr_bcast_nodes = {0,{0,}}; u32 tipc_highest_allowed_slave = 0; @@ -61,7 +61,7 @@ struct cluster *tipc_cltr_create(u32 addr) c_ptr = (struct cluster *)kmalloc(sizeof(*c_ptr), GFP_ATOMIC); if (c_ptr == NULL) - return 0; + return NULL; memset(c_ptr, 0, sizeof(*c_ptr)); c_ptr->addr = tipc_addr(tipc_zone(addr), tipc_cluster(addr), 0); @@ -73,7 +73,7 @@ struct cluster *tipc_cltr_create(u32 addr) c_ptr->nodes = (struct node **)kmalloc(alloc, GFP_ATOMIC); if (c_ptr->nodes == NULL) { kfree(c_ptr); - return 0; + return NULL; } memset(c_ptr->nodes, 0, alloc); if (in_own_cluster(addr)) @@ -91,7 +91,7 @@ struct cluster *tipc_cltr_create(u32 addr) } else { kfree(c_ptr); - c_ptr = 0; + c_ptr = NULL; } return c_ptr; @@ -204,7 +204,7 @@ struct node *tipc_cltr_select_node(struct cluster *c_ptr, u32 selector) assert(!in_own_cluster(c_ptr->addr)); if (!c_ptr->highest_node) - return 0; + return NULL; /* Start entry must be random */ while (mask > c_ptr->highest_node) { @@ -222,14 +222,14 @@ struct node *tipc_cltr_select_node(struct cluster *c_ptr, u32 selector) if (tipc_node_has_active_links(c_ptr->nodes[n_num])) return c_ptr->nodes[n_num]; } - return 0; + return NULL; } /* * Routing table management: See description in node.c */ -struct sk_buff *tipc_cltr_prepare_routing_msg(u32 data_size, u32 dest) +static struct sk_buff *tipc_cltr_prepare_routing_msg(u32 data_size, u32 dest) { u32 size = INT_H_SIZE + data_size; struct sk_buff *buf = buf_acquire(size); @@ -495,7 +495,7 @@ void tipc_cltr_remove_as_router(struct cluster *c_ptr, u32 router) * tipc_cltr_multicast - multicast message to local nodes */ -void tipc_cltr_multicast(struct cluster *c_ptr, struct sk_buff *buf, +static void tipc_cltr_multicast(struct cluster *c_ptr, struct sk_buff *buf, u32 lower, u32 upper) { struct sk_buff *buf_copy; diff --git a/net/tipc/cluster.h b/net/tipc/cluster.h index 9963642e1058..1b4cd309495a 100644 --- a/net/tipc/cluster.h +++ b/net/tipc/cluster.h @@ -86,7 +86,7 @@ static inline struct cluster *tipc_cltr_find(u32 addr) if (z_ptr) return z_ptr->clusters[1]; - return 0; + return NULL; } #endif diff --git a/net/tipc/config.c b/net/tipc/config.c index 3c8e6740e5ae..48b5de2dbe60 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -683,11 +683,11 @@ int tipc_cfg_init(void) memset(&mng, 0, sizeof(mng)); INIT_LIST_HEAD(&mng.link_subscribers); - res = tipc_attach(&mng.user_ref, 0, 0); + res = tipc_attach(&mng.user_ref, NULL, NULL); if (res) goto failed; - res = tipc_createport(mng.user_ref, 0, TIPC_CRITICAL_IMPORTANCE, + res = tipc_createport(mng.user_ref, NULL, TIPC_CRITICAL_IMPORTANCE, NULL, NULL, NULL, NULL, cfg_named_msg_event, NULL, NULL, &mng.port_ref); diff --git a/net/tipc/dbg.c b/net/tipc/dbg.c index 4f4beefa7830..26ef95d5fe38 100644 --- a/net/tipc/dbg.c +++ b/net/tipc/dbg.c @@ -81,7 +81,7 @@ void tipc_printbuf_init(struct print_buf *pb, char *raw, u32 sz) pb->crs = pb->buf = raw; pb->size = sz; - pb->next = 0; + pb->next = NULL; pb->buf[0] = 0; pb->buf[sz-1] = ~0; } @@ -216,7 +216,7 @@ void tipc_printf(struct print_buf *pb, const char *fmt, ...) } } pb_next = pb->next; - pb->next = 0; + pb->next = NULL; pb = pb_next; } spin_unlock_bh(&print_lock); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 53ba4630c10d..92601385e5f5 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -110,10 +110,10 @@ void tipc_disc_link_event(u32 addr, char *name, int up) * @b_ptr: ptr to bearer issuing message */ -struct sk_buff *tipc_disc_init_msg(u32 type, - u32 req_links, - u32 dest_domain, - struct bearer *b_ptr) +static struct sk_buff *tipc_disc_init_msg(u32 type, + u32 req_links, + u32 dest_domain, + struct bearer *b_ptr) { struct sk_buff *buf = buf_acquire(DSC_H_SIZE); struct tipc_msg *msg; diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 1f8d83b9c8b4..7a252785f727 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -169,7 +169,7 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) static void disable_bearer(struct tipc_bearer *tb_ptr) { - ((struct eth_bearer *)tb_ptr->usr_handle)->bearer = 0; + ((struct eth_bearer *)tb_ptr->usr_handle)->bearer = NULL; } /** @@ -285,7 +285,7 @@ void tipc_eth_media_stop(void) for (i = 0; i < MAX_ETH_BEARERS ; i++) { if (eth_bearers[i].bearer) { eth_bearers[i].bearer->blocked = 1; - eth_bearers[i].bearer = 0; + eth_bearers[i].bearer = NULL; } if (eth_bearers[i].dev) { dev_remove_pack(ð_bearers[i].tipc_packet_type); diff --git a/net/tipc/link.c b/net/tipc/link.c index 511872afa459..910b37e5083d 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -157,13 +157,13 @@ static void link_print(struct link *l_ptr, struct print_buf *buf, } \ } while (0) -static inline void dbg_print_link(struct link *l_ptr, const char *str) +static void dbg_print_link(struct link *l_ptr, const char *str) { if (DBG_OUTPUT) link_print(l_ptr, DBG_OUTPUT, str); } -static inline void dbg_print_buf_chain(struct sk_buff *root_buf) +static void dbg_print_buf_chain(struct sk_buff *root_buf) { if (DBG_OUTPUT) { struct sk_buff *buf = root_buf; @@ -176,50 +176,50 @@ static inline void dbg_print_buf_chain(struct sk_buff *root_buf) } /* - * Simple inlined link routines + * Simple link routines */ -static inline unsigned int align(unsigned int i) +static unsigned int align(unsigned int i) { return (i + 3) & ~3u; } -static inline int link_working_working(struct link *l_ptr) +static int link_working_working(struct link *l_ptr) { return (l_ptr->state == WORKING_WORKING); } -static inline int link_working_unknown(struct link *l_ptr) +static int link_working_unknown(struct link *l_ptr) { return (l_ptr->state == WORKING_UNKNOWN); } -static inline int link_reset_unknown(struct link *l_ptr) +static int link_reset_unknown(struct link *l_ptr) { return (l_ptr->state == RESET_UNKNOWN); } -static inline int link_reset_reset(struct link *l_ptr) +static int link_reset_reset(struct link *l_ptr) { return (l_ptr->state == RESET_RESET); } -static inline int link_blocked(struct link *l_ptr) +static int link_blocked(struct link *l_ptr) { return (l_ptr->exp_msg_count || l_ptr->blocked); } -static inline int link_congested(struct link *l_ptr) +static int link_congested(struct link *l_ptr) { return (l_ptr->out_queue_size >= l_ptr->queue_limit[0]); } -static inline u32 link_max_pkt(struct link *l_ptr) +static u32 link_max_pkt(struct link *l_ptr) { return l_ptr->max_pkt; } -static inline void link_init_max_pkt(struct link *l_ptr) +static void link_init_max_pkt(struct link *l_ptr) { u32 max_pkt; @@ -236,20 +236,20 @@ static inline void link_init_max_pkt(struct link *l_ptr) l_ptr->max_pkt_probes = 0; } -static inline u32 link_next_sent(struct link *l_ptr) +static u32 link_next_sent(struct link *l_ptr) { if (l_ptr->next_out) return msg_seqno(buf_msg(l_ptr->next_out)); return mod(l_ptr->next_out_no); } -static inline u32 link_last_sent(struct link *l_ptr) +static u32 link_last_sent(struct link *l_ptr) { return mod(link_next_sent(l_ptr) - 1); } /* - * Simple non-inlined link routines (i.e. referenced outside this file) + * Simple non-static link routines (i.e. referenced outside this file) */ int tipc_link_is_up(struct link *l_ptr) @@ -396,7 +396,7 @@ static void link_timeout(struct link *l_ptr) tipc_node_unlock(l_ptr->owner); } -static inline void link_set_timer(struct link *l_ptr, u32 time) +static void link_set_timer(struct link *l_ptr, u32 time) { k_start_timer(&l_ptr->timer, time); } @@ -573,7 +573,7 @@ void tipc_link_wakeup_ports(struct link *l_ptr, int all) if (win <= 0) break; list_del_init(&p_ptr->wait_list); - p_ptr->congested_link = 0; + p_ptr->congested_link = NULL; assert(p_ptr->wakeup); spin_lock_bh(p_ptr->publ.lock); p_ptr->publ.congested = 0; @@ -1004,9 +1004,9 @@ static int link_bundle_buf(struct link *l_ptr, return 1; } -static inline void link_add_to_outqueue(struct link *l_ptr, - struct sk_buff *buf, - struct tipc_msg *msg) +static void link_add_to_outqueue(struct link *l_ptr, + struct sk_buff *buf, + struct tipc_msg *msg) { u32 ack = mod(l_ptr->next_in_no - 1); u32 seqno = mod(l_ptr->next_out_no++); @@ -1156,8 +1156,8 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) * Link is locked. Returns user