diff options
| author | Linus Torvalds <torvalds@g5.osdl.org> | 2006-09-23 16:49:31 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@g5.osdl.org> | 2006-09-23 16:49:31 -0700 |
| commit | a4c12d6c5dde48c69464baf7c703e425ee511433 (patch) | |
| tree | 73c375e41a353e2da0461ff30d744bff73958b08 /net | |
| parent | 73af07de3e32b9ac328c3d1417258bb98a9b0a9b (diff) | |
| parent | 3b9f9a1c3903b64c38505f9fed3bb11e48dbc931 (diff) | |
Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (353 commits)
[IPV6] ADDRCONF: Mobile IPv6 Home Address support.
[IPV6] ADDRCONF: Allow non-DAD'able addresses.
[IPV6] NDISC: Fix is_router flag setting.
[IPV6] ADDRCONF: Convert addrconf_lock to RCU.
[IPV6] NDISC: Add proxy_ndp sysctl.
[IPV6] NDISC: Set per-entry is_router flag in Proxy NA.
[IPV6] NDISC: Avoid updating neighbor cache for proxied address in receiving NA.
[IPV6]: Don't forward packets to proxied link-local address.
[IPV6] NDISC: Handle NDP messages to proxied addresses.
[NETFILTER]: PPTP conntrack: fix another GRE keymap leak
[NETFILTER]: PPTP conntrack: fix GRE keymap leak
[NETFILTER]: PPTP conntrack: fix PPTP_IN_CALL message types
[NETFILTER]: PPTP conntrack: check call ID before changing state
[NETFILTER]: PPTP conntrack: clean up debugging cruft
[NETFILTER]: PPTP conntrack: consolidate header parsing
[NETFILTER]: PPTP conntrack: consolidate header size checks
[NETFILTER]: PPTP conntrack: simplify expectation handling
[NETFILTER]: PPTP conntrack: remove unnecessary cid/pcid header pointers
[NETFILTER]: PPTP conntrack: fix header definitions
[NETFILTER]: PPTP conntrack: remove more dead code
...
Diffstat (limited to 'net')
305 files changed, 18631 insertions, 9546 deletions
diff --git a/net/Kconfig b/net/Kconfig index 4959a4e1e0f..6528a935622 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -249,6 +249,11 @@ source "net/ieee80211/Kconfig" config WIRELESS_EXT bool +source "net/netlabel/Kconfig" + +config FIB_RULES + bool + endif # if NET endmenu # Networking diff --git a/net/Makefile b/net/Makefile index 065796f5fb1..ad4d14f4bb2 100644 --- a/net/Makefile +++ b/net/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_IP_DCCP) += dccp/ obj-$(CONFIG_IP_SCTP) += sctp/ obj-$(CONFIG_IEEE80211) += ieee80211/ obj-$(CONFIG_TIPC) += tipc/ +obj-$(CONFIG_NETLABEL) += netlabel/ ifeq ($(CONFIG_NET),y) obj-$(CONFIG_SYSCTL) += sysctl_net.o diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index 5df4b9a068b..c0a4ae28fcf 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -1,6 +1,5 @@ /* ATM driver model support. */ -#include <linux/config.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/kobject.h> diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 00704661e83..b87c2a88bdc 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -98,11 +98,6 @@ static struct notifier_block mpoa_notifier = { 0 }; -#ifdef CONFIG_PROC_FS -extern int mpc_proc_init(void); -extern void mpc_proc_clean(void); -#endif - struct mpoa_client *mpcs = NULL; /* FIXME */ static struct atm_mpoa_qos *qos_head = NULL; static DEFINE_TIMER(mpc_timer, NULL, 0, 0); @@ -1439,12 +1434,8 @@ static __init int atm_mpoa_init(void) { register_atm_ioctl(&atm_ioctl_ops); -#ifdef CONFIG_PROC_FS if (mpc_proc_init() != 0) printk(KERN_INFO "mpoa: failed to initialize /proc/mpoa\n"); - else - printk(KERN_INFO "mpoa: /proc/mpoa initialized\n"); -#endif printk("mpc.c: " __DATE__ " " __TIME__ " initialized\n"); @@ -1457,9 +1448,7 @@ static void __exit atm_mpoa_cleanup(void) struct atm_mpoa_qos *qos, *nextqos; struct lec_priv *priv; -#ifdef CONFIG_PROC_FS mpc_proc_clean(); -#endif del_timer(&mpc_timer); unregister_netdevice_notifier(&mpoa_notifier); diff --git a/net/atm/mpc.h b/net/atm/mpc.h index 863ddf6079e..3c7981a229e 100644 --- a/net/atm/mpc.h +++ b/net/atm/mpc.h @@ -50,4 +50,12 @@ int atm_mpoa_delete_qos(struct atm_mpoa_qos *qos); struct seq_file; void atm_mpoa_disp_qos(struct seq_file *m); +#ifdef CONFIG_PROC_FS +int mpc_proc_init(void); +void mpc_proc_clean(void); +#else +#define mpc_proc_init() (0) +#define mpc_proc_clean() do { } while(0) +#endif + #endif /* _MPC_H_ */ diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 864fbbc7b24..191b861e5e5 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -38,13 +38,10 @@ int br_dev_queue_push_xmit(struct sk_buff *skb) if (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb)) kfree_skb(skb); else { -#ifdef CONFIG_BRIDGE_NETFILTER /* ip_refrag calls ip_fragment, doesn't copy the MAC header. */ if (nf_bridge_maybe_copy_header(skb)) kfree_skb(skb); - else -#endif - { + else { skb_push(skb, ETH_HLEN); dev_queue_xmit(skb); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 05b3de88824..ac181be13d8 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -53,10 +53,10 @@ #ifdef CONFIG_SYSCTL static struct ctl_table_header *brnf_sysctl_header; -static int brnf_call_iptables = 1; -static int brnf_call_ip6tables = 1; -static int brnf_call_arptables = 1; -static int brnf_filter_vlan_tagged = 1; +static int brnf_call_iptables __read_mostly = 1; +static int brnf_call_ip6tables __read_mostly = 1; +static int brnf_call_arptables __read_mostly = 1; +static int brnf_filter_vlan_tagged __read_mostly = 1; #else #define brnf_filter_vlan_tagged 1 #endif @@ -127,14 +127,37 @@ static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) static inline void nf_bridge_save_header(struct sk_buff *skb) { - int header_size = 16; + int header_size = ETH_HLEN; if (skb->protocol == htons(ETH_P_8021Q)) - header_size = 18; + header_size += VLAN_HLEN; memcpy(skb->nf_bridge->data, skb->data - header_size, header_size); } +/* + * When forwarding bridge frames, we save a copy of the original + * header before processing. + */ +int nf_bridge_copy_header(struct sk_buff *skb) +{ + int err; + int header_size = ETH_HLEN; + + if (skb->protocol == htons(ETH_P_8021Q)) + header_size += VLAN_HLEN; + + err = skb_cow(skb, header_size); + if (err) + return err; + + memcpy(skb->data - header_size, skb->nf_bridge->data, header_size); + + if (skb->protocol == htons(ETH_P_8021Q)) + __skb_push(skb, VLAN_HLEN); + return 0; +} + /* PF_BRIDGE/PRE_ROUTING *********************************************/ /* Undo the changes made for ip6tables PREROUTING and continue the * bridge PRE_ROUTING hook. */ @@ -695,16 +718,6 @@ static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb, else pf = PF_INET6; -#ifdef CONFIG_NETFILTER_DEBUG - /* Sometimes we get packets with NULL ->dst here (for example, - * running a dhcp client daemon triggers this). This should now - * be fixed, but let's keep the check around. */ - if (skb->dst == NULL) { - printk(KERN_CRIT "br_netfilter: skb->dst == NULL."); - return NF_ACCEPT; - } -#endif - nf_bridge = skb->nf_bridge; nf_bridge->physoutdev = skb->dev; realindev = nf_bridge->physindev; @@ -786,7 +799,7 @@ 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.\n"); goto print_error; } #endif @@ -804,7 +817,7 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, #ifdef CONFIG_NETFILTER_DEBUG if (skb->dst == NULL) { - printk(KERN_CRIT "br_netfilter: skb->dst == NULL."); + printk(KERN_INFO "br_netfilter post_routing: skb->dst == NULL\n"); goto print_error; } #endif @@ -841,6 +854,7 @@ print_error: } printk(" head:%p, raw:%p, data:%p\n", skb->head, skb->mac.raw, skb->data); + dump_stack(); return NF_ACCEPT; #endif } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 53086fb7508..8f661195d09 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/rtnetlink.h> +#include <net/netlink.h> #include "br_private.h" /* @@ -76,26 +77,24 @@ rtattr_failure: void br_ifinfo_notify(int event, struct net_bridge_port *port) { struct sk_buff *skb; - int err = -ENOMEM; + int payload = sizeof(struct ifinfomsg) + 128; + int err = -ENOBUFS; pr_debug("bridge notify event=%d\n", event); - skb = alloc_skb(NLMSG_SPACE(sizeof(struct ifinfomsg) + 128), - GFP_ATOMIC); - if (!skb) - goto err_out; + skb = nlmsg_new(nlmsg_total_size(payload), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = br_fill_ifinfo(skb, port, 0, 0, event, 0); + if (err < 0) { + kfree_skb(skb); + goto errout; + } - err = br_fill_ifinfo(skb, port, current->pid, 0, event, 0); + err = rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); +errout: if (err < 0) - goto err_kfree; - - NETLINK_CB(skb).dst_group = RTNLGRP_LINK; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_ATOMIC); - return; - -err_kfree: - kfree_skb(skb); -err_out: - netlink_set_err(rtnl, 0, RTNLGRP_LINK, err); + rtnl_set_sk_err(RTNLGRP_LINK, err); } /* diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 3a13ed64345..3df55b2bd91 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -24,6 +24,7 @@ #include <linux/vmalloc.h> #include <linux/netfilter_bridge/ebtables.h> #include <linux/spinlock.h> +#include <linux/mutex.h> #include <asm/uaccess.h> #include <linux/smp.h> #include <linux/cpumask.h> @@ -31,36 +32,9 @@ /* needed for logical [in,out]-dev filtering */ #include "../br_private.h" -/* list_named_find */ -#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 - * Copyright (C) 1998 by Ori Pomerantz - * Print the string to the appropriate tty, the one - * the current task uses - */ -static void print_string(char *str) -{ - struct tty_struct *my_tty; - - /* The tty for the current task */ - my_tty = current->signal->tty; - if (my_tty != NULL) { - my_tty->driver->write(my_tty, 0, str, strlen(str)); - my_tty->driver->write(my_tty, 0, "\015\012", 2); - } -} - -#define BUGPRINT(args) print_string(args); -#else #define BUGPRINT(format, args...) printk("kernel msg: ebtables bug: please "\ "report to author: "format, ## args) /* #define BUGPRINT(format, args...) */ -#endif #define MEMPRINT(format, args...) printk("kernel msg: ebtables "\ ": out of memory: "format, ## args) /* #define MEMPRINT(format, args...) */ @@ -299,18 +273,22 @@ static inline void * find_inlist_lock_noload(struct list_head *head, const char *name, int *error, struct mutex *mutex) { - void *ret; + struct { + struct list_head list; + char name[EBT_FUNCTION_MAXNAMELEN]; + } *e; *error = mutex_lock_interruptible(mutex); if (*error != 0) return NULL; - ret = list_named_find(head, name); - if (!ret) { - *error = -ENOENT; - mutex_unlock(mutex); + list_for_each_entry(e, head, list) { + if (strcmp(e->name, name) == 0) + return e; } - return ret; + *error = -ENOENT; + mutex_unlock(mutex); + return NULL; } #ifndef CONFIG_KMOD @@ -1064,15 +1042,19 @@ free_newinfo: int ebt_register_target(struct ebt_target *target) { + struct ebt_target *t; int ret; ret = mutex_lock_interruptible(&ebt_mutex); if (ret != 0) return ret; - if (!list_named_insert(&ebt_targets, target)) { - mutex_unlock(&ebt_mutex); - return -EEXIST; + list_for_each_entry(t, &ebt_targets, list) { + if (strcmp(t->name, target->name) == 0) { + mutex_unlock(&ebt_mutex); + return -EEXIST; + } } + list_add(&target->list, &ebt_targets); mutex_unlock(&ebt_mutex); return 0; @@ -1081,21 +1063,25 @@ int ebt_register_target(struct ebt_target *target) void ebt_unregister_target(struct ebt_target *target) { mutex_lock(&ebt_mutex); - LIST_DELETE(&ebt_targets, target); + list_del(&target->list); mutex_unlock(&ebt_mutex); } int ebt_register_match(struct ebt_match *match) { + struct ebt_match *m; int ret; ret = mutex_lock_interruptible(&ebt_mutex); if (ret != 0) return ret; - if (!list_named_insert(&ebt_matches, match)) { - mutex_unlock(&ebt_mutex); - return -EEXIST; + list_for_each_entry(m, &ebt_matches, list) { + if (strcmp(m->name, match->name) == 0) { + mutex_unlock(&ebt_mutex); + return -EEXIST; + } } + list_add(&match->list, &ebt_matches); mutex_unlock(&ebt_mutex); return 0; @@ -1104,21 +1090,25 @@ int ebt_register_match(struct ebt_match *match) void ebt_unregister_match(struct ebt_match *match) { mutex_lock(&ebt_mutex); - LIST_DELETE(&ebt_matches, match); + list_del(&match->list); mutex_unlock(&ebt_mutex); } int ebt_register_watcher(struct ebt_watcher *watcher) { + struct ebt_watcher *w; int ret; ret = mutex_lock_interruptible(&ebt_mutex); if (ret != 0) return ret; - if (!list_named_insert(&ebt_watchers, watcher)) { - mutex_unlock(&ebt_mutex); - return -EEXIST; + list_for_each_entry(w, &ebt_watchers, list) { + if (strcmp(w->name, watcher->name) == 0) { + mutex_unlock(&ebt_mutex); + return -EEXIST; + } } + list_add(&watcher->list, &ebt_watchers); mutex_unlock(&ebt_mutex); return 0; @@ -1127,13 +1117,14 @@ int ebt_register_watcher(struct ebt_watcher *watcher) void ebt_unregister_watcher(struct ebt_watcher *watcher) { mutex_lock(&ebt_mutex); - LIST_DELETE(&ebt_watchers, watcher); + list_del(&watcher->list); mutex_unlock(&ebt_mutex); } int ebt_register_table(struct ebt_table *table) { struct ebt_table_info *newinfo; + struct ebt_table *t; int ret, i, countersize; if (!table || !table->table ||!table->table->entries || @@ -1179,10 +1170,12 @@ int ebt_register_table(struct ebt_table *table) if (ret != 0) goto free_chainstack; - if (list_named_find(&ebt_tables, table->name)) { - ret = -EEXIST; - BUGPRINT("Table name already exists\n"); - goto free_unlock; + list_for_each_entry(t, &ebt_tables, list) { + if (strcmp(t->name, table->name) == 0) { + ret = -EEXIST; + BUGPRINT("Table name already exists\n"); + goto free_unlock; + } } /* Hold a reference count if the chains aren't empty */ @@ -1190,7 +1183,7 @@ int ebt_register_table(struct ebt_table *table) ret = -ENOENT; goto free_unlock; } - list_prepend(&ebt_tables, table); + list_add(&table->list, &ebt_tables); mutex_unlock(&ebt_mutex); return 0; free_unlock: @@ -1216,7 +1209,7 @@ void ebt_unregister_table(struct ebt_table *table) return; } mutex_lock(&ebt_mutex); - LIST_DELETE(&ebt_tables, table); + list_del(&table->list); mutex_unlock(&ebt_mutex); vfree(table->private->entries); if (table->private->chainstack) { @@ -1486,7 +1479,7 @@ static int __init ebtables_init(void) int ret; mutex_lock(&ebt_mutex); - list_named_insert(&ebt_targets, &ebt_standard_target); + list_add(&ebt_standard_target.list, &ebt_targets); mutex_unlock(&ebt_mutex); if ((ret = nf_register_sockopt(&ebt_sockopts)) < 0) return ret; diff --git a/net/core/Makefile b/net/core/Makefile index 2645ba428d4..119568077da 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -17,3 +17,4 @@ obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_WIRELESS_EXT) += wireless.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_NET_DMA) += user_dma.o +obj-$(CONFIG_FIB_RULES) += fib_rules.o diff --git a/net/core/datagram.c b/net/core/datagram.c index aecddcc3040..f558c61aecc 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -417,7 +417,7 @@ unsigned int __skb_checksum_complete(struct sk_buff *skb) sum = (u16)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum)); if (likely(!sum)) { - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -462,7 +462,7 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, goto fault; if ((unsigned short)csum_fold(csum)) goto csum_error; - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); iov->iov_len -= chunk; iov->iov_base += chunk; diff --git a/net/core/dev.c b/net/core/dev.c index d4a1ec3bded..14de297d024 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -640,6 +640,8 @@ int dev_valid_name(const char *name) { if (*name == '\0') return 0; + if (strlen(name) >= IFNAMSIZ) + return 0; if (!strcmp(name, ".") || !strcmp(name, "..")) return 0; @@ -1166,12 +1168,12 @@ EXPORT_SYMBOL(netif_device_attach); * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. */ -int skb_checksum_help(struct sk_buff *skb, int inward) +int skb_checksum_help(struct sk_buff *skb) { unsigned int csum; int ret = 0, offset = skb->h.raw - skb->data; - if (inward) + if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; if (unlikely(skb_shinfo(skb)->gso_size)) { @@ -1223,7 +1225,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) skb->mac_len = skb->nh.raw - skb->data; __skb_pull(skb, skb->mac_len); - if (unlikely(skb->ip_summed != CHECKSUM_HW)) { + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { if (skb_header_cloned(skb) && (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) return ERR_PTR(err); @@ -1232,7 +1234,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) rcu_read_lock(); list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) { if (ptype->type == type && !ptype->dev && ptype->gso_segment) { - if (unlikely(skb->ip_summed != CHECKSUM_HW)) { + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { err = ptype->gso_send_check(skb); segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) @@ -1444,11 +1446,11 @@ int dev_queue_xmit(struct sk_buff *skb) /* If packet is not checksummed and device does not support * checksumming for this protocol, complete checksumming here. */ - if (skb->ip_summed == CHECKSUM_HW && + if (skb->ip_summed == CHECKSUM_PARTIAL && (!(dev->features & NETIF_F_GEN_CSUM) && (!(dev->features & NETIF_F_IP_CSUM) || skb->protocol != htons(ETH_P_IP)))) - if (skb_checksum_help(skb, 0)) + if (skb_checksum_help(skb)) goto out_kfree_skb; gso: @@ -3191,13 +3193,15 @@ struct net_device *alloc_netdev(int sizeof_priv, const char *name, struct net_device *dev; int alloc_size; + BUG_ON(strlen(name) >= sizeof(dev->name)); + /* ensure 32-byte alignment of both the device and private area */ alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST; alloc_size += sizeof_priv + NETDEV_ALIGN_CONST; p = kzalloc(alloc_size, GFP_KERNEL); if (!p) { - printk(KERN_ERR "alloc_dev: Unable to allocate device.\n"); + printk(KERN_ERR "alloc_netdev: Unable to allocate device.\n"); return NULL; } diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index c57d887da2e..b22648d04d3 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -21,8 +21,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> -#include <linux/module.h> +#include <linux/module.h> #include <asm/uaccess.h> #include <asm/system.h> #include <linux/bitops.h> diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c new file mode 100644 index 00000000000..a99d87d82b7 --- /dev/null +++ b/net/core/fib_rules.c @@ -0,0 +1,421 @@ +/* + * net/core/fib_rules.c Generic Routing Rules + * + * 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, version 2. + * + * Authors: Thomas Graf <tgraf@suug.ch> + */ + +#include <linux/config.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <net/fib_rules.h> + +static LIST_HEAD(rules_ops); +static DEFINE_SPINLOCK(rules_mod_lock); + +static void notify_rule_change(int event, struct fib_rule *rule, + struct fib_rules_ops *ops, struct nlmsghdr *nlh, + u32 pid); + +static struct fib_rules_ops *lookup_rules_ops(int family) +{ + struct fib_rules_ops *ops; + + rcu_read_lock(); + list_for_each_entry_rcu(ops, &rules_ops, list) { + if (ops->family == family) { + if (!try_module_get(ops->owner)) + ops = NULL; + rcu_read_unlock(); + return ops; + } + } + rcu_read_unlock(); + + return NULL; +} + +static void rules_ops_put(struct fib_rules_ops *ops) +{ + if (ops) + module_put(ops->owner); +} + +int fib_rules_register(struct fib_rules_ops *ops) +{ + int err = -EEXIST; + struct fib_rules_ops *o; + + if (ops->rule_size < sizeof(struct fib_rule)) + return -EINVAL; + + if (ops->match == NULL || ops->configure == NULL || + ops->compare == NULL || ops->fill == NULL || + ops->action == NULL) + return -EINVAL; + + spin_lock(&rules_mod_lock); + list_for_each_entry(o, &rules_ops, list) + if (ops->family == o->family) + goto errout; + + list_add_tail_rcu(&ops->list, &rules_ops); + err = 0; +errout: + spin_unlock(&rules_mod_lock); + + return err; +} + +EXPORT_SYMBOL_GPL(fib_rules_register); + +static void cleanup_ops(struct fib_rules_ops *ops) +{ + struct fib_rule *rule, *tmp; + + list_for_each_entry_safe(rule, tmp, ops->rules_list, list) { + list_del_rcu(&rule->list); + fib_rule_put(rule); + } +} + +int fib_rules_unregister(struct fib_rules_ops *ops) +{ + int err = 0; + struct fib_rules_ops *o; + + spin_lock(&rules_mod_lock); + list_for_each_entry(o, &rules_ops, list) { + if (o == ops) { + list_del_rcu(&o->list); + cleanup_ops(ops); + goto out; + } + } + + err = -ENOENT; +out: + spin_unlock(&rules_mod_lock); + + synchronize_rcu(); + + return err; +} + +EXPORT_SYMBOL_GPL(fib_rules_unregister); + +int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, + int flags, struct fib_lookup_arg *arg) +{ + struct fib_rule *rule; + int err; + + rcu_read_lock(); + + list_for_each_entry_rcu(rule, ops->rules_list, list) { + if (rule->ifindex && (rule->ifindex != fl->iif)) + continue; + + if (!ops->match(rule, fl, flags)) + continue; + + err = ops->action(rule, fl, flags, arg); + if (err != -EAGAIN) { + fib_rule_get(rule); + arg->rule = rule; + goto out; + } + } + + err = -ENETUNREACH; +out: + rcu_read_unlock(); + + return err; +} + +EXPORT_SYMBOL_GPL(fib_rules_lookup); + +int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +{ + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule, *r, *last = NULL; + struct nlattr *tb[FRA_MAX+1]; + int err = -EINVAL; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + goto errout; + + ops = lookup_rules_ops(frh->family); + if (ops == NULL) { + err = EAFNOSUPPORT; + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy); + if (err < 0) + goto errout; + + rule = kzalloc(ops->rule_size, GFP_KERNEL); + if (rule == NULL) { + err = -ENOMEM; + goto errout; + } + + if (tb[FRA_PRIORITY]) + rule->pref = nla_get_u32(tb[FRA_PRIORITY]); + + if (tb[FRA_IFNAME]) { + struct net_device *dev; + + rule->ifindex = -1; + nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ); + dev = __dev_get_by_name(rule->ifname); + if (dev) + rule->ifindex = dev->ifindex; + } + + rule->action = frh->action; + rule->flags = frh->flags; + rule->table = frh_get_table(frh, tb); + + if (!rule->pref && ops->default_pref) + rule->pref = ops->default_pref(); + + err = ops->configure(rule, skb, nlh, frh, tb); + if (err < 0) + goto errout_free; + + list_for_each_entry(r, ops->rules_list, list) { + if (r->pref > rule->pref) + break; + last = r; + } + + fib_rule_get(rule); + + if (last) + list_add_rcu(&rule->list, &last->list); + else + list_add_rcu(&rule->list, ops->rules_list); + + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid); + rules_ops_put(ops); + return 0; + +errout_free: + kfree(rule); +errout: + rules_ops_put(ops); + return err; +} + +int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +{ + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule; + struct nlattr *tb[FRA_MAX+1]; + int err = -EINVAL; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + goto errout; + + ops = lookup_rules_ops(frh->family); + if (ops == NULL) { + err = EAFNOSUPPORT; + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy); + if (err < 0) + goto errout; + + list_for_each_entry(rule, ops->rules_list, list) { + if (frh->action && (frh->action != rule->action)) + continue; + + if (frh->table && (frh_get_table(frh, tb) != rule->table)) + continue; + + if (tb[FRA_PRIORITY] && + (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) + continue; + + if (tb[FRA_IFNAME] && + nla_strcmp(tb[FRA_IFNAME], rule->ifname)) + continue; + + if (!ops->compare(rule, frh, tb)) + continue; + + if (rule->flags & FIB_RULE_PERMANENT) { + err = -EPERM; + goto errout; + } + + list_del_rcu(&rule->list); + synchronize_rcu(); + notify_rule_change(RTM_DELRULE, rule, ops, nlh, + NETLINK_CB(skb).pid); + fib_rule_put(rule); + rules_ops_put(ops); + return 0; + } + + err = -ENOENT; +errout: + rules_ops_put(ops); + return err; +} + +static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, + u32 pid, u32 seq, int type, int flags, + struct fib_rules_ops *ops) +{ + struct nlmsghdr *nlh; + struct fib_rule_hdr *frh; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); + if (nlh == NULL) + return -1; + + frh = nlmsg_data(nlh); + frh->table = rule->table; + NLA_PUT_U32(skb, FRA_TABLE, rule->table); + frh->res1 = 0; + frh->res2 = 0; + frh->action = rule->action; + frh->flags = rule->flags; + + if (rule->ifname[0]) + NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname); + + if (rule->pref) + NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref); + + if (ops->fill(rule, skb, nlh, frh) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); +} + +int fib_rules_dump(struct sk_buff *skb, struct netlink_callback *cb, int family) +{ + int idx = 0; + struct fib_rule *rule; + struct fib_rules_ops *ops; + + ops = lookup_rules_ops(family); + if (ops == NULL) + return -EAFNOSUPPORT; + + rcu_read_lock(); + list_for_each_entry(rule, ops->rules_list, list) { + if (idx < cb->args[0]) + goto skip; + + if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, RTM_NEWRULE, + NLM_F_MULTI, ops) < 0) + break; +skip: + idx++; + } + rcu_read_unlock(); + cb->args[0] = idx; + rules_ops_put(ops); + + return skb->len; +} + +EXPORT_SYMBOL_GPL(fib_rules_dump); + +static void notify_rule_change(int event, struct fib_rule *rule, + struct fib_rules_ops *ops, struct nlmsghdr *nlh, + u32 pid) +{ + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto errout; + + err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + err = rtnl_notify(skb, pid, ops->nlgroup, nlh, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(ops->nlgroup, err); +} + +static void attach_rules(struct list_head *rules, struct net_device *dev) +{ + struct fib_rule *rule; + + list_for_each_entry(rule, rules, list) { + if (rule->ifindex == -1 && + strcmp(dev->name, rule->ifname) == 0) + rule->ifindex = dev->ifindex; + } +} + +static void detach_rules(struct list_head *rules, struct net_device *dev) +{ + struct fib_rule *rule; + + list_for_each_entry(rule, rules, list) + if (rule->ifindex == dev->ifindex) + rule->ifindex = -1; +} + + +static int fib_rules_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct fib_rules_ops *ops; + + ASSERT_RTNL(); + rcu_read_lock(); + + switch (event) { + case NETDEV_REGISTER: + list_for_each_entry(ops, &rules_ops, list) + attach_rules(ops->rules_list, dev); + break; + + case NETDEV_UNREGISTER: + list_for_each_entry(ops, &rules_ops, list) + detach_rules(ops->rules_list, dev); + break; + } + + rcu_read_unlock(); + + return NOTIFY_DONE; +} + +static struct notifier_block fib_rules_notifier = { + .notifier_call = fib_rules_event, +}; + +static int __init fib_rules_init(void) +{ + return register_netdevice_notifier(&fib_rules_notifier); +} + +subsys_initcall(fib_rules_init); diff --git a/net/core/filter.c b/net/core/filter.c index 5b4486a60cf..6732782a5a4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -422,10 +422,10 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (!err) { struct sk_filter *old_fp; - spin_lock_bh(&sk->sk_lock.slock); - old_fp = sk->sk_filter; - sk->sk_filter = fp; - spin_unlock_bh(&sk->sk_lock.slock); + rcu_read_lock_bh(); + old_fp = rcu_dereference(sk->sk_filter); + rcu_assign_pointer(sk->sk_filter, fp); + rcu_read_unlock_bh(); fp = old_fp; } diff --git a/net/core/flow.c b/net/core/flow.c index 2191af5f26a..f23e7e38654 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -32,7 +32,6 @@ struct flow_cache_entry { u8 dir; struct flowi key; u32 genid; - u32 sk_sid; void *object; atomic_t *object_ref; }; @@ -165,7 +164,7 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2) return 0; } -void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, +void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver) { struct flow_cache_entry *fle, **head; @@ -189,7 +188,6 @@ void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, for (fle = *head; fle; fle = fle->next) { if (fle->family == family && fle->dir == dir && - fle->sk_sid == sk_sid && flow_key_compare(key, &fle->key) == 0) { if (fle->genid == atomic_read(&flow_cache_genid)) { void *ret = fle->object; @@ -214,7 +212,6 @@ void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, *head = fle; fle->family = family; fle->dir = dir; - fle->sk_sid = sk_sid; memcpy(&fle->key, key, sizeof(*key)); fle->object = NULL; flow_count(cpu)++; @@ -226,7 +223,7 @@ nocache: void *obj; atomic_t *obj_ref; - resolver(key, sk_sid, family, dir, &obj, &obj_ref); + resolver(key, family, dir, &obj, &obj_ref); if (fle) { fle->genid = atomic_read(&flow_cache_genid); @@ -346,12 +343,8 @@ static int __init flow_cache_init(void) flow_cachep = kmem_cache_create("flow_cache", sizeof(struct flow_cache_entry), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - - if (!flow_cachep) - panic("NET: failed to allocate flow cache slab\n"); - flow_hash_shift = 10; flow_lwm = 2 * flow_hash_size; flow_hwm = 4 * flow_hash_size; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index fe2113f54e2..b6c69e1463e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -30,6 +30,7 @@ #include <net/dst.h> #include <net/sock.h> #include <net/netevent.h> +#include <net/netlink.h> #include <linux/rtnetlink.h> #include <linux/random.h> #include <linux/string.h> @@ -888,7 +889,7 @@ out_unlock_bh: return rc; } -static __inline__ void neigh_update_hhs(struct neighbour *neigh) +static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, struct net_device*, unsigned char *) = @@ -1338,14 +1339,10 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) neigh_rand_reach_time(tbl->parms.base_reachable_time); if (!tbl->kmem_cachep) - tbl->kmem_cachep = kmem_cache_create(tbl->id, - tbl->entry_size, - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - - if (!tbl->kmem_cachep) - panic("cannot create neighbour cache"); - + tbl->kmem_cachep = + kmem_cache_create(tbl->id, tbl->entry_size, 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, + NULL, NULL); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) panic("cannot create neighbour cache statistics"); @@ -1440,48 +1437,62 @@ int neigh_table_clear(struct neigh_table *tbl) int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct ndmsg *ndm = NLMSG_DATA(nlh); - struct rtattr **nda = arg; + struct ndmsg *ndm; + struct nlattr *dst_attr; struct neigh_table *tbl; struct net_device *dev = NULL; - int err = -ENODEV; + int err = -EINVAL; - if (ndm->ndm_ifindex && - (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL) + if (nlmsg_len(nlh) < sizeof(*ndm)) goto out; + dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST); + if (dst_attr == NULL) + goto out; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex) { + dev = dev_get_by_index(ndm->ndm_ifindex); + if (dev == NULL) { + err = -ENODEV; + goto out; + } + } + read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { - struct rtattr *dst_attr = nda[NDA_DST - 1]; - struct neighbour *n; + struct neighbour *neigh; if (tbl->family != ndm->ndm_family) continue; read_unlock(&neigh_tbl_lock); - err = -EINVAL; - if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len) + if (nla_len(dst_attr) < tbl->key_len) goto out_dev_put; if (ndm->ndm_flags & NTF_PROXY) { - err = pneigh_delete(tbl, RTA_DATA(dst_attr), dev); + err = pneigh_delete(tbl, nla_data(dst_attr), dev); goto out_dev_put; } - if (!dev) - goto out; + if (dev == NULL) + goto out_dev_put; - n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev); - if (n) { - err = neigh_update(n, NULL, NUD_FAILED, - NEIGH_UPDATE_F_OVERRIDE| - NEIGH_UPDATE_F_ADMIN); - neigh_release(n); + neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); + if (neigh == NULL) { + err = -ENOENT; + goto out_dev_put; } + + err = neigh_update(neigh, NULL, NUD_FAILED, + NEIGH_UPDATE_F_OVERRIDE | + NEIGH_UPDATE_F_ADMIN); + neigh_release(neigh); goto out_dev_put; } read_unlock(&neigh_tbl_lock); - err = -EADDRNOTAVAIL; + err = -EAFNOSUPPORT; + out_dev_put: if (dev) dev_put(dev); @@ -1491,76 +1502,93 @@ out: int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct ndmsg *ndm = NLMSG_DATA(nlh); - struct rtattr **nda = arg; + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; struct neigh_table *tbl; struct net_device *dev = NULL; - int err = -ENODEV; + int err; - if (ndm->ndm_ifindex && - (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL) + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) goto out; + err = -EINVAL; + if (tb[NDA_DST] == NULL) + goto out; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex) { + dev = dev_get_by_index(ndm->ndm_ifindex); + if (dev == NULL) { + err = -ENODEV; + goto out; + } + + if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) + goto out_dev_put; + } + read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { - struct rtattr *lladdr_attr = nda[NDA_LLADDR - 1]; - struct rtattr *dst_attr = nda[NDA_DST - 1]; - int override = 1; - struct neighbour *n; + int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE; + struct neighbour *neigh; + void *dst, *lladdr; if (tbl->family != ndm->ndm_family) continue; read_unlock(&neigh_tbl_lock); - err = -EINVAL; - if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len) + if (nla_len(tb[NDA_DST]) < tbl->key_len) goto out_dev_put; + dst = nla_data(tb[NDA_DST]); + lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; if (ndm->ndm_flags & NTF_PROXY) { + struct pneigh_entry *pn; + err = -ENOBUFS; - if (pneigh_lookup(tbl, RTA_DATA(dst_attr), dev, 1)) + pn = pneigh_lookup(tbl, dst, dev, 1); + if (pn) { + pn->flags = ndm->ndm_flags; err = 0; + } goto out_dev_put; } - err = -EINVAL; - if (!dev) - goto out; - if (lladdr_attr && RTA_PAYLOAD(lladdr_attr) < dev->addr_len) + if (dev == NULL) goto out_dev_put; + + neigh = neigh_lookup(tbl, dst, dev); + if (neigh == NULL) { + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { + err = -ENOENT; + goto out_dev_put; + } - n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev); - if (n) { - if (nlh->nlmsg_flags & NLM_F_EXCL) { - err = -EEXIST; - neigh_release(n); + neigh = __neigh_lookup_errno(tbl, dst, dev); + if (IS_ERR(neigh)) { + err = PTR_ERR(neigh); goto out_dev_put; } - - override = nlh->nlmsg_flags & NLM_F_REPLACE; - } else if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { - err = -ENOENT; - goto out_dev_put; } else { - n = __neigh_lookup_errno(tbl, RTA_DATA(dst_attr), dev); - if (IS_ERR(n)) { - err = PTR_ERR(n); + if (nlh->nlmsg_flags & NLM_F_EXCL) { + err = -EEXIST; + neigh_release(neigh); goto out_dev_put; } - } - err = neigh_update(n, - lladdr_attr ? RTA_DATA(lladdr_attr) : NULL, - ndm->ndm_state, - (override ? NEIGH_UPDATE_F_OVERRIDE : 0) | - NEIGH_UPDATE_F_ADMIN); + if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) + flags &= ~NEIGH_UPDATE_F_OVERRIDE; + } - neigh_release(n); + err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); + neigh_release(neigh); goto out_dev_put; } read_unlock(&neigh_tbl_lock); - err = -EADDRNOTAVAIL; + err = -EAFNOSUPPORT; + out_dev_put: if (dev) dev_put(dev); @@ -1570,56 +1598,59 @@ out: static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) { - struct rtattr *nest = NULL; - - nest = RTA_NEST(skb, NDTA_PARMS); + struct nlattr *nest; + + nest = nla_nest_start(skb, NDTA_PARMS); + if (nest == NULL) + return -ENOBUFS; if (parms->dev) - RTA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); - - RTA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); - RTA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); - RTA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); - RTA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); - RTA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); - RTA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); - RTA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); - RTA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, + NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); + + NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); + NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); + NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); + NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); + NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); + NLA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); + NLA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); + NLA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, parms->base_reachable_time); - RTA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); - RTA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); - RTA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); - RTA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); - RTA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); - RTA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); + NLA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); + NLA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); + NLA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); + NLA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); + NLA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); + NLA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); - return RTA_NEST_END(skb, nest); + return nla_nest_end(skb, nest); -rtattr_failure: - return RTA_NEST_CANCEL(skb, nest); +nla_put_failure: + return nla_nest_cancel(skb, nest); } -static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, - struct netlink_callback *cb) +static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, + u32 pid, u32 seq, int type, int flags) { struct nlmsghdr *nlh; struct ndtmsg *ndtmsg; - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), - NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); + if (nlh == NULL) + return -ENOBUFS; - ndtmsg = NLMSG_DATA(nlh); + ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); - RTA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); - RTA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); - RTA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); - RTA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); + NLA_PUT_STRING(skb, NDTA_NAME, tbl->id); + NLA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); + NLA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); + NLA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); + NLA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); { unsigned long now = jiffies; @@ -1638,7 +1669,7 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, .ndtc_proxy_qlen = tbl->proxy_queue.qlen, }; - RTA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); + NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); } { @@ -1663,55 +1694,50 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, ndst.ndts_forced_gc_runs += st->forced_gc_runs; } - RTA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); + NLA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); } BUG_ON(tbl->parms.dev); if (neightbl_fill_parms(skb, &tbl->parms) < 0) - goto rtattr_failure; + goto nla_put_failure; read_unlock_bh(&tbl->lock); - return NLMSG_END(skb, nlh); + return nlmsg_end(skb, nlh); -rtattr_failure: +nla_put_failure: read_unlock_bh(&tbl->lock); - return NLMSG_CANCEL(skb, nlh); - -nlmsg_failure: - return -1; + return nlmsg_cancel(skb, nlh); } -static int neightbl_fill_param_info(struct neigh_table *tbl, +static int neightbl_fill_param_info(struct sk_buff *skb, + struct neigh_table *tbl, struct neigh_parms *parms, - struct sk_buff *skb, - struct netlink_callback *cb) + u32 pid, u32 seq, int type, + unsigned int flags) { struct ndtmsg *ndtmsg; struct nlmsghdr *nlh; - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), - NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); + if (nlh == NULL) + return -ENOBUFS; - ndtmsg = NLMSG_DATA(nlh); + ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); - if (neightbl_fill_parms(skb, parms) < 0) - goto rtattr_failure; + if (nla_put_string(skb, NDTA_NAME, tbl->id) < 0 || + neightbl_fill_parms(skb, parms) < 0) + goto errout; read_unlock_bh(&tbl->lock); - return NLMSG_END(skb, nlh); - -rtattr_failure: + return nlmsg_end(skb, nlh); +errout: read_unlock_bh(&tbl->lock); - return NLMSG_CANCEL(skb, nlh); - -nlmsg_failure: - return -1; + return nlmsg_cancel(skb, nlh); } static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, @@ -1727,28 +1753,61 @@ static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, return NULL; } +static struct nla_policy nl_neightbl_policy[NDTA_MAX+1] __read_mostly = { + [NDTA_NAME] = { .type = NLA_STRING }, + [NDTA_THRESH1] = { .type = NLA_U32 }, + [NDTA_THRESH2] = { .type = NLA_U32 }, + [NDTA_THRESH3] = { .type = NLA_U32 }, + [NDTA_GC_INTERVAL] = { .type = NLA_U64 }, + [NDTA_PARMS] = { .type = NLA_NESTED }, +}; + +static struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] __read_mostly = { + [NDTPA_IFINDEX] = { .type = NLA_U32 }, + [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, + [NDTPA_PROXY_QLEN] = { .type = NLA_U32 }, + [NDTPA_APP_PROBES] = { .type = NLA_U32 }, + [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_MCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 }, + [NDTPA_GC_STALETIME] = { .type = NLA_U64 }, + [NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 }, + [NDTPA_RETRANS_TIME] = { .type = NLA_U64 }, + [NDTPA_ANYCAST_DELAY] = { .type = NLA_U64 }, + [NDTPA_PROXY_DELAY] = { .type = NLA_U64 }, + [NDTPA_LOCKTIME] = { .type = NLA_U64 }, +}; + int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct neigh_table *tbl; - struct ndtmsg *ndtmsg = NLMSG_DATA(nlh); - struct rtattr **tb = arg; - int err = -EINVAL; + struct ndtmsg *ndtmsg; + struct nlattr *tb[NDTA_MAX+1]; + int err; - if (!tb[NDTA_NAME - 1] || !RTA_PAYLOAD(tb[NDTA_NAME - 1])) - return -EINVAL; + err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX, + nl_neightbl_policy); + if (err < 0) + goto errout; + + if (tb[NDTA_NAME] == NULL) { + err = -EINVAL; + goto errout; + } + ndtmsg = nlmsg_data(nlh); read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) continue; - if (!rtattr_strcmp(tb[NDTA_NAME - 1], tbl->id)) + if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) break; } if (tbl == NULL) { err = -ENOENT; - goto errout; + goto errout_locked; } /* @@ -1757,165 +1816,178 @@ int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) */ write_lock_bh(&tbl->lock); - if (tb[NDTA_THRESH1 - 1]) - tbl->gc_thresh1 = RTA_GET_U32(tb[NDTA_THRESH1 - 1]); - - if (tb[NDTA_THRESH2 - 1]) - tbl->gc_thresh2 = RTA_GET_U32(tb[NDTA_THRESH2 - 1]); - - if (tb[NDTA_THRESH3 - 1]) - tbl->gc_thresh3 = RTA_GET_U32(tb[NDTA_THRESH3 - 1]); - - if (tb[NDTA_GC_INTERVAL - 1]) - tbl->gc_interval = RTA_GET_MSECS(tb[NDTA_GC_INTERVAL - 1]); - - if (tb[NDTA_PARMS - 1]) { - struct rtattr *tbp[NDTPA_MAX]; + if (tb[NDTA_PARMS]) { + struct nlattr *tbp[NDTPA_MAX+1]; struct neigh_parms *p; - u32 ifindex = 0; + int i, ifindex = 0; - if (rtattr_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS - 1]) < 0) - goto rtattr_failure; + err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS], + nl_ntbl_parm_policy); + if (err < 0) + goto errout_tbl_lock; - if (tbp[NDTPA_IFINDEX - 1]) - ifindex = RTA_GET_U32(tbp[NDTPA_IFINDEX - 1]); + if (tbp[NDTPA_IFINDEX]) + ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]); p = lookup_neigh_params(tbl, ifindex); if (p == NULL) { err = -ENOENT; - goto rtattr_failure; + goto errout_tbl_lock; } - - if (tbp[NDTPA_QUEUE_LEN - 1]) - p->queue_len = RTA_GET_U32(tbp[NDTPA_QUEUE_LEN - 1]); - - if (tbp[NDTPA_PROXY_QLEN - 1]) - p->proxy_qlen = RTA_GET_U32(tbp[NDTPA_PROXY_QLEN - 1]); - - if (tbp[NDTPA_APP_PROBES - 1]) - p->app_probes = RTA_GET_U32(tbp[NDTPA_APP_PROBES - 1]); - if (tbp[NDTPA_UCAST_PROBES - 1]) - p->ucast_probes = - RTA_GET_U32(tbp[NDTPA_UCAST_PROBES - 1]); - - if (tbp[NDTPA_MCAST_PROBES - 1]) - p->mcast_probes = - RTA_GET_U32(tbp[NDTPA_MCAST_PROBES - 1]); - - if (tbp[NDTPA_BASE_REACHABLE_TIME - 1]) - p->base_reachable_time = - RTA_GET_MSECS(tbp[NDTPA_BASE_REACHABLE_TIME - 1]); - - if (tbp[NDTPA_GC_STALETIME - 1]) - p->gc_staletime = - RTA_GET_MSECS(tbp[NDTPA_GC_STALETIME - 1]); + for (i = 1; i <= NDTPA_MAX; i++) { + if (tbp[i] == NULL) + continue; - if (tbp[NDTPA_DELAY_PROBE_TIME - 1]) - p->delay_probe_time = - RTA_GET_MSECS(tbp[NDTPA_DELAY_PROBE_TIME - 1]); + switch (i) { + case NDTPA_QUEUE_LEN: + p->queue_len = nla_get_u32(tbp[i]); + break; + case NDTPA_PROXY_QLEN: + p->proxy_qlen = nla_get_u32(tbp[i]); + break; + case NDTPA_APP_PROBES: + p->app_probes = nla_get_u32(tbp[i]); + break; + case NDTPA_UCAST_PROBES: + p->ucast_probes = nla_get_u32(tbp[i]); + break; + case NDTPA_MCAST_PROBES: + p->mcast_probes = nla_get_u32(tbp[i]); + break; + case NDTPA_BASE_REACHABLE_TIME: + p->base_reachable_time = nla_get_msecs(tbp[i]); + break; + case NDTPA_GC_STALETIME: + p->gc_staletime = nla_get_msecs(tbp[i]); + break; + case NDTPA_DELAY_PROBE_TIME: + p->delay_probe_time = nla_get_msecs(tbp[i]); + break; + case NDTPA_RETRANS_TIME: + p->retrans_time = nla_get_msecs(tbp[i]); + break; + case NDTPA_ANYCAST_DELAY: + p->anycast_delay = nla_get_msecs(tbp[i]); + break; + case NDTPA_PROXY_DELAY: + p->proxy_delay = nla_get_msecs(tbp[i]); + break; + case NDTPA_LOCKTIME: + p->locktime = nla_get_msecs(tbp[i]); + break; + } + } + } - if (tbp[NDTPA_RETRANS_TIME - 1]) - p->retrans_time = - RTA_GET_MSECS(tbp[NDTPA_RETRANS_TIME - 1]); + if (tb[NDTA_THRESH1]) + tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]); - if (tbp[NDTPA_ANYCAST_DELAY - 1]) - p->anycast_delay = - RTA_GET_MSECS(tbp[NDTPA_ANYCAST_DELAY - 1]); + if (tb[NDTA_THRESH2]) + tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]); - if (tbp[NDTPA_PROXY_DELAY - 1]) - p->proxy_delay = - RTA_GET_MSECS(tbp[NDTPA_PROXY_DELAY - 1]); + if (tb[NDTA_THRESH3]) + tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]); - if (tbp[NDTPA_LOCKTIME - 1]) - p->locktime = RTA_GET_MSECS(tbp[NDTPA_LOCKTIME - 1]); - } + if (tb[NDTA_GC_INTERVAL]) + tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]); err = 0; -rtattr_failure: +errout_tbl_lock: write_unlock_bh(&tbl->lock); -errout: +errout_locked: read_unlock(&neigh_tbl_lock); +errout: return err; } int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { - int idx, family; - int s_idx = cb->args[0]; + int family, tidx, nidx = 0; + int tbl_skip = cb->args[0]; + int neigh_skip = cb->args[1]; struct neigh_table *tbl; - family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; read_lock(&neigh_tbl_lock); - for (tbl = neigh_tables, idx = 0; tbl; tbl = tbl->next) { + for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) { struct neigh_parms *p; - if (idx < s_idx || (family && tbl->family != family)) + if (tidx < tbl_skip || (family && tbl->family != family)) continue; - if (neightbl_fill_info(tbl, skb, cb) <= 0) + if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, + NLM_F_MULTI) <= 0) break; - for (++idx, p = tbl->parms.next; p; p = p->next, idx++) { - if (idx < s_idx) + for (nidx = 0, p = tbl->parms.next; p; p = p->next, nidx++) { + if (nidx < neigh_skip) continue; - if (neightbl_fill_param_info(tbl, p, skb, cb) <= 0) + if (neightbl_fill_param_info(skb, tbl, p, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGHTBL, + NLM_F_MULTI) <= 0) goto out; } + neigh_skip = 0; } out: read_unlock(&neigh_tbl_lock); - cb->args[0] = idx; + cb->args[0] = tidx; + cb->args[1] = nidx; return skb->len; } -static int neigh_fill_info(struct sk_buff *skb, struct neighbour *n, - u32 pid, u32 seq, int event, unsigned int flags) +static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, + u32 pid, u32 seq, int type, unsigned int flags) { unsigned long now = jiffies; - unsigned char *b = skb->tail; struct nda_cacheinfo ci; - int locked = 0; - u32 probes; - struct nlmsghdr *nlh = NLMSG_NEW(skb, pid, seq, event, - sizeof(struct ndmsg), flags); - struct ndmsg *ndm = NLMSG_DATA(nlh); + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -ENOBUFS; - ndm->ndm_family = n->ops->family; + ndm = nlmsg_data(nlh); + ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = n->flags; - ndm->ndm_type = n->type; - ndm->ndm_ifindex = n->dev->ifindex; - RTA_PUT(skb, NDA_DST, n->tbl->key_len, n->primary_key); - read_lock_bh(&n->lock); - locked = 1; - ndm->ndm_state = n->nud_state; - if (n->nud_state & NUD_VALID) - RTA_PUT(skb, NDA_LLADDR, n->dev->addr_len, n->ha); - ci.ndm_used = now - n->used; - ci.ndm_confirmed = now - n->confirmed; - ci.ndm_updated = now - n->updated; - ci.ndm_refcnt = atomic_read(&n->refcnt) - 1; - probes = atomic_read(&n->probes); - read_unlock_bh(&n->lock); - locked = 0; - RTA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); - RTA_PUT(skb, NDA_PROBES, sizeof(probes), &probes); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + ndm->ndm_flags = neigh->flags; + ndm->ndm_type = neigh->type; + ndm->ndm_ifindex = neigh->dev->ifindex; + + NLA_PUT(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key); -nlmsg_failure: -rtattr_failure: - if (locked) - read_unlock_bh(&n->lock); - skb_trim(skb, b - skb->data); - return -1; + read_lock_bh(&neigh->lock); + ndm->ndm_state = neigh->nud_state; + if ((neigh->nud_state & NUD_VALID) && + nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, neigh->ha) < 0) { + read_unlock_bh(&neigh->lock); + goto nla_put_failure; + } + + ci.ndm_used = now - neigh->used; + ci.ndm_confirmed = now - neigh->confirmed; + ci.ndm_updated = now - neigh->updated; + ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; + read_unlock_bh(&neigh->lock); + + NLA_PUT_U32(skb, NDA_PROBES, atomic_read(&neigh->probes)); + NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); } @@ -1959,7 +2031,7 @@ int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) int t, family, s_t; read_lock(&neigh_tbl_lock); - family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; s_t = cb->args[0]; for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) { @@ -2338,41 +2410,35 @@ static struct file_operations neigh_stat_seq_fops = { #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_ARPD -void neigh_app_ns(struct neighbour *n) +static void __neigh_notify(struct neighbour *n, int type, int flags) { - struct nlmsghdr *nlh; - int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256); - struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC); + struct sk_buff *skb; + int err = -ENOBUFS; - if (!skb) - return; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + if (skb == NULL) + goto errout; - if (neigh_fill_info(skb, n, 0, 0, RTM_GETNEIGH, 0) < 0) { + err = neigh_fill_info(skb, n, 0, 0, type, flags); + if (err < 0) { kfree_skb(skb); - return; + goto errout; } - nlh = (struct nlmsghdr *)skb->data; - nlh->nlmsg_flags = NLM_F_REQUEST; - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); + + err = rtnl_notify(skb, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_NEIGH, err); } -static void neigh_app_notify(struct neighbour *n) +void neigh_app_ns(struct neighbour *n) { - struct nlmsghdr *nlh; - int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256); - struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC); - - if (!skb) - return; + __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST); +} - if (neigh_fill_info(skb, n, 0, 0, RTM_NEWNEIGH, 0) < 0) { - kfree_skb(skb); - return; - } - nlh = (struct nlmsghdr *)skb->data; - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); +static void neigh_app_notify(struct neighbour *n) +{ + __neigh_notify(n, RTM_NEWNEIGH, 0); } #endif /* CONFIG_ARPD */ @@ -2386,7 +2452,7 @@ static struct neigh_sysctl_table { ctl_table neigh_neigh_dir[2]; ctl_table neigh_proto_dir[2]; ctl_table neigh_root_dir[2]; -} neigh_sysctl_template = { +} neigh_sysctl_template __read_mostly = { .neigh_vars = { { .ctl_name = NET_NEIGH_MCAST_SOLICIT, @@ -2659,7 +2725,6 @@ void neigh_sysctl_unregister(struct neigh_parms *p) #endif /* CONFIG_SYSCTL */ EXPORT_SYMBOL(__neigh_event_send); -EXPORT_SYMBOL(neigh_add); EXPORT_SYMBOL(neigh_changeaddr); EXPORT_SYMBOL(neigh_compat_output); EXPORT_SYMBOL(neigh_connected_output); @@ -2679,11 +2744,8 @@ EXPORT_SYMBOL(neigh_table_clear); EXPORT_SYMBOL(neigh_table_init); EXPORT_SYMBOL(neigh_table_init_no_netlink); EXPORT_SYMBOL(neigh_update); -EXPORT_SYMBOL(neigh_update_hhs); EXPORT_SYMBOL(pneigh_enqueue); EXPORT_SYMBOL(pneigh_lookup); -EXPORT_SYMBOL(neightbl_dump_info); -EXPORT_SYMBOL(neightbl_set); #ifdef CONFIG_ARPD EXPORT_SYMBOL(neigh_app_ns); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 471da451cd4..ead5920c26d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -110,7 +110,7 @@ static int checksum_udp(struct sk_buff *skb, struct udphdr *uh, psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); - if (skb->ip_summed == CHECKSUM_HW && + if (skb->ip_summed == CHECKSUM_COMPLETE && !(u16)csum_fold(csum_add(psum, skb->csum))) return 0; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6a7320b39ed..72145d4a260 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1786,7 +1786,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) * use ipv6_get_lladdr if/when it's get exported */ - read_lock(&addrconf_lock); + rcu_read_lock(); if ((idev = __in6_dev_get(pkt_dev->odev)) != NULL) { struct inet6_ifaddr *ifp; @@ -1805,7 +1805,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); if (err) printk("pktgen: ERROR: IPv6 link address not availble.\n"); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 30cc1ba6ed5..d8e25e08cb7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -35,6 +35,7 @@ #include <linux/init.h> #include <linux/security.h> #include <linux/mutex.h> +#include <linux/if_addr.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -49,6 +50,7 @@ #include <net/udp.h> #include <net/sock.h> #include <net/pkt_sched.h> +#include <net/fib_rules.h> #include <net/netlink.h> #ifdef CONFIG_NET_WIRELESS_RTNETLINK #include <linux/wireless.h> @@ -56,6 +58,7 @@ #endif /* CONFIG_NET_WIRELESS_RTNETLINK */ static DEFINE_MUTEX(rtnl_mutex); +static struct sock *rtnl; void rtnl_lock(void) { @@ -93,8 +96,6 @@ int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len) return 0; } -struct sock *rtnl; - struct rtnetlink_link * rtnetlink_links[NPROTO]; static const int rtm_min[RTM_NR_FAMILIES] = @@ -102,8 +103,7 @@ static const int rtm_min[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)), [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)), [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), - [RTM_FAM(RTM_NEWNEIGH)] = NLMSG_LENGTH(sizeof(struct ndmsg)), - [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), + [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)), [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)), [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)), [RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)), @@ -111,7 +111,6 @@ static const int rtm_min[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWPREFIX)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), - [RTM_FAM(RTM_NEWNEIGHTBL)] = NLMSG_LENGTH(sizeof(struct ndtmsg)), }; static const int rta_max[RTM_NR_FAMILIES] = @@ -119,13 +118,11 @@ static const int rta_max[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWLINK)] = IFLA_MAX, [RTM_FAM(RTM_NEWADDR)] = IFA_MAX, [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX, - [RTM_FAM(RTM_NEWNEIGH)] = NDA_MAX, - [RTM_FAM(RTM_NEWRULE)] = RTA_MAX, + [RTM_FAM(RTM_NEWRULE)] = FRA_MAX, [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX, [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, - [RTM_FAM(RTM_NEWNEIGHTBL)] = NDTA_MAX, }; void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) @@ -168,24 +165,52 @@ int rtnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo) return err; } +int rtnl_unicast(struct sk_buff *skb, u32 pid) +{ + return nlmsg_unicast(rtnl, skb, pid); +} + +int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group, + struct nlmsghdr *nlh, gfp_t flags) +{ + int report = 0; + + if (nlh) + report = nlmsg_report(nlh); + + return nlmsg_notify(rtnl, skb, pid, group, report, flags); +} + +void rtnl_set_sk_err(u32 group, int error) +{ + netlink_set_err(rtnl, 0, group, error); +} + int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) { - struct rtattr *mx = (struct rtattr*)skb->tail; - int i; + struct nlattr *mx; + int i, valid = 0; + + mx = nla_nest_start(skb, RTA_METRICS); + if (mx == NULL) + return -ENOBUFS; + + for (i = 0; i < RTAX_MAX; i++) { + if (metrics[i]) { + valid++; + NLA_PUT_U32(skb, i+1, metrics[i]); + } + } - RTA_PUT(skb, RTA_METRICS, 0, NULL); - for (i=0; i<RTAX_MAX; i++) { - if (metrics[i]) - RTA_PUT(skb, i+1, sizeof(u32), metrics+i); + if (!valid) { + nla_nest_cancel(skb, mx); + return 0; } - mx->rta_len = skb->tail - (u8*)mx; - if (mx->rta_len == RTA_LENGTH(0)) - skb_trim(skb, (u8*)mx - skb->data); - return 0; -rtattr_failure: - skb_trim(skb, (u8*)mx - skb->data); - return -1; + return nla_nest_end(skb, mx); + +nla_put_failure: + return nla_nest_cancel(skb, mx); } @@ -216,41 +241,73 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } -static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, - int type, u32 pid, u32 seq, u32 change, - unsigned int flags) +static void copy_rtnl_link_stats(struct rtnl_link_stats *a, + struct net_device_stats *b) { - struct ifinfomsg *r; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - - nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*r), flags); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev_get_flags(dev); - r->ifi_change = change; - - RTA_PUT(skb, IFLA_IFNAME, strlen(dev->name)+1, dev->name); - - if (1) { - u32 txqlen = dev->tx_queue_len; - RTA_PUT(skb, IFLA_TXQLEN, sizeof(txqlen), &txqlen); - } + a->rx_packets = b->rx_packets; + a->tx_packets = b->tx_packets; + a->rx_bytes = b->rx_bytes; + a->tx_bytes = b->tx_bytes; + a->rx_errors = b->rx_errors; + a->tx_errors = b->tx_errors; + a->rx_dropped = b->rx_dropped; + a->tx_dropped = b->tx_dropped; + + a->multicast = b->multicast; + a->collisions = b->collisions; + + a->rx_length_errors = b->rx_length_errors; + a->rx_over_errors = b->rx_over_errors; + a->rx_crc_errors = b->rx_crc_errors; + a->rx_frame_errors = b->rx_frame_errors; + a->rx_fifo_errors = b->rx_fifo_errors; + a->rx_missed_errors = b->rx_missed_errors; + + a->tx_aborted_errors = b->tx_aborted_errors; + a->tx_carrier_errors = b->tx_carrier_errors; + a->tx_fifo_errors = b->tx_fifo_errors; + a->tx_heartbeat_errors = b->tx_heartbeat_errors; + a->tx_window_errors = b->tx_window_errors; + + a->rx_compressed = b->rx_compressed; + a->tx_compressed = b->tx_compressed; +}; - if (1) { - u32 weight = dev->weight; - RTA_PUT(skb, IFLA_WEIGHT, sizeof(weight), &weight); - } +static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, + void *iwbuf, int iwbuflen, int type, u32 pid, + u32 seq, u32 change, unsigned int flags) +{ + struct ifinfomsg *ifm; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); + if (nlh == NULL) + return -ENOBUFS; + + ifm = nlmsg_data(nlh); + ifm->ifi_family = AF_UNSPEC; + ifm->__ifi_pad = 0; + ifm->ifi_type = dev->type; + ifm->ifi_index = dev->ifindex; + ifm->ifi_flags = dev_get_flags(dev); + ifm->ifi_change = change; + + NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); + NLA_PUT_U32(skb, IFLA_TXQLEN, dev->tx_queue_len); + NLA_PUT_U32(skb, IFLA_WEIGHT, dev->weight); + NLA_PUT_U8(skb, IFLA_OPERSTATE, + netif_running(dev) ? dev->operstate : IF_OPER_DOWN); + NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode); + NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); + + if (dev->ifindex != dev->iflink) + NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); + + if (dev->master) + NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex); - 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 (dev->qdisc_sleeping) + NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc_sleeping->ops->id); if (1) { struct rtnl_link_ifmap map = { @@ -261,58 +318,38 @@ static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, .dma = dev->dma, .port = dev->if_port, }; - RTA_PUT(skb, IFLA_MAP, sizeof(map), &map); + NLA_PUT(skb, IFLA_MAP, sizeof(map), &map); } if (dev->addr_len) { - RTA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - RTA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast); - } - - if (1) { - u32 mtu = dev->mtu; - RTA_PUT(skb, IFLA_MTU, sizeof(mtu), &mtu); - } - - if (dev->ifindex != dev->iflink) { - u32 iflink = dev->iflink; - RTA_PUT(skb, IFLA_LINK, sizeof(iflink), &iflink); - } - - if (dev->qdisc_sleeping) - RTA_PUT(skb, IFLA_QDISC, - strlen(dev->qdisc_sleeping->ops->id) + 1, - dev->qdisc_sleeping->ops->id); - - if (dev->master) { - u32 master = dev->master->ifindex; - RTA_PUT(skb, IFLA_MASTER, sizeof(master), &master); + NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); + NLA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast); } if (dev->get_stats) { - unsigned long *stats = (unsigned long*)dev->get_stats(dev); + struct net_device_stats *stats = dev->get_stats(dev); if (stats) { - struct rtattr *a; - __u32 *s; - int i; - int n = sizeof(struct rtnl_link_stats)/4; - - a = __RTA_PUT(skb, IFLA_STATS, n*4); - s = RTA_DATA(a); - for (i=0; i<n; i++) - s[i] = stats[i]; + struct nlattr *attr; + + attr = nla_reserve(skb, IFLA_STATS, + sizeof(struct rtnl_link_stats)); + if (attr == NULL) + goto nla_put_failure; + + copy_rtnl_link_stats(nla_data(attr), stats); } } - nlh->nlmsg_len = skb->tail - b; - return skb->len; -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + if (iwbuf) + NLA_PUT(skb, IFLA_WIRELESS, iwbuflen, iwbuf); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); } -static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) +static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->args[0]; @@ -322,10 +359,9 @@ static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *c for (dev=dev_base, idx=0; dev; dev = dev->next, idx++) { if (idx < s_idx) continue; - if (rtnetlink_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI) <= 0) + if (rtnl_fill_ifinfo(skb, dev, NULL, 0, RTM_NEWLINK, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0) break; } read_unlock(&dev_base_lock); @@ -334,52 +370,70 @@ static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *c return skb->len; } -static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static struct nla_policy ifla_policy[IFLA_MAX+1] __read_mostly = { + [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 }, + [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) }, + [IFLA_MTU] = { .type = NLA_U32 }, + [IFLA_TXQLEN] = { .type = NLA_U32 }, + [IFLA_WEIGHT] = { .type = NLA_U32 }, + [IFLA_OPERSTATE] = { .type = NLA_U8 }, + [IFLA_LINKMODE] = { .type = NLA_U8 }, +}; + +static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct ifinfomsg *ifm = NLMSG_DATA(nlh); - struct rtattr **ida = arg; + struct ifinfomsg *ifm; struct net_device *dev; - int err, send_addr_notify = 0; + int err, send_addr_notify = 0, modified = 0; + struct nlattr *tb[IFLA_MAX+1]; + char ifname[IFNAMSIZ]; + + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + goto errout; + + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + else + ifname[0] = '\0'; + err = -EINVAL; + ifm = nlmsg_data(nlh); if (ifm->ifi_index >= 0) dev = dev_get_by_index(ifm->ifi_index); - else if (ida[IFLA_IFNAME - 1]) { - char ifname[IFNAMSIZ]; - - if (rtattr_strlcpy(ifname, ida[IFLA_IFNAME - 1], - IFNAMSIZ) >= IFNAMSIZ) - return -EINVAL; + else if (tb[IFLA_IFNAME]) dev = dev_get_by_name(ifname); - } else - return -EINVAL; + else + goto errout; - if (!dev) - return -ENODEV; + if (dev == NULL) { + err = -ENODEV; + goto errout; + } - err = -EINVAL; + if (tb[IFLA_ADDRESS] && + nla_len(tb[IFLA_ADDRESS]) < dev->addr_len) + goto errout_dev; - if (ifm->ifi_flags) - dev_change_flags(dev, ifm->ifi_flags); + if (tb[IFLA_BROADCAST] && + nla_len(tb[IFLA_BROADCAST]) < dev->addr_len) + goto errout_dev; - if (ida[IFLA_MAP - 1]) { + if (tb[IFLA_MAP]) { struct rtnl_link_ifmap *u_map; struct ifmap k_map; if (!dev->set_config) { err = -EOPNOTSUPP; - goto out; + goto errout_dev; } if (!netif_device_present(dev)) { err = -ENODEV; - goto out; + goto errout_dev; } - - if (ida[IFLA_MAP - 1]->rta_len != RTA_LENGTH(sizeof(*u_map))) - goto out; - - u_map = RTA_DATA(ida[IFLA_MAP - 1]); + u_map = nla_data(tb[IFLA_MAP]); k_map.mem_start = (unsigned long) u_map->mem_start; k_map.mem_end = (unsigned long) u_map->mem_end; k_map.base_addr = (unsigned short) u_map->base_addr; @@ -388,200 +442,175 @@ static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) k_map.port = (unsigned char) u_map->port; err = dev->set_config(dev, &k_map); + if (err < 0) + goto errout_dev; - if (err) - goto out; + modified = 1; } - if (ida[IFLA_ADDRESS - 1]) { + if (tb[IFLA_ADDRESS]) { struct sockaddr *sa; int len; if (!dev->set_mac_address) { err = -EOPNOTSUPP; - goto out; + goto errout_dev; } + if (!netif_device_present(dev)) { err = -ENODEV; - goto out; + goto errout_dev; } - if (ida[IFLA_ADDRESS - 1]->rta_len != RTA_LENGTH(dev->addr_len)) - goto out; len = sizeof(sa_family_t) + dev->addr_len; sa = kmalloc(len, GFP_KERNEL); if (!sa) { err = -ENOMEM; - goto out; + goto errout_dev; } sa->sa_family = dev->type; - memcpy(sa->sa_data, RTA_DATA(ida[IFLA_ADDRESS - 1]), + memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), dev->addr_len); err = dev->set_mac_address(dev, sa); kfree(sa); if (err) - goto out; + goto errout_dev; send_addr_notify = 1; + modified = 1; } - if (ida[IFLA_BROADCAST - 1]) { - if (ida[IFLA_BROADCAST - 1]->rta_len != RTA_LENGTH(dev->addr_len)) - goto out; - memcpy(dev->broadcast, RTA_DATA(ida[IFLA_BROADCAST - 1]), - dev->addr_len); - send_addr_notify = 1; + if (tb[IFLA_MTU]) { + err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + if (err < 0) + goto errout_dev; + modified = 1; } - if (ida[IFLA_MTU - 1]) { - if (ida[IFLA_MTU - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; - err = dev_set_mtu(dev, *((u32 *) RTA_DATA(ida[IFLA_MTU - 1]))); - - if (err) - goto out; - + /* + * Interface selected by interface index but interface + * name provided implies that a name change has been + * requested. + */ + if (ifm->ifi_index >= 0 && ifname[0]) { + err = dev_change_name(dev, ifname); + if (err < 0) + goto errout_dev; + modified = 1; } - if (ida[IFLA_TXQLEN - 1]) { - if (ida[IFLA_TXQLEN - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; +#ifdef CONFIG_NET_WIRELESS_RTNETLINK + if (tb[IFLA_WIRELESS]) { + /* Call Wireless Extensions. + * Various stuff checked in there... */ + err = wireless_rtnetlink_set(dev, nla_data(tb[IFLA_WIRELESS]), + nla_len(tb[IFLA_WIRELESS])); + if (err < 0) + goto errout_dev; + } +#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - dev->tx_queue_len = *((u32 *) RTA_DATA(ida[IFLA_TXQLEN - 1])); + if (tb[IFLA_BROADCAST]) { + nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len); + send_addr_notify = 1; } - if (ida[IFLA_WEIGHT - 1]) { - if (ida[IFLA_WEIGHT - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; - dev->weight = *((u32 *) RTA_DATA(ida[IFLA_WEIGHT - 1])); - } + if (ifm->ifi_flags) + dev_change_flags(dev, ifm->ifi_flags); - if (ida[IFLA_OPERSTATE - 1]) { - if (ida[IFLA_OPERSTATE - 1]->rta_len != RTA_LENGTH(sizeof(u8))) - goto out; + if (tb[IFLA_TXQLEN]) + dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); - set_operstate(dev, *((u8 *) RTA_DATA(ida[IFLA_OPERSTATE - 1]))); - } + if (tb[IFLA_WEIGHT]) + dev->weight = nla_get_u32(tb[IFLA_WEIGHT]); - if (ida[IFLA_LINKMODE - 1]) { - if (ida[IFLA_LINKMODE - 1]->rta_len != RTA_LENGTH(sizeof(u8))) - goto out; + if (tb[IFLA_OPERSTATE]) + set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); + if (tb[IFLA_LINKMODE]) { write_lock_bh(&dev_base_lock); - dev->link_mode = *((u8 *) RTA_DATA(ida[IFLA_LINKMODE - 1])); + dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]); write_unlock_bh(&dev_base_lock); } - if (ifm->ifi_index >= 0 && ida[IFLA_IFNAME - 1]) { - char ifname[IFNAMSIZ]; - - if (rtattr_strlcpy(ifname, ida[IFLA_IFNAME - 1], - IFNAMSIZ) >= IFNAMSIZ) - goto out; - err = dev_change_name(dev, ifname); - if (err) - goto out; - } - -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - if (ida[IFLA_WIRELESS - 1]) { - - /* Call Wireless Extensions. - * Various stuff checked in there... */ - err = wireless_rtnetlink_set(dev, RTA_DATA(ida[IFLA_WIRELESS - 1]), ida[IFLA_WIRELESS - 1]->rta_len); - if (err) - goto out; - } -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - err = 0; -out: +errout_dev: + if (err < 0 && modified && net_ratelimit()) + printk(KERN_WARNING "A link change request failed with " + "some changes comitted already. Interface %s may " + "have been left with an inconsistent configuration, " + "please check.