data length. */ -static inline int link_send_buf_fast(struct link *l_ptr, struct sk_buff *buf, - u32 *used_max_pkt) +static int link_send_buf_fast(struct link *l_ptr, struct sk_buff *buf, + u32 *used_max_pkt) { struct tipc_msg *msg = buf_msg(buf); int res = msg_data_sz(msg); @@ -1355,7 +1355,7 @@ again: fragm_crs = 0; fragm_rest = 0; sect_rest = 0; - sect_crs = 0; + sect_crs = NULL; curr_sect = -1; /* Prepare reusable fragment header: */ @@ -1549,7 +1549,7 @@ u32 tipc_link_push_packet(struct link *l_ptr) msg_dbg(buf_msg(buf), ">DEF-PROT>"); l_ptr->unacked_window = 0; buf_discard(buf); - l_ptr->proto_msg_queue = 0; + l_ptr->proto_msg_queue = NULL; return TIPC_OK; } else { msg_dbg(buf_msg(buf), "|>DEF-PROT>"); @@ -1860,7 +1860,7 @@ u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail, struct sk_buff *buf) { - struct sk_buff *prev = 0; + struct sk_buff *prev = NULL; struct sk_buff *crs = *head; u32 seq_no = msg_seqno(buf_msg(buf)); @@ -1953,7 +1953,7 @@ static void link_handle_out_of_seq_msg(struct link *l_ptr, void tipc_link_send_proto_msg(struct link *l_ptr, u32 msg_typ, int probe_msg, u32 gap, u32 tolerance, u32 priority, u32 ack_mtu) { - struct sk_buff *buf = 0; + struct sk_buff *buf = NULL; struct tipc_msg *msg = l_ptr->pmsg; u32 msg_size = sizeof(l_ptr->proto_msg); @@ -2426,7 +2426,7 @@ static int link_recv_changeover_msg(struct link **l_ptr, } } exit: - *buf = 0; + *buf = NULL; buf_discard(tunnel_buf); return 0; } @@ -2539,42 +2539,37 @@ exit: * pending message. This makes dynamic memory allocation unecessary. */ -static inline u32 get_long_msg_seqno(struct sk_buff *buf) -{ - return msg_seqno(buf_msg(buf)); -} - -static inline void set_long_msg_seqno(struct sk_buff *buf, u32 seqno) +static void set_long_msg_seqno(struct sk_buff *buf, u32 seqno) { msg_set_seqno(buf_msg(buf), seqno); } -static inline u32 get_fragm_size(struct sk_buff *buf) +static u32 get_fragm_size(struct sk_buff *buf) { return msg_ack(buf_msg(buf)); } -static inline void set_fragm_size(struct sk_buff *buf, u32 sz) +static void set_fragm_size(struct sk_buff *buf, u32 sz) { msg_set_ack(buf_msg(buf), sz); } -static inline u32 get_expected_frags(struct sk_buff *buf) +static u32 get_expected_frags(struct sk_buff *buf) { return msg_bcast_ack(buf_msg(buf)); } -static inline void set_expected_frags(struct sk_buff *buf, u32 exp) +static void set_expected_frags(struct sk_buff *buf, u32 exp) { msg_set_bcast_ack(buf_msg(buf), exp); } -static inline u32 get_timer_cnt(struct sk_buff *buf) +static u32 get_timer_cnt(struct sk_buff *buf) { return msg_reroute_cnt(buf_msg(buf)); } -static inline void incr_timer_cnt(struct sk_buff *buf) +static void incr_timer_cnt(struct sk_buff *buf) { msg_incr_reroute_cnt(buf_msg(buf)); } @@ -2586,13 +2581,13 @@ static inline void incr_timer_cnt(struct sk_buff *buf) int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, struct tipc_msg **m) { - struct sk_buff *prev = 0; + struct sk_buff *prev = NULL; struct sk_buff *fbuf = *fb; struct tipc_msg *fragm = buf_msg(fbuf); struct sk_buff *pbuf = *pending; u32 long_msg_seq_no = msg_long_msgno(fragm); - *fb = 0; + *fb = NULL; msg_dbg(fragm,"FRG<REC<"); /* Is there an incomplete message waiting for this fragment? */ @@ -2670,8 +2665,8 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, static void link_check_defragm_bufs(struct link *l_ptr) { - struct sk_buff *prev = 0; - struct sk_buff *next = 0; + struct sk_buff *prev = NULL; + struct sk_buff *next = NULL; struct sk_buff *buf = l_ptr->defragm_buf; if (!buf) @@ -2750,19 +2745,19 @@ static struct link *link_find_link(const char *name, struct node **node) struct link *l_ptr; if (!link_name_validate(name, &link_name_parts)) - return 0; + return NULL; b_ptr = tipc_bearer_find_interface(link_name_parts.if_local); if (!b_ptr) - return 0; + return NULL; *node = tipc_node_find(link_name_parts.addr_peer); if (!*node) - return 0; + return NULL; l_ptr = (*node)->links[b_ptr->identity]; if (!l_ptr || strcmp(l_ptr->name, name)) - return 0; + return NULL; return l_ptr; } diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 830f90999041..953307a9df1d 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -168,8 +168,8 @@ void tipc_named_withdraw(struct publication *publ) void tipc_named_node_up(unsigned long node) { struct publication *publ; - struct distr_item *item = 0; - struct sk_buff *buf = 0; + struct distr_item *item = NULL; + struct sk_buff *buf = NULL; u32 left = 0; u32 rest; u32 max_item_buf; @@ -200,7 +200,7 @@ void tipc_named_node_up(unsigned long node) "<%u.%u.%u>\n", tipc_zone(node), tipc_cluster(node), tipc_node(node)); tipc_link_send(buf, node, node); - buf = 0; + buf = NULL; } } exit: diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 3f4b23bd08f7..d129422fc5c2 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -46,7 +46,7 @@ #include "cluster.h" #include "bcast.h" -int tipc_nametbl_size = 1024; /* must be a power of 2 */ +static int tipc_nametbl_size = 1024; /* must be a power of 2 */ /** * struct sub_seq - container for all published instances of a name sequence @@ -104,7 +104,7 @@ static atomic_t rsv_publ_ok = ATOMIC_INIT(0); rwlock_t tipc_nametbl_lock = RW_LOCK_UNLOCKED; -static inline int hash(int x) +static int hash(int x) { return(x & (tipc_nametbl_size - 1)); } @@ -121,7 +121,7 @@ static struct publication *publ_create(u32 type, u32 lower, u32 upper, (struct publication *)kmalloc(sizeof(*publ), GFP_ATOMIC); if (publ == NULL) { warn("Memory squeeze; failed to create publication\n"); - return 0; + return NULL; } memset(publ, 0, sizeof(*publ)); @@ -142,7 +142,7 @@ static struct publication *publ_create(u32 type, u32 lower, u32 upper, * tipc_subseq_alloc - allocate a specified number of sub-sequence structures */ -struct sub_seq *tipc_subseq_alloc(u32 cnt) +static struct sub_seq *tipc_subseq_alloc(u32 cnt) { u32 sz = cnt * sizeof(struct sub_seq); struct sub_seq *sseq = (struct sub_seq *)kmalloc(sz, GFP_ATOMIC); @@ -158,7 +158,7 @@ struct sub_seq *tipc_subseq_alloc(u32 cnt) * Allocates a single sub-sequence structure and sets it to all 0's. */ -struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_head) +static struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_head) { struct name_seq *nseq = (struct name_seq *)kmalloc(sizeof(*nseq), GFP_ATOMIC); @@ -168,7 +168,7 @@ struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_head) warn("Memory squeeze; failed to create name sequence\n"); kfree(nseq); kfree(sseq); - return 0; + return NULL; } memset(nseq, 0, sizeof(*nseq)); @@ -190,8 +190,8 @@ struct name_seq *tipc_nameseq_create(u32 type, struct hlist_head *seq_head) * Very time-critical, so binary searches through sub-sequence array. */ -static inline struct sub_seq *nameseq_find_subseq(struct name_seq *nseq, - u32 instance) +static struct sub_seq *nameseq_find_subseq(struct name_seq *nseq, + u32 instance) { struct sub_seq *sseqs = nseq->sseqs; int low = 0; @@ -207,7 +207,7 @@ static inline struct sub_seq *nameseq_find_subseq(struct name_seq *nseq, else return &sseqs[mid]; } - return 0; + return NULL; } /** @@ -243,9 +243,9 @@ static u32 nameseq_locate_subseq(struct name_seq *nseq, u32 instance) * tipc_nameseq_insert_publ - */ -struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, - u32 type, u32 lower, u32 upper, - u32 scope, u32 node, u32 port, u32 key) +static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, + u32 type, u32 lower, u32 upper, + u32 scope, u32 node, u32 port, u32 key) { struct subscription *s; struct subscription *st; @@ -263,7 +263,7 @@ struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, if ((sseq->lower != lower) || (sseq->upper != upper)) { warn("Overlapping publ <%u,%u,%u>\n", type, lower, upper); - return 0; + return NULL; } } else { u32 inspos; @@ -278,7 +278,7 @@ struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, if ((inspos < nseq->first_free) && (upper >= nseq->sseqs[inspos].lower)) { warn("Overlapping publ <%u,%u,%u>\n", type, lower, upper); - return 0; + return NULL; } /* Ensure there is space for new sub-sequence */ @@ -294,7 +294,7 @@ struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, nseq->alloc *= 2; } else { warn("Memory squeeze; failed to create sub-sequence\n"); - return 0; + return NULL; } } dbg("Have %u sseqs for type %u\n", nseq->alloc, type); @@ -319,7 +319,7 @@ struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, publ = publ_create(type, lower, upper, scope, node, port, key); if (!publ) - return 0; + return NULL; dbg("inserting publ %x, node=%x publ->node=%x, subscr->node=%x\n", publ, node, publ->node, publ->subscr.node); @@ -369,8 +369,8 @@ struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, * tipc_nameseq_remove_publ - */ -struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 inst, - u32 node, u32 ref, u32 key) +static struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 inst, + u32 node, u32 ref, u32 key) { struct publication *publ; struct publication *prev; @@ -394,7 +394,7 @@ struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 inst, i, &nseq->sseqs[i], nseq->sseqs[i].lower, nseq->sseqs[i].upper); } - return 0; + return NULL; } dbg("nameseq_remove: seq: %x, sseq %x, <%u,%u> key %u\n", nseq, sseq, nseq->type, inst, key); @@ -413,7 +413,7 @@ struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 inst, prev->zone_list_next = publ->zone_list_next; sseq->zone_list = publ->zone_list_next; } else { - sseq->zone_list = 0; + sseq->zone_list = NULL; } if (in_own_cluster(node)) { @@ -431,7 +431,7 @@ struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 inst, prev->cluster_list_next = publ->cluster_list_next; sseq->cluster_list = publ->cluster_list_next; } else { - sseq->cluster_list = 0; + sseq->cluster_list = NULL; } } @@ -450,7 +450,7 @@ struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 inst, prev->node_list_next = publ->node_list_next; sseq->node_list = publ->node_list_next; } else { - sseq->node_list = 0; + sseq->node_list = NULL; } } assert(!publ->node || (publ->node == node)); @@ -535,7 +535,7 @@ static struct name_seq *nametbl_find_seq(u32 type) } } - return 0; + return NULL; }; struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper, @@ -547,7 +547,7 @@ struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper, if (lower > upper) { warn("Failed to publish illegal <%u,%u,%u>\n", type, lower, upper); - return 0; + return NULL; } dbg("Publishing <%u,%u,%u> from %x\n", type, lower, upper, node); @@ -556,7 +556,7 @@ struct publication *tipc_nametbl_insert_publ(u32 type, u32 lower, u32 upper, dbg("tipc_nametbl_insert_publ: created %x\n", seq); } if (!seq) - return 0; + return NULL; assert(seq->type == type); return tipc_nameseq_insert_publ(seq, type, lower, upper, @@ -570,7 +570,7 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, struct name_seq *seq = nametbl_find_seq(type); if (!seq) - return 0; + return NULL; dbg("Withdrawing <%u,%u> from %x\n", type, lower, node); publ = tipc_nameseq_remove_publ(seq, lower, node, ref, key); @@ -594,7 +594,7 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) { struct sub_seq *sseq; - struct publication *publ = 0; + struct publication *publ = NULL; struct name_seq *seq; u32 ref; @@ -740,12 +740,12 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper, if (table.local_publ_count >= tipc_max_publications) { warn("Failed publish: max %u local publication\n", tipc_max_publications); - return 0; + return NULL; } if ((type < TIPC_RESERVED_TYPES) && !atomic_read(&rsv_publ_ok)) { warn("Failed to publish reserved name <%u,%u,%u>\n", type, lower, upper); - return 0; + return NULL; } write_lock_bh(&tipc_nametbl_lock); @@ -983,6 +983,7 @@ static void nametbl_list(struct print_buf *buf, u32 depth_info, } } +#if 0 void tipc_nametbl_print(struct print_buf *buf, const char *str) { tipc_printf(buf, str); @@ -990,6 +991,7 @@ void tipc_nametbl_print(struct print_buf *buf, const char *str) nametbl_list(buf, 0, 0, 0, 0); read_unlock_bh(&tipc_nametbl_lock); } +#endif #define MAX_NAME_TBL_QUERY 32768 @@ -1023,10 +1025,12 @@ struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space) return buf; } +#if 0 void tipc_nametbl_dump(void) { nametbl_list(TIPC_CONS, 0, 0, 0, 0); } +#endif int tipc_nametbl_init(void) { diff --git a/net/tipc/net.c b/net/tipc/net.c index 074891ad4f09..f7c8223ddf7d 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -116,7 +116,7 @@ */ rwlock_t tipc_net_lock = RW_LOCK_UNLOCKED; -struct network tipc_net = { 0 }; +struct network tipc_net = { NULL }; struct node *tipc_net_select_remote_node(u32 addr, u32 ref) { @@ -128,13 +128,14 @@ u32 tipc_net_select_router(u32 addr, u32 ref) return tipc_zone_select_router(tipc_net.zones[tipc_zone(addr)], addr, ref); } - +#if 0 u32 tipc_net_next_node(u32 a) { if (tipc_net.zones[tipc_zone(a)]) return tipc_zone_next_node(a); return 0; } +#endif void tipc_net_remove_as_router(u32 router) { @@ -181,7 +182,7 @@ static void net_stop(void) tipc_zone_delete(tipc_net.zones[z_num]); } kfree(tipc_net.zones); - tipc_net.zones = 0; + tipc_net.zones = NULL; } static void net_route_named_msg(struct sk_buff *buf) diff --git a/net/tipc/node.c b/net/tipc/node.c index 6d65010e5fa1..0d5db06e203f 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -155,7 +155,7 @@ static void node_select_active_links(struct node *n_ptr) u32 i; u32 highest_prio = 0; - active[0] = active[1] = 0; + active[0] = active[1] = NULL; for (i = 0; i < MAX_BEARERS; i++) { struct link *l_ptr = n_ptr->links[i]; @@ -214,7 +214,7 @@ int tipc_node_has_redundant_links(struct node *n_ptr) (n_ptr->active_links[0] != n_ptr->active_links[1])); } -int tipc_node_has_active_routes(struct node *n_ptr) +static int tipc_node_has_active_routes(struct node *n_ptr) { return (n_ptr && (n_ptr->last_router >= 0)); } @@ -240,7 +240,7 @@ struct node *tipc_node_attach_link(struct link *l_ptr) err("Attempt to create third link to %s\n", addr_string_fill(addr_string, n_ptr->addr)); - return 0; + return NULL; } if (!n_ptr->links[bearer_id]) { @@ -253,12 +253,12 @@ struct node *tipc_node_attach_link(struct link *l_ptr) l_ptr->b_ptr->publ.name, addr_string_fill(addr_string, l_ptr->addr)); } - return 0; + return NULL; } void tipc_node_detach_link(struct node *n_ptr, struct link *l_ptr) { - n_ptr->links[l_ptr->b_ptr->identity] = 0; + n_ptr->links[l_ptr->b_ptr->identity] = NULL; tipc_net.zones[tipc_zone(l_ptr->addr)]->links--; n_ptr->link_cnt--; } @@ -424,7 +424,7 @@ static void node_lost_contact(struct node *n_ptr) /* Notify subscribers */ list_for_each_entry_safe(ns, tns, &n_ptr->nsub, nodesub_list) { - ns->node = 0; + ns->node = NULL; list_del_init(&ns->nodesub_list); tipc_k_signal((Handler)ns->handle_node_down, (unsigned long)ns->usr_handle); @@ -443,7 +443,7 @@ struct node *tipc_node_select_next_hop(u32 addr, u32 selector) u32 router_addr; if (!tipc_addr_domain_valid(addr)) - return 0; + return NULL; /* Look for direct link to destination processsor */ n_ptr = tipc_node_find(addr); @@ -452,7 +452,7 @@ struct node *tipc_node_select_next_hop(u32 addr, u32 selector) /* Cluster local system nodes *must* have direct links */ if (!is_slave(addr) && in_own_cluster(addr)) - return 0; + return NULL; /* Look for cluster local router with direct link to node */ router_addr = tipc_node_select_router(n_ptr, selector); @@ -462,7 +462,7 @@ struct node *tipc_node_select_next_hop(u32 addr, u32 selector) /* Slave nodes can only be accessed within own cluster via a known router with direct link -- if no router was found,give up */ if (is_slave(addr)) - return 0; + return NULL; /* Inter zone/cluster -- find any direct link to remote cluster */ addr = tipc_addr(tipc_zone(addr), tipc_cluster(addr), 0); @@ -475,7 +475,7 @@ struct node *tipc_node_select_next_hop(u32 addr, u32 selector) if (router_addr) return tipc_node_select(router_addr, selector); - return 0; + return NULL; } /** diff --git a/net/tipc/node.h b/net/tipc/node.h index 29f7ae6992d4..781126e084ae 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -121,7 +121,7 @@ static inline struct node *tipc_node_find(u32 addr) if (c_ptr) return c_ptr->nodes[tipc_node(addr)]; } - return 0; + return NULL; } static inline struct node *tipc_node_select(u32 addr, u32 selector) diff --git a/net/tipc/node_subscr.c