\n", dev->name); + if (send_addr_notify) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); dev_put(dev); +errout: return err; } -#ifdef CONFIG_NET_WIRELESS_RTNETLINK -static int do_getlink(struct sk_buff *in_skb, struct nlmsghdr* in_nlh, void *arg) +static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct ifinfomsg *ifm = NLMSG_DATA(in_nlh); - struct rtattr **ida = arg; - struct net_device *dev; - struct ifinfomsg *r; - struct nlmsghdr *nlh; - int err = -ENOBUFS; - struct sk_buff *skb; - unsigned char *b; - char *iw_buf = NULL; + struct ifinfomsg *ifm; + struct nlattr *tb[IFLA_MAX+1]; + struct net_device *dev = NULL; + struct sk_buff *nskb; + char *iw_buf = NULL, *iw = NULL; int iw_buf_len = 0; + int err, payload; - if (ifm->ifi_index >= 0) + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + goto errout; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_index >= 0) { dev = dev_get_by_index(ifm->ifi_index); - else + if (dev == NULL) + return -ENODEV; + } else return -EINVAL; - if (!dev) - return -ENODEV; -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - if (ida[IFLA_WIRELESS - 1]) { +#ifdef CONFIG_NET_WIRELESS_RTNETLINK + if (tb[IFLA_WIRELESS]) { /* Call Wireless Extensions. We need to know the size before * we can alloc. Various stuff checked in there... */ - err = wireless_rtnetlink_get(dev, RTA_DATA(ida[IFLA_WIRELESS - 1]), ida[IFLA_WIRELESS - 1]->rta_len, &iw_buf, &iw_buf_len); - if (err) - goto out; + err = wireless_rtnetlink_get(dev, nla_data(tb[IFLA_WIRELESS]), + nla_len(tb[IFLA_WIRELESS]), + &iw_buf, &iw_buf_len); + if (err < 0) + goto errout; + + iw += IW_EV_POINT_OFF; } #endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - /* Create a skb big enough to include all the data. - * Some requests are way bigger than 4k... Jean II */ - skb = alloc_skb((NLMSG_LENGTH(sizeof(*r))) + (RTA_SPACE(iw_buf_len)), - GFP_KERNEL); - if (!skb) - goto out; - b = skb->tail; - - /* Put in the message the usual good stuff */ - nlh = NLMSG_PUT(skb, NETLINK_CB(in_skb).pid, in_nlh->nlmsg_seq, - RTM_NEWLINK, sizeof(*r)); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev->flags; - r->ifi_change = 0; - - /* Put the wireless payload if it exist */ - if(iw_buf != NULL) - RTA_PUT(skb, IFLA_WIRELESS, iw_buf_len, - iw_buf + IW_EV_POINT_OFF); - - nlh->nlmsg_len = skb->tail - b; - - /* Needed ? */ - NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; - - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; -out: - if(iw_buf != NULL) - kfree(iw_buf); + payload = NLMSG_ALIGN(sizeof(struct ifinfomsg) + + nla_total_size(iw_buf_len)); + nskb = nlmsg_new(nlmsg_total_size(payload), GFP_KERNEL); + if (nskb == NULL) { + err = -ENOBUFS; + goto errout; + } + + err = rtnl_fill_ifinfo(nskb, dev, iw, iw_buf_len, RTM_NEWLINK, + NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, 0); + if (err <= 0) { + kfree_skb(nskb); + goto errout; + } + + err = rtnl_unicast(skb, NETLINK_CB(skb).pid); +errout: + kfree(iw_buf); dev_put(dev); - return err; -rtattr_failure: -nlmsg_failure: - kfree_skb(skb); - goto out; + return err; } -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ -static int rtnetlink_dump_all(struct sk_buff *skb, struct netlink_callback *cb) +static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->family; @@ -608,20 +637,22 @@ static int rtnetlink_dump_all(struct sk_buff *skb, struct netlink_callback *cb) void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct ifinfomsg) + - sizeof(struct rtnl_link_ifmap) + - sizeof(struct rtnl_link_stats) + 128); + int err = -ENOBUFS; - skb = alloc_skb(size, GFP_KERNEL); - if (!skb) - return; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto errout; - if (rtnetlink_fill_ifinfo(skb, dev, type, 0, 0, change, 0) < 0) { + err = rtnl_fill_ifinfo(skb, dev, NULL, 0, type, 0, 0, change, 0); + if (err < 0) { kfree_skb(skb); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_LINK; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_KERNEL); + + err = rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_LINK, err); } /* Protected by RTNL sempahore. */ @@ -746,18 +777,19 @@ static void rtnetlink_rcv(struct sock *sk, int len) static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = { - [RTM_GETLINK - RTM_BASE] = { -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - .doit = do_getlink, -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - .dumpit = rtnetlink_dump_ifinfo }, - [RTM_SETLINK - RTM_BASE] = { .doit = do_setlink }, - [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETLINK - RTM_BASE] = { .doit = rtnl_getlink, + .dumpit = rtnl_dump_ifinfo }, + [RTM_SETLINK - RTM_BASE] = { .doit = rtnl_setlink }, + [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnl_dump_all }, + [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnl_dump_all }, [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, - [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, +#ifdef CONFIG_FIB_RULES + [RTM_NEWRULE - RTM_BASE] = { .doit = fib_nl_newrule }, + [RTM_DELRULE - RTM_BASE] = { .doit = fib_nl_delrule }, +#endif + [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnl_dump_all }, [RTM_GETNEIGHTBL - RTM_BASE] = { .dumpit = neightbl_dump_info }, [RTM_SETNEIGHTBL - RTM_BASE] = { .doit = neightbl_set }, }; @@ -817,7 +849,9 @@ EXPORT_SYMBOL(rtattr_strlcpy); EXPORT_SYMBOL(rtattr_parse); EXPORT_SYMBOL(rtnetlink_links); EXPORT_SYMBOL(rtnetlink_put_metrics); -EXPORT_SYMBOL(rtnl); EXPORT_SYMBOL(rtnl_lock); EXPORT_SYMBOL(rtnl_trylock); EXPORT_SYMBOL(rtnl_unlock); +EXPORT_SYMBOL(rtnl_unicast); +EXPORT_SYMBOL(rtnl_notify); +EXPORT_SYMBOL(rtnl_set_sk_err); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c54f3664bce..c448c7f6fde 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1397,7 +1397,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) unsigned int csum; long csstart; - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) csstart = skb->h.raw - skb->data; else csstart = skb_headlen(skb); @@ -1411,7 +1411,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, skb->len - csstart, 0); - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { long csstuff = csstart + skb->csum; *((unsigned short *)(to + csstuff)) = csum_fold(csum); @@ -1898,10 +1898,10 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, * @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. + * update the CHECKSUM_COMPLETE 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) { @@ -1994,7 +1994,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) frag = skb_shinfo(nskb)->frags; k = 0; - nskb->ip_summed = CHECKSUM_HW; + nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum = skb->csum; memcpy(skb_put(nskb, hsize), skb->data + offset, hsize); @@ -2046,19 +2046,14 @@ void __init skb_init(void) skbuff_head_cache = kmem_cache_create("skbuff_head_cache", sizeof(struct sk_buff), 0, - SLAB_HWCACHE_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!skbuff_head_cache) - panic("cannot create skbuff cache"); - skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", (2*sizeof(struct sk_buff)) + sizeof(atomic_t), 0, - SLAB_HWCACHE_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!skbuff_fclone_cache) - panic("cannot create skbuff cache"); } EXPORT_SYMBOL(___pskb_trim); diff --git a/net/core/sock.c b/net/core/sock.c index 51fcfbc041a..b77e155cbe6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -187,13 +187,13 @@ static struct lock_class_key af_callback_keys[AF_MAX]; #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) /* Run time adjustable parameters. */ -__u32 sysctl_wmem_max = SK_WMEM_MAX; -__u32 sysctl_rmem_max = SK_RMEM_MAX; -__u32 sysctl_wmem_default = SK_WMEM_MAX; -__u32 sysctl_rmem_default = SK_RMEM_MAX; +__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; +__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; +__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; +__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; /* Maximal space eaten by iovec or ancilliary data plus some space */ -int sysctl_optmem_max = sizeof(unsigned long)*(2*UIO_MAXIOV + 512); +int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -247,11 +247,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto out; } - /* It would be deadlock, if sock_queue_rcv_skb is used - with socket lock! We assume that users of this - function are lock free. - */ - err = sk_filter(sk, skb, 1); + err = sk_filter(sk, skb); if (err) goto out; @@ -278,7 +274,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb) { int rc = NET_RX_SUCCESS; - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard_and_relse; skb->dev = NULL; @@ -606,15 +602,15 @@ set_rcvbuf: break; case SO_DETACH_FILTER: - spin_lock_bh(&sk->sk_lock.slock); - filter = sk->sk_filter; + rcu_read_lock_bh(); + filter = rcu_dereference(sk->sk_filter); if (filter) { - sk->sk_filter = NULL; - spin_unlock_bh(&sk->sk_lock.slock); + rcu_assign_pointer(sk->sk_filter, NULL); sk_filter_release(sk, filter); + rcu_read_unlock_bh(); break; } - spin_unlock_bh(&sk->sk_lock.slock); + rcu_read_unlock_bh(); ret = -ENONET; break; @@ -884,10 +880,10 @@ void sk_free(struct sock *sk) if (sk->sk_destruct) sk->sk_destruct(sk); - filter = sk->sk_filter; + filter = rcu_dereference(sk->sk_filter); if (filter) { sk_filter_release(sk, filter); - sk->sk_filter = NULL; + rcu_assign_pointer(sk->sk_filter, NULL); } sock_disable_timestamp(sk); @@ -911,7 +907,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) if (newsk != NULL) { struct sk_filter *filter; - memcpy(newsk, sk, sk->sk_prot->obj_size); + sock_copy(newsk, sk); /* SANITY */ sk_node_init(&newsk->sk_node); diff --git a/net/core/utils.c b/net/core/utils.c index e31c90e0559..2682490777d 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -4,6 +4,7 @@ * Authors: * net_random Alan Cox * net_ratelimit Andy Kleen + * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * @@ -191,3 +192,215 @@ __be32 in_aton(const char *str) } EXPORT_SYMBOL(in_aton); + +#define IN6PTON_XDIGIT 0x00010000 +#define IN6PTON_DIGIT 0x00020000 +#define IN6PTON_COLON_MASK 0x00700000 +#define IN6PTON_COLON_1 0x00100000 /* single : requested */ +#define IN6PTON_COLON_2 0x00200000 /* second : requested */ +#define IN6PTON_COLON_1_2 0x00400000 /* :: requested */ +#define IN6PTON_DOT 0x00800000 /* . */ +#define IN6PTON_DELIM 0x10000000 +#define IN6PTON_NULL 0x20000000 /* first/tail */ +#define IN6PTON_UNKNOWN 0x40000000 + +static inline int digit2bin(char c, char delim) +{ + if (c == delim || c == '\0') + return IN6PTON_DELIM; + if (c == '.') + return IN6PTON_DOT; + if (c >= '0' && c <= '9') + return (IN6PTON_DIGIT | (c - '0')); + return IN6PTON_UNKNOWN; +} + +static inline int xdigit2bin(char c, char delim) +{ + if (c == delim || c == '\0') + return IN6PTON_DELIM; + if (c == ':') + return IN6PTON_COLON_MASK; + if (c == '.') + return IN6PTON_DOT; + if (c >= '0' && c <= '9') + return (IN6PTON_XDIGIT | IN6PTON_DIGIT| (c - '0')); + if (c >= 'a' && c <= 'f') + return (IN6PTON_XDIGIT | (c - 'a' + 10)); + if (c >= 'A' && c <= 'F') + return (IN6PTON_XDIGIT | (c - 'A' + 10)); + return IN6PTON_UNKNOWN; +} + +int in4_pton(const char *src, int srclen, + u8 *dst, + char delim, const char **end) +{ + const char *s; + u8 *d; + u8 dbuf[4]; + int ret = 0; + int i; + int w = 0; + + if (srclen < 0) + srclen = strlen(src); + s = src; + d = dbuf; + i = 0; + while(1) { + int c; + c = xdigit2bin(srclen > 0 ? *s : '\0', delim); + if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM))) { + goto out; + } + if (c & (IN6PTON_DOT | IN6PTON_DELIM)) { + if (w == 0) + goto out; + *d++ = w & 0xff; + w = 0; + i++; + if (c & IN6PTON_DELIM) { + if (i != 4) + goto out; + break; + } + goto cont; + } + w = (w * 10) + c; + if ((w & 0xffff) > 255) { + goto out; + } +cont: + if (i >= 4) + goto out; + s++; + srclen--; + } + ret = 1; + memcpy(dst, dbuf, sizeof(dbuf)); +out: + if (end) + *end = s; + return ret; +} + +EXPORT_SYMBOL(in4_pton); + +int in6_pton(const char *src, int srclen, + u8 *dst, + char delim, const char **end) +{ + const char *s, *tok = NULL; + u8 *d, *dc = NULL; + u8 dbuf[16]; + int ret = 0; + int i; + int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL; + int w = 0; + + memset(dbuf, 0, sizeof(dbuf)); + + s = src; + d = dbuf; + if (srclen < 0) + srclen = strlen(src); + + while (1) { + int c; + + c = xdigit2bin(srclen > 0 ? *s : '\0', delim); + if (!(c & state)) + goto out; + if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { + /* process one 16-bit word */ + if (!(state & IN6PTON_NULL)) { + *d++ = (w >> 8) & 0xff; + *d++ = w & 0xff; + } + w = 0; + if (c & IN6PTON_DELIM) { + /* We've processed last word */ + break; + } + /* + * COLON_1 => XDIGIT + * COLON_2 => XDIGIT|DELIM + * COLON_1_2 => COLON_2 + */ + switch (state & IN6PTON_COLON_MASK) { + case IN6PTON_COLON_2: + dc = d; + state = IN6PTON_XDIGIT | IN6PTON_DELIM; + if (dc - dbuf >= sizeof(dbuf)) + state |= IN6PTON_NULL; + break; + case IN6PTON_COLON_1|IN6PTON_COLON_1_2: + state = IN6PTON_XDIGIT | IN6PTON_COLON_2; + break; + case IN6PTON_COLON_1: + state = IN6PTON_XDIGIT; + break; + case IN6PTON_COLON_1_2: + state = IN6PTON_COLON_2; + break; + default: + state = 0; + } + tok = s + 1; + goto cont; + } + + if (c & IN6PTON_DOT) { + ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s); + if (ret > 0) { + d += 4; + break; + } + goto out; + } + + w = (w << 4) | (0xff & c); + state = IN6PTON_COLON_1 | IN6PTON_DELIM; + if (!(w & 0xf000)) { + state |= IN6PTON_XDIGIT; + } + if (!dc && d + 2 < dbuf + sizeof(dbuf)) { + state |= IN6PTON_COLON_1_2; + state &= ~IN6PTON_DELIM; + } + if (d + 2 >= dbuf + sizeof(dbuf)) { + state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2); + } +cont: + if ((dc && d + 4 < dbuf + sizeof(dbuf)) || + d + 4 == dbuf + sizeof(dbuf)) { + state |= IN6PTON_DOT; + } + if (d >= dbuf + sizeof(dbuf)) { + state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK); + } + s++; + srclen--; + } + + i = 15; d--; + + if (dc) { + while(d >= dc) + dst[i--] = *d--; + while(i >= dc - dbuf) + dst[i--] = 0; + while(i >= 0) + dst[i--] = *d--; + } else + memcpy(dst, dbuf, sizeof(dbuf)); + + ret = 1; +out: + if (end) + *end = s; + return ret; +} + +EXPORT_SYMBOL(in6_pton); diff --git a/net/core/wireless.c b/net/core/wireless.c index de0bde4b51d..3168fca312f 100644 --- a/net/core/wireless.c +++ b/net/core/wireless.c @@ -72,7 +72,6 @@ /***************************** INCLUDES *****************************/ -#include <linux/config.h> /* Not needed ??? */ #include <linux/module.h> #include <linux/types.h> /* off_t */ #include <linux/netdevice.h> /* struct ifreq, dev_get_by_name() */ @@ -86,6 +85,7 @@ #include <linux/wireless.h> /* Pretty obvious */ #include <net/iw_handler.h> /* New driver API */ +#include <net/netlink.h> #include <asm/uaccess.h> /* copy_to_user() */ @@ -1850,7 +1850,7 @@ static void wireless_nlevent_process(unsigned long data) struct sk_buff *skb; while ((skb = skb_dequeue(&wireless_nlevent_queue))) - netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_ATOMIC); + rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); } static DECLARE_TASKLET(wireless_nlevent_tasklet, wireless_nlevent_process, 0); diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 8c211c58893..4d176d33983 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -142,14 +142,13 @@ struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) struct dccp_ackvec *av = kmem_cache_alloc(dccp_ackvec_slab, priority); if (av != NULL) { - av->dccpav_buf_head = - av->dccpav_buf_tail = DCCP_MAX_ACKVEC_LEN - 1; + av->dccpav_buf_head = 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; + av->dccpav_vec_len = 0; INIT_LIST_HEAD(&av->dccpav_records); } @@ -353,11 +352,13 @@ static void dccp_ackvec_throw_record(struct dccp_ackvec *av, { 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; + /* sort out vector length */ + if (av->dccpav_buf_head <= avr->dccpavr_ack_ptr) + av->dccpav_vec_len = avr->dccpavr_ack_ptr - av->dccpav_buf_head; + else + av->dccpav_vec_len = DCCP_MAX_ACKVEC_LEN - 1 + - av->dccpav_buf_head + + avr->dccpavr_ack_ptr; /* free records */ list_for_each_entry_safe_from(avr, next, &av->dccpav_records, @@ -434,8 +435,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, break; found: if (between48(avr->dccpavr_ack_seqno, ackno_end_rl, ackno)) { - const u8 state = (*vector & - DCCP_ACKVEC_STATE_MASK) >> 6; + const u8 state = *vector & DCCP_ACKVEC_STATE_MASK; if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED) { #ifdef CONFIG_IP_DCCP_DEBUG struct dccp_sock *dp = dccp_sk(sk); diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index 0adf4b56c34..2424effac7f 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -54,9 +54,7 @@ struct dccp_ackvec { 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_nonce; u8 dccpav_ack_nonce; @@ -107,7 +105,7 @@ extern int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb); static inline int dccp_ackvec_pending(const struct dccp_ackvec *av) { - return av->dccpav_sent_len != av->dccpav_vec_len; + return av->dccpav_vec_len; } #else /* CONFIG_IP_DCCP_ACKVEC */ static inline int dccp_ackvec_init(void) diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig index ca00191628f..32752f75044 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -30,6 +30,14 @@ config IP_DCCP_CCID2 If in doubt, say M. +config IP_DCCP_CCID2_DEBUG + bool "CCID2 debug" + depends on IP_DCCP_CCID2 + ---help--- + Enable CCID2 debug messages. + + If in doubt, say N. + config IP_DCCP_CCID3 tristate "CCID3 (TCP-Friendly) (EXPERIMENTAL)" depends on IP_DCCP diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index e9615627dcd..457dd3db7f4 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -27,7 +27,6 @@ * * BUGS: * - sequence number wrapping - * - jiffies wrapping */ #include "../ccid.h" @@ -36,8 +35,7 @@ static int ccid2_debug; -#undef CCID2_DEBUG -#ifdef CCID2_DEBUG +#ifdef CONFIG_IP_DCCP_CCID2_DEBUG #define ccid2_pr_debug(format, a...) \ do { if (ccid2_debug) \ printk(KERN_DEBUG "%s: " format, __FUNCTION__, ##a); \ @@ -46,9 +44,7 @@ static int ccid2_debug; #define ccid2_pr_debug(format, a...) #endif -static const int ccid2_seq_len = 128; - -#ifdef CCID2_DEBUG +#ifdef CONFIG_IP_DCCP_CCID2_DEBUG static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) { int len = 0; @@ -71,8 +67,8 @@ static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) /* 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); + BUG_ON(time_before(seqp->ccid2s_sent, + prev->ccid2s_sent)); seqp = prev; } @@ -84,16 +80,57 @@ static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) 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); + BUG_ON(len != hctx->ccid2hctx_seqbufc * CCID2_SEQBUF_LEN); } #else #define ccid2_hc_tx_check_sanity(hctx) do {} while (0) #endif +static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx, int num, + gfp_t gfp) +{ + struct ccid2_seq *seqp; + int i; + + /* check if we have space to preserve the pointer to the buffer */ + if (hctx->ccid2hctx_seqbufc >= (sizeof(hctx->ccid2hctx_seqbuf) / + sizeof(struct ccid2_seq*))) + return -ENOMEM; + + /* allocate buffer and initialize linked list */ + seqp = kmalloc(sizeof(*seqp) * num, gfp); + if (seqp == NULL) + return -ENOMEM; + + for (i = 0; i < (num - 1); i++) { + seqp[i].ccid2s_next = &seqp[i + 1]; + seqp[i + 1].ccid2s_prev = &seqp[i]; + } + seqp[num - 1].ccid2s_next = seqp; + seqp->ccid2s_prev = &seqp[num - 1]; + + /* This is the first allocation. Initiate the head and tail. */ + if (hctx->ccid2hctx_seqbufc == 0) + hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqt = seqp; + else { + /* link the existing list with the one we just created */ + hctx->ccid2hctx_seqh->ccid2s_next = seqp; + seqp->ccid2s_prev = hctx->ccid2hctx_seqh; + + hctx->ccid2hctx_seqt->ccid2s_prev = &seqp[num - 1]; + seqp[num - 1].ccid2s_next = hctx->ccid2hctx_seqt; + } + + /* store the original pointer to the buffer so we can free it */ + hctx->ccid2hctx_seqbuf[hctx->ccid2hctx_seqbufc] = seqp; + hctx->ccid2hctx_seqbufc++; + + return 0; +} + static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb, int len) { @@ -122,7 +159,7 @@ static int ccid2_hc_tx_send_packet(struct sock *sk, } } - return 100; /* XXX */ + return 1; /* XXX CCID should dequeue when ready instead of polling */ } static void ccid2_change_l_ack_ratio(struct sock *sk, int val) @@ -150,10 +187,8 @@ static void ccid2_change_l_ack_ratio(struct sock *sk, int val) dp->dccps_l_ack_ratio = val; } -static void ccid2_change_cwnd(struct sock *sk, int val) +static void ccid2_change_cwnd(struct ccid2_hc_tx_sock *hctx, int val) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); - if (val == 0) val = 1; @@ -164,6 +199,17 @@ static void ccid2_change_cwnd(struct sock *sk, int val) hctx->ccid2hctx_cwnd = val; } +static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hctx, long val) +{ + ccid2_pr_debug("change SRTT to %ld\n", val); + hctx->ccid2hctx_srtt = val; +} + +static void ccid2_change_pipe(struct ccid2_hc_tx_sock *hctx, long val) +{ + hctx->ccid2hctx_pipe = val; +} + static void ccid2_start_rto_timer(struct sock *sk); static void ccid2_hc_tx_rto_expire(unsigned long data) @@ -193,11 +239,11 @@ static void ccid2_hc_tx_rto_expire(unsigned long data) ccid2_start_rto_timer(sk); /* adjust pipe, cwnd etc */ - hctx->ccid2hctx_pipe = 0; + ccid2_change_pipe(hctx, 0); hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd >> 1; if (hctx->ccid2hctx_ssthresh < 2) hctx->ccid2hctx_ssthresh = 2; - ccid2_change_cwnd(sk, 1); + ccid2_change_cwnd(hctx, 1); /* clear state about stuff we sent */ hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh; @@ -232,13 +278,14 @@ 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); + struct ccid2_seq *next; u64 seq; ccid2_hc_tx_check_sanity(hctx); BUG_ON(!hctx->ccid2hctx_sendwait); hctx->ccid2hctx_sendwait = 0; - hctx->ccid2hctx_pipe++; + ccid2_change_pipe(hctx, hctx->ccid2hctx_pipe + 1); BUG_ON(hctx->ccid2hctx_pipe < 0); /* There is an issue. What if another packet is sent between @@ -251,15 +298,23 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len) 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); + next = hctx->ccid2hctx_seqh->ccid2s_next; + /* check if we need to alloc more space */ + if (next == hctx->ccid2hctx_seqt) { + int rc; + + ccid2_pr_debug("allocating more space in history\n"); + rc = ccid2_hc_tx_alloc_seq(hctx, CCID2_SEQBUF_LEN, GFP_KERNEL); + BUG_ON(rc); /* XXX what do we do? */ - if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt) { - /* XXX allocate more space */ - WARN_ON(1); + next = hctx->ccid2hctx_seqh->ccid2s_next; + BUG_ON(next == hctx->ccid2hctx_seqt); } + hctx->ccid2hctx_seqh = next; + + ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd, + hctx->ccid2hctx_pipe); hctx->ccid2hctx_sent++; @@ -295,7 +350,7 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len) if (!timer_pending(&hctx->ccid2hctx_rtotimer)) ccid2_start_rto_timer(sk); -#ifdef CCID2_DEBUG +#ifdef CONFIG_IP_DCCP_CCID2_DEBUG ccid2_pr_debug("pipe=%d\n", hctx->ccid2hctx_pipe); ccid2_pr_debug("Sent: seq=%llu\n", seq); do { @@ -398,7 +453,7 @@ static inline void ccid2_new_ack(struct sock *sk, /* increase every 2 acks */ hctx->ccid2hctx_ssacks++; if (hctx->ccid2hctx_ssacks == 2) { - ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1); + ccid2_change_cwnd(hctx, hctx->ccid2hctx_cwnd+1); hctx->ccid2hctx_ssacks = 0; *maxincr = *maxincr - 1; } @@ -411,26 +466,28 @@ static inline void ccid2_new_ack(struct sock *sk, hctx->ccid2hctx_acks++; if (hctx->ccid2hctx_acks >= hctx->ccid2hctx_cwnd) { - ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1); + ccid2_change_cwnd(hctx, 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; + time_after(jiffies, hctx->ccid2hctx_lastrtt + hctx->ccid2hctx_srtt)) { + unsigned long r = (long)jiffies - (long)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; + ccid2_change_srtt(hctx, r); hctx->ccid2hctx_rttvar = r >> 1; } else { /* RTTVAR */ long tmp = hctx->ccid2hctx_srtt - r; + long srtt; + if (tmp < 0) tmp *= -1; @@ -440,10 +497,12 @@ static inline void ccid2_new_ack(struct sock *sk, hctx->ccid2hctx_rttvar += tmp; /* SRTT */ - hctx->ccid2hctx_srtt *= 7; - hctx->ccid2hctx_srtt >>= 3; + srtt = hctx->ccid2hctx_srtt; + srtt *= 7; + srtt >>= 3; tmp = r >> 3; - hctx->ccid2hctx_srtt += tmp; + srtt += tmp; + ccid2_change_srtt(hctx, srtt); } s = hctx->ccid2hctx_rttvar << 2; /* clock granularity is 1 when based on jiffies */ @@ -479,13 +538,29 @@ static void ccid2_hc_tx_dec_pipe(struct sock *sk) { struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); - hctx->ccid2hctx_pipe--; + ccid2_change_pipe(hctx, hctx->ccid2hctx_pipe-1); BUG_ON(hctx->ccid2hctx_pipe < 0); if (hctx->ccid2hctx_pipe == 0) ccid2_hc_tx_kill_rto_timer(sk); } +static void ccid2_congestion_event(struct ccid2_hc_tx_sock *hctx, + struct ccid2_seq *seqp) +{ + if (time_before(seqp->ccid2s_sent, hctx->ccid2hctx_last_cong)) { + ccid2_pr_debug("Multiple losses in an RTT---treating as one\n"); + return; + } + + hctx->ccid2hctx_last_cong = jiffies; + + ccid2_change_cwnd(hctx, hctx->ccid2hctx_cwnd >> 1); + hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd; + if (hctx->ccid2hctx_ssthresh < 2) + hctx->ccid2hctx_ssthresh = 2; +} + static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); @@ -496,7 +571,6 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) unsigned char veclen; int offset = 0; int done = 0; - int loss = 0; unsigned int maxincr = 0; ccid2_hc_tx_check_sanity(hctx); @@ -582,15 +656,16 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * run length */ while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) { - const u8 state = (*vector & - DCCP_ACKVEC_STATE_MASK) >> 6; + const u8 state = *vector & + DCCP_ACKVEC_STATE_MASK; /* new packet received or marked */ if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED && !seqp->ccid2s_acked) { if (state == DCCP_ACKVEC_STATE_ECN_MARKED) { - loss = 1; + ccid2_congestion_event(hctx, + seqp); } else ccid2_new_ack(sk, seqp, &maxincr); @@ -642,7 +717,13 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) /* check for lost packets */ while (1) { if (!seqp->ccid2s_acked) { - loss = 1; + ccid2_pr_debug("Packet lost: %llu\n", + seqp->ccid2s_seq); + /* XXX need to traverse from tail -> head in + * order to detect multiple congestion events in + * one ack vector. + */ + ccid2_congestion_event(hctx, seqp); ccid2_hc_tx_dec_pipe(sk); } if (seqp == hctx->ccid2hctx_seqt) @@ -661,53 +742,33 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) 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; + ccid2_change_cwnd(hctx, 1); + /* Initialize ssthresh to infinity. This means that we will exit the + * initial slow-start after the first packet loss. This is what we + * want. + */ + hctx->ccid2hctx_ssthresh = ~0; hctx->ccid2hctx_numdupack = 3; + hctx->ccid2hctx_seqbufc = 0; /* XXX init ~ to window size... */ - hctx->ccid2hctx_seqbuf = kmalloc(sizeof(*hctx->ccid2hctx_seqbuf) * - seqcount, gfp_any()); - if (hctx->ccid2hctx_seqbuf == NULL) + if (ccid2_hc_tx_alloc_seq(hctx, CCID2_SEQBUF_LEN, GFP_ATOMIC) != 0) 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; + ccid2_change_srtt(hctx, -1); hctx->ccid2hctx_rttvar = -1; hctx->ccid2hctx_lastrtt = 0; hctx->ccid2hctx_rpdupack = -1; + hctx->ccid2hctx_last_cong = jiffies; hctx->ccid2hctx_rtotimer.function = &ccid2_hc_tx_rto_expire; hctx->ccid2hctx_rtotimer.data = (unsigned long)sk; @@ -720,10 +781,13 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) static void ccid2_hc_tx_exit(struct sock *sk) { struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + int i; ccid2_hc_tx_kill_rto_timer(sk); - kfree(hctx->ccid2hctx_seqbuf); - hctx->ccid2hctx_seqbuf = NULL; + + for (i = 0; i < hctx->ccid2hctx_seqbufc; i++) + kfree(hctx->ccid2hctx_seqbuf[i]); + hctx->ccid2hctx_seqbufc = 0; } static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index 451a87464fa..5b2ef4acb30 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -35,6 +35,9 @@ struct ccid2_seq { struct ccid2_seq *ccid2s_next; }; +#define CCID2_SEQBUF_LEN 256 +#define CCID2_SEQBUF_MAX 128 + /** struct ccid2_hc_tx_sock - CCID2 TX half connection * * @ccid2hctx_ssacks - ACKs recv in slow start @@ -50,10 +53,11 @@ struct ccid2_hc_tx_sock { int ccid2hctx_cwnd; int ccid2hctx_ssacks; int ccid2hctx_acks; - int ccid2hctx_ssthresh; + unsigned int ccid2hctx_ssthresh; int ccid2hctx_pipe; int ccid2hctx_numdupack; - struct ccid2_seq *ccid2hctx_seqbuf; + struct ccid2_seq *ccid2hctx_seqbuf[CCID2_SEQBUF_MAX]; + int ccid2hctx_seqbufc; struct ccid2_seq *ccid2hctx_seqh; struct ccid2_seq *ccid2hctx_seqt; long ccid2hctx_rto; @@ -67,6 +71,7 @@ struct ccid2_hc_tx_sock { u64 ccid2hctx_rpseq; int ccid2hctx_rpdupack; int ccid2hctx_sendwait; + unsigned long ccid2hctx_last_cong; }; struct ccid2_hc_rx_sock { diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 090bc39e819..195aa956622 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -900,7 +900,7 @@ found: static void ccid3_hc_rx_update_li(struct sock *sk, u64 seq_loss, u8 win_loss) { struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); - struct dccp_li_hist_entry *next, *head; + struct dccp_li_hist_entry *head; u64 seq_temp; if (list_empty(&hcrx->ccid3hcrx_li_hist)) { @@ -908,15 +908,15 @@ static void ccid3_hc_rx_update_li(struct sock *sk, u64 seq_loss, u8 win_loss) &hcrx->ccid3hcrx_li_hist, seq_loss, win_loss)) return; - next = (struct dccp_li_hist_entry *) - hcrx->ccid3hcrx_li_hist.next; - next->dccplih_interval = ccid3_hc_rx_calc_first_li(sk); + head = list_entry(hcrx->ccid3hcrx_li_hist.next, + struct dccp_li_hist_entry, dccplih_node); + head->dccplih_interval = ccid3_hc_rx_calc_first_li(sk); } else { struct dccp_li_hist_entry *entry; struct list_head *tail; - head = (struct dccp_li_hist_entry *) - hcrx->ccid3hcrx_li_hist.next; + head = list_entry(hcrx->ccid3hcrx_li_hist.next, + struct dccp_li_hist_entry, dccplih_node); /* FIXME win count check removed as was wrong */ /* should make this check with receive history */ /* and compare there as per section 10.2 of RFC4342 */ diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index a5c5475724c..0a21be437ed 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -130,7 +130,7 @@ extern void dccp_send_delayed_ack(struct sock *sk); extern void dccp_send_sync(struct sock *sk, const u64 seq, const enum dccp_pkt_type pkt_type); -extern int dccp_write_xmit(struct sock *sk, struct sk_buff *skb, long *timeo); +extern void dccp_write_xmit(struct sock *sk, int block); extern void dccp_write_space(struct sock *sk); extern void dccp_init_xmit_timers(struct sock *sk); diff --git a/net/dccp/feat.h b/net/dccp/feat.h index b44c45504fb..cee553d416c 100644 --- a/net/dccp/feat.h +++ b/net/dccp/feat.h @@ -27,5 +27,10 @@ extern int dccp_feat_clone(struct sock *oldsk, struct sock *newsk); extern int dccp_feat_init(struct dccp_minisock *dmsk); 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; #endif /* _DCCP_FEAT_H */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 7f56f7e8f57..9a1a76a7dc4 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -501,6 +501,9 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) dccp_openreq_init(req, &dp, skb); + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_free; + ireq = inet_rsk(req); ireq->loc_addr = daddr; ireq->rmt_addr = saddr; @@ -605,10 +608,10 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) if (req != NULL) return dccp_check_req(sk, skb, req, prev); - nsk = __inet_lookup_established(&dccp_hashinfo, - iph->saddr, dh->dccph_sport, - iph->daddr, ntohs(dh->dccph_dport), - inet_iif(skb)); + nsk = inet_lookup_established(&dccp_hashinfo, + iph->saddr, dh->dccph_sport, + iph->daddr, dh->dccph_dport, + inet_iif(skb)); if (nsk != NULL) { if (nsk->sk_state != DCCP_TIME_WAIT) { bh_lock_sock(nsk); @@ -678,6 +681,7 @@ static struct dst_entry* dccp_v4_route_skb(struct sock *sk, } }; + security_skb_classify_flow(skb, &fl); if (ip_route_output_flow(&rt, &fl, sk, 0)) { IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); return NULL; @@ -921,7 +925,7 @@ static int dccp_v4_rcv(struct sk_buff *skb) * Look up flow ID in table and get corresponding socket */ sk = __inet_lookup(&dccp_hashinfo, skb->nh.iph->saddr, dh->dccph_sport, - skb->nh.iph->daddr, ntohs(dh->dccph_dport), + skb->nh.iph->daddr, dh->dccph_dport, inet_iif(skb)); /* diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 610c722ac27..7a47399cf31 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -201,6 +201,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = usin->sin6_port; fl.fl_ip_sport = inet->sport; + security_sk_classify_flow(sk, &fl); if (np->opt != NULL && np->opt->srcrt != NULL) { const struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; @@ -230,7 +231,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, ipv6_addr_copy(&np->saddr, saddr); inet->rcv_saddr = LOOPBACK4_IPV6; - __ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (np->opt != NULL) @@ -322,6 +323,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; + security_sk_classify_flow(sk, &fl); err = ip6_dst_lookup(sk, &dst, &fl); if (err) { @@ -422,6 +424,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, fl.oif = ireq6->iif; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; + security_req_classify_flow(req, &fl); if (dst == NULL) { opt = np->opt; @@ -566,6 +569,7 @@ static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) fl.oif = inet6_iif(rxskb); fl.fl_ip_dport = dh->dccph_dport; fl.fl_ip_sport = dh->dccph_sport; + security_skb_classify_flow(rxskb, &fl); /* sk = NULL, but it is safe for now. RST socket required. */ if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { @@ -622,6 +626,7 @@ static void dccp_v6_reqsk_send_ack(struct sk_buff *rxskb, fl.oif = inet6_iif(rxskb); fl.fl_ip_dport = dh->dccph_dport; fl.fl_ip_sport = dh->dccph_sport; + security_req_classify_flow(req, &fl); if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { @@ -704,6 +709,9 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) dccp_openreq_init(req, &dp, skb); + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_free; + ireq6 = inet6_rsk(req); ireq = inet_rsk(req); ipv6_addr_copy(&ireq6->rmt_addr, &skb->nh.ipv6h->saddr); @@ -842,6 +850,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; + security_sk_classify_flow(sk, &fl); if (ip6_dst_lookup(sk, &dst, &fl)) goto out; @@ -863,7 +872,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, * comment in that function for the gory details. -acme */ - __ip6_dst_store(newsk, dst, NULL); + __ip6_dst_store(newsk, dst, NULL, NULL); newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | NETIF_F_TSO); newdp6 = (struct dccp6_sock *)newsk; @@ -961,7 +970,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return dccp_v4_do_rcv(sk, skb); - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard; /* diff --git a/net/dccp/output.c b/net/dccp/output.c index 58669beee13..7102e3aed4c 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -198,7 +198,7 @@ static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, while (1) { prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + if (sk->sk_err) goto do_error; if (!*timeo) goto do_nonblock; @@ -234,37 +234,72 @@ do_interrupted: goto out; } -int dccp_write_xmit(struct sock *sk, struct sk_buff *skb, long *timeo) +static void dccp_write_xmit_timer(unsigned long data) { + struct sock *sk = (struct sock *)data; + struct dccp_sock *dp = dccp_sk(sk); + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) + sk_reset_timer(sk, &dp->dccps_xmit_timer, jiffies+1); + else + dccp_write_xmit(sk, 0); + bh_unlock_sock(sk); + sock_put(sk); +} + +void dccp_write_xmit(struct sock *sk, int block) { - const struct dccp_sock *dp = dccp_sk(sk); - int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb, + struct dccp_sock *dp = dccp_sk(sk); + struct sk_buff *skb; + long timeo = 30000; /* If a packet is taking longer than 2 secs + we have other issues */ + + while ((skb = skb_peek(&sk->sk_write_queue))) { + int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb, skb->len); - if (err > 0) - err = dccp_wait_for_ccid(sk, skb, timeo); + if (err > 0) { + if (!block) { + sk_reset_timer(sk, &dp->dccps_xmit_timer, + msecs_to_jiffies(err)+jiffies); + break; + } else + err = dccp_wait_for_ccid(sk, skb, &timeo); + if (err) { + printk(KERN_CRIT "%s:err at dccp_wait_for_ccid" + " %d\n", __FUNCTION__, err); + dump_stack(); + } + } - if (err == 0) { - struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); - const int len = skb->len; + skb_dequeue(&sk->sk_write_queue); + if (err == 0) { + struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); + const int len = skb->len; - if (sk->sk_state == DCCP_PARTOPEN) { - /* See 8.1.5. Handshake Completion */ - inet_csk_schedule_ack(sk); - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, + if (sk->sk_state == DCCP_PARTOPEN) { + /* See 8.1.5. Handshake Completion */ + inet_csk_schedule_ack(sk); + inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, inet_csk(sk)->icsk_rto, DCCP_RTO_MAX); - dcb->dccpd_type = DCCP_PKT_DATAACK; - } else if (dccp_ack_pending(sk)) - dcb->dccpd_type = DCCP_PKT_DATAACK; - else - dcb->dccpd_type = DCCP_PKT_DATA; - - err = dccp_transmit_skb(sk, skb); - ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len); - } else - kfree_skb(skb); - - return err; + dcb->dccpd_type = DCCP_PKT_DATAACK; + } else if (dccp_ack_pending(sk)) + dcb->dccpd_type = DCCP_PKT_DATAACK; + else + dcb->dccpd_type = DCCP_PKT_DATA; + + err = dccp_transmit_skb(sk, skb); + ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len); + if (err) { + printk(KERN_CRIT "%s:err from " + "ccid_hc_tx_packet_sent %d\n", + __FUNCTION__, err); + dump_stack(); + } + } else + kfree(skb); + } } int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb) @@ -426,6 +461,9 @@ static inline void dccp_connect_init(struct sock *sk) dccp_set_seqno(&dp->dccps_awl, max48(dp->dccps_awl, dp->dccps_iss)); icsk->icsk_retransmits = 0; + init_timer(&dp->dccps_xmit_timer); + dp->dccps_xmit_timer.data = (unsigned long)sk; + dp->dccps_xmit_timer.function = dccp_write_xmit_timer; } int dccp_connect(struct sock *sk) @@ -560,8 +598,10 @@ void dccp_send_close(struct sock *sk, const int active) DCCP_PKT_CLOSE : DCCP_PKT_CLOSEREQ; if (active) { + dccp_write_xmit(sk, 1); dccp_skb_entail(sk, skb); dccp_transmit_skb(sk, skb_clone(skb, prio)); + /* FIXME do we need a retransmit timer here? */ } else dccp_transmit_skb(sk, skb); } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 6f14bb5a28d..962df0ea31a 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -662,17 +662,8 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (rc != 0) goto out_discard; - rc = dccp_write_xmit(sk, skb, &timeo); - /* - * XXX we don't use sk_write_queue, so just discard the packet. - * Current plan however is to _use_ sk_write_queue with - * an algorith similar to tcp_sendmsg, where the main difference - * is that in DCCP we have to respect packet boundaries, so - * no coalescing of skbs. - * - * This bug was _quickly_ found & fixed by just looking at an OSTRA - * generated callgraph 8) -acme - */ + skb_queue_tail(&sk->sk_write_queue, skb); + dccp_write_xmit(sk,0); out_release: release_sock(sk); return rc ? : len; @@ -846,6 +837,7 @@ static int dccp_close_state(struct sock *sk) void dccp_close(struct sock *sk, long timeout) { + struct dccp_sock *dp = dccp_sk(sk); struct sk_buff *skb; int state; @@ -862,6 +854,8 @@ void dccp_close(struct sock *sk, long timeout) goto adjudge_to_death; } + sk_stop_timer(sk, &dp->dccps_xmit_timer); + /* * We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index c1ba9451bc3..38bc157876f 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -11,18 +11,12 @@ #include <linux/mm.h> #include <linux/sysctl.h> +#include "feat.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, diff --git a/net/decnet/Kconfig b/net/decnet/Kconfig index 92f2ec46fd2..36e72cb145b 100644 --- a/net/decnet/Kconfig +++ b/net/decnet/Kconfig @@ -27,6 +27,7 @@ config DECNET config DECNET_ROUTER bool "DECnet: router support (EXPERIMENTAL)" depends on DECNET && EXPERIMENTAL + select FIB_RULES ---help--- Add support for turning your DECnet Endnode into a level 1 or 2 router. This is an experimental, but functional option. If you diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 5486247735f..70e02737568 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -130,6 +130,7 @@ Version 0.0.6 2.1.110 07-aug-98 Eduardo Marcelo Serrat #include <linux/poll.h> #include <net/neighbour.h> #include <net/dst.h> +#include <net/fib_rules.h> #include <net/dn.h> #include <net/dn_nsp.h> #include <net/dn_dev.h> diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 476455fbdb0..01861feb608 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -34,6 +34,7 @@ #include <linux/seq_file.h> #include <linux/timer.h> #include <linux/string.h> +#include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/skbuff.h> @@ -45,6 +46,7 @@ #include <net/neighbour.h> #include <net/dst.h> #include <net/flow.h> +#include <net/fib_rules.h> #include <net/dn.h> #include <net/dn_dev.h> #include <net/dn_route.h> @@ -744,20 +746,23 @@ rtattr_failure: static void rtmsg_ifa(int event, struct dn_ifaddr *ifa) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct ifaddrmsg)+128); + int payload = sizeof(struct ifaddrmsg) + 128; + int err = -ENOBUFS; - skb = alloc_skb(size, GFP_KERNEL); - if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_DECnet_IFADDR, ENOBUFS); - return; - } - if (dn_dev_fill_ifaddr(skb, ifa, 0, 0, event, 0) < 0) { + skb = alloc_skb(nlmsg_total_size(payload), GFP_KERNEL); + if (skb == NULL) + goto errout; + + err = dn_dev_fill_ifaddr(skb, ifa, 0, 0, event, 0); + if (err < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_DECnet_IFADDR, EINVAL); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_DECnet_IFADDR; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_DECnet_IFADDR, GFP_KERNEL); + + err = rtnl_notify(skb, 0, RTNLGRP_DECnet_IFADDR, NULL, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_DECnet_IFADDR, err); } static int dn_dev_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) @@ -1417,8 +1422,6 @@ static struct rtnetlink_link dnet_rtnetlink_table[RTM_NR_MSGTYPES] = [RTM_DELROUTE - RTM_BASE] = { .doit = dn_fib_rtm_delroute, }, [RTM_GETROUTE - RTM_BASE] = { .doit = dn_cache_getroute, .dumpit = dn_fib_dump, }, - [RTM_NEWRULE - RTM_BASE] = { .doit = dn_fib_rtm_newrule, }, - [RTM_DELRULE - RTM_BASE] = { .doit = dn_fib_rtm_delrule, }, [RTM_GETRULE - RTM_BASE] = { .dumpit = dn_fib_dump_rules, }, #else [RTM_GETROUTE - RTM_BASE] = { .doit = dn_cache_getroute, diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index fa20e2efcfc..1cf010124ec 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -34,6 +34,7 @@ #include <net/neighbour.h> #include <net/dst.h> #include <net/flow.h> +#include <net/fib_rules.h> #include <net/dn.h> #include <net/dn_route.h> #include <net/dn_fib.h> @@ -54,11 +55,9 @@ #define endfor_nexthops(fi) } -extern int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb); - static DEFINE_SPINLOCK(dn_fib_multipath_lock); static struct dn_fib_info *dn_fib_info_list; -static DEFINE_RWLOCK(dn_fib_info_lock); +static DEFINE_SPINLOCK(dn_fib_info_lock); static struct { @@ -79,6 +78,9 @@ static struct [RTN_XRESOLVE] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE }, }; +static int dn_fib_sync_down(__le16 local, struct net_device *dev, int force); +static int dn_fib_sync_up(struct net_device *dev); + void dn_fib_free_info(struct dn_fib_info *fi) { if (fi->fib_dead == 0) { @@ -96,7 +98,7 @@ void dn_fib_free_info(struct dn_fib_info *fi) void dn_fib_release_info(struct dn_fib_info *fi) { - write_lock(&dn_fib_info_lock); + spin_lock(&dn_fib_info_lock); if (fi && --fi->fib_treeref == 0) { if (fi->fib_next) fi->fib_next->fib_prev = fi->fib_prev; @@ -107,7 +109,7 @@ void dn_fib_release_info(struct dn_fib_info *fi) fi->fib_dead = 1; dn_fib_info_put(fi); } - write_unlock(&dn_fib_info_lock); + spin_unlock(&dn_fib_info_lock); } static inline int dn_fib_nh_comp(const struct dn_fib_info *fi, const struct dn_fib_info *ofi) @@ -378,13 +380,13 @@ link_it: fi->fib_treeref++; atomic_inc(&fi->fib_clntref); - write_lock(&dn_fib_info_lock); + spin_lock(&dn_fib_info_lock); fi->fib_next = dn_fib_info_list; fi->fib_prev = NULL; if (dn_fib_info_list) dn_fib_info_list->fib_prev = fi; dn_fib_info_list = fi; - write_unlock(&dn_fib_info_lock); + spin_unlock(&dn_fib_info_lock); return fi; err_inval: @@ -490,7 +492,8 @@ static int dn_fib_check_attr(struct rtmsg *r, struct rtattr **rta) if (attr) { if (RTA_PAYLOAD(attr) < 4 && RTA_PAYLOAD(attr) != 2) return -EINVAL; - if (i != RTA_MULTIPATH && i != RTA_METRICS) + if (i != RTA_MULTIPATH && i != RTA_METRICS && + i != RTA_TABLE) rta[i-1] = (struct rtattr *)RTA_DATA(attr); } } @@ -507,7 +510,7 @@ int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (dn_fib_check_attr(r, rta)) return -EINVAL; - tb = dn_fib_get_table(r->rtm_table, 0); + tb = dn_fib_get_table(rtm_get_table(rta, r->rtm_table), 0); if (tb) return tb->delete(tb, r, (struct dn_kern_rta *)rta, nlh, &NETLINK_CB(skb)); @@ -523,46 +526,13 @@ int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (dn_fib_check_attr(r, rta)) return -EINVAL; - tb = dn_fib_get_table(r->rtm_table, 1); + tb = dn_fib_get_table(rtm_get_table(rta, r->rtm_table), 1); if (tb) return tb->insert(tb, r, (struct dn_kern_rta *)rta, nlh, &NETLINK_CB(skb)); return -ENOBUFS; } - -int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) -{ - int t; - int s_t; - struct dn_fib_table *tb; - - if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) && - ((struct rtmsg *)NLMSG_DATA(cb->nlh))->rtm_flags&RTM_F_CLONED) - return dn_cache_dump(skb, cb); - - s_t = cb->args[0]; - if (s_t == 0) - s_t = cb->args[0] = RT_MIN_TABLE; - - for(t = s_t; t <= RT_TABLE_MAX; t++) { - if (t < s_t) - continue; - if (t > s_t) - memset(&cb->args[1], 0, - sizeof(cb->args) - sizeof(cb->args[0])); - tb = dn_fib_get_table(t, 0); - if (tb == NULL) - continue; - if (tb->dump(tb, skb, cb) < 0) - break; - } - - cb->args[0] = t; - - return skb->len; -} - static void fib_magic(int cmd, int type, __le16 dst, int dst_len, struct dn_ifaddr *ifa) { struct dn_fib_table *tb; @@ -682,7 +652,7 @@ static int dn_fib_dnaddr_event(struct notifier_block *this, unsigned long event, return NOTIFY_DONE; } -int dn_fib_sync_down(__le16 local, struct net_device *dev, int force) +static int dn_fib_sync_down(__le16 local, struct net_device *dev, int force) { int ret = 0; int scope = RT_SCOPE_NOWHERE; @@ -726,7 +696,7 @@ int dn_fib_sync_down(__le16 local, struct net_device *dev, int force) } -int dn_fib_sync_up(struct net_device *dev) +static int dn_fib_sync_up(struct net_device *dev) { int ret = 0; @@ -760,22 +730,6 @@ int dn_fib_sync_up(struct net_device *dev) return ret; } -void dn_fib_flush(void) -{ - int flushed = 0; - struct dn_fib_table *tb; - int id; - - for(id = RT_TABLE_MAX; id > 0; id--) { - if ((tb = dn_fib_get_table(id, 0)) == NULL) - continue; - flushed += tb->flush(tb); - } - - if (flushed) - dn_rt_cache_flush(-1); -} - static struct notifier_block dn_fib_dnaddr_notifier = { .notifier_call = dn_fib_dnaddr_event, }; diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index 86f7f3b28e7..72ecc6e62ec 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -586,7 +586,7 @@ static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig goto out; } - err = sk_filter(sk, skb, 0); + err = sk_filter(sk, skb); if (err) goto out; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 743e9fcf7c5..dd0761e3d28 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -80,6 +80,7 @@ #include <net/neighbour.h> #include <net/dst.h> #include <net/flow.h> +#include <net/fib_rules.h> #include <net/dn.h> #include <net/dn_dev.h> #include <net/dn_nsp.h> @@ -1284,7 +1285,7 @@ static int dn_route_input_slow(struct sk_buff *skb) dev_hold(out_dev); if (res.r) - src_map = dn_fib_rules_policy(fl.fld_src, &res, &flags); + src_map = fl.fld_src; /* no NAT support for now */ gateway = DN_FIB_RES_GW(res); if (res.type == RTN_NAT) { @@ -1485,6 +1486,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, r->rtm_src_len = 0; r->rtm_tos = 0; r->rtm_table = RT_TABLE_MAIN; + RTA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); r->rtm_type = rt->rt_type; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; r->rtm_scope = RT_SCOPE_UNIVERSE; @@ -1609,9 +1611,7 @@ int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg) goto out_free; } - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - - return err; + return rtnl_unicast(skb, NETLINK_CB(in_skb).pid); out_free: kfree_skb(skb); @@ -1781,14 +1781,9 @@ void __init dn_route_init(void) { int i, goal, order; - dn_dst_ops.kmem_cachep = kmem_cache_create("dn_dst_cache", - sizeof(struct dn_route), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - - if (!dn_dst_ops.kmem_cachep) - panic("DECnet: Failed to allocate dn_dst_cache\n"); - + dn_dst_ops.kmem_cachep = + kmem_cache_create("dn_dst_cache", sizeof(struct dn_route), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); init_timer(&dn_route_timer); dn_route_timer.function = dn_dst_check_expire; dn_route_timer.expires = jiffies + decnet_dst_gc_interval * HZ; diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 6986be754ef..3e0c882c90b 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -11,259 +11,213 @@ * * * Changes: + * Steve Whitehouse <steve@chygwyn.com> + * Updated for Thomas Graf's generic rules * */ -#include <linux/string.h> #include <linux/net.h> -#include <linux/socket.h> -#include <linux/sockios.h> #include <linux/init.h> -#include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> -#include <linux/proc_fs.h> #include <linux/netdevice.h> -#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> #include <net/dst.h> #include <net/flow.h> +#include <net/fib_rules.h> #include <net/dn.h> #include <net/dn_fib.h> #include <net/dn_neigh.h> #include <net/dn_dev.h> +static struct fib_rules_ops dn_fib_rules_ops; + struct dn_fib_rule { - 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; - __le16 r_src; - __le16 r_srcmask; - __le16 r_dst; - __le16 r_dstmask; - __le16 r_srcmap; - u8 r_flags; + struct fib_rule common; + unsigned char dst_len; + unsigned char src_len; + __le16 src; + __le16 srcmask; + __le16 dst; + __le16 dstmask; + __le16 srcmap; + u8 flags; #ifdef CONFIG_DECNET_ROUTE_FWMARK - u32 r_fwmark; + u32 fwmark; + u32 fwmask; #endif - int r_ifindex; - char r_ifname[IFNAMSIZ]; - int r_dead; - struct rcu_head rcu; }; static struct dn_fib_rule default_rule = { - .r_clntref = ATOMIC_INIT(2), - .r_preference = 0x7fff, - .r_table = RT_TABLE_MAIN, - .r_action = RTN_UNICAST + .common = { + .refcnt = ATOMIC_INIT(2), + .pref = 0x7fff, + .table = RT_TABLE_MAIN, + .action = FR_ACT_TO_TBL, + }, }; -static struct hlist_head dn_fib_rules; +static LIST_HEAD(dn_fib_rules); + -int dn_fib_rtm_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +int dn_fib_lookup(struct flowi *flp, struct dn_fib_res *res) { - struct rtattr **rta = arg; - struct rtmsg *rtm = NLMSG_DATA(nlh); - struct dn_fib_rule *r; - struct hlist_node *node; - int err = -ESRCH; - - 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 && - (!rta[RTA_DST-1] || memcmp(RTA_DATA(rta[RTA_DST-1]), &r->r_dst, 2) == 0) && -#ifdef CONFIG_DECNET_ROUTE_FWMARK - (!rta[RTA_PROTOINFO-1] || memcmp(RTA_DATA(rta[RTA_PROTOINFO-1]), &r->r_fwmark, 4) == 0) && -#endif - (!rtm->rtm_type || rtm->rtm_type == r->r_action) && - (!rta[RTA_PRIORITY-1] || memcmp(RTA_DATA(rta[RTA_PRIORITY-1]), &r->r_preference, 4) == 0) && - (!rta[RTA_IIF-1] || rtattr_strcmp(rta[RTA_IIF-1], r->r_ifname) == 0) && - (!rtm->rtm_table || (r && rtm->rtm_table == r->r_table))) { - - err = -EPERM; - if (r == &default_rule) - break; - - hlist_del_rcu(&r->r_hlist); - r->r_dead = 1; - dn_fib_rule_put(r); - err = 0; - break; - } - } + struct fib_lookup_arg arg = { + .result = res, + }; + int err; + + err = fib_rules_lookup(&dn_fib_rules_ops, flp, 0, &arg); + res->r = arg.rule; return err; } -static inline void dn_fib_rule_put_rcu(struct rcu_head *head) +static int dn_fib_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) { - struct dn_fib_rule *r = container_of(head, struct dn_fib_rule, rcu); - kfree(r); -} + int err = -EAGAIN; + struct dn_fib_table *tbl; -void dn_fib_rule_put(struct dn_fib_rule *r) -{ - if (atomic_dec_and_test(&r->r_clntref)) { - if (r->r_dead) - call_rcu(&r->rcu, dn_fib_rule_put_rcu); - else - printk(KERN_DEBUG "Attempt to free alive dn_fib_rule\n"); + switch(rule->action) { + case FR_ACT_TO_TBL: + break; + + case FR_ACT_UNREACHABLE: + err = -ENETUNREACH; + goto errout; + + case FR_ACT_PROHIBIT: + err = -EACCES; + goto errout; + + case FR_ACT_BLACKHOLE: + default: + err = -EINVAL; + goto errout; } + + tbl = dn_fib_get_table(rule->table, 0); + if (tbl == NULL) + goto errout; + + err = tbl->lookup(tbl, flp, (struct dn_fib_res *)arg->result); + if (err > 0) + err = -EAGAIN; +errout: + return err; } +static struct nla_policy dn_fib_rule_policy[FRA_MAX+1] __read_mostly = { + [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, + [FRA_PRIORITY] = { .type = NLA_U32 }, + [FRA_SRC] = { .type = NLA_U16 }, + [FRA_DST] = { .type = NLA_U16 }, + [FRA_FWMARK] = { .type = NLA_U32 }, + [FRA_FWMASK] = { .type = NLA_U32 }, + [FRA_TABLE] = { .type = NLA_U32 }, +}; -int dn_fib_rtm_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int dn_fib_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { - struct rtattr **rta = arg; - struct rtmsg *rtm = NLMSG_DATA(nlh); - 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) - return -EINVAL; - - if (rta[RTA_IIF-1] && RTA_PAYLOAD(rta[RTA_IIF-1]) > IFNAMSIZ) - return -EINVAL; - - if (rtm->rtm_type == RTN_NAT) - return -EINVAL; - - table_id = rtm->rtm_table; - if (table_id == RT_TABLE_UNSPEC) { - struct dn_fib_table *tb; - if (rtm->rtm_type == RTN_UNICAST) { - if ((tb = dn_fib_empty_table()) == NULL) - return -ENOBUFS; - table_id = tb->n; - } - } + struct dn_fib_rule *r = (struct dn_fib_rule *)rule; + u16 daddr = fl->fld_dst; + u16 saddr = fl->fld_src; + + if (((saddr ^ r->src) & r->srcmask) || + ((daddr ^ r->dst) & r->dstmask)) + return 0; - new_r = kzalloc(sizeof(*new_r), GFP_KERNEL); - if (!new_r) - return -ENOMEM; - - if (rta[RTA_SRC-1]) - memcpy(&new_r->r_src, RTA_DATA(rta[RTA_SRC-1]), 2); - if (rta[RTA_DST-1]) - memcpy(&new_r->r_dst, RTA_DATA(rta[RTA_DST-1]), 2); - if (rta[RTA_GATEWAY-1]) - memcpy(&new_r->r_srcmap, RTA_DATA(rta[RTA_GATEWAY-1]), 2); - new_r->r_src_len = rtm->rtm_src_len; - new_r->r_dst_len = rtm->rtm_dst_len; - new_r->r_srcmask = dnet_make_mask(rtm->rtm_src_len); - new_r->r_dstmask = dnet_make_mask(rtm->rtm_dst_len); #ifdef CONFIG_DECNET_ROUTE_FWMARK - if (rta[RTA_PROTOINFO-1]) - memcpy(&new_r->r_fwmark, RTA_DATA(rta[RTA_PROTOINFO-1]), 4); + if ((r->fwmark ^ fl->fld_fwmark) & r->fwmask) + return 0; #endif - new_r->r_action = rtm->rtm_type; - new_r->r_flags = rtm->rtm_flags; - if (rta[RTA_PRIORITY-1]) - memcpy(&new_r->r_preference, RTA_DATA(rta[RTA_PRIORITY-1]), 4); - new_r->r_table = table_id; - if (rta[RTA_IIF-1]) { - struct net_device *dev; - rtattr_strlcpy(new_r->r_ifname, rta[RTA_IIF-1], IFNAMSIZ); - new_r->r_ifindex = -1; - dev = dev_get_by_name(new_r->r_ifname); - if (dev) { - new_r->r_ifindex = dev->ifindex; - dev_put(dev); - } - } - r = container_of(dn_fib_rules.first, struct dn_fib_rule, r_hlist); - if (!new_r->r_preference) { - 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; + return 1; +} + +static int dn_fib_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct nlmsghdr *nlh, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + int err = -EINVAL; + struct dn_fib_rule *r = (struct dn_fib_rule *)rule; + + if (frh->src_len > 16 || frh->dst_len > 16 || frh->tos) + goto errout; + + if (rule->table == RT_TABLE_UNSPEC) { + if (rule->action == FR_ACT_TO_TBL) { + struct dn_fib_table *table; + + table = dn_fib_empty_table(); + if (table == NULL) { + err = -ENOBUFS; + goto errout; + } + + rule->table = table->n; } } - hlist_for_each_entry(r, node, &dn_fib_rules, r_hlist) { - if (r->r_preference > new_r->r_preference) - break; - last = r; + if (tb[FRA_SRC]) + r->src = nla_get_u16(tb[FRA_SRC]); + + if (tb[FRA_DST]) + r->dst = nla_get_u16(tb[FRA_DST]); + +#ifdef CONFIG_DECNET_ROUTE_FWMARK + if (tb[FRA_FWMARK]) { + r->fwmark = nla_get_u32(tb[FRA_FWMARK]); + if (r->fwmark) + /* compatibility: if the mark value is non-zero all bits + * are compared unless a mask is explicitly specified. + */ + r->fwmask = 0xFFFFFFFF; } - atomic_inc(&new_r->r_clntref); - 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; -} + if (tb[FRA_FWMASK]) + r->fwmask = nla_get_u32(tb[FRA_FWMASK]); +#endif + r->src_len = frh->src_len; + r->srcmask = dnet_make_mask(r->src_len); + r->dst_len = frh->dst_len; + r->dstmask = dnet_make_mask(r->dst_len); + err = 0; +errout: + return err; +} -int dn_fib_lookup(const struct flowi *flp, struct dn_fib_res *res) +static int dn_fib_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) { - struct dn_fib_rule *r, *policy; - struct dn_fib_table *tb; - __le16 saddr = flp->fld_src; - __le16 daddr = flp->fld_dst; - struct hlist_node *node; - int err; + struct dn_fib_rule *r = (struct dn_fib_rule *)rule; + + if (frh->src_len && (r->src_len != frh->src_len)) + return 0; - rcu_read_lock(); + if (frh->dst_len && (r->dst_len != frh->dst_len)) + return 0; - 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 - (r->r_fwmark && r->r_fwmark != flp->fld_fwmark) || + if (tb[FRA_FWMARK] && (r->fwmark != nla_get_u32(tb[FRA_FWMARK]))) + return 0; + + if (tb[FRA_FWMASK] && (r->fwmask != nla_get_u32(tb[FRA_FWMASK]))) + return 0; #endif - (r->r_ifindex && r->r_ifindex != flp->iif)) - continue; - - switch(r->r_action) { - case RTN_UNICAST: - case RTN_NAT: - policy = r; - break; - case RTN_UNREACHABLE: - rcu_read_unlock(); - return -ENETUNREACH; - default: - case RTN_BLACKHOLE: - rcu_read_unlock(); - return -EINVAL; - case RTN_PROHIBIT: - rcu_read_unlock(); - return -EACCES; - } - if ((tb = dn_fib_get_table(r->r_table, 0)) == NULL) - continue; - err = tb->lookup(tb, flp, res); - if (err == 0) { - res->r = policy; - if (policy) - atomic_inc(&policy->r_clntref); - rcu_read_unlock(); - return 0; - } - if (err < 0 && err != -EAGAIN) { - rcu_read_unlock(); - return err; - } - } + if (tb[FRA_SRC] && (r->src != nla_get_u16(tb[FRA_SRC]))) + return 0; + + if (tb[FRA_DST] && (r->dst != nla_get_u16(tb[FRA_DST]))) + return 0; - rcu_read_unlock(); - return -ESRCH; + return 1; } unsigned dnet_addr_type(__le16 addr) @@ -271,7 +225,7 @@ unsigned dnet_addr_type(__le16 addr) struct flowi fl = { .nl_u = { .dn_u = { .daddr = addr } } }; struct dn_fib_res res; unsigned ret = RTN_UNICAST; - struct dn_fib_table *tb = dn_fib_tables[RT_TABLE_LOCAL]; + struct dn_fib_table *tb = dn_fib_get_table(RT_TABLE_LOCAL, 0); res.r = NULL; @@ -284,142 +238,79 @@ unsigned dnet_addr_type(__le16 addr) return ret; } -__le16 dn_fib_rules_policy(__le16 saddr, struct dn_fib_res *res, unsigned *flags) +static int dn_fib_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct nlmsghdr *nlh, struct fib_rule_hdr *frh) { - struct dn_fib_rule *r = res->r; + struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - if (r->r_action == RTN_NAT) { - int addrtype = dnet_addr_type(r->r_srcmap); + frh->family = AF_DECnet; + frh->dst_len = r->dst_len; + frh->src_len = r->src_len; + frh->tos = 0; - if (addrtype == RTN_NAT) { - saddr = (saddr&~r->r_srcmask)|r->r_srcmap; - *flags |= RTCF_SNAT; - } else if (addrtype == RTN_LOCAL || r->r_srcmap == 0) { - saddr = r->r_srcmap; - *flags |= RTCF_MASQ; - } - } - return saddr; -} - -static void dn_fib_rules_detach(struct net_device *dev) -{ - struct hlist_node *node; - struct dn_fib_rule *r; - - hlist_for_each_entry(r, node, &dn_fib_rules, r_hlist) { - if (r->r_ifindex == dev->ifindex) - r->r_ifindex = -1; - } -} +#ifdef CONFIG_DECNET_ROUTE_FWMARK + if (r->fwmark) + NLA_PUT_U32(skb, FRA_FWMARK, r->fwmark); + if (r->fwmask || r->fwmark) + NLA_PUT_U32(skb, FRA_FWMASK, r->fwmask); +#endif + if (r->dst_len) + NLA_PUT_U16(skb, FRA_DST, r->dst); + if (r->src_len) + NLA_PUT_U16(skb, FRA_SRC, r->src); -static void dn_fib_rules_attach(struct net_device *dev) -{ - struct hlist_node *node; - struct dn_fib_rule *r; + return 0; - 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; - } +nla_put_failure: + return -ENOBUFS; } -static int dn_fib_rules_event(struct notifier_block *this, unsigned long event, void *ptr) +static u32 dn_fib_rule_default_pref(void) { - struct net_device *dev = ptr; - - switch(event) { - case NETDEV_UNREGISTER: - dn_fib_rules_detach(dev); - dn_fib_sync_down(0, dev, 1); - case NETDEV_REGISTER: - dn_fib_rules_attach(dev); - dn_fib_sync_up(dev); + struct list_head *pos; + struct fib_rule *rule; + + if (!list_empty(&dn_fib_rules)) { + pos = dn_fib_rules.next; + if (pos->next != &dn_fib_rules) { + rule = list_entry(pos->next, struct fib_rule, list); + if (rule->pref) + return rule->pref - 1; + } } - return NOTIFY_DONE; -} - - -static struct notifier_block dn_fib_rules_notifier = { - .notifier_call = dn_fib_rules_event, -}; - -static int dn_fib_fill_rule(struct sk_buff *skb, struct dn_fib_rule *r, - struct netlink_callback *cb, unsigned int flags) -{ - struct rtmsg *rtm; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - - - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWRULE, sizeof(*rtm), flags); - rtm = NLMSG_DATA(nlh); - rtm->rtm_family = AF_DECnet; - rtm->rtm_dst_len = r->r_dst_len; - rtm->rtm_src_len = r->r_src_len; - rtm->rtm_tos = 0; -#ifdef CONFIG_DECNET_ROUTE_FWMARK - if (r->r_fwmark) - RTA_PUT(skb, RTA_PROTOINFO, 4, &r->r_fwmark); -#endif - rtm->rtm_table = r->r_table; - rtm->rtm_protocol = 0; - rtm->rtm_scope = 0; - rtm->rtm_type = r->r_action; - rtm->rtm_flags = r->r_flags; - - if (r->r_dst_len) - RTA_PUT(skb, RTA_DST, 2, &r->r_dst); - if (r->r_src_len) - RTA_PUT(skb, RTA_SRC, 2, &r->r_src); - if (r->r_ifname[0]) - RTA_PUT(skb, RTA_IIF, IFNAMSIZ, &r->r_ifname); - if (r->r_preference) - RTA_PUT(skb, RTA_PRIORITY, 4, &r->r_preference); - if (r->r_srcmap) - RTA_PUT(skb, RTA_GATEWAY, 2, &r->r_srcmap); - nlh->nlmsg_len = skb->tail - b; - return skb->len; - -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + return 0; } int dn_fib_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) { - int idx = 0; - int s_idx = cb->args[0]; - struct dn_fib_rule *r; - struct hlist_node *node; - - rcu_read_lock(); - hlist_for_each_entry(r, node, &dn_fib_rules, r_hlist) { - if (idx < s_idx) - goto next; - if (dn_fib_fill_rule(skb, r, cb, NLM_F_MULTI) < 0) - break; -next: - idx++; - } - rcu_read_unlock(); - cb->args[0] = idx; - - return skb->len; + return fib_rules_dump(skb, cb, AF_DECnet); } +static struct fib_rules_ops dn_fib_rules_ops = { + .family = AF_DECnet, + .rule_size = sizeof(struct dn_fib_rule), + .action = dn_fib_rule_action, + .match = dn_fib_rule_match, + .configure = dn_fib_rule_configure, + .compare = dn_fib_rule_compare, + .fill = dn_fib_rule_fill, + .default_pref = dn_fib_rule_default_pref, + .nlgroup = RTNLGRP_DECnet_RULE, + .policy = dn_fib_rule_policy, + .rules_list = &dn_fib_rules, + .owner = THIS_MODULE, +}; + 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); + list_add_tail(&default_rule.common.list, &dn_fib_rules); + fib_rules_register(&dn_fib_rules_ops); } void __exit dn_fib_rules_cleanup(void) { - unregister_netdevice_notifier(&dn_fib_rules_notifier); + fib_rules_unregister(&dn_fib_rules_ops); } diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index e926c952e36..317904bb589 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -30,6 +30,7 @@ #include <net/neighbour.h> #include <net/dst.h> #include <net/flow.h> +#include <net/fib_rules.h> #include <net/dn.h> #include <net/dn_route.h> #include <net/dn_fib.h> @@ -74,9 +75,9 @@ for( ; ((f) = *(fp)) != NULL; (fp) = &(f)->fn_next) for( ; ((f) = *(fp)) != NULL && dn_key_eq((f)->fn_key, (key)); (fp) = &(f)->fn_next) #define RT_TABLE_MIN 1 - +#define DN_FIB_TABLE_HASHSZ 256 +static struct hlist_head dn_fib_table_hash[DN_FIB_TABLE_HASHSZ]; static DEFINE_RWLOCK(dn_fib_tables_lock); -struct dn_fib_table *dn_fib_tables[RT_TABLE_MAX + 1]; static kmem_cache_t *dn_hash_kmem __read_mostly; static int dn_fib_hash_zombies; @@ -263,7 +264,7 @@ static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct dn_kern } static int dn_fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u8 tb_id, u8 type, u8 scope, void *dst, int dst_len, + u32 tb_id, u8 type, u8 scope, void *dst, int dst_len, struct dn_fib_info *fi, unsigned int flags) { struct rtmsg *rtm; @@ -277,6 +278,7 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_src_len = 0; rtm->rtm_tos = 0; rtm->rtm_table = tb_id; + RTA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = scope; rtm->rtm_type = type; @@ -326,29 +328,29 @@ rtattr_failure: } -static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, int tb_id, +static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, u32 tb_id, struct nlmsghdr *nlh, struct netlink_skb_parms *req) { struct sk_buff *skb; u32 pid = req ? req->pid : 0; - int size = NLMSG_SPACE(sizeof(struct rtmsg) + 256); + int err = -ENOBUFS; - skb = alloc_skb(size, GFP_KERNEL); - if (!skb) - return; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto errout; - if (dn_fib_dump_info(skb, pid, nlh->nlmsg_seq, event, tb_id, - f->fn_type, f->fn_scope, &f->fn_key, z, - DN_FIB_INFO(f), 0) < 0) { + err = dn_fib_dump_info(skb, pid, nlh->nlmsg_seq, event, tb_id, + f->fn_type, f->fn_scope, &f->fn_key, z, + DN_FIB_INFO(f), 0); + if (err < 0) { kfree_skb(skb); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_DECnet_ROUTE; - if (nlh->nlmsg_flags & NLM_F_ECHO) - atomic_inc(&skb->users); - netlink_broadcast(rtnl, skb, pid, RTNLGRP_DECnet_ROUTE, GFP_KERNEL); - if (nlh->nlmsg_flags & NLM_F_ECHO) - netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT); + + err = rtnl_notify(skb, pid, RTNLGRP_DECnet_ROUTE, nlh, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_DECnet_ROUTE, err); } static __inline__ int dn_hash_dump_bucket(struct sk_buff *skb, @@ -359,7 +361,7 @@ static __inline__ int dn_hash_dump_bucket(struct sk_buff *skb, { int i, s_i; - s_i = cb->args[3]; + s_i = cb->args[4]; for(i = 0; f; i++, f = f->fn_next) { if (i < s_i) continue; @@ -372,11 +374,11 @@ static __inline__ int dn_hash_dump_bucket(struct sk_buff *skb, (f->fn_state & DN_S_ZOMBIE) ? 0 : f->fn_type, f->fn_scope, &f->fn_key, dz->dz_order, f->fn_info, NLM_F_MULTI) < 0) { - cb->args[3] = i; + cb->args[4] = i; return -1; } } - cb->args[3] = i; + cb->args[4] = i; return skb->len; } @@ -387,20 +389,20 @@ static __inline__ int dn_hash_dump_zone(struct sk_buff *skb, { int h, s_h; - s_h = cb->args[2]; + s_h = cb->args[3]; for(h = 0; h < dz->dz_divisor; h++) { if (h < s_h) continue; if (h > s_h) - memset(&cb->args[3], 0, sizeof(cb->args) - 3*sizeof(cb->args[0])); + memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0])); if (dz->dz_hash == NULL || dz->dz_hash[h] == NULL) continue; if (dn_hash_dump_bucket(skb, cb, tb, dz, dz->dz_hash[h]) < 0) { - cb->args[2] = h; + cb->args[3] = h; return -1; } } - cb->args[2] = h; + cb->args[3] = h; return skb->len; } @@ -411,26 +413,63 @@ static int dn_fib_table_dump(struct dn_fib_table *tb, struct sk_buff *skb, struct dn_zone *dz; struct dn_hash *table = (struct dn_hash *)tb->data; - s_m = cb->args[1]; + s_m = cb->args[2]; read_lock(&dn_fib_tables_lock); for(dz = table->dh_zone_list, m = 0; dz; dz = dz->dz_next, m++) { if (m < s_m) continue; if (m > s_m) - memset(&cb->args[2], 0, sizeof(cb->args) - 2*sizeof(cb->args[0])); + memset(&cb->args[3], 0, sizeof(cb->args) - 3*sizeof(cb->args[0])); if (dn_hash_dump_zone(skb, cb, tb, dz) < 0) { - cb->args[1] = m; + cb->args[2] = m; read_unlock(&dn_fib_tables_lock); return -1; } } read_unlock(&dn_fib_tables_lock); - cb->args[1] = m; + cb->args[2] = m; return skb->len; } +int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + unsigned int h, s_h; + unsigned int e = 0, s_e; + struct dn_fib_table *tb; + struct hlist_node *node; + int dumped = 0; + + if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) && + ((struct rtmsg *)NLMSG_DATA(cb->nlh))->rtm_flags&RTM_F_CLONED) + return dn_cache_dump(skb, cb); + + s_h = cb->args[0]; + s_e = cb->args[1]; + + for (h = s_h; h < DN_FIB_TABLE_HASHSZ; h++, s_h = 0) { + e = 0; + hlist_for_each_entry(tb, node, &dn_fib_table_hash[h], hlist) { + if (e < s_e) + goto next; + if (dumped) + memset(&cb->args[2], 0, sizeof(cb->args) - + 2 * sizeof(cb->args[0])); + if (tb->dump(tb, skb, cb) < 0) + goto out; + dumped = 1; +next: + e++; + } + } +out: + cb->args[1] = e; + cb->args[0] = h; + + return skb->len; +} + static int dn_fib_table_insert(struct dn_fib_table *tb, struct rtmsg *r, struct dn_kern_rta *rta, struct nlmsghdr *n, struct netlink_skb_parms *req) { struct dn_hash *table = (struct dn_hash *)tb->data; @@ -739,9 +778,11 @@ out: } -struct dn_fib_table *dn_fib_get_table(int n, int create) +struct dn_fib_table *dn_fib_get_table(u32 n, int create) { struct dn_fib_table *t; + struct hlist_node *node; + unsigned int h; if (n < RT_TABLE_MIN) return NULL; @@ -749,8 +790,15 @@ struct dn_fib_table *dn_fib_get_table(int n, int create) if (n > RT_TABLE_MAX) return NULL; - if (dn_fib_tables[n]) - return dn_fib_tables[n]; + h = n & (DN_FIB_TABLE_HASHSZ - 1); + rcu_read_lock(); + hlist_for_each_entry_rcu(t, node, &dn_fib_table_hash[h], hlist) { + if (t->n == n) { + rcu_read_unlock(); + return t; + } + } + rcu_read_unlock(); if (!create) return NULL; @@ -771,33 +819,37 @@ struct dn_fib_table *dn_fib_get_table(int n, int create) t->flush = dn_fib_table_flush; t->dump = dn_fib_table_dump; memset(t->data, 0, sizeof(struct dn_hash)); - dn_fib_tables[n] = t; + hlist_add_head_rcu(&t->hlist, &dn_fib_table_hash[h]); return t; } -static void dn_fib_del_tree(int n) -{ - struct dn_fib_table *t; - - write_lock(&dn_fib_tables_lock); - t = dn_fib_tables[n]; - dn_fib_tables[n] = NULL; - write_unlock(&dn_fib_tables_lock); - - kfree(t); -} - struct dn_fib_table *dn_fib_empty_table(void) { - int id; + u32 id; for(id = RT_TABLE_MIN; id <= RT_TABLE_MAX; id++) - if (dn_fib_tables[id] == NULL) + if (dn_fib_get_table(id, 0) == NULL) return dn_fib_get_table(id, 1); return NULL; } +void dn_fib_flush(void) +{ + int flushed = 0; + struct dn_fib_table *tb; + struct hlist_node *node; + unsigned int h; + + for (h = 0; h < DN_FIB_TABLE_HASHSZ; h++) { + hlist_for_each_entry(tb, node, &dn_fib_table_hash[h], hlist) + flushed += tb->flush(tb); + } + + if (flushed) + dn_rt_cache_flush(-1); +} + void __init dn_fib_table_init(void) { dn_hash_kmem = kmem_cache_create("dn_fib_info_cache", @@ -808,10 +860,17 @@ void __init dn_fib_table_init(void) void __exit dn_fib_table_cleanup(void) { - int i; - - for (i = RT_TABLE_MIN; i <= RT_TABLE_MAX; ++i) - dn_fib_del_tree(i); + struct dn_fib_table *t; + struct hlist_node *node, *next; + unsigned int h; - return; + write_lock(&dn_fib_tables_lock); + for (h = 0; h < DN_FIB_TABLE_HASHSZ; h++) { + hlist_for_each_entry_safe(t, node, next, &dn_fib_table_hash[h], + hlist) { + hlist_del(&t->hlist); + kfree(t); + } + } + write_unlock(&dn_fib_tables_lock); } diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 387c71c584e..43863933f27 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -64,81 +64,79 @@ __setup("ether=", netdev_boot_setup); -/* - * Create the Ethernet MAC header for an arbitrary protocol layer +/** + * eth_header - create the Ethernet header + * @skb: buffer to alter + * @dev: source device + * @type: Ethernet type field + * @daddr: destination address (NULL leave destination address) + * @saddr: source address (NULL use device source address) + * @len: packet length (<= skb->len) * - * saddr=NULL means use device source address - * daddr=NULL means leave destination address (eg unresolved arp) + * + * Set the protocol type. For a packet of type ETH_P_802_3 we put the length + * in here instead. It is up to the 802.2 layer to carry protocol information. */ - int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, - void *daddr, void *saddr, unsigned len) + void *daddr, void *saddr, unsigned len) { - struct ethhdr *eth = (struct ethhdr *)skb_push(skb,ETH_HLEN); + struct ethhdr *eth = (struct ethhdr *)skb_push(skb, ETH_HLEN); - /* - * Set the protocol type. For a packet of type ETH_P_802_3 we put the length - * in here instead. It is up to the 802.2 layer to carry protocol information. - */ - - if(type!