b/net/tipc/node_subscr.c index afeea121d8be..cff4068cc755 100644 --- a/net/tipc/node_subscr.c +++ b/net/tipc/node_subscr.c @@ -47,7 +47,7 @@ void tipc_nodesub_subscribe(struct node_subscr *node_sub, u32 addr, void *usr_handle, net_ev_handler handle_down) { - node_sub->node = 0; + node_sub->node = NULL; if (addr == tipc_own_addr) return; if (!tipc_addr_node_valid(addr)) { diff --git a/net/tipc/port.c b/net/tipc/port.c index 72aae52bfec1..67e96cb1e825 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -54,8 +54,8 @@ #define MAX_REJECT_SIZE 1024 -static struct sk_buff *msg_queue_head = 0; -static struct sk_buff *msg_queue_tail = 0; +static struct sk_buff *msg_queue_head = NULL; +static struct sk_buff *msg_queue_tail = NULL; spinlock_t tipc_port_list_lock = SPIN_LOCK_UNLOCKED; static spinlock_t queue_lock = SPIN_LOCK_UNLOCKED; @@ -67,27 +67,22 @@ static struct sk_buff* port_build_peer_abort_msg(struct port *,u32 err); static void port_timeout(unsigned long ref); -static inline u32 port_peernode(struct port *p_ptr) +static u32 port_peernode(struct port *p_ptr) { return msg_destnode(&p_ptr->publ.phdr); } -static inline u32 port_peerport(struct port *p_ptr) +static u32 port_peerport(struct port *p_ptr) { return msg_destport(&p_ptr->publ.phdr); } -static inline u32 port_out_seqno(struct port *p_ptr) +static u32 port_out_seqno(struct port *p_ptr) { return msg_transp_seqno(&p_ptr->publ.phdr); } -static inline void port_set_out_seqno(struct port *p_ptr, u32 seqno) -{ - msg_set_transp_seqno(&p_ptr->publ.phdr,seqno); -} - -static inline void port_incr_out_seqno(struct port *p_ptr) +static void port_incr_out_seqno(struct port *p_ptr) { struct tipc_msg *m = &p_ptr->publ.phdr; @@ -258,11 +253,11 @@ u32 tipc_createport_raw(void *usr_handle, p_ptr->publ.usr_handle = usr_handle; INIT_LIST_HEAD(&p_ptr->wait_list); INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list); - p_ptr->congested_link = 0; + p_ptr->congested_link = NULL; p_ptr->max_pkt = MAX_PKT_DEFAULT; p_ptr->dispatcher = dispatcher; p_ptr->wakeup = wakeup; - p_ptr->user_port = 0; + p_ptr->user_port = NULL; k_init_timer(&p_ptr->timer, (Handler)port_timeout, ref); spin_lock_bh(&tipc_port_list_lock); INIT_LIST_HEAD(&p_ptr->publications); @@ -276,9 +271,9 @@ u32 tipc_createport_raw(void *usr_handle, int tipc_deleteport(u32 ref) { struct port *p_ptr; - struct sk_buff *buf = 0; + struct sk_buff *buf = NULL; - tipc_withdraw(ref, 0, 0); + tipc_withdraw(ref, 0, NULL); p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; @@ -329,13 +324,13 @@ void *tipc_get_handle(const u32 ref) p_ptr = tipc_port_lock(ref); if (!p_ptr) - return 0; + return NULL; handle = p_ptr->publ.usr_handle; tipc_port_unlock(p_ptr); return handle; } -static inline int port_unreliable(struct port *p_ptr) +static int port_unreliable(struct port *p_ptr) { return msg_src_droppable(&p_ptr->publ.phdr); } @@ -364,7 +359,7 @@ int tipc_set_portunreliable(u32 ref, unsigned int isunreliable) return TIPC_OK; } -static inline int port_unreturnable(struct port *p_ptr) +static int port_unreturnable(struct port *p_ptr) { return msg_dest_droppable(&p_ptr->publ.phdr); } @@ -475,7 +470,7 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) /* send self-abort message when rejecting on a connected port */ if (msg_connected(msg)) { - struct sk_buff *abuf = 0; + struct sk_buff *abuf = NULL; struct port *p_ptr = tipc_port_lock(msg_destport(msg)); if (p_ptr) { @@ -510,7 +505,7 @@ int tipc_port_reject_sections(struct port *p_ptr, struct tipc_msg *hdr, static void port_timeout(unsigned long ref) { struct port *p_ptr = tipc_port_lock(ref); - struct sk_buff *buf = 0; + struct sk_buff *buf = NULL; if (!p_ptr || !p_ptr->publ.connected) return; @@ -540,7 +535,7 @@ static void port_timeout(unsigned long ref) static void port_handle_node_down(unsigned long ref) { struct port *p_ptr = tipc_port_lock(ref); - struct sk_buff* buf = 0; + struct sk_buff* buf = NULL; if (!p_ptr) return; @@ -555,7 +550,7 @@ static struct sk_buff *port_build_self_abort_msg(struct port *p_ptr, u32 err) u32 imp = msg_importance(&p_ptr->publ.phdr); if (!p_ptr->publ.connected) - return 0; + return NULL; if (imp < TIPC_CRITICAL_IMPORTANCE) imp++; return port_build_proto_msg(p_ptr->publ.ref, @@ -575,7 +570,7 @@ static struct sk_buff *port_build_peer_abort_msg(struct port *p_ptr, u32 err) u32 imp = msg_importance(&p_ptr->publ.phdr); if (!p_ptr->publ.connected) - return 0; + return NULL; if (imp < TIPC_CRITICAL_IMPORTANCE) imp++; return port_build_proto_msg(port_peerport(p_ptr), @@ -594,8 +589,8 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf) struct tipc_msg *msg = buf_msg(buf); struct port *p_ptr = tipc_port_lock(msg_destport(msg)); u32 err = TIPC_OK; - struct sk_buff *r_buf = 0; - struct sk_buff *abort_buf = 0; + struct sk_buff *r_buf = NULL; + struct sk_buff *abort_buf = NULL; msg_dbg(msg, "PORT<RECV<:"); @@ -804,7 +799,7 @@ static void port_dispatcher_sigh(void *dummy) spin_lock_bh(&queue_lock); buf = msg_queue_head; - msg_queue_head = 0; + msg_queue_head = NULL; spin_unlock_bh(&queue_lock); while (buf) { @@ -991,8 +986,8 @@ static void port_wakeup_sh(unsigned long ref) { struct port *p_ptr; struct user_port *up_ptr; - tipc_continue_event cb = 0; - void *uh = 0; + tipc_continue_event cb = NULL; + void *uh = NULL; p_ptr = tipc_port_lock(ref); if (p_ptr) { @@ -1016,7 +1011,7 @@ static void port_wakeup(struct tipc_port *p_ptr) void tipc_acknowledge(u32 ref, u32 ack) { struct port *p_ptr; - struct sk_buff *buf = 0; + struct sk_buff *buf = NULL; p_ptr = tipc_port_lock(ref); if (!p_ptr) @@ -1062,7 +1057,7 @@ int tipc_createport(u32 user_ref, if (up_ptr == NULL) { return -ENOMEM; } - ref = tipc_createport_raw(0, port_dispatcher, port_wakeup, importance); + ref = tipc_createport_raw(NULL, port_dispatcher, port_wakeup, importance); p_ptr = tipc_port_lock(ref); if (!p_ptr) { kfree(up_ptr); @@ -1273,7 +1268,7 @@ int tipc_disconnect(u32 ref) int tipc_shutdown(u32 ref) { struct port *p_ptr; - struct sk_buff *buf = 0; + struct sk_buff *buf = NULL; p_ptr = tipc_port_lock(ref); if (!p_ptr) diff --git a/net/tipc/ref.c b/net/tipc/ref.c index 5a13c2defe4a..33bbf5095094 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -61,7 +61,7 @@ * because entry 0's reference field has the form XXXX|1--1. */ -struct ref_table tipc_ref_table = { 0 }; +struct ref_table tipc_ref_table = { NULL }; static rwlock_t ref_table_lock = RW_LOCK_UNLOCKED; @@ -86,7 +86,7 @@ int tipc_ref_table_init(u32 requested_size, u32 start) write_lock_bh(&ref_table_lock); index_mask = sz - 1; for (i = sz - 1; i >= 0; i--) { - table[i].object = 0; + table[i].object = NULL; table[i].lock = SPIN_LOCK_UNLOCKED; table[i].data.next_plus_upper = (start & ~index_mask) + i - 1; } @@ -108,7 +108,7 @@ void tipc_ref_table_stop(void) return; vfree(tipc_ref_table.entries); - tipc_ref_table.entries = 0; + tipc_ref_table.entries = NULL; } /** @@ -173,7 +173,7 @@ void tipc_ref_discard(u32 ref) assert(entry->data.reference == ref); /* mark entry as unused */ - entry->object = 0; + entry->object = NULL; if (tipc_ref_table.first_free == 0) tipc_ref_table.first_free = index; else diff --git a/net/tipc/ref.h b/net/tipc/ref.h index 4f8f9f40dcac..6d20006be45b 100644 --- a/net/tipc/ref.h +++ b/net/tipc/ref.h @@ -92,7 +92,7 @@ static inline void *tipc_ref_lock(u32 ref) return r->object; spin_unlock_bh(&r->lock); } - return 0; + return NULL; } /** @@ -125,7 +125,7 @@ static inline void *tipc_ref_deref(u32 ref) if (likely(r->data.reference == ref)) return r->object; } - return 0; + return NULL; } #endif diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 67253bfcd702..648a734e6044 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -88,7 +88,7 @@ static atomic_t tipc_queue_size = ATOMIC_INIT(0); * with non-socket interfaces. * See net.c for description of locking policy. */ -static inline void sock_lock(struct tipc_sock* tsock) +static void sock_lock(struct tipc_sock* tsock) { spin_lock_bh(tsock->p->lock); } @@ -96,7 +96,7 @@ static inline void sock_lock(struct tipc_sock* tsock) /* * sock_unlock(): Unlock a port/socket pair */ -static inline void sock_unlock(struct