=ETH_P_802_3) + if (type != ETH_P_802_3) eth->h_proto = htons(type); else eth->h_proto = htons(len); /* - * Set the source hardware address. + * Set the source hardware address. */ - - if(!saddr) + + if (!saddr) saddr = dev->dev_addr; - memcpy(eth->h_source,saddr,dev->addr_len); + memcpy(eth->h_source, saddr, dev->addr_len); - if(daddr) - { - memcpy(eth->h_dest,daddr,dev->addr_len); + if (daddr) { + memcpy(eth->h_dest, daddr, dev->addr_len); return ETH_HLEN; } - + /* - * Anyway, the loopback-device should never use this function... + * Anyway, the loopback-device should never use this function... */ - if (dev->flags & (IFF_LOOPBACK|IFF_NOARP)) - { + if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { memset(eth->h_dest, 0, dev->addr_len); return ETH_HLEN; } - + return -ETH_HLEN; } - -/* - * Rebuild the Ethernet MAC header. This is called after an ARP - * (or in future other address resolution) has completed on this - * sk_buff. We now let ARP fill in the other fields. +/** + * eth_rebuild_header- rebuild the Ethernet MAC header. + * @skb: socket buffer to update * - * This routine CANNOT use cached dst->neigh! - * Really, it is used only when dst->neigh is wrong. + * This is called after an ARP or IPV6 ndisc it's resolution on this + * sk_buff. We now let protocol (ARP) fill in the other fields. + * + * This routine CANNOT use cached dst->neigh! + * Really, it is used only when dst->neigh is wrong. */ - int eth_rebuild_header(struct sk_buff *skb) { struct ethhdr *eth = (struct ethhdr *)skb->data; struct net_device *dev = skb->dev; - switch (eth->h_proto) - { + switch (eth->h_proto) { #ifdef CONFIG_INET case __constant_htons(ETH_P_IP): - return arp_find(eth->h_dest, skb); -#endif + return arp_find(eth->h_dest, skb); +#endif default: printk(KERN_DEBUG - "%s: unable to resolve type %X addresses.\n", + "%s: unable to resolve type %X addresses.\n", dev->name, (int)eth->h_proto); - + memcpy(eth->h_source, dev->dev_addr, dev->addr_len); break; } @@ -146,62 +144,70 @@ int eth_rebuild_header(struct sk_buff *skb) return 0; } - -/* - * Determine the packet's protocol ID. The rule here is that we - * assume 802.3 if the type field is short enough to be a length. - * This is normal practice and works for any 'now in use' protocol. +/** + * eth_type_trans - determine the packet's protocol ID. + * @skb: received socket data + * @dev: receiving network device + * + * The rule here is that we + * assume 802.3 if the type field is short enough to be a length. + * This is normal practice and works for any 'now in use' protocol. */ - __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) { struct ethhdr *eth; unsigned char *rawp; - + skb->mac.raw = skb->data; - skb_pull(skb,ETH_HLEN); + skb_pull(skb, ETH_HLEN); eth = eth_hdr(skb); - + if (is_multicast_ether_addr(eth->h_dest)) { if (!compare_ether_addr(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; } - + /* - * This ALLMULTI check should be redundant by 1.4 - * so don't forget to remove it. + * This ALLMULTI check should be redundant by 1.4 + * so don't forget to remove it. * - * Seems, you forgot to remove it. All silly devices - * seems to set IFF_PROMISC. + * Seems, you forgot to remove it. All silly devices + * seems to set IFF_PROMISC. */ - - else if(1 /*dev->flags&IFF_PROMISC*/) { + + else if (1 /*dev->flags&IFF_PROMISC */ ) { if (unlikely(compare_ether_addr(eth->h_dest, dev->dev_addr))) skb->pkt_type = PACKET_OTHERHOST; } - + if (ntohs(eth->h_proto) >= 1536) return eth->h_proto; - + rawp = skb->data; - + /* - * This is a magic hack to spot IPX packets. Older Novell breaks - * the protocol design and runs IPX over 802.3 without an 802.2 LLC - * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This - * won't work for fault tolerant netware but does for the rest. + * This is a magic hack to spot IPX packets. Older Novell breaks + * the protocol design and runs IPX over 802.3 without an 802.2 LLC + * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This + * won't work for fault tolerant netware but does for the rest. */ if (*(unsigned short *)rawp == 0xFFFF) return htons(ETH_P_802_3); - + /* - * Real 802.2 LLC + * Real 802.2 LLC */ return htons(ETH_P_802_2); } +EXPORT_SYMBOL(eth_type_trans); +/** + * eth_header_parse - extract hardware address from packet + * @skb: packet to extract header from + * @haddr: destination buffer + */ static int eth_header_parse(struct sk_buff *skb, unsigned char *haddr) { struct ethhdr *eth = eth_hdr(skb); @@ -209,14 +215,20 @@ static int eth_header_parse(struct sk_buff *skb, unsigned char *haddr) return ETH_ALEN; } +/** + * eth_header_cache - fill cache entry from neighbour + * @neigh: source neighbour + * @hh: destination cache entry + * Create an Ethernet header template from the neighbour. + */ int eth_header_cache(struct neighbour *neigh, struct hh_cache *hh) { unsigned short type = hh->hh_type; struct ethhdr *eth; struct net_device *dev = neigh->dev; - eth = (struct ethhdr*) - (((u8*)hh->hh_data) + (HH_DATA_OFF(sizeof(*eth)))); + eth = (struct ethhdr *) + (((u8 *) hh->hh_data) + (HH_DATA_OFF(sizeof(*eth)))); if (type == __constant_htons(ETH_P_802_3)) return -1; @@ -228,27 +240,47 @@ int eth_header_cache(struct neighbour *neigh, struct hh_cache *hh) return 0; } -/* +/** + * eth_header_cache_update - update cache entry + * @hh: destination cache entry + * @dev: network device + * @haddr: new hardware address + * * Called by Address Resolution module to notify changes in address. */ - -void eth_header_cache_update(struct hh_cache *hh, struct net_device *dev, unsigned char * haddr) +void eth_header_cache_update(struct hh_cache *hh, struct net_device *dev, + unsigned char *haddr) { - memcpy(((u8*)hh->hh_data) + HH_DATA_OFF(sizeof(struct ethhdr)), + memcpy(((u8 *) hh->hh_data) + HH_DATA_OFF(sizeof(struct ethhdr)), haddr, dev->addr_len); } -EXPORT_SYMBOL(eth_type_trans); - +/** + * eth_mac_addr - set new Ethernet hardware address + * @dev: network device + * @p: socket address + * Change hardware address of device. + * + * This doesn't change hardware matching, so needs to be overridden + * for most real devices. + */ static int eth_mac_addr(struct net_device *dev, void *p) { - struct sockaddr *addr=p; + struct sockaddr *addr = p; if (netif_running(dev)) return -EBUSY; - memcpy(dev->dev_addr, addr->sa_data,dev->addr_len); + memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); return 0; } +/** + * eth_change_mtu - set new MTU size + * @dev: network device + * @new_mtu: new Maximum Transfer Unit + * + * Allow changing MTU size. Needs to be overridden for devices + * supporting jumbo frames. + */ static int eth_change_mtu(struct net_device *dev, int new_mtu) { if (new_mtu < 68 || new_mtu > ETH_DATA_LEN) @@ -257,8 +289,10 @@ static int eth_change_mtu(struct net_device *dev, int new_mtu) return 0; } -/* - * Fill in the fields of the device structure with ethernet-generic values. +/** + * ether_setup - setup Ethernet network device + * @dev: network device + * Fill in the fields of the device structure with Ethernet-generic values. */ void ether_setup(struct net_device *dev) { @@ -277,21 +311,21 @@ void ether_setup(struct net_device *dev) dev->tx_queue_len = 1000; /* Ethernet wants good queues */ dev->flags = IFF_BROADCAST|IFF_MULTICAST; - memset(dev->broadcast,0xFF, ETH_ALEN); + memset(dev->broadcast, 0xFF, ETH_ALEN); } EXPORT_SYMBOL(ether_setup); /** - * alloc_etherdev - Allocates and sets up an ethernet device + * alloc_etherdev - Allocates and sets up an Ethernet device * @sizeof_priv: Size of additional driver-private structure to be allocated - * for this ethernet device + * for this Ethernet device * - * Fill in the fields of the device structure with ethernet-generic + * Fill in the fields of the device structure with Ethernet-generic * values. Basically does everything except registering the device. * * Constructs a new net device, complete with a private data area of - * size @sizeof_priv. A 32-byte (not bit) alignment is enforced for + * size (sizeof_priv). A 32-byte (not bit) alignment is enforced for * this private data area. */ diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 3b5d504a74b..1650b64415a 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -88,6 +88,7 @@ config IP_FIB_HASH config IP_MULTIPLE_TABLES bool "IP: policy routing" depends on IP_ADVANCED_ROUTER + select FIB_RULES ---help--- Normally, a router decides what to do with a received packet based solely on the packet's final destination address. If you say Y here, diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 4878fc5be85..f66049e28ae 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -47,6 +47,7 @@ obj-$(CONFIG_TCP_CONG_VEGAS) += tcp_vegas.o obj-$(CONFIG_TCP_CONG_VENO) += tcp_veno.o obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o +obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c84a32070f8..fdd89e37b9a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -67,7 +67,6 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/types.h> @@ -392,7 +391,7 @@ int inet_release(struct socket *sock) } /* It is off by default, see below. */ -int sysctl_ip_nonlocal_bind; +int sysctl_ip_nonlocal_bind __read_mostly; int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { @@ -988,7 +987,7 @@ void inet_unregister_protosw(struct inet_protosw *p) * Shall we try to damage output packets if routing dev changes? */ -int sysctl_ip_dynaddr; +int sysctl_ip_dynaddr __read_mostly; static int inet_sk_reselect_saddr(struct sock *sk) { @@ -1074,6 +1073,7 @@ int inet_sk_rebuild_header(struct sock *sk) }, }; + security_sk_classify_flow(sk, &fl); err = ip_route_output_flow(&rt, &fl, sk, 0); } if (!err) @@ -1254,10 +1254,7 @@ static int __init inet_init(void) struct list_head *r; int rc = -EINVAL; - if (sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb)) { - printk(KERN_CRIT "%s: panic\n", __FUNCTION__); - goto out; - } + BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb)); rc = proto_register(&tcp_prot, 1); if (rc) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 2b98943e6b0..99542977e47 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -35,7 +35,7 @@ static int ip_clear_mutable_options(struct iphdr *iph, u32 *daddr) switch (*optptr) { case IPOPT_SEC: case 0x85: /* Some "Extended Security" crap. */ - case 0x86: /* Another "Commercial Security" crap. */ + case IPOPT_CIPSO: case IPOPT_RA: case 0x80|21: /* RFC1770 */ break; @@ -265,7 +265,7 @@ static int ah_init_state(struct xfrm_state *x) goto error; x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) + ahp->icv_trunc_len); - if (x->props.mode) + if (x->props.mode == XFRM_MODE_TUNNEL) x->props.header_len += sizeof(struct iphdr); x->data = ahp; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c new file mode 100644 index 00000000000..80a2a0911b4 --- /dev/null +++ b/net/ipv4/cipso_ipv4.c @@ -0,0 +1,1607 @@ +/* + * CIPSO - Commercial IP Security Option + * + * This is an implementation of the CIPSO 2.2 protocol as specified in + * draft-ietf-cipso-ipsecurity-01.txt with additional tag types as found in + * FIPS-188, copies of both documents can be found in the Documentation + * directory. While CIPSO never became a full IETF RFC standard many vendors + * have chosen to adopt the protocol and over the years it has become a + * de-facto standard for labeled networking. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/init.h> +#include <linux/types.h> +#include <linux/rcupdate.h> +#include <linux/list.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/jhash.h> +#include <net/ip.h> +#include <net/icmp.h> +#include <net/tcp.h> +#include <net/netlabel.h> +#include <net/cipso_ipv4.h> +#include <asm/bug.h> + +struct cipso_v4_domhsh_entry { + char *domain; + u32 valid; + struct list_head list; + struct rcu_head rcu; +}; + +/* List of available DOI definitions */ +/* XXX - Updates should be minimal so having a single lock for the + * cipso_v4_doi_list and the cipso_v4_doi_list->dom_list should be + * okay. */ +/* XXX - This currently assumes a minimal number of different DOIs in use, + * if in practice there are a lot of different DOIs this list should + * probably be turned into a hash table or something similar so we + * can do quick lookups. */ +static DEFINE_SPINLOCK(cipso_v4_doi_list_lock); +static struct list_head cipso_v4_doi_list = LIST_HEAD_INIT(cipso_v4_doi_list); + +/* Label mapping cache */ +int cipso_v4_cache_enabled = 1; +int cipso_v4_cache_bucketsize = 10; +#define CIPSO_V4_CACHE_BUCKETBITS 7 +#define CIPSO_V4_CACHE_BUCKETS (1 << CIPSO_V4_CACHE_BUCKETBITS) +#define CIPSO_V4_CACHE_REORDERLIMIT 10 +struct cipso_v4_map_cache_bkt { + spinlock_t lock; + u32 size; + struct list_head list; +}; +struct cipso_v4_map_cache_entry { + u32 hash; + unsigned char *key; + size_t key_len; + + struct netlbl_lsm_cache lsm_data; + + u32 activity; + struct list_head list; +}; +static struct cipso_v4_map_cache_bkt *cipso_v4_cache = NULL; + +/* Restricted bitmap (tag #1) flags */ +int cipso_v4_rbm_optfmt = 0; +int cipso_v4_rbm_strictvalid = 1; + +/* + * Helper Functions + */ + +/** + * cipso_v4_bitmap_walk - Walk a bitmap looking for a bit + * @bitmap: the bitmap + * @bitmap_len: length in bits + * @offset: starting offset + * @state: if non-zero, look for a set (1) bit else look for a cleared (0) bit + * + * Description: + * Starting at @offset, walk the bitmap from left to right until either the + * desired bit is found or we reach the end. Return the bit offset, -1 if + * not found, or -2 if error. + */ +static int cipso_v4_bitmap_walk(const unsigned char *bitmap, + u32 bitmap_len, + u32 offset, + u8 state) +{ + u32 bit_spot; + u32 byte_offset; + unsigned char bitmask; + unsigned char byte; + + /* gcc always rounds to zero when doing integer division */ + byte_offset = offset / 8; + byte = bitmap[byte_offset]; + bit_spot = offset; + bitmask = 0x80 >> (offset % 8); + + while (bit_spot < bitmap_len) { + if ((state && (byte & bitmask) == bitmask) || + (state == 0 && (byte & bitmask) == 0)) + return bit_spot; + + bit_spot++; + bitmask >>= 1; + if (bitmask == 0) { + byte = bitmap[++byte_offset]; + bitmask = 0x80; + } + } + + return -1; +} + +/** + * cipso_v4_bitmap_setbit - Sets a single bit in a bitmap + * @bitmap: the bitmap + * @bit: the bit + * @state: if non-zero, set the bit (1) else clear the bit (0) + * + * Description: + * Set a single bit in the bitmask. Returns zero on success, negative values + * on error. + */ +static void cipso_v4_bitmap_setbit(unsigned char *bitmap, + u32 bit, + u8 state) +{ + u32 byte_spot; + u8 bitmask; + + /* gcc always rounds to zero when doing integer division */ + byte_spot = bit / 8; + bitmask = 0x80 >> (bit % 8); + if (state) + bitmap[byte_spot] |= bitmask; + else + bitmap[byte_spot] &= ~bitmask; +} + +/** + * cipso_v4_doi_domhsh_free - Frees a domain list entry + * @entry: the entry's RCU field + * + * Description: + * This function is designed to be used as a callback to the call_rcu() + * function so that the memory allocated to a domain list entry can be released + * safely. + * + */ +static void cipso_v4_doi_domhsh_free(struct rcu_head *entry) +{ + struct cipso_v4_domhsh_entry *ptr; + + ptr = container_of(entry, struct cipso_v4_domhsh_entry, rcu); + kfree(ptr->domain); + kfree(ptr); +} + +/** + * cipso_v4_cache_entry_free - Frees a cache entry + * @entry: the entry to free + * + * Description: + * This function frees the memory associated with a cache entry. + * + */ +static void cipso_v4_cache_entry_free(struct cipso_v4_map_cache_entry *entry) +{ + if (entry->lsm_data.free) + entry->lsm_data.free(entry->lsm_data.data); + kfree(entry->key); + kfree(entry); +} + +/** + * cipso_v4_map_cache_hash - Hashing function for the CIPSO cache + * @key: the hash key + * @key_len: the length of the key in bytes + * + * Description: + * The CIPSO tag hashing function. Returns a 32-bit hash value. + * + */ +static u32 cipso_v4_map_cache_hash(const unsigned char *key, u32 key_len) +{ + return jhash(key, key_len, 0); +} + +/* + * Label Mapping Cache Functions + */ + +/** + * cipso_v4_cache_init - Initialize the CIPSO cache + * + * Description: + * Initializes the CIPSO label mapping cache, this function should be called + * before any of the other functions defined in this file. Returns zero on + * success, negative values on error. + * + */ +static int cipso_v4_cache_init(void) +{ + u32 iter; + + cipso_v4_cache = kcalloc(CIPSO_V4_CACHE_BUCKETS, + sizeof(struct cipso_v4_map_cache_bkt), + GFP_KERNEL); + if (cipso_v4_cache == NULL) + return -ENOMEM; + + for (iter = 0; iter < CIPSO_V4_CACHE_BUCKETS; iter++) { + spin_lock_init(&cipso_v4_cache[iter].lock); + cipso_v4_cache[iter].size = 0; + INIT_LIST_HEAD(&cipso_v4_cache[iter].list); + } + + return 0; +} + +/** + * cipso_v4_cache_invalidate - Invalidates the current CIPSO cache + * + * Description: + * Invalidates and frees any entries in the CIPSO cache. Returns zero on + * success and negative values on failure. + * + */ +void cipso_v4_cache_invalidate(void) +{ + struct cipso_v4_map_cache_entry *entry, *tmp_entry; + u32 iter; + + for (iter = 0; iter < CIPSO_V4_CACHE_BUCKETS; iter++) { + spin_lock(&cipso_v4_cache[iter].lock); + list_for_each_entry_safe(entry, + tmp_entry, + &cipso_v4_cache[iter].list, list) { + list_del(&entry->list); + cipso_v4_cache_entry_free(entry); + } + cipso_v4_cache[iter].size = 0; + spin_unlock(&cipso_v4_cache[iter].lock); + } + + return; +} + +/** + * cipso_v4_cache_check - Check the CIPSO cache for a label mapping + * @key: the buffer to check + * @key_len: buffer length in bytes + * @secattr: the security attribute struct to use + * + * Description: + * This function checks the cache to see if a label mapping already exists for + * the given key. If there is a match then the cache is adjusted and the + * @secattr struct is populated with the correct LSM security attributes. The + * cache is adjusted in the following manner if the entry is not already the + * first in the cache bucket: + * + * 1. The cache entry's activity counter is incremented + * 2. The previous (higher ranking) entry's activity counter is decremented + * 3. If the difference between the two activity counters is geater than + * CIPSO_V4_CACHE_REORDERLIMIT the two entries are swapped + * + * Returns zero on success, -ENOENT for a cache miss, and other negative values + * on error. + * + */ +static int cipso_v4_cache_check(const unsigned char *key, + u32 key_len, + struct netlbl_lsm_secattr *secattr) +{ + u32 bkt; + struct cipso_v4_map_cache_entry *entry; + struct cipso_v4_map_cache_entry *prev_entry = NULL; + u32 hash; + + if (!cipso_v4_cache_enabled) + return -ENOENT; + + hash = cipso_v4_map_cache_hash(key, key_len); + bkt = hash & (CIPSO_V4_CACHE_BUCKETBITS - 1); + spin_lock(&cipso_v4_cache[bkt].lock); + list_for_each_entry(entry, &cipso_v4_cache[bkt].list, list) { + if (entry->hash == hash && + entry->key_len == key_len && + memcmp(entry->key, key, key_len) == 0) { + entry->activity += 1; + secattr->cache.free = entry->lsm_data.free; + secattr->cache.data = entry->lsm_data.data; + if (prev_entry == NULL) { + spin_unlock(&cipso_v4_cache[bkt].lock); + return 0; + } + + if (prev_entry->activity > 0) + prev_entry->activity -= 1; + if (entry->activity > prev_entry->activity && + entry->activity - prev_entry->activity > + CIPSO_V4_CACHE_REORDERLIMIT) { + __list_del(entry->list.prev, entry->list.next); + __list_add(&entry->list, + prev_entry->list.prev, + &prev_entry->list); + } + + spin_unlock(&cipso_v4_cache[bkt].lock); + return 0; + } + prev_entry = entry; + } + spin_unlock(&cipso_v4_cache[bkt].lock); + + return -ENOENT; +} + +/** + * cipso_v4_cache_add - Add an entry to the CIPSO cache + * @skb: the packet + * @secattr: the packet's security attributes + * + * Description: + * Add a new entry into the CIPSO label mapping cache. Add the new entry to + * head of the cache bucket's list, if the cache bucket is out of room remove + * the last entry in the list first. It is important to note that there is + * currently no checking for duplicate keys. Returns zero on success, + * negative values on failure. + * + */ +int cipso_v4_cache_add(const struct sk_buff *skb, + const struct netlbl_lsm_secattr *secattr) +{ + int ret_val = -EPERM; + u32 bkt; + struct cipso_v4_map_cache_entry *entry = NULL; + struct cipso_v4_map_cache_entry *old_entry = NULL; + unsigned char *cipso_ptr; + u32 cipso_ptr_len; + + if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0) + return 0; + + cipso_ptr = CIPSO_V4_OPTPTR(skb); + cipso_ptr_len = cipso_ptr[1]; + + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); + if (entry == NULL) + return -ENOMEM; + entry->key = kmalloc(cipso_ptr_len, GFP_ATOMIC); + if (entry->key == NULL) { + ret_val = -ENOMEM; + goto cache_add_failure; + } + memcpy(entry->key, cipso_ptr, cipso_ptr_len); + entry->key_len = cipso_ptr_len; + entry->hash = cipso_v4_map_cache_hash(cipso_ptr, cipso_ptr_len); + entry->lsm_data.free = secattr->cache.free; + entry->lsm_data.data = secattr->cache.data; + + bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETBITS - 1); + spin_lock(&cipso_v4_cache[bkt].lock); + if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) { + list_add(&entry->list, &cipso_v4_cache[bkt].list); + cipso_v4_cache[bkt].size += 1; + } else { + old_entry = list_entry(cipso_v4_cache[bkt].list.prev, + struct cipso_v4_map_cache_entry, list); + list_del(&old_entry->list); + list_add(&entry->list, &cipso_v4_cache[bkt].list); + cipso_v4_cache_entry_free(old_entry); + } + spin_unlock(&cipso_v4_cache[bkt].lock); + + return 0; + +cache_add_failure: + if (entry) + cipso_v4_cache_entry_free(entry); + return ret_val; +} + +/* + * DOI List Functions + */ + +/** + * cipso_v4_doi_search - Searches for a DOI definition + * @doi: the DOI to search for + * + * Description: + * Search the DOI definition list for a DOI definition with a DOI value that + * matches @doi. The caller is responsibile for calling rcu_read_[un]lock(). + * Returns a pointer to the DOI definition on success and NULL on failure. + */ +static struct cipso_v4_doi *cipso_v4_doi_search(u32 doi) +{ + struct cipso_v4_doi *iter; + + list_for_each_entry_rcu(iter, &cipso_v4_doi_list, list) + if (iter->doi == doi && iter->valid) + return iter; + return NULL; +} + +/** + * cipso_v4_doi_add - Add a new DOI to the CIPSO protocol engine + * @doi_def: the DOI structure + * + * Description: + * The caller defines a new DOI for use by the CIPSO engine and calls this + * function to add it to the list of acceptable domains. The caller must + * ensure that the mapping table specified in @doi_def->map meets all of the + * requirements of the mapping type (see cipso_ipv4.h for details). Returns + * zero on success and non-zero on failure. + * + */ +int cipso_v4_doi_add(struct cipso_v4_doi *doi_def) +{ + if (doi_def == NULL || doi_def->doi == CIPSO_V4_DOI_UNKNOWN) + return -EINVAL; + + doi_def->valid = 1; + INIT_RCU_HEAD(&doi_def->rcu); + INIT_LIST_HEAD(&doi_def->dom_list); + + rcu_read_lock(); + if (cipso_v4_doi_search(doi_def->doi) != NULL) + goto doi_add_failure_rlock; + spin_lock(&cipso_v4_doi_list_lock); + if (cipso_v4_doi_search(doi_def->doi) != NULL) + goto doi_add_failure_slock; + list_add_tail_rcu(&doi_def->list, &cipso_v4_doi_list); + spin_unlock(&cipso_v4_doi_list_lock); + rcu_read_unlock(); + + return 0; + +doi_add_failure_slock: + spin_unlock(&cipso_v4_doi_list_lock); +doi_add_failure_rlock: + rcu_read_unlock(); + return -EEXIST; +} + +/** + * cipso_v4_doi_remove - Remove an existing DOI from the CIPSO protocol engine + * @doi: the DOI value + * @callback: the DOI cleanup/free callback + * + * Description: + * Removes a DOI definition from the CIPSO engine, @callback is called to + * free any memory. The NetLabel routines will be called to release their own + * LSM domain mappings as well as our own domain list. Returns zero on + * success and negative values on failure. + * + */ +int cipso_v4_doi_remove(u32 doi, void (*callback) (struct rcu_head * head)) +{ + struct cipso_v4_doi *doi_def; + struct cipso_v4_domhsh_entry *dom_iter; + + rcu_read_lock(); + if (cipso_v4_doi_search(doi) != NULL) { + spin_lock(&cipso_v4_doi_list_lock); + doi_def = cipso_v4_doi_search(doi); + if (doi_def == NULL) { + spin_unlock(&cipso_v4_doi_list_lock); + rcu_read_unlock(); + return -ENOENT; + } + doi_def->valid = 0; + list_del_rcu(&doi_def->list); + spin_unlock(&cipso_v4_doi_list_lock); + list_for_each_entry_rcu(dom_iter, &doi_def->dom_list, list) + if (dom_iter->valid) + netlbl_domhsh_remove(dom_iter->domain); + cipso_v4_cache_invalidate(); + rcu_read_unlock(); + + call_rcu(&doi_def->rcu, callback); + return 0; + } + rcu_read_unlock(); + + return -ENOENT; +} + +/** + * cipso_v4_doi_getdef - Returns a pointer to a valid DOI definition + * @doi: the DOI value + * + * Description: + * Searches for a valid DOI definition and if one is found it is returned to + * the caller. Otherwise NULL is returned. The caller must ensure that + * rcu_read_lock() is held while accessing the returned definition. + * + */ +struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi) +{ + return cipso_v4_doi_search(doi); +} + +/** + * cipso_v4_doi_dump_all - Dump all the CIPSO DOI definitions into a sk_buff + * @headroom: the amount of headroom to allocate for the sk_buff + * + * Description: + * Dump a list of all the configured DOI values into a sk_buff. The returned + * sk_buff has room at the front of the sk_buff for @headroom bytes. See + * net/netlabel/netlabel_cipso_v4.h for the LISTALL message format. This + * function may fail if another process is changing the DOI list at the same + * time. Returns a pointer to a sk_buff on success, NULL on error. + * + */ +struct sk_buff *cipso_v4_doi_dump_all(size_t headroom) +{ + struct sk_buff *skb = NULL; + struct cipso_v4_doi *iter; + u32 doi_cnt = 0; + ssize_t buf_len; + + buf_len = NETLBL_LEN_U32; + rcu_read_lock(); + list_for_each_entry_rcu(iter, &cipso_v4_doi_list, list) + if (iter->valid) { + doi_cnt += 1; + buf_len += 2 * NETLBL_LEN_U32; + } + + skb = netlbl_netlink_alloc_skb(headroom, buf_len, GFP_ATOMIC); + if (skb == NULL) + goto doi_dump_all_failure; + + if (nla_put_u32(skb, NLA_U32, doi_cnt) != 0) + goto doi_dump_all_failure; + buf_len -= NETLBL_LEN_U32; + list_for_each_entry_rcu(iter, &cipso_v4_doi_list, list) + if (iter->valid) { + if (buf_len < 2 * NETLBL_LEN_U32) + goto doi_dump_all_failure; + if (nla_put_u32(skb, NLA_U32, iter->doi) != 0) + goto doi_dump_all_failure; + if (nla_put_u32(skb, NLA_U32, iter->type) != 0) + goto doi_dump_all_failure; + buf_len -= 2 * NETLBL_LEN_U32; + } + rcu_read_unlock(); + + return skb; + +doi_dump_all_failure: + rcu_read_unlock(); + kfree(skb); + return NULL; +} + +/** + * cipso_v4_doi_dump - Dump a CIPSO DOI definition into a sk_buff + * @doi: the DOI value + * @headroom: the amount of headroom to allocate for the sk_buff + * + * Description: + * Lookup the DOI definition matching @doi and dump it's contents into a + * sk_buff. The returned sk_buff has room at the front of the sk_buff for + * @headroom bytes. See net/netlabel/netlabel_cipso_v4.h for the LIST message + * format. This function may fail if another process is changing the DOI list + * at the same time. Returns a pointer to a sk_buff on success, NULL on error. + * + */ +struct sk_buff *cipso_v4_doi_dump(u32 doi, size_t headroom) +{ + struct sk_buff *skb = NULL; + struct cipso_v4_doi *iter; + u32 tag_cnt = 0; + u32 lvl_cnt = 0; + u32 cat_cnt = 0; + ssize_t buf_len; + ssize_t tmp; + + rcu_read_lock(); + iter = cipso_v4_doi_getdef(doi); + if (iter == NULL) + goto doi_dump_failure; + buf_len = NETLBL_LEN_U32; + switch (iter->type) { + case CIPSO_V4_MAP_PASS: + buf_len += NETLBL_LEN_U32; + while(tag_cnt < CIPSO_V4_TAG_MAXCNT && + iter->tags[tag_cnt] != CIPSO_V4_TAG_INVALID) { + tag_cnt += 1; + buf_len += NETLBL_LEN_U8; + } + break; + case CIPSO_V4_MAP_STD: + buf_len += 3 * NETLBL_LEN_U32; + while (tag_cnt < CIPSO_V4_TAG_MAXCNT && + iter->tags[tag_cnt] != CIPSO_V4_TAG_INVALID) { + tag_cnt += 1; + buf_len += NETLBL_LEN_U8; + } + for (tmp = 0; tmp < iter->map.std->lvl.local_size; tmp++) + if (iter->map.std->lvl.local[tmp] != + CIPSO_V4_INV_LVL) { + lvl_cnt += 1; + buf_len += NETLBL_LEN_U32 + NETLBL_LEN_U8; + } + for (tmp = 0; tmp < iter->map.std->cat.local_size; tmp++) + if (iter->map.std->cat.local[tmp] != + CIPSO_V4_INV_CAT) { + cat_cnt += 1; + buf_len += NETLBL_LEN_U32 + NETLBL_LEN_U16; + } + break; + } + + skb = netlbl_netlink_alloc_skb(headroom, buf_len, GFP_ATOMIC); + if (skb == NULL) + goto doi_dump_failure; + + if (nla_put_u32(skb, NLA_U32, iter->type) != 0) + goto doi_dump_failure; + buf_len -= NETLBL_LEN_U32; + if (iter != cipso_v4_doi_getdef(doi)) + goto doi_dump_failure; + switch (iter->type) { + case CIPSO_V4_MAP_PASS: + if (nla_put_u32(skb, NLA_U32, tag_cnt) != 0) + goto doi_dump_failure; + buf_len -= NETLBL_LEN_U32; + for (tmp = 0; + tmp < CIPSO_V4_TAG_MAXCNT && + iter->tags[tmp] != CIPSO_V4_TAG_INVALID; + tmp++) { + if (buf_len < NETLBL_LEN_U8) + goto doi_dump_failure; + if (nla_put_u8(skb, NLA_U8, iter->tags[tmp]) != 0) + goto doi_dump_failure; + buf_len -= NETLBL_LEN_U8; + } + break; + case CIPSO_V4_MAP_STD: + if (nla_put_u32(skb, NLA_U32, tag_cnt) != 0) + goto doi_dump_failure; + if (nla_put_u32(skb, NLA_U32, lvl_cnt) != 0) + goto doi_dump_failure; + if (nla_put_u32(skb, NLA_U32, cat_cnt) != 0) + goto doi_dump_failure; + buf_len -= 3 * NETLBL_LEN_U32; + for (tmp = 0; + tmp < CIPSO_V4_TAG_MAXCNT && + iter->tags[tmp] != CIPSO_V4_TAG_INVALID; + tmp++) { + if (buf_len < NETLBL_LEN_U8) + goto doi_dump_failure; + if (nla_put_u8(skb, NLA_U8, iter->tags[tmp]) != 0) + goto doi_dump_failure; + buf_len -= NETLBL_LEN_U8; + } + for (tmp = 0; tmp < iter->map.std->lvl.local_size; tmp++) + if (iter->map.std->lvl.local[tmp] != + CIPSO_V4_INV_LVL) { + if (buf_len < NETLBL_LEN_U32 + NETLBL_LEN_U8) + goto doi_dump_failure; + if (nla_put_u32(skb, NLA_U32, tmp) != 0) + goto doi_dump_failure; + if (nla_put_u8(skb, + NLA_U8, + iter->map.std->lvl.local[tmp]) != 0) + goto doi_dump_failure; + buf_len -= NETLBL_LEN_U32 + NETLBL_LEN_U8; + } + for (tmp = 0; tmp < iter->map.std->cat.local_size; tmp++) + if (iter->map.std->cat.local[tmp] != + CIPSO_V4_INV_CAT) { + if (buf_len < NETLBL_LEN_U32 + NETLBL_LEN_U16) + goto doi_dump_failure; + if (nla_put_u32(skb, NLA_U32, tmp) != 0) + goto doi_dump_failure; + if (nla_put_u16(skb, + NLA_U16, + iter->map.std->cat.local[tmp]) != 0) + goto doi_dump_failure; + buf_len -= NETLBL_LEN_U32 + NETLBL_LEN_U16; + } + break; + } + rcu_read_unlock(); + + return skb; + +doi_dump_failure: + rcu_read_unlock(); + kfree(skb); + return NULL; +} + +/** + * cipso_v4_doi_domhsh_add - Adds a domain entry to a DOI definition + * @doi_def: the DOI definition + * @domain: the domain to add + * + * Description: + * Adds the @domain to the the DOI specified by @doi_def, this function + * should only be called by external functions (i.e. NetLabel). This function + * does allocate memory. Returns zero on success, negative values on failure. + * + */ +int cipso_v4_doi_domhsh_add(struct cipso_v4_doi *doi_def, const char *domain) +{ + struct cipso_v4_domhsh_entry *iter; + struct cipso_v4_domhsh_entry *new_dom; + + new_dom = kzalloc(sizeof(*new_dom), GFP_KERNEL); + if (new_dom == NULL) + return -ENOMEM; + if (domain) { + new_dom->domain = kstrdup(domain, GFP_KERNEL); + if (new_dom->domain == NULL) { + kfree(new_dom); + return -ENOMEM; + } + } + new_dom->valid = 1; + INIT_RCU_HEAD(&new_dom->rcu); + + rcu_read_lock(); + spin_lock(&cipso_v4_doi_list_lock); + list_for_each_entry_rcu(iter, &doi_def->dom_list, list) + if (iter->valid && + ((domain != NULL && iter->domain != NULL && + strcmp(iter->domain, domain) == 0) || + (domain == NULL && iter->domain == NULL))) { + spin_unlock(&cipso_v4_doi_list_lock); + rcu_read_unlock(); + kfree(new_dom->domain); + kfree(new_dom); + return -EEXIST; + } + list_add_tail_rcu(&new_dom->list, &doi_def->dom_list); + spin_unlock(&cipso_v4_doi_list_lock); + rcu_read_unlock(); + + return 0; +} + +/** + * cipso_v4_doi_domhsh_remove - Removes a domain entry from a DOI definition + * @doi_def: the DOI definition + * @domain: the domain to remove + * + * Description: + * Removes the @domain from the DOI specified by @doi_def, this function + * should only be called by external functions (i.e. NetLabel). Returns zero + * on success and negative values on error. + * + */ +int cipso_v4_doi_domhsh_remove(struct cipso_v4_doi *doi_def, + const char *domain) +{ + struct cipso_v4_domhsh_entry *iter; + + rcu_read_lock(); + spin_lock(&cipso_v4_doi_list_lock); + list_for_each_entry_rcu(iter, &doi_def->dom_list, list) + if (iter->valid && + ((domain != NULL && iter->domain != NULL && + strcmp(iter->domain, domain) == 0) || + (domain == NULL && iter->domain == NULL))) { + iter->valid = 0; + list_del_rcu(&iter->list); + spin_unlock(&cipso_v4_doi_list_lock); + rcu_read_unlock(); + call_rcu(&iter->rcu, cipso_v4_doi_domhsh_free); + + return 0; + } + spin_unlock(&cipso_v4_doi_list_lock); + rcu_read_unlock(); + + return -ENOENT; +} + +/* + * Label Mapping Functions + */ + +/** + * cipso_v4_map_lvl_valid - Checks to see if the given level is understood + * @doi_def: the DOI definition + * @level: the level to check + * + * Description: + * Checks the given level against the given DOI definition and returns a + * negative value if the level does not have a valid mapping and a zero value + * if the level is defined by the DOI. + * + */ +static int cipso_v4_map_lvl_valid(const struct cipso_v4_doi *doi_def, u8 level) +{ + switch (doi_def->type) { + case CIPSO_V4_MAP_PASS: + return 0; + case CIPSO_V4_MAP_STD: + if (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL) + return 0; + break; + } + + return -EFAULT; +} + +/** + * cipso_v4_map_lvl_hton - Perform a level mapping from the host to the network + * @doi_def: the DOI definition + * @host_lvl: the host MLS level + * @net_lvl: the network/CIPSO MLS level + * + * Description: + * Perform a label mapping to translate a local MLS level to the correct + * CIPSO level using the given DOI definition. Returns zero on success, + * negative values otherwise. + * + */ +static int cipso_v4_map_lvl_hton(const struct cipso_v4_doi *doi_def, + u32 host_lvl, + u32 *net_lvl) +{ + switch (doi_def->type) { + case CIPSO_V4_MAP_PASS: + *net_lvl = host_lvl; + return 0; + case CIPSO_V4_MAP_STD: + if (host_lvl < doi_def->map.std->lvl.local_size) { + *net_lvl = doi_def->map.std->lvl.local[host_lvl]; + return 0; + } + break; + } + + return -EINVAL; +} + +/** + * cipso_v4_map_lvl_ntoh - Perform a level mapping from the network to the host + * @doi_def: the DOI definition + * @net_lvl: the network/CIPSO MLS level + * @host_lvl: the host MLS level + * + * Description: + * Perform a label mapping to translate a CIPSO level to the correct local MLS + * level using the given DOI definition. Returns zero on success, negative + * values otherwise. + * + */ +static int cipso_v4_map_lvl_ntoh(const struct cipso_v4_doi *doi_def, + u32 net_lvl, + u32 *host_lvl) +{ + struct cipso_v4_std_map_tbl *map_tbl; + + switch (doi_def->type) { + case CIPSO_V4_MAP_PASS: + *host_lvl = net_lvl; + return 0; + case CIPSO_V4_MAP_STD: + map_tbl = doi_def->map.std; + if (net_lvl < map_tbl->lvl.cipso_size && + map_tbl->lvl.cipso[net_lvl] < CIPSO_V4_INV_LVL) { + *host_lvl = doi_def->map.std->lvl.cipso[net_lvl]; + return 0; + } + break; + } + + return -EINVAL; +} + +/** + * cipso_v4_map_cat_rbm_valid - Checks to see if the category bitmap is valid + * @doi_def: the DOI definition + * @bitmap: category bitmap + * @bitmap_len: bitmap length in bytes + * + * Description: + * Checks the given category bitmap against the given DOI definition and + * returns a negative value if any of the categories in the bitmap do not have + * a valid mapping and a zero value if all of the categories are valid. + * + */ +static int cipso_v4_map_cat_rbm_valid(const struct cipso_v4_doi *doi_def, + const unsigned char *bitmap, + u32 bitmap_len) +{ + int cat = -1; + u32 bitmap_len_bits = bitmap_len * 8; + u32 