tipc_sock* tsock) +static void sock_unlock(struct tipc_sock* tsock) { spin_unlock_bh(tsock->p->lock); } @@ -119,7 +119,7 @@ static inline void sock_unlock(struct tipc_sock* tsock) * Returns pollmask value */ -static inline u32 pollmask(struct socket *sock) +static u32 pollmask(struct socket *sock) { u32 mask; @@ -144,7 +144,7 @@ static inline u32 pollmask(struct socket *sock) * @tsock: TIPC socket */ -static inline void advance_queue(struct tipc_sock *tsock) +static void advance_queue(struct tipc_sock *tsock) { sock_lock(tsock); buf_discard(skb_dequeue(&tsock->sk.sk_receive_queue)); @@ -178,7 +178,7 @@ static int tipc_create(struct socket *sock, int protocol) if (unlikely(protocol != 0)) return -EPROTONOSUPPORT; - ref = tipc_createport_raw(0, &dispatch, &wakeupdispatch, TIPC_LOW_IMPORTANCE); + ref = tipc_createport_raw(NULL, &dispatch, &wakeupdispatch, TIPC_LOW_IMPORTANCE); if (unlikely(!ref)) return -ENOMEM; @@ -265,7 +265,7 @@ static int release(struct socket *sock) sock_lock(tsock); buf = skb_dequeue(&sk->sk_receive_queue); if (!buf) - tsock->p->usr_handle = 0; + tsock->p->usr_handle = NULL; sock_unlock(tsock); if (!buf) break; @@ -319,7 +319,7 @@ static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) return -ERESTARTSYS; if (unlikely(!uaddr_len)) { - res = tipc_withdraw(tsock->p->ref, 0, 0); + res = tipc_withdraw(tsock->p->ref, 0, NULL); goto exit; } @@ -412,7 +412,7 @@ static unsigned int poll(struct file *file, struct socket *sock, * Returns 0 if permission is granted, otherwise errno */ -static inline int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) +static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) { struct tipc_cfg_msg_hdr hdr; @@ -695,7 +695,7 @@ static int auto_connect(struct socket *sock, struct tipc_sock *tsock, * Note: Address is not captured if not requested by receiver. */ -static inline void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) +static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) { struct sockaddr_tipc *addr = (struct sockaddr_tipc *)m->msg_name; @@ -721,7 +721,7 @@ static inline void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) * Returns 0 if successful, otherwise errno */ -static inline int anc_data_recv(struct msghdr *m, struct tipc_msg *msg, +static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg, struct tipc_port *tport) { u32 anc_data[3]; @@ -1226,7 +1226,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, { struct tipc_sock *tsock = tipc_sk(sock->sk); struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest; - struct msghdr m = {0,}; + struct msghdr m = {NULL,}; struct sk_buff *buf; struct tipc_msg *msg; int res; @@ -1251,7 +1251,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, /* Send a 'SYN-' to destination */ m.msg_name = dest; - if ((res = send_msg(0, sock, &m, 0)) < 0) { + if ((res = send_msg(NULL, sock, &m, 0)) < 0) { sock->state = SS_DISCONNECTING; return res; } @@ -1367,9 +1367,9 @@ static int accept(struct socket *sock, struct socket *newsock, int flags) msg_dbg(msg,"<ACC<: "); if (!msg_data_sz(msg)) { - struct msghdr m = {0,}; + struct msghdr m = {NULL,}; - send_packet(0, newsock, &m, 0); + send_packet(NULL, newsock, &m, 0); advance_queue(tsock); } else { sock_lock(tsock); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 5ff38b9f3194..c5f026c7fd38 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -86,7 +86,7 @@ static struct top_srv topsrv = { 0 }; * Returns converted value */ -static inline u32 htohl(u32 in, int swap) +static u32 htohl(u32 in, int swap) { char *c = (char *)∈ @@ -381,7 +381,7 @@ static void subscr_named_msg_event(void *usr_handle, struct tipc_name_seq const *dest) { struct subscriber *subscriber; - struct iovec msg_sect = {0, 0}; + struct iovec msg_sect = {NULL, 0}; spinlock_t *subscriber_lock; dbg("subscr_named_msg_event: orig = %x own = %x,\n", @@ -413,13 +413,13 @@ static void subscr_named_msg_event(void *usr_handle, tipc_createport(topsrv.user_ref, (void *)(unsigned long)subscriber->ref, importance, - 0, - 0, + NULL, + NULL, subscr_conn_shutdown_event, - 0, - 0, + NULL, + NULL, subscr_conn_msg_event, - 0, + NULL, &subscriber->port_ref); if (subscriber->port_ref == 0) { warn("Memory squeeze; failed to create subscription port\n"); @@ -461,22 +461,22 @@ int tipc_subscr_start(void) INIT_LIST_HEAD(&topsrv.subscriber_list); spin_lock_bh(&topsrv.lock); - res = tipc_attach(&topsrv.user_ref, 0, 0); + res = tipc_attach(&topsrv.user_ref, NULL, NULL); if (res) { spin_unlock_bh(&topsrv.lock); return res; } res = tipc_createport(topsrv.user_ref, - 0, + NULL, TIPC_CRITICAL_IMPORTANCE, - 0, - 0, - 0, - 0, + NULL, + NULL, + NULL, + NULL, subscr_named_msg_event, - 0, - 0, + NULL, + NULL, &topsrv.setup_port); if (res) goto failed; diff --git a/net/tipc/user_reg.c b/net/tipc/user_reg.c index 106200d76587..3f3f933976e9 100644 --- a/net/tipc/user_reg.c +++ b/net/tipc/user_reg.c @@ -65,7 +65,7 @@ struct tipc_user { #define MAX_USERID 64 #define USER_LIST_SIZE ((MAX_USERID + 1) * sizeof(struct tipc_user)) -static struct tipc_user *users = 0; +static struct tipc_user *users = NULL; static u32 next_free_user = MAX_USERID + 1; static spinlock_t reg_lock = SPIN_LOCK_UNLOCKED; @@ -149,7 +149,7 @@ void tipc_reg_stop(void) reg_callback(&users[id]); } kfree(users); - users = 0; + users = NULL; } /** diff --git a/net/tipc/zone.c b/net/tipc/zone.c index 7c11f7f83a21..2803e1b4f170 100644 --- a/net/tipc/zone.c +++ b/net/tipc/zone.c @@ -44,11 +44,11 @@ struct _zone *tipc_zone_create(u32 addr) { - struct _zone *z_ptr = 0; + struct _zone *z_ptr = NULL; u32 z_num; if (!tipc_addr_domain_valid(addr)) - return 0; + return NULL; z_ptr = (struct _zone *)kmalloc(sizeof(*z_ptr), GFP_ATOMIC); if (z_ptr != NULL) { @@ -114,10 +114,10 @@ struct node *tipc_zone_select_remote_node(struct _zone *z_ptr, u32 addr, u32 ref u32 c_num; if (!z_ptr) - return 0; + return NULL; c_ptr = z_ptr->clusters[tipc_cluster(addr)]; if (!c_ptr) - return 0; + return NULL; n_ptr = tipc_cltr_select_node(c_ptr, ref); if (n_ptr) return n_ptr; @@ -126,12 +126,12 @@ struct node *tipc_zone_select_remote_node(struct _zone *z_ptr, u32 addr, u32 ref for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { c_ptr = z_ptr->clusters[c_num]; if (!c_ptr) - return 0; + return NULL; n_ptr = tipc_cltr_select_node(c_ptr, ref); if (n_ptr) return n_ptr; } - return 0; + return NULL; } u32 tipc_zone_select_router(struct _zone *z_ptr, u32 addr, u32 ref) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c323cc6a28b0..2b4cc2eea5b3 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -566,7 +566,7 @@ static struct sock * unix_create1(struct socket *sock) u->mnt = NULL; spin_lock_init(&u->lock); atomic_set(&u->inflight, sock ? 0 : -1); - init_MUTEX(&u->readsem); /* single task reading lock */ + mutex_init(&u->readlock); /* single task reading lock */ init_waitqueue_head(&u->peer_wait); unix_insert_socket(unix_sockets_unbound, sk); out: @@ -623,7 +623,7 @@ static int unix_autobind(struct socket *sock) struct unix_address * addr; int err; - down(&u->readsem); + mutex_lock(&u->readlock); err = 0; if (u->addr) @@ -661,7 +661,7 @@ retry: spin_unlock(&unix_table_lock); err = 0; -out: up(&u->readsem); +out: mutex_unlock(&u->readlock); return err; } @@ -744,7 +744,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; - down(&u->readsem); + mutex_lock(&u->readlock); err = -EINVAL; if (u->addr) @@ -816,7 +816,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) out_unlock: spin_unlock(&unix_table_lock); out_up: - up(&u->readsem); + mutex_unlock(&u->readlock); out: return err; @@ -1427,15 +1427,15 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, while(sent < len) { /* - * Optimisation for the fact that under 0.01% of X messages typically - * need breaking up. + * Optimisation for the fact that under 0.01% of X + * messages typically need breaking up. */ - size=len-sent; + size = len-sent; /* Keep two messages in the pipe so it schedules better */ - if (size > sk->sk_sndbuf / 2 - 64) - size = sk->sk_sndbuf / 2 - 64; + if (size > ((sk->sk_sndbuf >> 1) - 64)) + size = (sk->sk_sndbuf >> 1) - 64; if (size > SKB_MAX_ALLOC) size = SKB_MAX_ALLOC; @@ -1545,7 +1545,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, msg->msg_namelen = 0; - down(&u->readsem); + mutex_lock(&u->readlock); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) @@ -1600,7 +1600,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, out_free: skb_free_datagram(sk,skb); out_unlock: - up(&u->readsem); + mutex_unlock(&u->readlock); out: return err; } @@ -1676,7 +1676,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, memset(&tmp_scm, 0, sizeof(tmp_scm)); } - down(&u->readsem); + mutex_lock(&u->readlock); do { @@ -1700,7 +1700,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, err = -EAGAIN; if (!timeo) break; - up(&u->readsem); + mutex_unlock(&u->readlock); timeo = unix_stream_data_wait(sk, timeo); @@ -1708,7 +1708,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, err = sock_intr_errno(timeo); goto out; } - down(&u->readsem); + mutex_lock(&u->readlock); continue; } @@ -1774,7 +1774,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, } } while (size); - up(&u->readsem); + mutex_unlock(&u->readlock); scm_recv(sock, msg, siocb->scm, flags); out: return copied ? : err; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 411802bd4d37..746c2f4a5fa6 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -76,6 +76,7 @@ #include <linux/netdevice.h> #include <linux/file.h> #include <linux/proc_fs.h> +#include <linux/mutex.h> #include <net/sock.h> #include <net/af_unix.h> @@ -169,7 +170,7 @@ static void maybe_unmark_and_push(struct sock *x) void unix_gc(void) { - static DECLARE_MUTEX(unix_gc_sem); + static DEFINE_MUTEX(unix_gc_sem); int i; struct sock *s; struct sk_buff_head hitlist; @@ -179,7 +180,7 @@ void unix_gc(void) * Avoid a recursive GC. */ - if (down_trylock(&unix_gc_sem)) + if (!mutex_trylock(&unix_gc_sem)) return; spin_lock(&unix_table_lock); @@ -308,5 +309,5 @@ void unix_gc(void) */ __skb_queue_purge(&hitlist); - up(&unix_gc_sem); + mutex_unlock(&unix_gc_sem); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ae62054a9fc4..f5eae9febd26 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -26,8 +26,8 @@ #include <net/xfrm.h> #include <net/ip.h> -DECLARE_MUTEX(xfrm_cfg_sem); -EXPORT_SYMBOL(xfrm_cfg_sem); +DEFINE_MUTEX(xfrm_cfg_mutex); +EXPORT_SYMBOL(xfrm_cfg_mutex); static DEFINE_RWLOCK(xfrm_policy_lock); @@ -203,7 +203,7 @@ static void xfrm_policy_timer(unsigned long data) } if (warn) - km_policy_expired(xp, dir, 0); + km_policy_expired(xp, dir, 0, 0); if (next != LONG_MAX && !mod_timer(&xp->timer, jiffies + make_jiffies(next))) xfrm_pol_hold(xp); @@ -216,7 +216,7 @@ out: expired: read_unlock(&xp->lock); if (!xfrm_policy_delete(xp, dir)) - km_policy_expired(xp, dir, 1); + km_policy_expired(xp, dir, 1, 0); xfrm_pol_put(xp); } @@ -621,6 +621,7 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir) } return -ENOENT; } +EXPORT_SYMBOL(xfrm_policy_delete); int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index c656cbaf35e8..a8e14dc1b04e 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -20,6 +20,15 @@ #include <linux/module.h> #include <asm/uaccess.h> +struct sock *xfrm_nl; +EXPORT_SYMBOL(xfrm_nl); + +u32 sysctl_xfrm_aevent_etime = XFRM_AE_ETIME; +EXPORT_SYMBOL(sysctl_xfrm_aevent_etime); + +u32 sysctl_xfrm_aevent_rseqth = XFRM_AE_SEQT_SIZE; +EXPORT_SYMBOL(sysctl_xfrm_aevent_rseqth); + /* Each xfrm_state may be linked to two tables: 1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl) @@ -50,18 +59,20 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock); static int xfrm_state_gc_flush_bundles; -static int __xfrm_state_delete(struct xfrm_state *x); +int __xfrm_state_delete(struct xfrm_state *x); static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned short family); static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo); -static int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); -static void km_state_expired(struct xfrm_state *x, int hard); +int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); +void km_state_expired(struct xfrm_state *x, int hard, u32 pid); static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (del_timer(&x->timer)) BUG(); + if (del_timer(&x->rtimer)) + BUG(); kfree(x->aalg); kfree(x->ealg); kfree(x->calg); @@ -153,7 +164,7 @@ static void xfrm_timer_handler(unsigned long data) x->km.dying = warn; if (warn) - km_state_expired(x, 0); + km_state_expired(x, 0, 0); resched: if (next != LONG_MAX && !mod_timer(&x->timer, jiffies + make_jiffies(next))) @@ -168,13 +179,15 @@ expired: goto resched; } if (!__xfrm_state_delete(x) && x->id.spi) - km_state_expired(x, 1); + km_state_expired(x, 1, 0); out: spin_unlock(&x->lock); xfrm_state_put(x); } +static void xfrm_replay_timer_handler(unsigned long data); + struct xfrm_state *xfrm_state_alloc(void) { struct xfrm_state *x; @@ -190,11 +203,16 @@ struct xfrm_state *xfrm_state_alloc(void) init_timer(&x->timer); x->timer.function = xfrm_timer_handler; x->timer.data = (unsigned long)x; + init_timer(&x->rtimer); + x->rtimer.function = xfrm_replay_timer_handler; + x->rtimer.data = (unsigned long)x; x->curlft.add_time = (unsigned long)xtime.tv_sec; x->lft.soft_byte_limit = XFRM_INF; x->lft.soft_packet_limit = XFRM_INF; x->lft.hard_byte_limit = XFRM_INF; x->lft.hard_packet_limit = XFRM_INF; + x->replay_maxage = 0; + x->replay_maxdiff = 0; spin_lock_init(&x->lock); } return x; @@ -212,7 +230,7 @@ void __xfrm_state_destroy(struct xfrm_state *x) } EXPORT_SYMBOL(__xfrm_state_destroy); -static int __xfrm_state_delete(struct xfrm_state *x) +int __xfrm_state_delete(struct xfrm_state *x) { int err = -ESRCH; @@ -228,6 +246,8 @@ static int __xfrm_state_delete(struct xfrm_state *x) spin_unlock(&xfrm_state_lock); if (del_timer(&x->timer)) __xfrm_state_put(x); + if (del_timer(&x->rtimer)) + __xfrm_state_put(x); /* The number two in this test is the reference * mentioned in the comment below plus the reference @@ -249,6 +269,7 @@ static int __xfrm_state_delete(struct xfrm_state *x) return err; } +EXPORT_SYMBOL(__xfrm_state_delete); int xfrm_state_delete(struct xfrm_state *x) { @@ -426,6 +447,10 @@ static void __xfrm_state_insert(struct xfrm_state *x) if (!mod_timer(&x->timer, jiffies + HZ)) xfrm_state_hold(x); + if (x->replay_maxage && + !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) + xfrm_state_hold(x); + wake_up(&km_waitq); } @@ -580,7 +605,7 @@ int xfrm_state_check_expire(struct xfrm_state *x) (x->curlft.bytes >= x->lft.soft_byte_limit || x->curlft.packets >= x->lft.soft_packet_limit)) { x->km.dying = 1; - km_state_expired(x, 0); + km_state_expired(x, 0, 0); } return 0; } @@ -762,6 +787,61 @@ out: } EXPORT_SYMBOL(xfrm_state_walk); + +void xfrm_replay_notify(struct xfrm_state *x, int event) +{ + struct km_event c; + /* we send notify messages in case + * 1. we updated on of the sequence numbers, and the seqno difference + * is at least x->replay_maxdiff, in this case we also update the + * timeout of our timer function + * 2. if x->replay_maxage has elapsed since last update, + * and there were changes + * + * The state structure must be locked! + */ + + switch (event) { + case XFRM_REPLAY_UPDATE: + if (x->replay_maxdiff && + (x->replay.seq - x->preplay.seq < x->replay_maxdiff) && + (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff)) + return; + + break; + + case XFRM_REPLAY_TIMEOUT: + if ((x->replay.seq == x->preplay.seq) && + (x->replay.bitmap == x->preplay.bitmap) && + (x->replay.oseq == x->preplay.oseq)) + return; + + break; + } + + memcpy(&x->preplay, &x->replay, sizeof(struct xfrm_replay_state)); + c.event = XFRM_MSG_NEWAE; + c.data.aevent = event; + km_state_notify(x, &c); + + if (x->replay_maxage && + !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) + xfrm_state_hold(x); +} +EXPORT_SYMBOL(xfrm_replay_notify); + +static void xfrm_replay_timer_handler(unsigned long data) +{ + struct xfrm_state *x = (struct xfrm_state*)data; + + spin_lock(&x->lock); + + if (xfrm_aevent_is_on() && x->km.state == XFRM_STATE_VALID) + xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT); + + spin_unlock(&x->lock); +} + int xfrm_replay_check(struct xfrm_state *x, u32 seq) { u32 diff; @@ -805,6 +885,9 @@ void xfrm_replay_advance(struct xfrm_state *x, u32 seq) diff = x->replay.seq - seq; x->replay.bitmap |= (1U << diff); } + + if (xfrm_aevent_is_on()) + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } EXPORT_SYMBOL(xfrm_replay_advance); @@ -835,11 +918,12 @@ void km_state_notify(struct xfrm_state *x, struct km_event *c) EXPORT_SYMBOL(km_policy_notify); EXPORT_SYMBOL(km_state_notify); -static void km_state_expired(struct xfrm_state *x, int hard) +void km_state_expired(struct xfrm_state *x, int hard, u32 pid) { struct km_event c; c.data.hard = hard; + c.pid = pid; c.event = XFRM_MSG_EXPIRE; km_state_notify(x, &c); @@ -847,11 +931,12 @@ static void km_state_expired(struct xfrm_state *x, int hard) wake_up(&km_waitq); } +EXPORT_SYMBOL(km_state_expired); /* * We send to all registered managers regardless of failure * We are happy with one success */ -static int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) +int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) { int err = -EINVAL, acqret; struct xfrm_mgr *km; @@ -865,6 +950,7 @@ static int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_polic read_unlock(&xfrm_km_lock); return err; } +EXPORT_SYMBOL(km_query); int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, u16 sport) { @@ -883,17 +969,19 @@ int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, u16 sport) } EXPORT_SYMBOL(km_new_mapping); -void km_policy_expired(struct xfrm_policy *pol, int dir, int hard) +void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid) { struct km_event c; c.data.hard = hard; + c.pid = pid; c.event = XFRM_MSG_POLEXPIRE; km_policy_notify(pol, dir, &c); if (hard) wake_up(&km_waitq); } +EXPORT_SYMBOL(km_policy_expired); int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen) { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 7de17559249a..81d1005830f4 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -28,8 +28,6 @@ #include <net/netlink.h> #include <asm/uaccess.h> -static struct sock *xfrm_nl; - static int verify_one_alg(struct rtattr **xfrma, enum xfrm_attr_type_t type) { struct rtattr *rt = xfrma[type - 1]; @@ -103,9 +101,6 @@ static inline int verify_sec_ctx_len(struct rtattr **xfrma) uctx = RTA_DATA(rt); - if (uctx->ctx_len > PAGE_SIZE) - return -EINVAL; - len += sizeof(struct xfrm_user_sec_ctx); len += uctx->ctx_len; @@ -276,6 +271,56 @@ static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info * x->props.flags = p->flags; } +/* + * someday when pfkey also has support, we could have the code + * somehow made shareable and move it to xfrm_state.c - JHS + * +*/ +static int xfrm_update_ae_params(struct xfrm_state *x, struct rtattr **xfrma) +{ + int err = - EINVAL; + struct rtattr *rp = xfrma[XFRMA_REPLAY_VAL-1]; + struct rtattr *lt = xfrma[XFRMA_LTIME_VAL-1]; + struct rtattr *et = xfrma[XFRMA_ETIMER_THRESH-1]; + struct rtattr *rt = xfrma[XFRMA_REPLAY_THRESH-1]; + + if (rp) { + struct xfrm_replay_state *replay; + if (RTA_PAYLOAD(rp) < sizeof(*replay)) + goto error; + replay = RTA_DATA(rp); + memcpy(&x->replay, replay, sizeof(*replay)); + memcpy(&x->preplay, replay, sizeof(*replay)); + } + + if (lt) { + struct xfrm_lifetime_cur *ltime; + if (RTA_PAYLOAD(lt) < sizeof(*ltime)) + goto error; + ltime = RTA_DATA(lt); + x->curlft.bytes = ltime->bytes; + x->curlft.packets = ltime->packets; + x->curlft.add_time = ltime->add_time; + x->curlft.use_time = ltime->use_time; + } + + if (et) { + if (RTA_PAYLOAD(et) < sizeof(u32)) + goto error; + x->replay_maxage = *(u32*)RTA_DATA(et); + } + + if (rt) { + if (RTA_PAYLOAD(rt) < sizeof(u32)) + goto error; + x->replay_maxdiff = *(u32*)RTA_DATA(rt); + } + + return 0; +error: + return err; +} + static struct xfrm_state *xfrm_state_construct(struct xfrm_usersa_info *p, struct rtattr **xfrma, int *errp) @@ -311,6 +356,18 @@ static struct xfrm_state *xfrm_state_construct(struct xfrm_usersa_info *p, goto error; x->km.seq = p->seq; + x->replay_maxdiff = sysctl_xfrm_aevent_rseqth; + /* sysctl_xfrm_aevent_etime is in 100ms units */ + x->replay_maxage = (sysctl_xfrm_aevent_etime*HZ)/XFRM_AE_ETH_M; + x->preplay.bitmap = 0; + x->preplay.seq = x->replay.seq+x->replay_maxdiff; + x->preplay.oseq = x->replay.oseq +x->replay_maxdiff; + + /* override default values from above */ + + err = xfrm_update_ae_params(x, (struct rtattr **)xfrma); + if (err < 0) + goto error; return x; @@ -1025,9 +1082,142 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma return 0; } -static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) + +static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, struct km_event *c) +{ + struct xfrm_aevent_id *id; + struct nlmsghdr *nlh; + struct xfrm_lifetime_cur ltime; + unsigned char *b = skb->tail; + + nlh = NLMSG_PUT(skb, c->pid, c->seq, XFRM_MSG_NEWAE, sizeof(*id)); + id = NLMSG_DATA(nlh); + nlh->nlmsg_flags = 0; + + id->sa_id.daddr = x->id.daddr; + id->sa_id.spi = x->id.spi; + id->sa_id.family = x->props.family; + id->sa_id.proto = x->id.proto; + id->flags = c->data.aevent; + + RTA_PUT(skb, XFRMA_REPLAY_VAL, sizeof(x->replay), &x->replay); + + ltime.bytes = x->curlft.bytes; + ltime.packets = x->curlft.packets; + ltime.add_time = x->curlft.add_time; + ltime.use_time = x->curlft.use_time; + + RTA_PUT(skb, XFRMA_LTIME_VAL, sizeof(struct xfrm_lifetime_cur), <ime); + + if (id->flags&XFRM_AE_RTHR) { + RTA_PUT(skb,XFRMA_REPLAY_THRESH,sizeof(u32),&x->replay_maxdiff); + } + + if (id->flags&XFRM_AE_ETHR) { + u32 etimer = x->replay_maxage*10/HZ; + RTA_PUT(skb,XFRMA_ETIMER_THRESH,sizeof(u32),&etimer); + } + + nlh->nlmsg_len = skb->tail - b; + return skb->len; + +rtattr_failure: +nlmsg_failure: + skb_trim(skb, b - skb->data); + return -1; +} + +static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) +{ + struct xfrm_state *x; + struct sk_buff *r_skb; + int err; + struct km_event c; + struct xfrm_aevent_id *p = NLMSG_DATA(nlh); + int len = NLMSG_LENGTH(sizeof(struct xfrm_aevent_id)); + struct xfrm_usersa_id *id = &p->sa_id; + + len += RTA_SPACE(sizeof(struct xfrm_replay_state)); + len += RTA_SPACE(sizeof(struct xfrm_lifetime_cur)); + + if (p->flags&XFRM_AE_RTHR) + len+=RTA_SPACE(sizeof(u32)); + + if (p->flags&XFRM_AE_ETHR) + len+=RTA_SPACE(sizeof(u32)); + + r_skb = alloc_skb(len, GFP_ATOMIC); + if (r_skb == NULL) + return -ENOMEM; + + x = xfrm_state_lookup(&id->daddr, id->spi, id->proto, id->family); + if (x == NULL) { + kfree(r_skb); + return -ESRCH; + } + + /* + * XXX: is this lock really needed - none of the other + * gets lock (the concern is things getting updated + * while we are still reading) - jhs + */ + spin_lock_bh(&x->lock); + c.data.aevent = p->flags; + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + + if (build_aevent(r_skb, x, &c) < 0) + BUG(); + err = netlink_unicast(xfrm_nl, r_skb, + NETLINK_CB(skb).pid, MSG_DONTWAIT); + spin_unlock_bh(&x->lock); + xfrm_state_put(x); + return err; +} + +static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) { + struct xfrm_state *x; struct km_event c; + int err = - EINVAL; + struct xfrm_aevent_id *p = NLMSG_DATA(nlh); + struct rtattr *rp = xfrma[XFRMA_REPLAY_VAL-1]; + struct rtattr *lt = xfrma[XFRMA_LTIME_VAL-1]; + + if (!lt && !rp) + return err; + + /* pedantic mode - thou shalt sayeth replaceth */ + if (!