cipso_cat_size = doi_def->map.std->cat.cipso_size; + u32 *cipso_array = doi_def->map.std->cat.cipso; + + switch (doi_def->type) { + case CIPSO_V4_MAP_PASS: + return 0; + case CIPSO_V4_MAP_STD: + for (;;) { + cat = cipso_v4_bitmap_walk(bitmap, + bitmap_len_bits, + cat + 1, + 1); + if (cat < 0) + break; + if (cat >= cipso_cat_size || + cipso_array[cat] >= CIPSO_V4_INV_CAT) + return -EFAULT; + } + + if (cat == -1) + return 0; + break; + } + + return -EFAULT; +} + +/** + * cipso_v4_map_cat_rbm_hton - Perform a category mapping from host to network + * @doi_def: the DOI definition + * @host_cat: the category bitmap in host format + * @host_cat_len: the length of the host's category bitmap in bytes + * @net_cat: the zero'd out category bitmap in network/CIPSO format + * @net_cat_len: the length of the CIPSO bitmap in bytes + * + * Description: + * Perform a label mapping to translate a local MLS category bitmap to the + * correct CIPSO bitmap using the given DOI definition. Returns the minimum + * size in bytes of the network bitmap on success, negative values otherwise. + * + */ +static int cipso_v4_map_cat_rbm_hton(const struct cipso_v4_doi *doi_def, + const unsigned char *host_cat, + u32 host_cat_len, + unsigned char *net_cat, + u32 net_cat_len) +{ + int host_spot = -1; + u32 net_spot; + u32 net_spot_max = 0; + u32 host_clen_bits = host_cat_len * 8; + u32 net_clen_bits = net_cat_len * 8; + u32 host_cat_size = doi_def->map.std->cat.local_size; + u32 *host_cat_array = doi_def->map.std->cat.local; + + switch (doi_def->type) { + case CIPSO_V4_MAP_PASS: + net_spot_max = host_cat_len - 1; + while (net_spot_max > 0 && host_cat[net_spot_max] == 0) + net_spot_max--; + if (net_spot_max > net_cat_len) + return -EINVAL; + memcpy(net_cat, host_cat, net_spot_max); + return net_spot_max; + case CIPSO_V4_MAP_STD: + for (;;) { + host_spot = cipso_v4_bitmap_walk(host_cat, + host_clen_bits, + host_spot + 1, + 1); + if (host_spot < 0) + break; + if (host_spot >= host_cat_size) + return -EPERM; + + net_spot = host_cat_array[host_spot]; + if (net_spot >= net_clen_bits) + return -ENOSPC; + cipso_v4_bitmap_setbit(net_cat, net_spot, 1); + + if (net_spot > net_spot_max) + net_spot_max = net_spot; + } + + if (host_spot == -2) + return -EFAULT; + + if (++net_spot_max % 8) + return net_spot_max / 8 + 1; + return net_spot_max / 8; + } + + return -EINVAL; +} + +/** + * cipso_v4_map_cat_rbm_ntoh - Perform a category mapping from network to host + * @doi_def: the DOI definition + * @net_cat: the category bitmap in network/CIPSO format + * @net_cat_len: the length of the CIPSO bitmap in bytes + * @host_cat: the zero'd out category bitmap in host format + * @host_cat_len: the length of the host's category bitmap in bytes + * + * Description: + * Perform a label mapping to translate a CIPSO bitmap to the correct local + * MLS category bitmap using the given DOI definition. Returns the minimum + * size in bytes of the host bitmap on success, negative values otherwise. + * + */ +static int cipso_v4_map_cat_rbm_ntoh(const struct cipso_v4_doi *doi_def, + const unsigned char *net_cat, + u32 net_cat_len, + unsigned char *host_cat, + u32 host_cat_len) +{ + u32 host_spot; + u32 host_spot_max = 0; + int net_spot = -1; + u32 net_clen_bits = net_cat_len * 8; + u32 host_clen_bits = host_cat_len * 8; + u32 net_cat_size = doi_def->map.std->cat.cipso_size; + u32 *net_cat_array = doi_def->map.std->cat.cipso; + + switch (doi_def->type) { + case CIPSO_V4_MAP_PASS: + if (net_cat_len > host_cat_len) + return -EINVAL; + memcpy(host_cat, net_cat, net_cat_len); + return net_cat_len; + case CIPSO_V4_MAP_STD: + for (;;) { + net_spot = cipso_v4_bitmap_walk(net_cat, + net_clen_bits, + net_spot + 1, + 1); + if (net_spot < 0) + break; + if (net_spot >= net_cat_size || + net_cat_array[net_spot] >= CIPSO_V4_INV_CAT) + return -EPERM; + + host_spot = net_cat_array[net_spot]; + if (host_spot >= host_clen_bits) + return -ENOSPC; + cipso_v4_bitmap_setbit(host_cat, host_spot, 1); + + if (host_spot > host_spot_max) + host_spot_max = host_spot; + } + + if (net_spot == -2) + return -EFAULT; + + if (++host_spot_max % 8) + return host_spot_max / 8 + 1; + return host_spot_max / 8; + } + + return -EINVAL; +} + +/* + * Protocol Handling Functions + */ + +#define CIPSO_V4_HDR_LEN 6 + +/** + * cipso_v4_gentag_hdr - Generate a CIPSO option header + * @doi_def: the DOI definition + * @len: the total tag length in bytes + * @buf: the CIPSO option buffer + * + * Description: + * Write a CIPSO header into the beginning of @buffer. Return zero on success, + * negative values on failure. + * + */ +static int cipso_v4_gentag_hdr(const struct cipso_v4_doi *doi_def, + u32 len, + unsigned char *buf) +{ + if (CIPSO_V4_HDR_LEN + len > 40) + return -ENOSPC; + + buf[0] = IPOPT_CIPSO; + buf[1] = CIPSO_V4_HDR_LEN + len; + *(u32 *)&buf[2] = htonl(doi_def->doi); + + return 0; +} + +#define CIPSO_V4_TAG1_CAT_LEN 30 + +/** + * cipso_v4_gentag_rbm - Generate a CIPSO restricted bitmap tag (type #1) + * @doi_def: the DOI definition + * @secattr: the security attributes + * @buffer: the option buffer + * @buffer_len: length of buffer in bytes + * + * Description: + * Generate a CIPSO option using the restricted bitmap tag, tag type #1. The + * actual buffer length may be larger than the indicated size due to + * translation between host and network category bitmaps. Returns zero on + * success, negative values on failure. + * + */ +static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def, + const struct netlbl_lsm_secattr *secattr, + unsigned char **buffer, + u32 *buffer_len) +{ + int ret_val = -EPERM; + unsigned char *buf = NULL; + u32 buf_len; + u32 level; + + if (secattr->mls_cat) { + buf = kzalloc(CIPSO_V4_HDR_LEN + 4 + CIPSO_V4_TAG1_CAT_LEN, + GFP_ATOMIC); + if (buf == NULL) + return -ENOMEM; + + ret_val = cipso_v4_map_cat_rbm_hton(doi_def, + secattr->mls_cat, + secattr->mls_cat_len, + &buf[CIPSO_V4_HDR_LEN + 4], + CIPSO_V4_TAG1_CAT_LEN); + if (ret_val < 0) + goto gentag_failure; + + /* This will send packets using the "optimized" format when + * possibile as specified in section 3.4.2.6 of the + * CIPSO draft. */ + if (cipso_v4_rbm_optfmt && (ret_val > 0 && ret_val < 10)) + ret_val = 10; + + buf_len = 4 + ret_val; + } else { + buf = kzalloc(CIPSO_V4_HDR_LEN + 4, GFP_ATOMIC); + if (buf == NULL) + return -ENOMEM; + buf_len = 4; + } + + ret_val = cipso_v4_map_lvl_hton(doi_def, secattr->mls_lvl, &level); + if (ret_val != 0) + goto gentag_failure; + + ret_val = cipso_v4_gentag_hdr(doi_def, buf_len, buf); + if (ret_val != 0) + goto gentag_failure; + + buf[CIPSO_V4_HDR_LEN] = 0x01; + buf[CIPSO_V4_HDR_LEN + 1] = buf_len; + buf[CIPSO_V4_HDR_LEN + 3] = level; + + *buffer = buf; + *buffer_len = CIPSO_V4_HDR_LEN + buf_len; + + return 0; + +gentag_failure: + kfree(buf); + return ret_val; +} + +/** + * cipso_v4_parsetag_rbm - Parse a CIPSO restricted bitmap tag + * @doi_def: the DOI definition + * @tag: the CIPSO tag + * @secattr: the security attributes + * + * Description: + * Parse a CIPSO restricted bitmap tag (tag type #1) and return the security + * attributes in @secattr. Return zero on success, negatives values on + * failure. + * + */ +static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def, + const unsigned char *tag, + struct netlbl_lsm_secattr *secattr) +{ + int ret_val; + u8 tag_len = tag[1]; + u32 level; + + ret_val = cipso_v4_map_lvl_ntoh(doi_def, tag[3], &level); + if (ret_val != 0) + return ret_val; + secattr->mls_lvl = level; + secattr->mls_lvl_vld = 1; + + if (tag_len > 4) { + switch (doi_def->type) { + case CIPSO_V4_MAP_PASS: + secattr->mls_cat_len = tag_len - 4; + break; + case CIPSO_V4_MAP_STD: + secattr->mls_cat_len = + doi_def->map.std->cat.local_size; + break; + } + secattr->mls_cat = kzalloc(secattr->mls_cat_len, GFP_ATOMIC); + if (secattr->mls_cat == NULL) + return -ENOMEM; + + ret_val = cipso_v4_map_cat_rbm_ntoh(doi_def, + &tag[4], + tag_len - 4, + secattr->mls_cat, + secattr->mls_cat_len); + if (ret_val < 0) { + kfree(secattr->mls_cat); + return ret_val; + } + secattr->mls_cat_len = ret_val; + } + + return 0; +} + +/** + * cipso_v4_validate - Validate a CIPSO option + * @option: the start of the option, on error it is set to point to the error + * + * Description: + * This routine is called to validate a CIPSO option, it checks all of the + * fields to ensure that they are at least valid, see the draft snippet below + * for details. If the option is valid then a zero value is returned and + * the value of @option is unchanged. If the option is invalid then a + * non-zero value is returned and @option is adjusted to point to the + * offending portion of the option. From the IETF draft ... + * + * "If any field within the CIPSO options, such as the DOI identifier, is not + * recognized the IP datagram is discarded and an ICMP 'parameter problem' + * (type 12) is generated and returned. The ICMP code field is set to 'bad + * parameter' (code 0) and the pointer is set to the start of the CIPSO field + * that is unrecognized." + * + */ +int cipso_v4_validate(unsigned char **option) +{ + unsigned char *opt = *option; + unsigned char *tag; + unsigned char opt_iter; + unsigned char err_offset = 0; + u8 opt_len; + u8 tag_len; + struct cipso_v4_doi *doi_def = NULL; + u32 tag_iter; + + /* caller already checks for length values that are too large */ + opt_len = opt[1]; + if (opt_len < 8) { + err_offset = 1; + goto validate_return; + } + + rcu_read_lock(); + doi_def = cipso_v4_doi_getdef(ntohl(*((u32 *)&opt[2]))); + if (doi_def == NULL) { + err_offset = 2; + goto validate_return_locked; + } + + opt_iter = 6; + tag = opt + opt_iter; + while (opt_iter < opt_len) { + for (tag_iter = 0; doi_def->tags[tag_iter] != tag[0];) + if (doi_def->tags[tag_iter] == CIPSO_V4_TAG_INVALID || + ++tag_iter == CIPSO_V4_TAG_MAXCNT) { + err_offset = opt_iter; + goto validate_return_locked; + } + + tag_len = tag[1]; + if (tag_len > (opt_len - opt_iter)) { + err_offset = opt_iter + 1; + goto validate_return_locked; + } + + switch (tag[0]) { + case CIPSO_V4_TAG_RBITMAP: + if (tag_len < 4) { + err_offset = opt_iter + 1; + goto validate_return_locked; + } + + /* We are already going to do all the verification + * necessary at the socket layer so from our point of + * view it is safe to turn these checks off (and less + * work), however, the CIPSO draft says we should do + * all the CIPSO validations here but it doesn't + * really specify _exactly_ what we need to validate + * ... so, just make it a sysctl tunable. */ + if (cipso_v4_rbm_strictvalid) { + if (cipso_v4_map_lvl_valid(doi_def, + tag[3]) < 0) { + err_offset = opt_iter + 3; + goto validate_return_locked; + } + if (tag_len > 4 && + cipso_v4_map_cat_rbm_valid(doi_def, + &tag[4], + tag_len - 4) < 0) { + err_offset = opt_iter + 4; + goto validate_return_locked; + } + } + break; + default: + err_offset = opt_iter; + goto validate_return_locked; + } + + tag += tag_len; + opt_iter += tag_len; + } + +validate_return_locked: + rcu_read_unlock(); +validate_return: + *option = opt + err_offset; + return err_offset; +} + +/** + * cipso_v4_error - Send the correct reponse for a bad packet + * @skb: the packet + * @error: the error code + * @gateway: CIPSO gateway flag + * + * Description: + * Based on the error code given in @error, send an ICMP error message back to + * the originating host. From the IETF draft ... + * + * "If the contents of the CIPSO [option] are valid but the security label is + * outside of the configured host or port label range, the datagram is + * discarded and an ICMP 'destination unreachable' (type 3) is generated and + * returned. The code field of the ICMP is set to 'communication with + * destination network administratively prohibited' (code 9) or to + * 'communication with destination host administratively prohibited' + * (code 10). The value of the code is dependent on whether the originator + * of the ICMP message is acting as a CIPSO host or a CIPSO gateway. The + * recipient of the ICMP message MUST be able to handle either value. The + * same procedure is performed if a CIPSO [option] can not be added to an + * IP packet because it is too large to fit in the IP options area." + * + * "If the error is triggered by receipt of an ICMP message, the message is + * discarded and no response is permitted (consistent with general ICMP + * processing rules)." + * + */ +void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) +{ + if (skb->nh.iph->protocol == IPPROTO_ICMP || error != -EACCES) + return; + + if (gateway) + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0); + else + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0); +} + +/** + * cipso_v4_socket_setattr - Add a CIPSO option to a socket + * @sock: the socket + * @doi_def: the CIPSO DOI to use + * @secattr: the specific security attributes of the socket + * + * Description: + * Set the CIPSO option on the given socket using the DOI definition and + * security attributes passed to the function. This function requires + * exclusive access to @sock->sk, which means it either needs to be in the + * process of being created or locked via lock_sock(sock->sk). Returns zero on + * success and negative values on failure. + * + */ +int cipso_v4_socket_setattr(const struct socket *sock, + const struct cipso_v4_doi *doi_def, + const struct netlbl_lsm_secattr *secattr) +{ + int ret_val = -EPERM; + u32 iter; + unsigned char *buf = NULL; + u32 buf_len = 0; + u32 opt_len; + struct ip_options *opt = NULL; + struct sock *sk; + struct inet_sock *sk_inet; + struct inet_connection_sock *sk_conn; + + /* In the case of sock_create_lite(), the sock->sk field is not + * defined yet but it is not a problem as the only users of these + * "lite" PF_INET sockets are functions which do an accept() call + * afterwards so we will label the socket as part of the accept(). */ + sk = sock->sk; + if (sk == NULL) + return 0; + + /* XXX - This code assumes only one tag per CIPSO option which isn't + * really a good assumption to make but since we only support the MAC + * tags right now it is a safe assumption. */ + iter = 0; + do { + switch (doi_def->tags[iter]) { + case CIPSO_V4_TAG_RBITMAP: + ret_val = cipso_v4_gentag_rbm(doi_def, + secattr, + &buf, + &buf_len); + break; + default: + ret_val = -EPERM; + goto socket_setattr_failure; + } + + iter++; + } while (ret_val != 0 && + iter < CIPSO_V4_TAG_MAXCNT && + doi_def->tags[iter] != CIPSO_V4_TAG_INVALID); + if (ret_val != 0) + goto socket_setattr_failure; + + /* We can't use ip_options_get() directly because it makes a call to + * ip_options_get_alloc() which allocates memory with GFP_KERNEL and + * we can't block here. */ + opt_len = (buf_len + 3) & ~3; + opt = kzalloc(sizeof(*opt) + opt_len, GFP_ATOMIC); + if (opt == NULL) { + ret_val = -ENOMEM; + goto socket_setattr_failure; + } + memcpy(opt->__data, buf, buf_len); + opt->optlen = opt_len; + opt->is_data = 1; + kfree(buf); + buf = NULL; + ret_val = ip_options_compile(opt, NULL); + if (ret_val != 0) + goto socket_setattr_failure; + + sk_inet = inet_sk(sk); + if (sk_inet->is_icsk) { + sk_conn = inet_csk(sk); + if (sk_inet->opt) + sk_conn->icsk_ext_hdr_len -= sk_inet->opt->optlen; + sk_conn->icsk_ext_hdr_len += opt->optlen; + sk_conn->icsk_sync_mss(sk, sk_conn->icsk_pmtu_cookie); + } + opt = xchg(&sk_inet->opt, opt); + kfree(opt); + + return 0; + +socket_setattr_failure: + kfree(buf); + kfree(opt); + return ret_val; +} + +/** + * cipso_v4_socket_getattr - Get the security attributes from a socket + * @sock: the socket + * @secattr: the security attributes + * + * Description: + * Query @sock to see if there is a CIPSO option attached to the socket and if + * there is return the CIPSO security attributes in @secattr. Returns zero on + * success and negative values on failure. + * + */ +int cipso_v4_socket_getattr(const struct socket *sock, + struct netlbl_lsm_secattr *secattr) +{ + int ret_val = -ENOMSG; + struct sock *sk; + struct inet_sock *sk_inet; + unsigned char *cipso_ptr; + u32 doi; + struct cipso_v4_doi *doi_def; + + sk = sock->sk; + lock_sock(sk); + sk_inet = inet_sk(sk); + if (sk_inet->opt == NULL || sk_inet->opt->cipso == 0) + goto socket_getattr_return; + cipso_ptr = sk_inet->opt->__data + sk_inet->opt->cipso - + sizeof(struct iphdr); + ret_val = cipso_v4_cache_check(cipso_ptr, cipso_ptr[1], secattr); + if (ret_val == 0) + goto socket_getattr_return; + + doi = ntohl(*(u32 *)&cipso_ptr[2]); + rcu_read_lock(); + doi_def = cipso_v4_doi_getdef(doi); + if (doi_def == NULL) { + rcu_read_unlock(); + goto socket_getattr_return; + } + switch (cipso_ptr[6]) { + case CIPSO_V4_TAG_RBITMAP: + ret_val = cipso_v4_parsetag_rbm(doi_def, + &cipso_ptr[6], + secattr); + break; + } + rcu_read_unlock(); + +socket_getattr_return: + release_sock(sk); + return ret_val; +} + +/** + * cipso_v4_skbuff_getattr - Get the security attributes from the CIPSO option + * @skb: the packet + * @secattr: the security attributes + * + * Description: + * Parse the given packet's CIPSO option and return the security attributes. + * Returns zero on success and negative values on failure. + * + */ +int cipso_v4_skbuff_getattr(const struct sk_buff *skb, + struct netlbl_lsm_secattr *secattr) +{ + int ret_val = -ENOMSG; + unsigned char *cipso_ptr; + u32 doi; + struct cipso_v4_doi *doi_def; + + if (!CIPSO_V4_OPTEXIST(skb)) + return -ENOMSG; + cipso_ptr = CIPSO_V4_OPTPTR(skb); + if (cipso_v4_cache_check(cipso_ptr, cipso_ptr[1], secattr) == 0) + return 0; + + doi = ntohl(*(u32 *)&cipso_ptr[2]); + rcu_read_lock(); + doi_def = cipso_v4_doi_getdef(doi); + if (doi_def == NULL) + goto skbuff_getattr_return; + switch (cipso_ptr[6]) { + case CIPSO_V4_TAG_RBITMAP: + ret_val = cipso_v4_parsetag_rbm(doi_def, + &cipso_ptr[6], + secattr); + break; + } + +skbuff_getattr_return: + rcu_read_unlock(); + return ret_val; +} + +/* + * Setup Functions + */ + +/** + * cipso_v4_init - Initialize the CIPSO module + * + * Description: + * Initialize the CIPSO module and prepare it for use. Returns zero on success + * and negative values on failure. + * + */ +static int __init cipso_v4_init(void) +{ + int ret_val; + + ret_val = cipso_v4_cache_init(); + if (ret_val != 0) + panic("Failed to initialize the CIPSO/IPv4 cache (%d)\n", + ret_val); + + return 0; +} + +subsys_initcall(cipso_v4_init); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a6cc31d911e..8e8d1f17d77 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -43,6 +43,7 @@ #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> +#include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/inet.h> #include <linux/netdevice.h> @@ -62,6 +63,7 @@ #include <net/ip.h> #include <net/route.h> #include <net/ip_fib.h> +#include <net/netlink.h> struct ipv4_devconf ipv4_devconf = { .accept_redirects = 1, @@ -78,7 +80,15 @@ static struct ipv4_devconf ipv4_devconf_dflt = { .accept_source_route = 1, }; -static void rtmsg_ifa(int event, struct in_ifaddr *); +static struct nla_policy ifa_ipv4_policy[IFA_MAX+1] __read_mostly = { + [IFA_LOCAL] = { .type = NLA_U32 }, + [IFA_ADDRESS] = { .type = NLA_U32 }, + [IFA_BROADCAST] = { .type = NLA_U32 }, + [IFA_ANYCAST] = { .type = NLA_U32 }, + [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, +}; + +static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, @@ -229,8 +239,8 @@ int inet_addr_onlink(struct in_device *in_dev, u32 a, u32 b) return 0; } -static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, - int destroy) +static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, + int destroy, struct nlmsghdr *nlh, u32 pid) { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1 = *ifap; @@ -263,7 +273,7 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, if (!do_promote) { *ifap1 = ifa->ifa_next; - rtmsg_ifa(RTM_DELADDR, ifa); + rtmsg_ifa(RTM_DELADDR, ifa, nlh, pid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa); inet_free_ifa(ifa); @@ -288,7 +298,7 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, is valid, it will try to restore deleted routes... Grr. So that, this order is correct. */ - rtmsg_ifa(RTM_DELADDR, ifa1); + rtmsg_ifa(RTM_DELADDR, ifa1, nlh, pid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { @@ -300,7 +310,7 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, } promote->ifa_flags &= ~IFA_F_SECONDARY; - rtmsg_ifa(RTM_NEWADDR, promote); + rtmsg_ifa(RTM_NEWADDR, promote, nlh, pid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); for (ifa = promote->ifa_next; ifa; ifa = ifa->ifa_next) { @@ -319,7 +329,14 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, } } -static int inet_insert_ifa(struct in_ifaddr *ifa) +static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, + int destroy) +{ + __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); +} + +static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, + u32 pid) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1, **ifap, **last_primary; @@ -364,12 +381,17 @@ static int inet_insert_ifa(struct in_ifaddr *ifa) /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ - rtmsg_ifa(RTM_NEWADDR, ifa); + rtmsg_ifa(RTM_NEWADDR, ifa, nlh, pid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); return 0; } +static int inet_insert_ifa(struct in_ifaddr *ifa) +{ + return __inet_insert_ifa(ifa, NULL, 0); +} + static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) { struct in_device *in_dev = __in_dev_get_rtnl(dev); @@ -421,87 +443,134 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, u32 prefix, static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct rtattr **rta = arg; + struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; - struct ifaddrmsg *ifm = NLMSG_DATA(nlh); + struct ifaddrmsg *ifm; struct in_ifaddr *ifa, **ifap; + int err = -EINVAL; ASSERT_RTNL(); - if ((in_dev = inetdev_by_index(ifm->ifa_index)) == NULL) - goto out; + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy); + if (err < 0) + goto errout; + + ifm = nlmsg_data(nlh); + in_dev = inetdev_by_index(ifm->ifa_index); + if (in_dev == NULL) { + err = -ENODEV; + goto errout; + } + __in_dev_put(in_dev); for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; ifap = &ifa->ifa_next) { - if ((rta[IFA_LOCAL - 1] && - memcmp(RTA_DATA(rta[IFA_LOCAL - 1]), - &ifa->ifa_local, 4)) || - (rta[IFA_LABEL - 1] && - rtattr_strcmp(rta[IFA_LABEL - 1], ifa->ifa_label)) || - (rta[IFA_ADDRESS - 1] && - (ifm->ifa_prefixlen != ifa->ifa_prefixlen || - !inet_ifa_match(*(u32*)RTA_DATA(rta[IFA_ADDRESS - 1]), - ifa)))) + if (tb[IFA_LOCAL] && + ifa->ifa_local != nla_get_u32(tb[IFA_LOCAL])) + continue; + + if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) + continue; + + if (tb[IFA_ADDRESS] && + (ifm->ifa_prefixlen != ifa->ifa_prefixlen || + !inet_ifa_match(nla_get_u32(tb[IFA_ADDRESS]), ifa))) continue; - inet_del_ifa(in_dev, ifap, 1); + + __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).pid); return 0; } -out: - return -EADDRNOTAVAIL; + + err = -EADDRNOTAVAIL; +errout: + return err; } -static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static struct in_ifaddr *rtm_to_ifaddr(struct nlmsghdr *nlh) { - struct rtattr **rta = arg; + struct nlattr *tb[IFA_MAX+1]; + struct in_ifaddr *ifa; + struct ifaddrmsg *ifm; struct net_device *dev; struct in_device *in_dev; - struct ifaddrmsg *ifm = NLMSG_DATA(nlh); - struct in_ifaddr *ifa; - int rc = -EINVAL; + int err = -EINVAL; - ASSERT_RTNL(); + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy); + if (err < 0) + goto errout; - if (ifm->ifa_prefixlen > 32 || !rta[IFA_LOCAL - 1]) - goto out; + ifm = nlmsg_data(nlh); + if (ifm->ifa_prefixlen > 32 || tb[IFA_LOCAL] == NULL) + goto errout; - rc = -ENODEV; - if ((dev = __dev_get_by_index(ifm->ifa_index)) == NULL) - goto out; + dev = __dev_get_by_index(ifm->ifa_index); + if (dev == NULL) { + err = -ENODEV; + goto errout; + } - rc = -ENOBUFS; - if ((in_dev = __in_dev_get_rtnl(dev)) == NULL) { + in_dev = __in_dev_get_rtnl(dev); + if (in_dev == NULL) { in_dev = inetdev_init(dev); - if (!in_dev) - goto out; + if (in_dev == NULL) { + err = -ENOBUFS; + goto errout; + } } - if ((ifa = inet_alloc_ifa()) == NULL) - goto out; + ifa = inet_alloc_ifa(); + if (ifa == NULL) { + /* + * A potential indev allocation can be left alive, it stays + * assigned to its device and is destroy with it. + */ + err = -ENOBUFS; + goto errout; + } + + in_dev_hold(in_dev); + + if (tb[IFA_ADDRESS] == NULL) + tb[IFA_ADDRESS] = tb[IFA_LOCAL]; - if (!rta[IFA_ADDRESS - 1]) - rta[IFA_ADDRESS - 1] = rta[IFA_LOCAL - 1]; - memcpy(&ifa->ifa_local, RTA_DATA(rta[IFA_LOCAL - 1]), 4); - memcpy(&ifa->ifa_address, RTA_DATA(rta[IFA_ADDRESS - 1]), 4); ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); - if (rta[IFA_BROADCAST - 1]) - memcpy(&ifa->ifa_broadcast, - RTA_DATA(rta[IFA_BROADCAST - 1]), 4); - if (rta[IFA_ANYCAST - 1]) - memcpy(&ifa->ifa_anycast, RTA_DATA(rta[IFA_ANYCAST - 1]), 4); ifa->ifa_flags = ifm->ifa_flags; ifa->ifa_scope = ifm->ifa_scope; - in_dev_hold(in_dev); - ifa->ifa_dev = in_dev; - if (rta[IFA_LABEL - 1]) - rtattr_strlcpy(ifa->ifa_label, rta[IFA_LABEL - 1], IFNAMSIZ); + ifa->ifa_dev = in_dev; + + ifa->ifa_local = nla_get_u32(tb[IFA_LOCAL]); + ifa->ifa_address = nla_get_u32(tb[IFA_ADDRESS]); + + if (tb[IFA_BROADCAST]) + ifa->ifa_broadcast = nla_get_u32(tb[IFA_BROADCAST]); + + if (tb[IFA_ANYCAST]) + ifa->ifa_anycast = nla_get_u32(tb[IFA_ANYCAST]); + + if (tb[IFA_LABEL]) + nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); - rc = inet_insert_ifa(ifa); -out: - return rc; + return ifa; + +errout: + return ERR_PTR(err); +} + +static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct in_ifaddr *ifa; + + ASSERT_RTNL(); + + ifa = rtm_to_ifaddr(nlh); + if (IS_ERR(ifa)) + return PTR_ERR(ifa); + + return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).pid); } /* @@ -1056,32 +1125,37 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); - ifm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*ifm), flags); + if (nlh == NULL) + return -ENOBUFS; + + ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; ifm->ifa_flags = ifa->ifa_flags|IFA_F_PERMANENT; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; + if (ifa->ifa_address) - RTA_PUT(skb, IFA_ADDRESS, 4, &ifa->ifa_address); + NLA_PUT_U32(skb, IFA_ADDRESS, ifa->ifa_address); + if (ifa->ifa_local) - RTA_PUT(skb, IFA_LOCAL, 4, &ifa->ifa_local); + NLA_PUT_U32(skb, IFA_LOCAL, ifa->ifa_local); + if (ifa->ifa_broadcast) - RTA_PUT(skb, IFA_BROADCAST, 4, &ifa->ifa_broadcast); + NLA_PUT_U32(skb, IFA_BROADCAST, ifa->ifa_broadcast); + if (ifa->ifa_anycast) - RTA_PUT(skb, IFA_ANYCAST, 4, &ifa->ifa_anycast); + NLA_PUT_U32(skb, IFA_ANYCAST, ifa->ifa_anycast); + if (ifa->ifa_label[0]) - RTA_PUT(skb, IFA_LABEL, IFNAMSIZ, &ifa->ifa_label); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label); -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); } static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) @@ -1127,19 +1201,27 @@ done: return skb->len; } -static void rtmsg_ifa(int event, struct in_ifaddr* ifa) +static void rtmsg_ifa(int event, struct in_ifaddr* ifa, struct nlmsghdr *nlh, + u32 pid) { - int size = NLMSG_SPACE(sizeof(struct ifaddrmsg) + 128); - struct sk_buff *skb = alloc_skb(size, GFP_KERNEL); + struct sk_buff *skb; + u32 seq = nlh ? nlh->nlmsg_seq : 0; + int err = -ENOBUFS; + + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto errout; - if (!skb) - netlink_set_err(rtnl, 0, RTNLGRP_IPV4_IFADDR, ENOBUFS); - else if (inet_fill_ifaddr(skb, ifa, 0, 0, event, 0) < 0) { + err = inet_fill_ifaddr(skb, ifa, pid, seq, event, 0); + if (err < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV4_IFADDR, EINVAL); - } else { - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV4_IFADDR, GFP_KERNEL); + goto errout; } + + err = rtnl_notify(skb, pid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_IPV4_IFADDR, err); } static struct rtnetlink_link inet_rtnetlink_table[RTM_NR_MSGTYPES] = { @@ -1151,9 +1233,7 @@ static struct rtnetlink_link inet_rtnetlink_table[RTM_NR_MSGTYPES] = { [RTM_GETROUTE - RTM_BASE] = { .doit = inet_rtm_getroute, .dumpit = inet_dump_fib, }, #ifdef CONFIG_IP_MULTIPLE_TABLES - [RTM_NEWRULE - RTM_BASE] = { .doit = inet_rtm_newrule, }, - [RTM_DELRULE - RTM_BASE] = { .doit = inet_rtm_delrule, }, - [RTM_GETRULE - RTM_BASE] = { .dumpit = inet_dump_rules, }, + [RTM_GETRULE - RTM_BASE] = { .dumpit = fib4_rules_dump, }, #endif }; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b428489f6cc..13b29360d10 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -95,8 +95,13 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) esph->seq_no = htonl(++x->replay.oseq); xfrm_aevent_doreplay(x); - if (esp->conf.ivlen) + if (esp->conf.ivlen) { + if (unlikely(!esp->conf.ivinitted)) { + get_random_bytes(esp->conf.ivec, esp->conf.ivlen); + esp->conf.ivinitted = 1; + } crypto_blkcipher_set_iv(tfm, esp->conf.ivec, esp->conf.ivlen); + } do { struct scatterlist *sg = &esp->sgbuf[0]; @@ -248,7 +253,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) * as per draft-ietf-ipsec-udp-encaps-06, * section 3.1.2 */ - if (!x->props.mode) + if (x->props.mode == XFRM_MODE_TRANSPORT) skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -267,7 +272,7 @@ static u32 esp4_get_max_size(struct xfrm_state *x, int mtu) struct esp_data *esp = x->data; u32 blksize = ALIGN(crypto_blkcipher_blocksize(esp->conf.tfm), 4); - if (x->props.mode) { + if (x->props.mode == XFRM_MODE_TUNNEL) { mtu = ALIGN(mtu + 2, blksize); } else { /* The worst case. */ @@ -378,12 +383,12 @@ static int esp_init_state(struct xfrm_state *x) esp->conf.ivec = kmalloc(esp->conf.ivlen, GFP_KERNEL); if (unlikely(esp->conf.ivec == NULL)) goto error; - get_random_bytes(esp->conf.ivec, esp->conf.ivlen); + esp->conf.ivinitted = 0; } if (crypto_blkcipher_setkey(tfm, esp->conf.key, esp->conf.key_len)) goto error; x->props.header_len = sizeof(struct ip_esp_hdr) + esp->conf.ivlen; - if (x->props.mode) + if (x->props.mode == XFRM_MODE_TUNNEL) x->props.header_len += sizeof(struct iphdr); if (x->encap) { struct xfrm_encap_tmpl *encap = x->encap; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index ba2a70745a6..cfb527c060e 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -32,10 +32,12 @@ #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> +#include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> +#include <linux/list.h> #include <net/ip.h> #include <net/protocol.h> @@ -50,48 +52,67 @@ #ifndef CONFIG_IP_MULTIPLE_TABLES -#define RT_TABLE_MIN RT_TABLE_MAIN - struct fib_table *ip_fib_local_table; struct fib_table *ip_fib_main_table; -#else +#define FIB_TABLE_HASHSZ 1 +static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; -#define RT_TABLE_MIN 1 +#else -struct fib_table *fib_tables[RT_TABLE_MAX+1]; +#define FIB_TABLE_HASHSZ 256 +static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; -struct fib_table *__fib_new_table(int id) +struct fib_table *fib_new_table(u32 id) { struct fib_table *tb; + unsigned int h; + if (id == 0) + id = RT_TABLE_MAIN; + tb = fib_get_table(id); + if (tb) + return tb; tb = fib_hash_init(id); if (!tb) return NULL; - fib_tables[id] = tb; + h = id & (FIB_TABLE_HASHSZ - 1); + hlist_add_head_rcu(&tb->tb_hlist, &fib_table_hash[h]); return tb; } +struct fib_table *fib_get_table(u32 id) +{ + struct fib_table *tb; + struct hlist_node *node; + unsigned int h; + if (id == 0) + id = RT_TABLE_MAIN; + h = id & (FIB_TABLE_HASHSZ - 1); + rcu_read_lock(); + hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb_hlist) { + if (tb->tb_id == id) { + rcu_read_unlock(); + return tb; + } + } + rcu_read_unlock(); + return NULL; +} #endif /* CONFIG_IP_MULTIPLE_TABLES */ - static void fib_flush(void) { int flushed = 0; -#ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_table *tb; - int id; + struct hlist_node *node; + unsigned int h; - for (id = RT_TABLE_MAX; id>0; id--) { - if ((tb = fib_get_table(id))==NULL) - continue; - flushed += tb->tb_flush(tb); + for (h = 0; h < FIB_TABLE_HASHSZ; h++) { + hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist) + flushed += tb->tb_flush(tb); } -#else /* CONFIG_IP_MULTIPLE_TABLES */ - flushed += ip_fib_main_table->tb_flush(ip_fib_main_table); - flushed += ip_fib_local_table->tb_flush(ip_fib_local_table); -#endif /* CONFIG_IP_MULTIPLE_TABLES */ if (flushed) rt_cache_flush(-1); @@ -232,42 +253,190 @@ e_inval: #ifndef CONFIG_IP_NOSIOCRT +static inline u32 sk_extract_addr(struct sockaddr *addr) +{ + return ((struct sockaddr_in *) addr)->sin_addr.s_addr; +} + +static int put_rtax(struct nlattr *mx, int len, int type, u32 value) +{ + struct nlattr *nla; + + nla = (struct nlattr *) ((char *) mx + len); + nla->nla_type = type; + nla->nla_len = nla_attr_size(4); + *(u32 *) nla_data(nla) = value; + + return len + nla_total_size(4); +} + +static int rtentry_to_fib_config(int cmd, struct rtentry *rt, + struct fib_config *cfg) +{ + u32 addr; + int plen; + + memset(cfg, 0, sizeof(*cfg)); + + if (rt->rt_dst.sa_family != AF_INET) + return -EAFNOSUPPORT; + + /* + * Check mask for validity: + * a) it must be contiguous. + * b) destination must have all host bits clear. + * c) if application forgot to set correct family (AF_INET), + * reject request unless it is absolutely clear i.e. + * both family and mask are zero. + */ + plen = 32; + addr = sk_extract_addr(&rt->rt_dst); + if (!(rt->rt_flags & RTF_HOST)) { + u32 mask = sk_extract_addr(&rt->rt_genmask); + + if (rt->rt_genmask.sa_family != AF_INET) { + if (mask || rt->rt_genmask.sa_family) + return -EAFNOSUPPORT; + } + + if (bad_mask(mask, addr)) + return -EINVAL; + + plen = inet_mask_len(mask); + } + + cfg->fc_dst_len = plen; + cfg->fc_dst = addr; + + if (cmd != SIOCDELRT) { + cfg->fc_nlflags = NLM_F_CREATE; + cfg->fc_protocol = RTPROT_BOOT; + } + + if (rt->rt_metric) + cfg->fc_priority = rt->rt_metric - 1; + + if (rt->rt_flags & RTF_REJECT) { + cfg->fc_scope = RT_SCOPE_HOST; + cfg->fc_type = RTN_UNREACHABLE; + return 0; + } + + cfg->fc_scope = RT_SCOPE_NOWHERE; + cfg->fc_type = RTN_UNICAST; + + if (rt->rt_dev) { + char *colon; + struct net_device *dev; + char devname[IFNAMSIZ]; + + if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1)) + return -EFAULT; + + devname[IFNAMSIZ-1] = 0; + colon = strchr(devname, ':'); + if (colon) + *colon = 0; + dev = __dev_get_by_name(devname); + if (!dev) + return -ENODEV; + cfg->fc_oif = dev->ifindex; + if (colon) { + struct in_ifaddr *ifa; + struct in_device *in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) + return -ENODEV; + *colon = ':'; + for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) + if (strcmp(ifa->ifa_label, devname) == 0) + break; + if (ifa == NULL) + return -ENODEV; + cfg->fc_prefsrc = ifa->ifa_local; + } + } + + addr = sk_extract_addr(&rt->rt_gateway); + if (rt->rt_gateway.sa_family == AF_INET && addr) { + cfg->fc_gw = addr; + if (rt->rt_flags & RTF_GATEWAY && + inet_addr_type(addr) == RTN_UNICAST) + cfg->fc_scope = RT_SCOPE_UNIVERSE; + } + + if (cmd == SIOCDELRT) + return 0; + + if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw) + return -EINVAL; + + if (cfg->fc_scope == RT_SCOPE_NOWHERE) + cfg->fc_scope = RT_SCOPE_LINK; + + if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) { + struct nlattr *mx; + int len = 0; + + mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL); + if (mx == NULL) + return -ENOMEM; + + if (rt->rt_flags & RTF_MTU) + len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40); + + if (rt->rt_flags & RTF_WINDOW) + len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window); + + if (rt->rt_flags & RTF_IRTT) + len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3); + + cfg->fc_mx = mx; + cfg->fc_mx_len = len; + } + + return 0; +} + /* * Handle IP routing ioctl calls. These are used to manipulate the routing tables */ int ip_rt_ioctl(unsigned int cmd, void __user *arg) { + struct fib_config cfg; + struct rtentry rt; int err; - struct kern_rta rta; - struct rtentry r; - struct { - struct nlmsghdr nlh; - struct rtmsg rtm; - } req; switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (copy_from_user(&r, arg, sizeof(struct rtentry))) + + if (copy_from_user(&rt, arg, sizeof(rt))) return -EFAULT; + rtnl_lock(); - err = fib_convert_rtentry(cmd, &req.nlh, &req.rtm, &rta, &r); + err = rtentry_to_fib_config(cmd, &rt, &cfg); if (err == 0) { + struct fib_table *tb; + if (cmd == SIOCDELRT) { - struct fib_table *tb = fib_get_table(req.rtm.rtm_table); - err = -ESRCH; + tb = fib_get_table(cfg.fc_table); if (tb) - err = tb->tb_delete(tb, &req.rtm, &rta, &req.nlh, NULL); + err = tb->tb_delete(tb, &cfg); + else + err = -ESRCH; } else { - struct fib_table *tb = fib_new_table(req.rtm.rtm_table); - err = -ENOBUFS; + tb = fib_new_table(cfg.fc_table); if (tb) - err = tb->tb_insert(tb, &req.rtm, &rta, &req.nlh, NULL); + err = tb->tb_insert(tb, &cfg); + else + err = -ENOBUFS; } - kfree(rta.rta_mx); + + /* allocated by rtentry_to_fib_config() */ + kfree(cfg.fc_mx); } rtnl_unlock(); return err; @@ -284,77 +453,169 @@ int ip_rt_ioctl(unsigned int cmd, void *arg) #endif -static int inet_check_attr(struct rtmsg *r, struct rtattr **rta) +struct nla_policy rtm_ipv4_policy[RTA_MAX+1] __read_mostly = { + [RTA_DST] = { .type = NLA_U32 }, + [RTA_SRC] = { .type = NLA_U32 }, + [RTA_IIF] = { .type = NLA_U32 }, + [RTA_OIF] = { .type = NLA_U32 }, + [RTA_GATEWAY] = { .type = NLA_U32 }, + [RTA_PRIORITY] = { .type = NLA_U32 }, + [RTA_PREFSRC] = { .type = NLA_U32 }, + [RTA_METRICS] = { .type = NLA_NESTED }, + [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, + [RTA_PROTOINFO] = { .type = NLA_U32 }, + [RTA_FLOW] = { .type = NLA_U32 }, + [RTA_MP_ALGO] = { .type = NLA_U32 }, +}; + +static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh, + struct fib_config *cfg) { - int i; - - for (i=1; i<=RTA_MAX; i++, rta++) { - struct rtattr *attr = *rta; - if (attr) { - if (RTA_PAYLOAD(attr) < 4) - return -EINVAL; - if (i != RTA_MULTIPATH && i != RTA_METRICS) - *rta = (struct rtattr*)RTA_DATA(attr); + struct nlattr *attr; + int err, remaining; + struct rtmsg *rtm; + + err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy); + if (err < 0) + goto errout; + + memset(cfg, 0, sizeof(*cfg)); + + rtm = nlmsg_data(nlh); + cfg->fc_family = rtm->rtm_family; + cfg->fc_dst_len = rtm->rtm_dst_len; + cfg->fc_src_len = rtm->rtm_src_len; + cfg->fc_tos = rtm->rtm_tos; + cfg->fc_table = rtm->rtm_table; + cfg->fc_protocol = rtm->rtm_protocol; + cfg->fc_scope = rtm->rtm_scope; + cfg->fc_type = rtm->rtm_type; + cfg->fc_flags = rtm->rtm_flags; + cfg->fc_nlflags = nlh->nlmsg_flags; + + cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; + cfg->fc_nlinfo.nlh = nlh; + + nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) { + switch (attr->nla_type) { + case RTA_DST: + cfg->fc_dst = nla_get_u32(attr); + break; + case RTA_SRC: + cfg->fc_src = nla_get_u32(attr); + break; + case RTA_OIF: + cfg->fc_oif = nla_get_u32(attr); + break; + case RTA_GATEWAY: + cfg->fc_gw = nla_get_u32(attr); + break; + case RTA_PRIORITY: + cfg->fc_priority = nla_get_u32(attr); + break; + case RTA_PREFSRC: + cfg->fc_prefsrc = nla_get_u32(attr); + break; + case RTA_METRICS: + cfg->fc_mx = nla_data(attr); + cfg->fc_mx_len = nla_len(attr); + break; + case RTA_MULTIPATH: + cfg->fc_mp = nla_data(attr); + cfg->fc_mp_len = nla_len(attr); + break; + case RTA_FLOW: + cfg->fc_flow = nla_get_u32(attr); + break; + case RTA_MP_ALGO: + cfg->fc_mp_alg = nla_get_u32(attr); + break; + case RTA_TABLE: + cfg->fc_table = nla_get_u32(attr); + break; } } + return 0; +errout: + return err; } int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct fib_table * tb; - struct rtattr **rta = arg; - struct rtmsg *r = NLMSG_DATA(nlh); + struct fib_config cfg; + struct fib_table *tb; + int err; - if (inet_check_attr(r, rta)) - return -EINVAL; + err = rtm_to_fib_config(skb, nlh, &cfg); + if (err < 0) + goto errout; - tb = fib_get_table(r->rtm_table); - if (tb) - return tb->tb_delete(tb, r, (struct kern_rta*)rta, nlh, &NETLINK_CB(skb)); - return -ESRCH; + tb = fib_get_table(cfg.fc_table); + if (tb == NULL) { + err = -ESRCH; + goto errout; + } + + err = tb->tb_delete(tb, &cfg); +errout: + return err; } int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct fib_table * tb; - struct rtattr **rta = arg; - struct rtmsg *r = NLMSG_DATA(nlh); + struct fib_config cfg; + struct fib_table *tb; + int err; - if (inet_check_attr(r, rta)) - return -EINVAL; + err = rtm_to_fib_config(skb, nlh, &cfg); + if (err < 0) + goto errout; - tb = fib_new_table(r->rtm_table); - if (tb) - return tb->tb_insert(tb, r, (struct kern_rta*)rta, nlh, &NETLINK_CB(skb)); - return -ENOBUFS; + tb = fib_new_table(cfg.fc_table); + if (tb == NULL) { + err = -ENOBUFS; + goto errout; + } + + err = tb->tb_insert(tb, &cfg); +errout: + return err; } int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - int t; - int s_t; + unsigned int h, s_h; + unsigned int e = 0, s_e; struct fib_table *tb; + struct hlist_node *node; + int dumped = 0; - if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) && - ((struct rtmsg*)NLMSG_DATA(cb->nlh))->rtm_flags&RTM_F_CLONED) + if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && + ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED) return ip_rt_dump(skb, cb); - s_t = cb->args[0]; - if (s_t == 0) - s_t = cb->args[0] = RT_TABLE_MIN; - - for (t=s_t; t<=RT_TABLE_MAX; t++) { - if (t < s_t) continue; - if (t > s_t) - memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); - if ((tb = fib_get_table(t))==NULL) - continue; - if (tb->tb_dump(tb, skb, cb) < 0) - break; + s_h = cb->args[0]; + s_e = cb->args[1]; + + for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { + e = 0; + hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist) { + if (e < s_e) + goto next; + if (dumped) + memset(&cb->args[2], 0, sizeof(cb->args) - + 2 * sizeof(cb->args[0])); + if (tb->tb_dump(tb, skb, cb) < 0) + goto out; + dumped = 1; +next: + e++; + } } - - cb->args[0] = t; +out: + cb->args[1] = e; + cb->args[0] = h; return skb->len; } @@ -366,17 +627,19 @@ int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) only when netlink is already locked. */ -static void fib_magic(int cmd, int type, u32 dst, int dst_len, struct in_ifaddr *ifa) +static void fib_magic(int cmd, int type, u32 dst, int dst_len, + struct in_ifaddr *ifa) { - struct fib_table * tb; - struct { - struct nlmsghdr nlh; - struct rtmsg rtm; - } req; - struct kern_rta rta; - - memset(&req.rtm, 0, sizeof(req.rtm)); - memset(&rta, 0, sizeof(rta)); + struct fib_table *tb; + struct fib_config cfg = { + .fc_protocol = RTPROT_KERNEL, + .fc_type = type, + .fc_dst = dst, + .fc_dst_len = dst_len, + .fc_prefsrc = ifa->ifa_local, + .fc_oif = ifa->ifa_dev->dev->ifindex, + .fc_nlflags = NLM_F_CREATE | NLM_F_APPEND, + }; if (type == RTN_UNICAST) tb = fib_new_table(RT_TABLE_MAIN); @@ -386,26 +649,17 @@ static void fib_magic(int cmd, int type, u32 dst, int dst_len, struct in_ifaddr if (tb == NULL) return; - req.nlh.nlmsg_len = sizeof(req); - req.nlh.nlmsg_type = cmd; - req.nlh.nlmsg_flags = NLM_F_REQUEST|NLM_F_CREATE|NLM_F_APPEND; - req.nlh.nlmsg_pid = 0; - req.nlh.nlmsg_seq = 0; + cfg.fc_table = tb->tb_id; - req.rtm.rtm_dst_len = dst_len; - req.rtm.rtm_table = tb->tb_id; - req.rtm.rtm_protocol = RTPROT_KERNEL; - req.rtm.rtm_scope = (type != RTN_LOCAL ? RT_SCOPE_LINK : RT_SCOPE_HOST); - req.rtm.rtm_type = type; - - rta.rta_dst = &dst; - rta.rta_prefsrc = &ifa->ifa_local; - rta.rta_oif = &ifa->ifa_dev->dev->ifindex; + if (type != RTN_LOCAL) + cfg.fc_scope = RT_SCOPE_LINK; + else + cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) - tb->tb_insert(tb, &req.rtm, &rta, &req.nlh, NULL); + tb->tb_insert(tb, &cfg); else - tb->tb_delete(tb, &req.rtm, &rta, &req.nlh, NULL); + tb->tb_delete(tb, &cfg); } void fib_add_ifaddr(struct in_ifaddr *ifa) @@ -652,11 +906,17 @@ static struct notifier_block fib_netdev_notifier = { void __init ip_fib_init(void) { + unsigned int i; + + for (i = 0; i < FIB_TABLE_HASHSZ; i++) + INIT_HLIST_HEAD(&fib_table_hash[i]); #ifndef CONFIG_IP_MULTIPLE_TABLES ip_fib_local_table = fib_hash_init(RT_TABLE_LOCAL); + hlist_add_head_rcu(&ip_fib_local_table->tb_hlist, &fib_table_hash[0]); ip_fib_main_table = fib_hash_init(RT_TABLE_MAIN); + hlist_add_head_rcu(&ip_fib_main_table->tb_hlist, &fib_table_hash[0]); #else - fib_rules_init(); + fib4_rules_init(); #endif register_netdevice_notifier(&fib_netdev_notifier); diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 72c633b357c..88133b383dc 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -379,42 +379,39 @@ static struct fib_node *fib_find_node(struct fn_zone *fz, u32 key) return NULL; } -static int -fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, - struct nlmsghdr *n, struct netlink_skb_parms *req) +static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; struct fib_node *new_f, *f; struct fib_alias *fa, *new_fa; struct fn_zone *fz; struct fib_info *fi; - int z = r->rtm_dst_len; - int type = r->rtm_type; - u8 tos = r->rtm_tos; + u8 tos = cfg->fc_tos; u32 key; int err; - if (z > 32) + if (cfg->fc_dst_len > 32) return -EINVAL; - fz = table->fn_zones[z]; - if (!fz && !(fz = fn_new_zone(table, z))) + + fz = table->fn_zones[cfg->fc_dst_len]; + if (!fz && !(fz = fn_new_zone(table, cfg->fc_dst_len))) return -ENOBUFS; key = 0; - if (rta->rta_dst) { - u32 dst; - memcpy(&dst, rta->rta_dst, 4); - if (dst & ~FZ_MASK(fz)) + if (cfg->fc_dst) { + if (cfg->fc_dst & ~FZ_MASK(fz)) return -EINVAL; - key = fz_key(dst, fz); + key = fz_key(cfg->fc_dst, fz); } - if ((fi = fib_create_info(r, rta, n, &err)) == NULL) - return err; + fi = fib_create_info(cfg); + if (IS_ERR(fi)) + return PTR_ERR(fi); if (fz->fz_nent > (fz->fz_divisor<<1) && fz->fz_divisor < FZ_MAX_DIVISOR && - (z==32 || (1<<z) > fz->fz_divisor)) + (cfg->fc_dst_len == 32 || + (1 << cfg->fc_dst_len) > fz->fz_divisor)) fn_rehash_zone(fz); f = fib_find_node(fz, key); @@ -440,18 +437,18 @@ fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, struct fib_alias *fa_orig; err = -EEXIST; - if (n->nlmsg_flags & NLM_F_EXCL) + if (cfg->fc_nlflags & NLM_F_EXCL) goto out; - if (n->nlmsg_flags & NLM_F_REPLACE) { + if (cfg->fc_nlflags & NLM_F_REPLACE) { struct fib_info *fi_drop; u8 state; write_lock_bh(&fib_hash_lock); fi_drop = fa->fa_info; fa->fa_info = fi; - fa->fa_type = type; - fa->fa_scope = r->rtm_scope; + fa->fa_type = cfg->fc_type; + fa->fa_scope = cfg->fc_scope; state = fa->fa_state; fa->fa_state &= ~FA_S_ACCESSED; fib_hash_genid++; @@ -474,17 +471,17 @@ fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, break; if (fa->fa_info->fib_priority != fi->fib_priority) break; - if (fa->fa_type == type && - fa->fa_scope == r->rtm_scope && + if (fa->fa_type == cfg->fc_type && + fa->fa_scope == cfg->fc_scope && fa->fa_info == fi) goto out; } - if (!(n->nlmsg_flags & NLM_F_APPEND)) + if (!(cfg->fc_nlflags & NLM_F_APPEND)) fa = fa_orig; } err = -ENOENT; - if (!(n->nlmsg_flags&NLM_F_CREATE)) + if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; err = -ENOBUFS; @@ -506,8 +503,8 @@ fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, new_fa->fa_info = fi; new_fa->fa_tos = tos; - new_fa->fa_type = type; - new_fa->fa_scope = r->rtm_scope; + new_fa->fa_type = cfg->fc_type; + new_fa->fa_scope = cfg->fc_scope; new_fa->fa_state = 0; /* @@ -526,7 +523,8 @@ fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, fz->fz_nent++; rt_cache_flush(-1); - rtmsg_fib(RTM_NEWROUTE, key, new_fa, z, tb->tb_id, n, req); + rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, tb->tb_id, + &cfg->fc_nlinfo); return 0; out_free_new_fa: @@ -537,30 +535,25 @@ out: } -static int -fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, - struct nlmsghdr *n, struct netlink_skb_parms *req) +static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash*)tb->tb_data; struct fib_node *f; struct fib_alias *fa, *fa_to_delete; - int z = r->rtm_dst_len; struct fn_zone *fz; u32 key; - u8 tos = r->rtm_tos; - if (z > 32) + if (cfg->fc_dst_len > 32) return -EINVAL; - if ((fz = table->fn_zones[z]) == NULL) + + if ((fz = table->fn_zones[cfg->fc_dst_len]) == NULL) return -ESRCH; key = 0; - if (rta->rta_dst) { - u32 dst; - memcpy(&dst, rta->rta_dst, 4); - if (dst & ~FZ_MASK(fz)) + if (cfg->fc_dst) { + if (cfg->fc_dst & ~FZ_MASK(fz)) return -EINVAL; - key = fz_key(dst, fz); + key = fz_key(cfg->fc_dst, fz); } f = fib_find_node(fz, key); @@ -568,7 +561,7 @@ fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, if (!f) fa = NULL; else - fa = fib_find_alias(&f->fn_alias, tos, 0); + fa = fib_find_alias(&f->fn_alias, cfg->fc_tos, 0); if (!fa) return -ESRCH; @@ -577,16 +570,16 @@ fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, list_for_each_entry_continue(fa, &f->fn_alias, fa_list) { struct fib_info *fi = fa->fa_info; - if (fa->fa_tos != tos) + if (fa->fa_tos != cfg->fc_tos) break; - if ((!r->rtm_type || - fa->fa_type == r->rtm_type) && - (r->rtm_scope == RT_SCOPE_NOWHERE || - fa->fa_scope == r->rtm_scope) && - (!r->rtm_protocol || - fi->fib_protocol == r->rtm_protocol) && - fib_nh_match(r, n, rta, fi) == 0) { + if ((!cfg->fc_type || + fa->fa_type == cfg->fc_type) && + (cfg->fc_scope == RT_SCOPE_NOWHERE || + fa->fa_scope == cfg->fc_scope) && + (!cfg->fc_protocol || + fi->fib_protocol == cfg->fc_protocol) && + fib_nh_match(cfg, fi) == 0) { fa_to_delete = fa; break; } @@ -596,7 +589,8 @@ fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, int kill_fn; fa = fa_to_delete; - rtmsg_fib(RTM_DELROUTE, key, fa, z, tb->tb_id, n, req); + rtmsg_fib(RTM_DELROUTE, key, fa, cfg->fc_dst_len, + tb->tb_id, &cfg->fc_nlinfo); kill_fn = 0; write_lock_bh(&fib_hash_lock); @@ -684,7 +678,7 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, struct fib_node *f; int i, s_i; - s_i = cb->args[3]; + s_i = cb->args[4]; i = 0; hlist_for_each_entry(f, node, head, fn_hash) { struct fib_alias *fa; @@ -699,19 +693,19 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, tb->tb_id, fa->fa_type, fa->fa_scope, - &f->fn_key, + f->fn_key, fz->fz_order, fa->fa_tos, fa->fa_info, NLM_F_MULTI) < 0) { - cb->args[3] = i; + cb->args[4] = i; return -1; } next: i++; } } - cb->args[3] = i; + cb->args[4] = i; return skb->len; } @@ -722,21 +716,21 @@ fn_hash_dump_zone(struct sk_buff *skb, struct netlink_callback *cb, { int h, s_h; - s_h = cb->args[2]; + s_h = cb->args[3]; for (h=0; h < fz->fz_divisor; h++) { if (h < s_h) continue; if (h > s_h) - memset(&cb->args[3], 0, - sizeof(cb->args) - 3*sizeof(cb->args[0])); + memset(&cb->args[4], 0, + sizeof(cb->args) - 4*sizeof(cb->args[0])); if (fz->fz_hash == NULL || hlist_empty(&fz->fz_hash[h])) continue; if (fn_hash_dump_bucket(skb, cb, tb, fz, &fz->fz_hash[h])<0) { - cb->args[2] = h; + cb->args[3] = h; return -1; } } - cb->args[2] = h; + cb->args[3] = h; return skb->len; } @@ -746,28 +740,28 @@ static int fn_hash_dump(struct fib_table *tb, struct sk_buff *skb, struct netlin struct fn_zone *fz; struct fn_hash *table = (struct fn_hash*)tb->tb_data; - s_m = cb->args[1]; + s_m = cb->args[2]; read_lock(&fib_hash_lock); for (fz = table->fn_zone_list, m=0; fz; fz = fz->fz_next, m++) { if (m < s_m) continue; if (m > s_m) - memset(&cb->args[2], 0, - sizeof(cb->args) - 2*sizeof(cb->args[0])); + memset(&cb->args[3], 0, + sizeof(cb->args) - 3*sizeof(cb->args[0])); if (fn_hash_dump_zone(skb, cb, tb, fz) < 0) { - cb->args[1] = m; + cb->args[2] = m; read_unlock(&fib_hash_lock); return -1; } } read_unlock(&fib_hash_lock); - cb->args[1] = m; + cb->args[2] = m; return skb->len; } #ifdef CONFIG_IP_MULTIPLE_TABLES -struct fib_table * fib_hash_init(int id) +struct fib_table * fib_hash_init(u32 id) #else -struct fib_table * __init fib_hash_init(int id) +struct fib_table * __init fib_hash_init(u32 id) #endif { struct fib_table *tb; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index ef6609ea0eb..fd6f7769f8a 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -23,19 +23,14 @@ extern int fib_semantic_match(struct list_head *head, struct fib_result *res, __u32 zone, __u32 mask, int prefixlen); extern void fib_release_info(struct fib_info *); -extern struct fib_info *fib_create_info(const struct rtmsg *r, - struct kern_rta *rta, - const struct nlmsghdr *, - int *err); -extern int fib_nh_match(struct rtmsg *r, struct nlmsghdr *, - struct kern_rta *rta, struct fib_info *fi); +extern struct fib_info *fib_create_info(struct fib_config *cfg); +extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u8 tb_id, u8 type, u8 scope, void *dst, + u32 tb_id, u8 type, u8 scope, u32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); extern void rtmsg_fib(int event, u32 key, struct fib_alias *fa, - int z, int tb_id, - struct nlmsghdr *n, struct netlink_skb_parms *req); + int dst_len, u32 tb_id, struct nl_info *info); extern struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio); extern int fib_detect_death(struct fib_info *fi, int order, diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 79b04718bdf..52b2adae4f2 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -5,9 +5,8 @@ * * IPv4 Forwarding Information Base: policy rules. * - * Version: $Id: fib_rules.c,v 1.17 2001/10/31 21:55:54 davem Exp $ - * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> + * Thomas Graf <tgraf@suug.ch> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -19,463 +18,350 @@ * Marc Boucher : routing by fwmark */ -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/string.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/errno.h> -#include <linux/in.h> -#include <linux/inet.h> -#include <linux/inetdevice.h> #include <linux/netdevice.h> -#include <linux/if_arp.h> -#include <linux/proc_fs.h> -#include <linux/skbuff.h> #include <linux/netlink.h> +#include <linux/inetdevice.h> #include <linux/init.h> #include <linux/list.h> #include <linux/rcupdate.h> - #include <net/ip.h> -#include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> -#include <net/sock.h> #include <net/ip_fib.h> +#include <net/fib_rules.h> -#define FRprintk(a...) +static struct fib_rules_ops fib4_rules_ops; -struct fib_rule +struct fib4_rule { - struct hlist_node 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; - u32 r_src; - u32 r_srcmask; - u32 r_dst; - u32 r_dstmask; - u32 r_srcmap; - u8 r_flags; - u8 r_tos; + struct fib_rule common; + u8 dst_len; + u8 src_len; + u8 tos; + u32 src; + u32 srcmask; + u32 dst; + u32 dstmask; #ifdef CONFIG_IP_ROUTE_FWMARK - u32 r_fwmark; + u32 fwmark; + u32 fwmask; #endif - int r_ifindex; #ifdef CONFIG_NET_CLS_ROUTE - __u32 r_tclassid; + u32 tclassid; #endif - char r_ifname[IFNAMSIZ]; - int r_dead; - struct rcu_head rcu; }; -static struct fib_rule default_rule = { - .r_clntref = ATOMIC_INIT(2), - .r_preference = 0x7FFF, - .r_table = RT_TABLE_DEFAULT, - .r_action = RTN_UNICAST, +static struct fib4_rule default_rule = { + .common = { + .refcnt = ATOMIC_INIT(2), + .pref = 0x7FFF, + .table = RT_TABLE_DEFAULT, + .action = FR_ACT_TO_TBL, + }, }; -static struct fib_rule main_rule = { - .r_clntref = ATOMIC_INIT(2), - .r_preference = 0x7FFE, - .r_table = RT_TABLE_MAIN, - .r_action = RTN_UNICAST, +static struct fib4_rule main_rule = { + .common = { + .refcnt = ATOMIC_INIT(2), + .pref = 0x7FFE, + .table = RT_TABLE_MAIN, + .action = FR_ACT_TO_TBL, + }, }; -static struct fib_rule local_rule = { - .r_clntref = ATOMIC_INIT(2), - .r_table = RT_TABLE_LOCAL, - .r_action = RTN_UNICAST, +static struct fib4_rule local_rule = { + .common = { + .refcnt = ATOMIC_INIT(2), + .table = RT_TABLE_LOCAL, + .action = FR_ACT_TO_TBL, + .flags = FIB_RULE_PERMANENT, + }, }; -static struct hlist_head fib_rules; +static LIST_HEAD(fib4_rules); -/* writer func called from netlink -- rtnl_sem hold*/ - -static void rtmsg_rule(int, struct fib_rule *); - -int inet_rtm_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +#ifdef CONFIG_NET_CLS_ROUTE +u32 fib_rules_tclass(struct fib_result *res) { - struct rtattr **rta = arg; - struct rtmsg *rtm = NLMSG_DATA(nlh); - struct fib_rule *r; - struct hlist_node *node; - int err = -ESRCH; - - 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 && - (!rta[RTA_DST-1] || memcmp(RTA_DATA(rta[RTA_DST-1]), &r->r_dst, 4) == 0) && - rtm->rtm_tos == r->r_tos && -#ifdef CONFIG_IP_ROUTE_FWMARK - (!rta[RTA_PROTOINFO-1] || memcmp(RTA_DATA(rta[RTA_PROTOINFO-1]), &r->r_fwmark, 4) == 0) && -#endif - (!rtm->rtm_type || rtm->rtm_type == r->r_action) && - (!rta[RTA_PRIORITY-1] || memcmp(RTA_DATA(rta[RTA_PRIORITY-1]), &r->r_preference, 4) == 0) && - (!rta[RTA_IIF-1] || rtattr_strcmp(rta[RTA_IIF-1], r->r_ifname) == 0) && - (!rtm->rtm_table || (r && rtm->rtm_table == r->r_table))) { - err = -EPERM; - if (r == &local_rule) - break; - - hlist_del_rcu(&r->hlist); - r->r_dead = 1; - rtmsg_rule(RTM_DELRULE, r); - fib_rule_put(r); - err = 0; - break; - } - } - return err; + return res->r ? ((struct fib4_rule *) res->r)->tclassid : 0; } +#endif -/* Allocate new unique table id */ - -static struct fib_table *fib_empty_table(void) +int fib_lookup(struct flowi *flp, struct fib_result *res) { - int id; + struct fib_lookup_arg arg = { + .result = res, + }; + int err; - for (id = 1; id <= RT_TABLE_MAX; id++) - if (fib_tables[id] == NULL) - return __fib_new_table(id); - return NULL; -} + err = fib_rules_lookup(&fib4_rules_ops, flp, 0, &arg); + res->r = arg.rule; -static inline void fib_rule_put_rcu(struct rcu_head *head) -{ - struct fib_rule *r = container_of(head, struct fib_rule, rcu); - kfree(r); + return err; } -void fib_rule_put(struct fib_rule *r) +static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) { - if (atomic_dec_and_test(&r->r_clntref)) { - if (r->r_dead) - call_rcu(&r->rcu, fib_rule_put_rcu); - else - printk("Freeing alive rule %p\n", r); + int err = -EAGAIN; + struct fib_table *tbl; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + + case FR_ACT_UNREACHABLE: + err = -ENETUNREACH; + goto errout; + + case FR_ACT_PROHIBIT: + err = -EACCES; + goto errout; + + case FR_ACT_BLACKHOLE: + default: + err = -EINVAL; + goto errout; } + + if ((tbl = fib_get_table(rule->table)) == NULL) + goto errout; + + err = tbl->tb_lookup(tbl, flp, (struct fib_result *) arg->result); + if (err > 0) + err = -EAGAIN; +errout: + return err; } -/* writer func called from netlink -- rtnl_sem hold*/ -int inet_rtm_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +void fib_select_default(const struct flowi *flp, struct fib_result *res) { - struct rtattr **rta = arg; - struct rtmsg *rtm = NLMSG_DATA(nlh); - 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 || - (rtm->rtm_tos & ~IPTOS_TOS_MASK)) - return -EINVAL; - - if (rta[RTA_IIF-1] && RTA_PAYLOAD(rta[RTA_IIF-1]) > IFNAMSIZ) - return -EINVAL; - - table_id = rtm->rtm_table; - if (table_id == RT_TABLE_UNSPEC) { - struct fib_table *table; - if (rtm->rtm_type == RTN_UNICAST) { - if ((table = fib_empty_table()) == NULL) - return -ENOBUFS; - table_id = table->tb_id; - } + if (res->r && res->r->action == FR_ACT_TO_TBL && + FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) { + struct fib_table *tb; + if ((tb = fib_get_table(res->r->table)) != NULL) + tb->tb_select_default(tb, flp, res); } +} - new_r = kzalloc(sizeof(*new_r), GFP_KERNEL); - if (!new_r) - return -ENOMEM; - - if (rta[RTA_SRC-1]) - memcpy(&new_r->r_src, RTA_DATA(rta[RTA_SRC-1]), 4); - if (rta[RTA_DST-1]) - memcpy(&new_r->r_dst, RTA_DATA(rta[RTA_DST-1]), 4); - if (rta[RTA_GATEWAY-1]) - memcpy(&new_r->r_srcmap, RTA_DATA(rta[RTA_GATEWAY-1]), 4); - new_r->r_src_len = rtm->rtm_src_len; - new_r->r_dst_len = rtm->rtm_dst_len; - new_r->r_srcmask = inet_make_mask(rtm->rtm_src_len); - new_r->r_dstmask = inet_make_mask(rtm->rtm_dst_len); - new_r->r_tos = rtm->rtm_tos; -#ifdef CONFIG_IP_ROUTE_FWMARK - if (rta[RTA_PROTOINFO-1]) - memcpy(&new_r->r_fwmark, RTA_DATA(rta[RTA_PROTOINFO-1]), 4); -#endif - new_r->r_action = rtm->rtm_type; - new_r->r_flags = rtm->rtm_flags; - if (rta[RTA_PRIORITY-1]) - memcpy(&new_r->r_preference, RTA_DATA(rta[RTA_PRIORITY-1]), 4); - new_r->r_table = table_id; - if (rta[RTA_IIF-1]) { - struct net_device *dev; - rtattr_strlcpy(new_r->r_ifname, rta[RTA_IIF-1], IFNAMSIZ); - new_r->r_ifindex = -1; - dev = __dev_get_by_name(new_r->r_ifname); - if (dev) - new_r->r_ifindex = dev->ifindex; - } -#ifdef CONFIG_NET_CLS_ROUTE - 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); +static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) +{ + struct fib4_rule *r = (struct fib4_rule *) rule; + u32 daddr = fl->fl4_dst; + u32 saddr = fl->fl4_src; - if (!new_r->r_preference) { - 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; - } - } + if (((saddr ^ r->src) & r->srcmask) || + ((daddr ^ r->dst) & r->dstmask)) + return 0; - hlist_for_each_entry(r, node, &fib_rules, hlist) { - if (r->r_preference > new_r->r_preference) - break; - last = r; - } - atomic_inc(&new_r->r_clntref); + if (r->tos && (r->tos != fl->fl4_tos)) + return 0; - if (last) - hlist_add_after_rcu(&last->hlist, &new_r->hlist); - else - hlist_add_before_rcu(&new_r->hlist, &r->hlist); +#ifdef CONFIG_IP_ROUTE_FWMARK + if ((r->fwmark ^ fl->fl4_fwmark) & r->fwmask) + return 0; +#endif - rtmsg_rule(RTM_NEWRULE, new_r); - return 0; + return 1; } -#ifdef CONFIG_NET_CLS_ROUTE -u32 fib_rules_tclass(struct fib_result *res) +static struct fib_table *fib_empty_table(void) { - if (res->r) - return res->r->r_tclassid; - return 0; + u32 id; + + for (id = 1; id <= RT_TABLE_MAX; id++) + if (fib_get_table(id) == NULL) + return fib_new_table(id); + return NULL; } -#endif -/* callers should hold rtnl semaphore */ +static struct nla_policy fib4_rule_policy[FRA_MAX+1] __read_mostly = { + [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, + [FRA_PRIORITY] = { .type = NLA_U32 }, + [FRA_SRC] = { .type = NLA_U32 }, + [FRA_DST] = { .type = NLA_U32 }, + [FRA_FWMARK] = { .type = NLA_U32 }, + [FRA_FWMASK] = { .type = NLA_U32 }, + [FRA_FLOW] = { .type = NLA_U32 }, + [FRA_TABLE] = { .type = NLA_U32 }, +}; -static void fib_rules_detach(struct net_device *dev) +static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct nlmsghdr *nlh, struct fib_rule_hdr *frh, + struct nlattr **tb) { - struct hlist_node *node; - struct fib_rule *r; + int err = -EINVAL; + struct fib4_rule *rule4 = (struct fib4_rule *) rule; + + if (frh->src_len > 32 || frh->dst_len > 32 || + (frh->tos & ~IPTOS_TOS_MASK)) + goto errout; + + if (rule->table == RT_TABLE_UNSPEC) { + if (rule->action == FR_ACT_TO_TBL) { + struct fib_table *table; - hlist_for_each_entry(r, node, &fib_rules, hlist) { - if (r->r_ifindex == dev->ifindex) - r->r_ifindex = -1; + table = fib_empty_table(); + if (table == NULL) { + err = -ENOBUFS; + goto errout; + } + rule->table = table->tb_id; + } } -} -/* callers should hold rtnl semaphore */ + if (tb[FRA_SRC]) + rule4->src = nla_get_u32(tb[FRA_SRC]); -static void fib_rules_attach(struct net_device *dev) -{ - struct hlist_node *node; - struct fib_rule *r; + if (tb[FRA_DST]) + rule4->dst = nla_get_u32(tb[FRA_DST]); - 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; +#ifdef CONFIG_IP_ROUTE_FWMARK + if (tb[FRA_FWMARK]) { + rule4->fwmark = nla_get_u32(tb[FRA_FWMARK]); + if (rule4->fwmark) + /* compatibility: if the mark value is non-zero all bits + * are compared unless a mask is explicitly specified. + */ + rule4->fwmask = 0xFFFFFFFF; } + + if (tb[FRA_FWMASK]) + rule4->fwmask = nla_get_u32(tb[FRA_FWMASK]); +#endif + +#ifdef CONFIG_NET_CLS_ROUTE + if (tb[FRA_FLOW]) + rule4->tclassid = nla_get_u32(tb[FRA_FLOW]); +#endif + + rule4->src_len = frh->src_len; + rule4->srcmask = inet_make_mask(rule4->src_len); + rule4->dst_len = frh->dst_len; + rule4->dstmask = inet_make_mask(rule4->dst_len); + rule4->tos = frh->tos; + + err = 0; +errout: + return err; } -int fib_lookup(const struct flowi *flp, struct fib_result *res) +static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) { - int err; - struct fib_rule *r, *policy; - struct fib_table *tb; - struct hlist_node *node; + struct fib4_rule *rule4 = (struct fib4_rule *) rule; - u32 daddr = flp->fl4_dst; - u32 saddr = flp->fl4_src; + if (frh->src_len && (rule4->src_len != frh->src_len)) + return 0; -FRprintk("Lookup: %u.%u.%u.%u <- %u.%u.%u.%u ", - NIPQUAD(flp->fl4_dst), NIPQUAD(flp->fl4_src)); + if (frh->dst_len && (rule4->dst_len != frh->dst_len)) + return 0; - rcu_read_lock(); + if (frh->tos && (rule4->tos != frh->tos)) + return 0; - 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) || #ifdef CONFIG_IP_ROUTE_FWMARK - (r->r_fwmark && r->r_fwmark != flp->fl4_fwmark) || + if (tb[FRA_FWMARK] && (rule4->fwmark != nla_get_u32(tb[FRA_FWMARK]))) + return 0; + + if (tb[FRA_FWMASK] && (rule4->fwmask != nla_get_u32(tb[FRA_FWMASK]))) + return 0; #endif - (r->r_ifindex && r->r_ifindex != flp->iif)) - continue; - -FRprintk("tb %d r %d ", r->r_table, r->r_action); - switch (r->r_action) { - case RTN_UNICAST: - policy = r; - break; - case RTN_UNREACHABLE: - rcu_read_unlock(); - return -ENETUNREACH; - default: - case RTN_BLACKHOLE: - rcu_read_unlock(); - return -EINVAL; - case RTN_PROHIBIT: - rcu_read_unlock(); - return -EACCES; - } - if ((tb = fib_get_table(r->r_table)) == NULL) - continue; - err = tb->tb_lookup(tb, flp, res); - if (err == 0) { - res->r = policy; - if (policy) - atomic_inc(&policy->r_clntref); - rcu_read_unlock(); - return 0; - } - if (err < 0 && err != -EAGAIN) { - rcu_read_unlock(); - return err; - } - } -FRprintk("FAILURE\n"); - rcu_read_unlock(); - return -ENETUNREACH; -} +#ifdef CONFIG_NET_CLS_ROUTE + if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW]))) + return 0; +#endif -void fib_select_default(const struct flowi *flp, struct fib_result *res) -{ - if (res->r && res->r->r_action == RTN_UNICAST && - FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) { - struct fib_table *tb; - if ((tb = fib_get_table(res->r->r_table)) != NULL) - tb->tb_select_default(tb, flp, res); - } -} + if (tb[FRA_SRC] && (rule4->src != nla_get_u32(tb[FRA_SRC]))) + return 0; -static int fib_rules_event(struct notifier_block *this, unsigned long event, void *ptr) -{ - struct net_device *dev = ptr; + if (tb[FRA_DST] && (rule4->dst != nla_get_u32(tb[FRA_DST]))) + return 0; - if (event == NETDEV_UNREGISTER) - fib_rules_detach(dev); - else if (event == NETDEV_REGISTER) - fib_rules_attach(dev); - return NOTIFY_DONE; + return 1; } +static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct nlmsghdr *nlh, struct fib_rule_hdr *frh) +{ + struct fib4_rule *rule4 = (struct fib4_rule *) rule; -static struct notifier_block fib_rules_notifier = { - .notifier_call =fib_rules_event, -}; + frh->family = AF_INET; + frh->dst_len = rule4->dst_len; + frh->src_len = rule4->src_len; + frh->tos = rule4->tos; -static __inline__ int inet_fill_rule(struct sk_buff *skb, - struct fib_rule *r, - u32 pid, u32 seq, int event, - unsigned int flags) -{ - struct rtmsg *rtm; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags); - rtm = NLMSG_DATA(nlh); - rtm->rtm_family = AF_INET; - rtm->rtm_dst_len = r->r_dst_len; - rtm->rtm_src_len = r->r_src_len; - rtm->rtm_tos = r->r_tos; #ifdef CONFIG_IP_ROUTE_FWMARK - if (r->r_fwmark) - RTA_PUT(skb, RTA_PROTOINFO, 4, &r->r_fwmark); + if (rule4->fwmark) + NLA_PUT_U32(skb, FRA_FWMARK, rule4->fwmark); + + if (rule4->fwmask || rule4->fwmark) + NLA_PUT_U32(skb, FRA_FWMASK, rule4->fwmask); #endif - rtm->rtm_table = r->r_table; - rtm->rtm_protocol = 0; - rtm->rtm_scope = 0; - rtm->rtm_type = r->r_action; - rtm->rtm_flags = r->r_flags; - - if (r->r_dst_len) - RTA_PUT(skb, RTA_DST, 4, &r->r_dst); - if (r->r_src_len) - RTA_PUT(skb, RTA_SRC, 4, &r->r_src); - if (r->r_ifname[0]) - RTA_PUT(skb, RTA_IIF, IFNAMSIZ, &r->r_ifname); - if (r->r_preference) - RTA_PUT(skb, RTA_PRIORITY, 4, &r->r_preference); - if (r->r_srcmap) - RTA_PUT(skb, RTA_GATEWAY, 4, &r->r_srcmap); + + if (rule4->dst_len) + NLA_PUT_U32(skb, FRA_DST, rule4->dst); + + if (rule4->src_len) + NLA_PUT_U32(skb, FRA_SRC, rule4->src); + #ifdef CONFIG_NET_CLS_ROUTE - if (r->r_tclassid) - RTA_PUT(skb, RTA_FLOW, 4, &r->r_tclassid); + if (rule4->tclassid) + NLA_PUT_U32(skb, FRA_FLOW, rule4->tclassid); #endif - nlh->nlmsg_len = skb->tail - b; - return skb->len; + return 0; -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; +nla_put_failure: + return -ENOBUFS; } -/* callers should hold rtnl semaphore */ - -static void rtmsg_rule(int event, struct fib_rule *r) +int fib4_rules_dump(struct sk_buff *skb, struct netlink_callback *cb) { - int size = NLMSG_SPACE(sizeof(struct rtmsg) + 128); - struct sk_buff *skb = alloc_skb(size, GFP_KERNEL); - - if (!skb) - netlink_set_err(rtnl, 0, RTNLGRP_IPV4_RULE, ENOBUFS); - else if (inet_fill_rule(skb, r, 0, 0, event, 0) < 0) { - kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV4_RULE, EINVAL); - } else { - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV4_RULE, GFP_KERNEL); - } + return fib_rules_dump(skb, cb, AF_INET); } -int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb) +static u32 fib4_rule_default_pref(void) { - 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) { - if (idx < s_idx) - goto next; - if (inet_fill_rule(skb, r, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_NEWRULE, NLM_F_MULTI) < 0) - break; -next: - idx++; + struct list_head *pos; + struct fib_rule *rule; + + if (!list_empty(&fib4_rules)) { + pos = fib4_rules.next; + if (pos->next != &fib4_rules) { + rule = list_entry(pos->next, struct fib_rule, list); + if (rule->pref) + return rule->pref - 1; + } } - rcu_read_unlock(); - cb->args[0] = idx; - return skb->len; + return 0; } -void __init fib_rules_init(void) +static struct fib_rules_ops fib4_rules_ops = { + .family = AF_INET, + .rule_size = sizeof(struct fib4_rule), + .action = fib4_rule_action, + .match = fib4_rule_match, + .configure = fib4_rule_configure, + .compare = fib4_rule_compare, + .fill = fib4_rule_fill, + .default_pref = fib4_rule_default_pref, + .nlgroup = RTNLGRP_IPV4_RULE, + .policy = fib4_rule_policy, + .rules_list = &fib4_rules, + .owner = THIS_MODULE, +}; + +void __init fib4_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); + list_add_tail(&local_rule.common.list, &fib4_rules); + list_add_tail(&main_rule.common.list, &fib4_rules); + list_add_tail(&default_rule.common.list, &fib4_rules); + + fib_rules_register(&fib4_rules_ops); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 51738000f3d..2ead09543f6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -33,7 +33,6 @@ #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/skbuff.h> -#include <linux/netlink.h> #include <linux/init.h> #include <net/arp.h> @@ -44,12 +43,14 @@ #include <net/sock.h> #include <net/ip_fib.h> #include <net/ip_mp_alg.h> +#include <net/netlink.h> +#include <net/nexthop.h> #include "fib_lookup.h" #define FSprintk(a...) -static DEFINE_RWLOCK(fib_info_lock); +static DEFINE_SPINLOCK(fib_info_lock); static struct hlist_head *fib_info_hash; static struct hlist_head *fib_info_laddrhash; static unsigned int fib_hash_size; @@ -159,7 +160,7 @@ void free_fib_info(struct fib_info *fi) void fib_release_info(struct fib_info *fi) { - write_lock_bh(&fib_info_lock); + spin_lock_bh(&fib_info_lock); if (fi && --fi->fib_treeref == 0) { hlist_del(&fi->fib_hash); if (fi->fib_prefsrc) @@ -172,7 +173,7 @@ void fib_release_info(struct fib_info *fi) fi->fib_dead = 1; fib_info_put(fi); } - write_unlock_bh(&fib_info_lock); + spin_unlock_bh(&fib_info_lock); } static __inline__ int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) @@ -254,7 +255,7 @@ int ip_fib_check_default(u32 gw, struct net_device *dev) struct fib_nh *nh; unsigned int hash; - read_lock(&fib_info_lock); + spin_lock(&fib_info_lock); hash = fib_devindex_hashfn(dev->ifindex); head = &fib_info_devhash[hash]; @@ -262,41 +263,41 @@ int ip_fib_check_default(u32 gw, struct net_device *dev) if (nh->nh_dev == dev && nh->nh_gw == gw && !