(nlh->nlmsg_flags&NLM_F_REPLACE)) + return err; + + x = xfrm_state_lookup(&p->sa_id.daddr, p->sa_id.spi, p->sa_id.proto, p->sa_id.family); + if (x == NULL) + return -ESRCH; + + if (x->km.state != XFRM_STATE_VALID) + goto out; + + spin_lock_bh(&x->lock); + err = xfrm_update_ae_params(x,(struct rtattr **)xfrma); + spin_unlock_bh(&x->lock); + if (err < 0) + goto out; + + c.event = nlh->nlmsg_type; + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + c.data.aevent = XFRM_AE_CU; + km_state_notify(x, &c); + err = 0; +out: + xfrm_state_put(x); + return err; +} + +static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) +{ +struct km_event c; xfrm_policy_flush(); c.event = nlh->nlmsg_type; @@ -1037,6 +1227,139 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **x return 0; } +static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) +{ + struct xfrm_policy *xp; + struct xfrm_user_polexpire *up = NLMSG_DATA(nlh); + struct xfrm_userpolicy_info *p = &up->pol; + int err = -ENOENT; + + if (p->index) + xp = xfrm_policy_byid(p->dir, p->index, 0); + else { + struct rtattr **rtattrs = (struct rtattr **)xfrma; + struct rtattr *rt = rtattrs[XFRMA_SEC_CTX-1]; + struct xfrm_policy tmp; + + err = verify_sec_ctx_len(rtattrs); + if (err) + return err; + + memset(&tmp, 0, sizeof(struct xfrm_policy)); + if (rt) { + struct xfrm_user_sec_ctx *uctx = RTA_DATA(rt); + + if ((err = security_xfrm_policy_alloc(&tmp, uctx))) + return err; + } + xp = xfrm_policy_bysel_ctx(p->dir, &p->sel, tmp.security, 0); + security_xfrm_policy_free(&tmp); + } + + if (xp == NULL) + return err; + read_lock(&xp->lock); + if (xp->dead) { + read_unlock(&xp->lock); + goto out; + } + + read_unlock(&xp->lock); + err = 0; + if (up->hard) { + xfrm_policy_delete(xp, p->dir); + } else { + // reset the timers here? + printk("Dont know what to do with soft policy expire\n"); + } + km_policy_expired(xp, p->dir, up->hard, current->pid); + +out: + xfrm_pol_put(xp); + return err; +} + +static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) +{ + struct xfrm_state *x; + int err; + struct xfrm_user_expire *ue = NLMSG_DATA(nlh); + struct xfrm_usersa_info *p = &ue->state; + + x = xfrm_state_lookup(&p->id.daddr, p->id.spi, p->id.proto, p->family); + err = -ENOENT; + + if (x == NULL) + return err; + + err = -EINVAL; + + spin_lock_bh(&x->lock); + if (x->km.state != XFRM_STATE_VALID) + goto out; + km_state_expired(x, ue->hard, current->pid); + + if (ue->hard) + __xfrm_state_delete(x); +out: + spin_unlock_bh(&x->lock); + xfrm_state_put(x); + return err; +} + +static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) +{ + struct xfrm_policy *xp; + struct xfrm_user_tmpl *ut; + int i; + struct rtattr *rt = xfrma[XFRMA_TMPL-1]; + + struct xfrm_user_acquire *ua = NLMSG_DATA(nlh); + struct xfrm_state *x = xfrm_state_alloc(); + int err = -ENOMEM; + + if (!x) + return err; + + err = verify_newpolicy_info(&ua->policy); + if (err) { + printk("BAD policy passed\n"); + kfree(x); + return err; + } + + /* build an XP */ + xp = xfrm_policy_construct(&ua->policy, (struct rtattr **) xfrma, &err); if (!xp) { + kfree(x); + return err; + } + + memcpy(&x->id, &ua->id, sizeof(ua->id)); + memcpy(&x->props.saddr, &ua->saddr, sizeof(ua->saddr)); + memcpy(&x->sel, &ua->sel, sizeof(ua->sel)); + + ut = RTA_DATA(rt); + /* extract the templates and for each call km_key */ + for (i = 0; i < xp->xfrm_nr; i++, ut++) { + struct xfrm_tmpl *t = &xp->xfrm_vec[i]; + memcpy(&x->id, &t->id, sizeof(x->id)); + x->props.mode = t->mode; + x->props.reqid = t->reqid; + x->props.family = ut->family; + t->aalgos = ua->aalgos; + t->ealgos = ua->ealgos; + t->calgos = ua->calgos; + err = km_query(x, t, xp); + + } + + kfree(x); + kfree(xp); + + return 0; +} + + #define XMSGSIZE(type) NLMSG_LENGTH(sizeof(struct type)) static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { @@ -1054,6 +1377,8 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_polexpire), [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush), [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = NLMSG_LENGTH(0), + [XFRM_MSG_NEWAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), + [XFRM_MSG_GETAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), }; #undef XMSGSIZE @@ -1071,10 +1396,15 @@ static struct xfrm_link { [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy, .dump = xfrm_dump_policy }, [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = { .doit = xfrm_alloc_userspi }, + [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_acquire }, + [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_sa_expire }, [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_add_policy }, [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = { .doit = xfrm_add_sa }, + [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_pol_expire}, [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = { .doit = xfrm_flush_sa }, [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_flush_policy }, + [XFRM_MSG_NEWAE - XFRM_MSG_BASE] = { .doit = xfrm_new_ae }, + [XFRM_MSG_GETAE - XFRM_MSG_BASE] = { .doit = xfrm_get_ae }, }; static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp) @@ -1156,26 +1486,26 @@ static void xfrm_netlink_rcv(struct sock *sk, int len) unsigned int qlen = 0; do { - down(&xfrm_cfg_sem); + mutex_lock(&xfrm_cfg_mutex); netlink_run_queue(sk, &qlen, &xfrm_user_rcv_msg); - up(&xfrm_cfg_sem); + mutex_unlock(&xfrm_cfg_mutex); } while (qlen); } -static int build_expire(struct sk_buff *skb, struct xfrm_state *x, int hard) +static int build_expire(struct sk_buff *skb, struct xfrm_state *x, struct km_event *c) { struct xfrm_user_expire *ue; struct nlmsghdr *nlh; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, XFRM_MSG_EXPIRE, + nlh = NLMSG_PUT(skb, c->pid, 0, XFRM_MSG_EXPIRE, sizeof(*ue)); ue = NLMSG_DATA(nlh); nlh->nlmsg_flags = 0; copy_to_user_state(x, &ue->state); - ue->hard = (hard != 0) ? 1 : 0; + ue->hard = (c->data.hard != 0) ? 1 : 0; nlh->nlmsg_len = skb->tail - b; return skb->len; @@ -1194,13 +1524,31 @@ static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c) if (skb == NULL) return -ENOMEM; - if (build_expire(skb, x, c->data.hard) < 0) + if (build_expire(skb, x, c) < 0) BUG(); NETLINK_CB(skb).dst_group = XFRMNLGRP_EXPIRE; return netlink_broadcast(xfrm_nl, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); } +static int xfrm_aevent_state_notify(struct xfrm_state *x, struct km_event *c) +{ + struct sk_buff *skb; + int len = NLMSG_LENGTH(sizeof(struct xfrm_aevent_id)); + + len += RTA_SPACE(sizeof(struct xfrm_replay_state)); + len += RTA_SPACE(sizeof(struct xfrm_lifetime_cur)); + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + + if (build_aevent(skb, x, c) < 0) + BUG(); + + NETLINK_CB(skb).dst_group = XFRMNLGRP_AEVENTS; + return netlink_broadcast(xfrm_nl, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC); +} + static int xfrm_notify_sa_flush(struct km_event *c) { struct xfrm_usersa_flush *p; @@ -1313,6 +1661,8 @@ static int xfrm_send_state_notify(struct xfrm_state *x, struct km_event *c) switch (c->event) { case XFRM_MSG_EXPIRE: return xfrm_exp_state_notify(x, c); + case XFRM_MSG_NEWAE: + return xfrm_aevent_state_notify(x, c); case XFRM_MSG_DELSA: case XFRM_MSG_UPDSA: case XFRM_MSG_NEWSA: @@ -1443,13 +1793,14 @@ static struct xfrm_policy *xfrm_compile_policy(u16 family, int opt, } static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, - int dir, int hard) + int dir, struct km_event *c) { struct xfrm_user_polexpire *upe; struct nlmsghdr *nlh; + int hard = c->data.hard; unsigned char *b = skb->tail; - nlh = NLMSG_PUT(skb, 0, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe)); + nlh = NLMSG_PUT(skb, c->pid, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe)); upe = NLMSG_DATA(nlh); nlh->nlmsg_flags = 0; @@ -1480,7 +1831,7 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_eve if (skb == NULL) return -ENOMEM; - if (build_polexpire(skb, xp, dir, c->data.hard) < 0) + if (build_polexpire(skb, xp, dir, c) < 0) BUG(); NETLINK_CB(skb).dst_group = XFRMNLGRP_EXPIRE; @@ -1596,12 +1947,15 @@ static struct xfrm_mgr netlink_mgr = { static int __init xfrm_user_init(void) { + struct sock *nlsk; + printk(KERN_INFO "Initializing IPsec netlink socket\n"); - xfrm_nl = netlink_kernel_create(NETLINK_XFRM, XFRMNLGRP_MAX, - xfrm_netlink_rcv, THIS_MODULE); - if (xfrm_nl == NULL) + nlsk = netlink_kernel_create(NETLINK_XFRM, XFRMNLGRP_MAX, + xfrm_netlink_rcv, THIS_MODULE); + if (nlsk == NULL) return -ENOMEM; + rcu_assign_pointer(xfrm_nl, nlsk); xfrm_register_km(&netlink_mgr); @@ -1610,11 +1964,16 @@ static int __init xfrm_user_init(void) static void __exit xfrm_user_exit(void) { + struct sock *nlsk = xfrm_nl; + xfrm_unregister_km(&netlink_mgr); - sock_release(xfrm_nl->sk_socket); + rcu_assign_pointer(xfrm_nl, NULL); + synchronize_rcu(); + sock_release(nlsk->sk_socket); } module_init(xfrm_user_init); module_exit(xfrm_user_exit); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM); + |