(nh->nh_flags&RTNH_F_DEAD)) { - read_unlock(&fib_info_lock); + spin_unlock(&fib_info_lock); return 0; } } - read_unlock(&fib_info_lock); + spin_unlock(&fib_info_lock); return -1; } void rtmsg_fib(int event, u32 key, struct fib_alias *fa, - int z, int tb_id, - struct nlmsghdr *n, struct netlink_skb_parms *req) + int dst_len, u32 tb_id, struct nl_info *info) { struct sk_buff *skb; - u32 pid = req ? req->pid : n->nlmsg_pid; - int size = NLMSG_SPACE(sizeof(struct rtmsg)+256); - - skb = alloc_skb(size, GFP_KERNEL); - if (!skb) - return; - - if (fib_dump_info(skb, pid, n->nlmsg_seq, event, tb_id, - fa->fa_type, fa->fa_scope, &key, z, - fa->fa_tos, - fa->fa_info, 0) < 0) { + int payload = sizeof(struct rtmsg) + 256; + u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; + int err = -ENOBUFS; + + skb = nlmsg_new(nlmsg_total_size(payload), GFP_KERNEL); + if (skb == NULL) + goto errout; + + err = fib_dump_info(skb, info->pid, seq, event, tb_id, + fa->fa_type, fa->fa_scope, key, dst_len, + fa->fa_tos, fa->fa_info, 0); + if (err < 0) { kfree_skb(skb); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV4_ROUTE; - if (n->nlmsg_flags&NLM_F_ECHO) - atomic_inc(&skb->users); - netlink_broadcast(rtnl, skb, pid, RTNLGRP_IPV4_ROUTE, GFP_KERNEL); - if (n->nlmsg_flags&NLM_F_ECHO) - netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT); + + err = rtnl_notify(skb, info->pid, RTNLGRP_IPV4_ROUTE, + info->nlh, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_IPV4_ROUTE, err); } /* Return the first fib alias matching TOS with @@ -342,102 +343,100 @@ int fib_detect_death(struct fib_info *fi, int order, #ifdef CONFIG_IP_ROUTE_MULTIPATH -static u32 fib_get_attr32(struct rtattr *attr, int attrlen, int type) -{ - while (RTA_OK(attr,attrlen)) { - if (attr->rta_type == type) - return *(u32*)RTA_DATA(attr); - attr = RTA_NEXT(attr, attrlen); - } - return 0; -} - -static int -fib_count_nexthops(struct rtattr *rta) +static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) { int nhs = 0; - struct rtnexthop *nhp = RTA_DATA(rta); - int nhlen = RTA_PAYLOAD(rta); - while (nhlen >= (int)sizeof(struct rtnexthop)) { - if ((nhlen -= nhp->rtnh_len) < 0) - return 0; + while (rtnh_ok(rtnh, remaining)) { nhs++; - nhp = RTNH_NEXT(nhp); - }; - return nhs; + rtnh = rtnh_next(rtnh, &remaining); + } + + /* leftover implies invalid nexthop configuration, discard it */ + return remaining > 0 ? 0 : nhs; } -static int -fib_get_nhs(struct fib_info *fi, const struct rtattr *rta, const struct rtmsg *r) +static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, + int remaining, struct fib_config *cfg) { - struct rtnexthop *nhp = RTA_DATA(rta); - int nhlen = RTA_PAYLOAD(rta); - change_nexthops(fi) { - int attrlen = nhlen - sizeof(struct rtnexthop); - if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0) + int attrlen; + + if (!rtnh_ok(rtnh, remaining)) return -EINVAL; - nh->nh_flags = (r->rtm_flags&~0xFF) | nhp->rtnh_flags; - nh->nh_oif = nhp->rtnh_ifindex; - nh->nh_weight = nhp->rtnh_hops + 1; - if (attrlen) { - nh->nh_gw = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_GATEWAY); + + nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; + nh->nh_oif = rtnh->rtnh_ifindex; + nh->nh_weight = rtnh->rtnh_hops + 1; + + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + nh->nh_gw = nla ? nla_get_u32(nla) : 0; #ifdef CONFIG_NET_CLS_ROUTE - nh->nh_tclassid = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_FLOW); + nla = nla_find(attrs, attrlen, RTA_FLOW); + nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; #endif } - nhp = RTNH_NEXT(nhp); + + rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); + return 0; } #endif -int fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct kern_rta *rta, - struct fib_info *fi) +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - struct rtnexthop *nhp; - int nhlen; + struct rtnexthop *rtnh; + int remaining; #endif - if (rta->rta_priority && - *rta->rta_priority != fi->fib_priority) + if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority) return 1; - if (rta->rta_oif || rta->rta_gw) { - if ((!rta->rta_oif || *rta->rta_oif == fi->fib_nh->nh_oif) && - (!rta->rta_gw || memcmp(rta->rta_gw, &fi->fib_nh->nh_gw, 4) == 0)) + if (cfg->fc_oif || cfg->fc_gw) { + if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && + (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) return 0; return 1; } #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (rta->rta_mp == NULL) + if (cfg->fc_mp == NULL) return 0; - nhp = RTA_DATA(rta->rta_mp); - nhlen = RTA_PAYLOAD(rta->rta_mp); + + rtnh = cfg->fc_mp; + remaining = cfg->fc_mp_len; for_nexthops(fi) { - int attrlen = nhlen - sizeof(struct rtnexthop); - u32 gw; + int attrlen; - if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0) + if (!rtnh_ok(rtnh, remaining)) return -EINVAL; - if (nhp->rtnh_ifindex && nhp->rtnh_ifindex != nh->nh_oif) + + if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif) return 1; - if (attrlen) { - gw = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_GATEWAY); - if (gw && gw != nh->nh_gw) + + attrlen = rtnh_attrlen(rtnh); + if (attrlen < 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + if (nla && nla_get_u32(nla) != nh->nh_gw) return 1; #ifdef CONFIG_NET_CLS_ROUTE - gw = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_FLOW); - if (gw && gw != nh->nh_tclassid) + nla = nla_find(attrs, attrlen, RTA_FLOW); + if (nla && nla_get_u32(nla) != nh->nh_tclassid) return 1; #endif } - nhp = RTNH_NEXT(nhp); + + rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); #endif return 0; @@ -488,7 +487,8 @@ int fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct kern_rta *rta, |-> {local prefix} (terminal node) */ -static int fib_check_nh(const struct rtmsg *r, struct fib_info *fi, struct fib_nh *nh) +static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, + struct fib_nh *nh) { int err; @@ -502,7 +502,7 @@ static int fib_check_nh(const struct rtmsg *r, struct fib_info *fi, struct fib_n if (nh->nh_flags&RTNH_F_ONLINK) { struct net_device *dev; - if (r->rtm_scope >= RT_SCOPE_LINK) + if (cfg->fc_scope >= RT_SCOPE_LINK) return -EINVAL; if (inet_addr_type(nh->nh_gw) != RTN_UNICAST) return -EINVAL; @@ -516,10 +516,15 @@ static int fib_check_nh(const struct rtmsg *r, struct fib_info *fi, struct fib_n return 0; } { - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = nh->nh_gw, - .scope = r->rtm_scope + 1 } }, - .oif = nh->nh_oif }; + struct flowi fl = { + .nl_u = { + .ip4_u = { + .daddr = nh->nh_gw, + .scope = cfg->fc_scope + 1, + }, + }, + .oif = nh->nh_oif, + }; /* It is not necessary, but requires a bit of thinking */ if (fl.fl4_scope < RT_SCOPE_LINK) @@ -598,7 +603,7 @@ static void fib_hash_move(struct hlist_head *new_info_hash, unsigned int old_size = fib_hash_size; unsigned int i, bytes; - write_lock_bh(&fib_info_lock); + spin_lock_bh(&fib_info_lock); old_info_hash = fib_info_hash; old_laddrhash = fib_info_laddrhash; fib_hash_size = new_size; @@ -639,46 +644,35 @@ static void fib_hash_move(struct hlist_head *new_info_hash, } fib_info_laddrhash = new_laddrhash; - write_unlock_bh(&fib_info_lock); + spin_unlock_bh(&fib_info_lock); bytes = old_size * sizeof(struct hlist_head *); fib_hash_free(old_info_hash, bytes); fib_hash_free(old_laddrhash, bytes); } -struct fib_info * -fib_create_info(const struct rtmsg *r, struct kern_rta *rta, - const struct nlmsghdr *nlh, int *errp) +struct fib_info *fib_create_info(struct fib_config *cfg) { int err; struct fib_info *fi = NULL; struct fib_info *ofi; -#ifdef CONFIG_IP_ROUTE_MULTIPATH int nhs = 1; -#else - const int nhs = 1; -#endif -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - u32 mp_alg = IP_MP_ALG_NONE; -#endif /* Fast check to catch the most weird cases */ - if (fib_props[r->rtm_type].scope > r->rtm_scope) + if (fib_props[cfg->fc_type].scope > cfg->fc_scope) goto err_inval; #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (rta->rta_mp) { - nhs = fib_count_nexthops(rta->rta_mp); + if (cfg->fc_mp) { + nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); if (nhs == 0) goto err_inval; } #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - if (rta->rta_mp_alg) { - mp_alg = *rta->rta_mp_alg; - - if (mp_alg < IP_MP_ALG_NONE || - mp_alg > IP_MP_ALG_MAX) + if (cfg->fc_mp_alg) { + if (cfg->fc_mp_alg < IP_MP_ALG_NONE || + cfg->fc_mp_alg > IP_MP_ALG_MAX) goto err_inval; } #endif @@ -714,43 +708,42 @@ fib_create_info(const struct rtmsg *r, struct kern_rta *rta, goto failure; fib_info_cnt++; - fi->fib_protocol = r->rtm_protocol; + fi->fib_protocol = cfg->fc_protocol; + fi->fib_flags = cfg->fc_flags; + fi->fib_priority = cfg->fc_priority; + fi->fib_prefsrc = cfg->fc_prefsrc; fi->fib_nhs = nhs; change_nexthops(fi) { nh->nh_parent = fi; } endfor_nexthops(fi) - fi->fib_flags = r->rtm_flags; - if (rta->rta_priority) - fi->fib_priority = *rta->rta_priority; - if (rta->rta_mx) { - int attrlen = RTA_PAYLOAD(rta->rta_mx); - struct rtattr *attr = RTA_DATA(rta->rta_mx); - - while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; - if (flavor) { - if (flavor > RTAX_MAX) + if (cfg->fc_mx) { + struct nlattr *nla; + int remaining; + + nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { + int type = nla->nla_type; + + if (type) { + if (type > RTAX_MAX) goto err_inval; - fi->fib_metrics[flavor-1] = *(unsigned*)RTA_DATA(attr); + fi->fib_metrics[type - 1] = nla_get_u32(nla); } - attr = RTA_NEXT(attr, attrlen); } } - if (rta->rta_prefsrc) - memcpy(&fi->fib_prefsrc, rta->rta_prefsrc, 4); - if (rta->rta_mp) { + if (cfg->fc_mp) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - if ((err = fib_get_nhs(fi, rta->rta_mp, r)) != 0) + err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg); + if (err != 0) goto failure; - if (rta->rta_oif && fi->fib_nh->nh_oif != *rta->rta_oif) + if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) goto err_inval; - if (rta->rta_gw && memcmp(&fi->fib_nh->nh_gw, rta->rta_gw, 4)) + if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) goto err_inval; #ifdef CONFIG_NET_CLS_ROUTE - if (rta->rta_flow && memcmp(&fi->fib_nh->nh_tclassid, rta->rta_flow, 4)) + if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) goto err_inval; #endif #else @@ -758,34 +751,32 @@ fib_create_info(const struct rtmsg *r, struct kern_rta *rta, #endif } else { struct fib_nh *nh = fi->fib_nh; - if (rta->rta_oif) - nh->nh_oif = *rta->rta_oif; - if (rta->rta_gw) - memcpy(&nh->nh_gw, rta->rta_gw, 4); + + nh->nh_oif = cfg->fc_oif; + nh->nh_gw = cfg->fc_gw; + nh->nh_flags = cfg->fc_flags; #ifdef CONFIG_NET_CLS_ROUTE - if (rta->rta_flow) - memcpy(&nh->nh_tclassid, rta->rta_flow, 4); + nh->nh_tclassid = cfg->fc_flow; #endif - nh->nh_flags = r->rtm_flags; #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->nh_weight = 1; #endif } #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - fi->fib_mp_alg = mp_alg; + fi->fib_mp_alg = cfg->fc_mp_alg; #endif - if (fib_props[r->rtm_type].error) { - if (rta->rta_gw || rta->rta_oif || rta->rta_mp) + if (fib_props[cfg->fc_type].error) { + if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) goto err_inval; goto link_it; } - if (r->rtm_scope > RT_SCOPE_HOST) + if (cfg->fc_scope > RT_SCOPE_HOST) goto err_inval; - if (r->rtm_scope == RT_SCOPE_HOST) { + if (cfg->fc_scope == RT_SCOPE_HOST) { struct fib_nh *nh = fi->fib_nh; /* Local address is added. */ @@ -798,14 +789,14 @@ fib_create_info(const struct rtmsg *r, struct kern_rta *rta, goto failure; } else { change_nexthops(fi) { - if ((err = fib_check_nh(r, fi, nh)) != 0) + if ((err = fib_check_nh(cfg, fi, nh)) != 0) goto failure; } endfor_nexthops(fi) } if (fi->fib_prefsrc) { - if (r->rtm_type != RTN_LOCAL || rta->rta_dst == NULL || - memcmp(&fi->fib_prefsrc, rta->rta_dst, 4)) + if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || + fi->fib_prefsrc != cfg->fc_dst) if (inet_addr_type(fi->fib_prefsrc) != RTN_LOCAL) goto err_inval; } @@ -820,7 +811,7 @@ link_it: fi->fib_treeref++; atomic_inc(&fi->fib_clntref); - write_lock_bh(&fib_info_lock); + spin_lock_bh(&fib_info_lock); hlist_add_head(&fi->fib_hash, &fib_info_hash[fib_info_hashfn(fi)]); if (fi->fib_prefsrc) { @@ -839,19 +830,19 @@ link_it: head = &fib_info_devhash[hash]; hlist_add_head(&nh->nh_hash, head); } endfor_nexthops(fi) - write_unlock_bh(&fib_info_lock); + spin_unlock_bh(&fib_info_lock); return fi; err_inval: err = -EINVAL; failure: - *errp = err; if (fi) { fi->fib_dead = 1; free_fib_info(fi); } - return NULL; + + return ERR_PTR(err); } /* Note! fib_semantic_match intentionally uses RCU list functions. */ @@ -937,224 +928,89 @@ u32 __fib_res_prefsrc(struct fib_result *res) return inet_select_addr(FIB_RES_DEV(*res), FIB_RES_GW(*res), res->scope); } -int -fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u8 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos, - struct fib_info *fi, unsigned int flags) +int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, + u32 tb_id, u8 type, u8 scope, u32 dst, int dst_len, u8 tos, + struct fib_info *fi, unsigned int flags) { + struct nlmsghdr *nlh; struct rtmsg *rtm; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags); - rtm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags); + if (nlh == NULL) + return -ENOBUFS; + + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET; rtm->rtm_dst_len = dst_len; rtm->rtm_src_len = 0; rtm->rtm_tos = tos; rtm->rtm_table = tb_id; + NLA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = scope; - if (rtm->rtm_dst_len) - RTA_PUT(skb, RTA_DST, 4, dst); rtm->rtm_protocol = fi->fib_protocol; + + if (rtm->rtm_dst_len) + NLA_PUT_U32(skb, RTA_DST, dst); + if (fi->fib_priority) - RTA_PUT(skb, RTA_PRIORITY, 4, &fi->fib_priority); + NLA_PUT_U32(skb, RTA_PRIORITY, fi->fib_priority); + if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) - goto rtattr_failure; + goto nla_put_failure; + if (fi->fib_prefsrc) - RTA_PUT(skb, RTA_PREFSRC, 4, &fi->fib_prefsrc); + NLA_PUT_U32(skb, RTA_PREFSRC, fi->fib_prefsrc); + if (fi->fib_nhs == 1) { if (fi->fib_nh->nh_gw) - RTA_PUT(skb, RTA_GATEWAY, 4, &fi->fib_nh->nh_gw); + NLA_PUT_U32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw); + if (fi->fib_nh->nh_oif) - RTA_PUT(skb, RTA_OIF, sizeof(int), &fi->fib_nh->nh_oif); + NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif); #ifdef CONFIG_NET_CLS_ROUTE if (fi->fib_nh[0].nh_tclassid) - RTA_PUT(skb, RTA_FLOW, 4, &fi->fib_nh[0].nh_tclassid); + NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid); #endif } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { - struct rtnexthop *nhp; - struct rtattr *mp_head; - if (skb_tailroom(skb) <= RTA_SPACE(0)) - goto rtattr_failure; - mp_head = (struct rtattr*)skb_put(skb, RTA_SPACE(0)); + struct rtnexthop *rtnh; + struct nlattr *mp; + + mp = nla_nest_start(skb, RTA_MULTIPATH); + if (mp == NULL) + goto nla_put_failure; for_nexthops(fi) { - if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) - goto rtattr_failure; - nhp = (struct rtnexthop*)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); - nhp->rtnh_flags = nh->nh_flags & 0xFF; - nhp->rtnh_hops = nh->nh_weight-1; - nhp->rtnh_ifindex = nh->nh_oif; + rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); + if (rtnh == NULL) + goto nla_put_failure; + + rtnh->rtnh_flags = nh->nh_flags & 0xFF; + rtnh->rtnh_hops = nh->nh_weight - 1; + rtnh->rtnh_ifindex = nh->nh_oif; + if (nh->nh_gw) - RTA_PUT(skb, RTA_GATEWAY, 4, &nh->nh_gw); + NLA_PUT_U32(skb, RTA_GATEWAY, nh->nh_gw); #ifdef CONFIG_NET_CLS_ROUTE if (nh->nh_tclassid) - RTA_PUT(skb, RTA_FLOW, 4, &nh->nh_tclassid); + NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid); #endif - nhp->rtnh_len = skb->tail - (unsigned char*)nhp; + /* length of rtnetlink header + attributes */ + rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); - mp_head->rta_type = RTA_MULTIPATH; - mp_head->rta_len = skb->tail - (u8*)mp_head; - } -#endif - nlh->nlmsg_len = skb->tail - b; - return skb->len; - -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; -} - -#ifndef CONFIG_IP_NOSIOCRT - -int -fib_convert_rtentry(int cmd, struct nlmsghdr *nl, struct rtmsg *rtm, - struct kern_rta *rta, struct rtentry *r) -{ - int plen; - u32 *ptr; - - memset(rtm, 0, sizeof(*rtm)); - memset(rta, 0, sizeof(*rta)); - - if (r->rt_dst.sa_family != AF_INET) - return -EAFNOSUPPORT; - - /* Check mask for validity: - a) it must be contiguous. - b) destination must have all host bits clear. - c) if application forgot to set correct family (AF_INET), - reject request unless it is absolutely clear i.e. - both family and mask are zero. - */ - plen = 32; - ptr = &((struct sockaddr_in*)&r->rt_dst)->sin_addr.s_addr; - if (!(r->rt_flags&RTF_HOST)) { - u32 mask = ((struct sockaddr_in*)&r->rt_genmask)->sin_addr.s_addr; - if (r->rt_genmask.sa_family != AF_INET) { - if (mask || r->rt_genmask.sa_family) - return -EAFNOSUPPORT; - } - if (bad_mask(mask, *ptr)) - return -EINVAL; - plen = inet_mask_len(mask); - } - - nl->nlmsg_flags = NLM_F_REQUEST; - nl->nlmsg_pid = 0; - nl->nlmsg_seq = 0; - nl->nlmsg_len = NLMSG_LENGTH(sizeof(*rtm)); - if (cmd == SIOCDELRT) { - nl->nlmsg_type = RTM_DELROUTE; - nl->nlmsg_flags = 0; - } else { - nl->nlmsg_type = RTM_NEWROUTE; - nl->nlmsg_flags = NLM_F_REQUEST|NLM_F_CREATE; - rtm->rtm_protocol = RTPROT_BOOT; - } - - rtm->rtm_dst_len = plen; - rta->rta_dst = ptr; - - if (r->rt_metric) { - *(u32*)&r->rt_pad3 = r->rt_metric - 1; - rta->rta_priority = (u32*)&r->rt_pad3; - } - if (r->rt_flags&RTF_REJECT) { - rtm->rtm_scope = RT_SCOPE_HOST; - rtm->rtm_type = RTN_UNREACHABLE; - return 0; - } - rtm->rtm_scope = RT_SCOPE_NOWHERE; - rtm->rtm_type = RTN_UNICAST; - - if (r->rt_dev) { - char *colon; - struct net_device *dev; - char devname[IFNAMSIZ]; - - if (copy_from_user(devname, r->rt_dev, IFNAMSIZ-1)) - return -EFAULT; - devname[IFNAMSIZ-1] = 0; - colon = strchr(devname, ':'); - if (colon) - *colon = 0; - dev = __dev_get_by_name(devname); - if (!dev) - return -ENODEV; - rta->rta_oif = &dev->ifindex; - if (colon) { - struct in_ifaddr *ifa; - struct in_device *in_dev = __in_dev_get_rtnl(dev); - if (!in_dev) - return -ENODEV; - *colon = ':'; - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) - if (strcmp(ifa->ifa_label, devname) == 0) - break; - if (ifa == NULL) - return -ENODEV; - rta->rta_prefsrc = &ifa->ifa_local; - } - } - ptr = &((struct sockaddr_in*)&r->rt_gateway)->sin_addr.s_addr; - if (r->rt_gateway.sa_family == AF_INET && *ptr) { - rta->rta_gw = ptr; - if (r->rt_flags&RTF_GATEWAY && inet_addr_type(*ptr) == RTN_UNICAST) - rtm->rtm_scope = RT_SCOPE_UNIVERSE; + nla_nest_end(skb, mp); } +#endif + return nlmsg_end(skb, nlh); - if (cmd == SIOCDELRT) - return 0; - - if (r->rt_flags&RTF_GATEWAY && rta->rta_gw == NULL) - return -EINVAL; - - if (rtm->rtm_scope == RT_SCOPE_NOWHERE) - rtm->rtm_scope = RT_SCOPE_LINK; - - if (r->rt_flags&(RTF_MTU|RTF_WINDOW|RTF_IRTT)) { - struct rtattr *rec; - struct rtattr *mx = kmalloc(RTA_LENGTH(3*RTA_LENGTH(4)), GFP_KERNEL); - if (mx == NULL) - return -ENOMEM; - rta->rta_mx = mx; - mx->rta_type = RTA_METRICS; - mx->rta_len = RTA_LENGTH(0); - if (r->rt_flags&RTF_MTU) { - rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len)); - rec->rta_type = RTAX_ADVMSS; - rec->rta_len = RTA_LENGTH(4); - mx->rta_len += RTA_LENGTH(4); - *(u32*)RTA_DATA(rec) = r->rt_mtu - 40; - } - if (r->rt_flags&RTF_WINDOW) { - rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len)); - rec->rta_type = RTAX_WINDOW; - rec->rta_len = RTA_LENGTH(4); - mx->rta_len += RTA_LENGTH(4); - *(u32*)RTA_DATA(rec) = r->rt_window; - } - if (r->rt_flags&RTF_IRTT) { - rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len)); - rec->rta_type = RTAX_RTT; - rec->rta_len = RTA_LENGTH(4); - mx->rta_len += RTA_LENGTH(4); - *(u32*)RTA_DATA(rec) = r->rt_irtt<<3; - } - } - return 0; +nla_put_failure: + return nlmsg_cancel(skb, nlh); } -#endif - /* Update FIB if: - local address disappeared -> we must delete all the entries diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 01801c0f885..9c3ff6ba6e2 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1124,17 +1124,14 @@ err: return fa_head; } -static int -fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, - struct nlmsghdr *nlhdr, struct netlink_skb_parms *req) +static int fn_trie_insert(struct fib_table *tb, struct fib_config *cfg) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *new_fa; struct list_head *fa_head = NULL; struct fib_info *fi; - int plen = r->rtm_dst_len; - int type = r->rtm_type; - u8 tos = r->rtm_tos; + int plen = cfg->fc_dst_len; + u8 tos = cfg->fc_tos; u32 key, mask; int err; struct leaf *l; @@ -1142,13 +1139,9 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, if (plen > 32) return -EINVAL; - key = 0; - if (rta->rta_dst) - memcpy(&key, rta->rta_dst, 4); - - key = ntohl(key); + key = ntohl(cfg->fc_dst); - pr_debug("Insert table=%d %08x/%d\n", tb->tb_id, key, plen); + pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); mask = ntohl(inet_make_mask(plen)); @@ -1157,10 +1150,11 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, key = key & mask; - fi = fib_create_info(r, rta, nlhdr, &err); - - if (!fi) + fi = fib_create_info(cfg); + if (IS_ERR(fi)) { + err = PTR_ERR(fi); goto err; + } l = fib_find_node(t, key); fa = NULL; @@ -1185,10 +1179,10 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, struct fib_alias *fa_orig; err = -EEXIST; - if (nlhdr->nlmsg_flags & NLM_F_EXCL) + if (cfg->fc_nlflags & NLM_F_EXCL) goto out; - if (nlhdr->nlmsg_flags & NLM_F_REPLACE) { + if (cfg->fc_nlflags & NLM_F_REPLACE) { struct fib_info *fi_drop; u8 state; @@ -1200,8 +1194,8 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, fi_drop = fa->fa_info; new_fa->fa_tos = fa->fa_tos; new_fa->fa_info = fi; - new_fa->fa_type = type; - new_fa->fa_scope = r->rtm_scope; + new_fa->fa_type = cfg->fc_type; + new_fa->fa_scope = cfg->fc_scope; state = fa->fa_state; new_fa->fa_state &= ~FA_S_ACCESSED; @@ -1224,17 +1218,17 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, break; if (fa->fa_info->fib_priority != fi->fib_priority) break; - if (fa->fa_type == type && - fa->fa_scope == r->rtm_scope && + if (fa->fa_type == cfg->fc_type && + fa->fa_scope == cfg->fc_scope && fa->fa_info == fi) { goto out; } } - if (!(nlhdr->nlmsg_flags & NLM_F_APPEND)) + if (!(cfg->fc_nlflags & NLM_F_APPEND)) fa = fa_orig; } err = -ENOENT; - if (!(nlhdr->nlmsg_flags & NLM_F_CREATE)) + if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; err = -ENOBUFS; @@ -1244,8 +1238,8 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, new_fa->fa_info = fi; new_fa->fa_tos = tos; - new_fa->fa_type = type; - new_fa->fa_scope = r->rtm_scope; + new_fa->fa_type = cfg->fc_type; + new_fa->fa_scope = cfg->fc_scope; new_fa->fa_state = 0; /* * Insert new entry to the list. @@ -1262,7 +1256,8 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, (fa ? &fa->fa_list : fa_head)); rt_cache_flush(-1); - rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, nlhdr, req); + rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, + &cfg->fc_nlinfo); succeeded: return 0; @@ -1548,28 +1543,21 @@ static int trie_leaf_remove(struct trie *t, t_key key) return 1; } -static int -fn_trie_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, - struct nlmsghdr *nlhdr, struct netlink_skb_parms *req) +static int fn_trie_delete(struct fib_table *tb, struct fib_config *cfg) { struct trie *t = (struct trie *) tb->tb_data; u32 key, mask; - int plen = r->rtm_dst_len; - u8 tos = r->rtm_tos; + int plen = cfg->fc_dst_len; + u8 tos = cfg->fc_tos; struct fib_alias *fa, *fa_to_delete; struct list_head *fa_head; struct leaf *l; struct leaf_info *li; - if (plen > 32) return -EINVAL; - key = 0; - if (rta->rta_dst) - memcpy(&key, rta->rta_dst, 4); - - key = ntohl(key); + key = ntohl(cfg->fc_dst); mask = ntohl(inet_make_mask(plen)); if (key & ~mask) @@ -1598,13 +1586,12 @@ fn_trie_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, if (fa->fa_tos != tos) break; - if ((!r->rtm_type || - fa->fa_type == r->rtm_type) && - (r->rtm_scope == RT_SCOPE_NOWHERE || - fa->fa_scope == r->rtm_scope) && - (!r->rtm_protocol || - fi->fib_protocol == r->rtm_protocol) && - fib_nh_match(r, nlhdr, rta, fi) == 0) { + if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && + (cfg->fc_scope == RT_SCOPE_NOWHERE || + fa->fa_scope == cfg->fc_scope) && + (!cfg->fc_protocol || + fi->fib_protocol == cfg->fc_protocol) && + fib_nh_match(cfg, fi) == 0) { fa_to_delete = fa; break; } @@ -1614,7 +1601,8 @@ fn_trie_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, return -ESRCH; fa = fa_to_delete; - rtmsg_fib(RTM_DELROUTE, htonl(key), fa, plen, tb->tb_id, nlhdr, req); + rtmsg_fib(RTM_DELROUTE, htonl(key), fa, plen, tb->tb_id, + &cfg->fc_nlinfo); l = fib_find_node(t, key); li = find_leaf_info(l, plen); @@ -1848,7 +1836,7 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, struct fi u32 xkey = htonl(key); - s_i = cb->args[3]; + s_i = cb->args[4]; i = 0; /* rcu_read_lock is hold by caller */ @@ -1866,16 +1854,16 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, struct fi tb->tb_id, fa->fa_type, fa->fa_scope, - &xkey, + xkey, plen, fa->fa_tos, fa->fa_info, 0) < 0) { - cb->args[3] = i; + cb->args[4] = i; return -1; } i++; } - cb->args[3] = i; + cb->args[4] = i; return skb->len; } @@ -1886,14 +1874,14 @@ static int fn_trie_dump_plen(struct trie *t, int plen, struct fib_table *tb, str struct list_head *fa_head; struct leaf *l = NULL; - s_h = cb->args[2]; + s_h = cb->args[3]; for (h = 0; (l = nextleaf(t, l)) != NULL; h++) { if (h < s_h) continue; if (h > s_h) - memset(&cb->args[3], 0, - sizeof(cb->args) - 3*sizeof(cb->args[0])); + memset(&cb->args[4], 0, + sizeof(cb->args) - 4*sizeof(cb->args[0])); fa_head = get_fa_head(l, plen); @@ -1904,11 +1892,11 @@ static int fn_trie_dump_plen(struct trie *t, int plen, struct fib_table *tb, str continue; if (fn_trie_dump_fa(l->key, plen, fa_head, tb, skb, cb)<0) { - cb->args[2] = h; + cb->args[3] = h; return -1; } } - cb->args[2] = h; + cb->args[3] = h; return skb->len; } @@ -1917,23 +1905,23 @@ static int fn_trie_dump(struct fib_table *tb, struct sk_buff *skb, struct netlin int m, s_m; struct trie *t = (struct trie *) tb->tb_data; - s_m = cb->args[1]; + s_m = cb->args[2]; rcu_read_lock(); for (m = 0; m <= 32; m++) { if (m < s_m) continue; if (m > s_m) - memset(&cb->args[2], 0, - sizeof(cb->args) - 2*sizeof(cb->args[0])); + memset(&cb->args[3], 0, + sizeof(cb->args) - 3*sizeof(cb->args[0])); if (fn_trie_dump_plen(t, 32-m, tb, skb, cb)<0) { - cb->args[1] = m; + cb->args[2] = m; goto out; } } rcu_read_unlock(); - cb->args[1] = m; + cb->args[2] = m; return skb->len; out: rcu_read_unlock(); @@ -1943,9 +1931,9 @@ out: /* Fix more generic FIB names for init later */ #ifdef CONFIG_IP_MULTIPLE_TABLES -struct fib_table * fib_hash_init(int id) +struct fib_table * fib_hash_init(u32 id) #else -struct fib_table * __init fib_hash_init(int id) +struct fib_table * __init fib_hash_init(u32 id) #endif { struct fib_table *tb; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 4c86ac3d882..c2ad07e48ab 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -187,11 +187,11 @@ struct icmp_err icmp_err_convert[] = { }; /* Control parameters for ECHO replies. */ -int sysctl_icmp_echo_ignore_all; -int sysctl_icmp_echo_ignore_broadcasts = 1; +int sysctl_icmp_echo_ignore_all __read_mostly; +int sysctl_icmp_echo_ignore_broadcasts __read_mostly = 1; /* Control parameter - ignore bogus broadcast responses? */ -int sysctl_icmp_ignore_bogus_error_responses = 1; +int sysctl_icmp_ignore_bogus_error_responses __read_mostly = 1; /* * Configurable global rate limit. @@ -205,9 +205,9 @@ int sysctl_icmp_ignore_bogus_error_responses = 1; * time exceeded (11), parameter problem (12) */ -int sysctl_icmp_ratelimit = 1 * HZ; -int sysctl_icmp_ratemask = 0x1818; -int sysctl_icmp_errors_use_inbound_ifaddr; +int sysctl_icmp_ratelimit __read_mostly = 1 * HZ; +int sysctl_icmp_ratemask __read_mostly = 0x1818; +int sysctl_icmp_errors_use_inbound_ifaddr __read_mostly; /* * ICMP control array. This specifies what to do with each ICMP. @@ -406,6 +406,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) .saddr = rt->rt_spec_dst, .tos = RT_TOS(skb->nh.iph->tos) } }, .proto = IPPROTO_ICMP }; + security_skb_classify_flow(skb, &fl); if (ip_route_output_key(&rt, &fl)) goto out_unlock; } @@ -560,6 +561,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info) } } }; + security_skb_classify_flow(skb_in, &fl); if (ip_route_output_key(&rt, &fl)) goto out_unlock; } @@ -928,7 +930,7 @@ int icmp_rcv(struct sk_buff *skb) ICMP_INC_STATS_BH(ICMP_MIB_INMSGS); switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (!(u16)csum_fold(skb->csum)) break; /* fall through */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 8e8117c19e4..58be8227b0c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -931,7 +931,7 @@ int igmp_rcv(struct sk_buff *skb) goto drop; switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (!(u16)csum_fold(skb->csum)) break; /* fall through */ @@ -1397,8 +1397,8 @@ static struct in_device * ip_mc_find_dev(struct ip_mreqn *imr) /* * Join a socket to a group */ -int sysctl_igmp_max_memberships = IP_MAX_MEMBERSHIPS; -int sysctl_igmp_max_msf = IP_MAX_MSF; +int sysctl_igmp_max_memberships __read_mostly = IP_MAX_MEMBERSHIPS; +int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF; static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e50a1bfd7cc..07204391d08 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -327,6 +327,7 @@ struct dst_entry* inet_csk_route_req(struct sock *sk, { .sport = inet_sk(sk)->sport, .dport = ireq->rmt_port } } }; + security_req_classify_flow(req, &fl); if (ip_route_output_flow(&rt, &fl, sk, 0)) { IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); return NULL; @@ -509,6 +510,8 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, /* Deinitialize accept_queue to trap illegal accesses. */ memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); + + security_inet_csk_clone(newsk, req); } return newsk; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 95fac553299..fb296c9a7f3 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -124,8 +124,10 @@ EXPORT_SYMBOL(inet_listen_wlock); * remote address for the connection. So always assume those are both * wildcarded during the search since they can never be otherwise. */ -struct sock *__inet_lookup_listener(const struct hlist_head *head, const u32 daddr, - const unsigned short hnum, const int dif) +static struct sock *inet_lookup_listener_slow(const struct hlist_head *head, + const u32 daddr, + const unsigned short hnum, + const int dif) { struct sock *result = NULL, *sk; const struct hlist_node *node; @@ -159,6 +161,33 @@ struct sock *__inet_lookup_listener(const struct hlist_head *head, const u32 dad return result; } +/* Optimize the common listener case. */ +struct sock *__inet_lookup_listener(struct inet_hashinfo *hashinfo, + const u32 daddr, const unsigned short hnum, + const int dif) +{ + struct sock *sk = NULL; + const struct hlist_head *head; + + read_lock(&hashinfo->lhash_lock); + head = &hashinfo->listening_hash[inet_lhashfn(hnum)]; + if (!hlist_empty(head)) { + const struct inet_sock *inet = inet_sk((sk = __sk_head(head))); + + if (inet->num == hnum && !sk->sk_node.next && + (!inet->rcv_saddr || inet->rcv_saddr == daddr) && + (sk->sk_family == PF_INET || !ipv6_only_sock(sk)) && + !sk->sk_bound_dev_if) + goto sherry_cache; + sk = inet_lookup_listener_slow(head, daddr, hnum, dif); + } + if (sk) { +sherry_cache: + sock_hold(sk); + } + read_unlock(&hashinfo->lhash_lock); + return sk; +} EXPORT_SYMBOL_GPL(__inet_lookup_listener); /* called with local bh disabled */ diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 03ff62ebcfe..a675602ef29 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -126,12 +126,9 @@ void __init inet_initpeers(void) peer_cachep = kmem_cache_create("inet_peer_cache", sizeof(struct inet_peer), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!peer_cachep) - panic("cannot create inet_peer_cache"); - /* All the timers, started at system startup tend to synchronize. Perturb it a bit. */ diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b84b53a4752..165d72859dd 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -54,15 +54,15 @@ * even the most extreme cases without allowing an attacker to measurably * harm machine performance. */ -int sysctl_ipfrag_high_thresh = 256*1024; -int sysctl_ipfrag_low_thresh = 192*1024; +int sysctl_ipfrag_high_thresh __read_mostly = 256*1024; +int sysctl_ipfrag_low_thresh __read_mostly = 192*1024; -int sysctl_ipfrag_max_dist = 64; +int sysctl_ipfrag_max_dist __read_mostly = 64; /* Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival by TTL. */ -int sysctl_ipfrag_time = IP_FRAG_TIME; +int sysctl_ipfrag_time __read_mostly = IP_FRAG_TIME; struct ipfrag_skb_cb { @@ -130,7 +130,7 @@ static unsigned int ipqhashfn(u16 id, u32 saddr, u32 daddr, u8 prot) } static struct timer_list ipfrag_secret_timer; -int sysctl_ipfrag_secret_interval = 10 * 60 * HZ; +int sysctl_ipfrag_secret_interval __read_mostly = 10 * 60 * HZ; static void ipfrag_secret_rebuild(unsigned long dummy) { @@ -665,7 +665,7 @@ static struct sk_buff *ip_frag_reasm(struct ipq *qp, struct net_device *dev) head->len += fp->len; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_HW) + else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; atomic_sub(fp->truesize, &ip_frag_mem); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0f9b3a31997..f5fba051df3 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -393,7 +393,8 @@ out: int code = skb->h.icmph->code; int rel_type = 0; int rel_code = 0; - int rel_info = 0; + __be32 rel_info = 0; + __u32 n = 0; u16 flags; int grehlen = (iph->ihl<<2) + 4; struct sk_buff *skb2; @@ -422,14 +423,16 @@ out: default: return; case ICMP_PARAMETERPROB: - if (skb->h.icmph->un.gateway < (iph->ihl<<2)) + n = ntohl(skb->h.icmph->un.gateway) >> 24; + if (n < (iph->ihl<<2)) return; /* So... This guy found something strange INSIDE encapsulated packet. Well, he is fool, but what can we do ? */ rel_type = ICMP_PARAMETERPROB; - rel_info = skb->h.icmph->un.gateway - grehlen; + n -= grehlen; + rel_info = htonl(n << 24); break; case ICMP_DEST_UNREACH: @@ -440,13 +443,14 @@ out: return; case ICMP_FRAG_NEEDED: /* And it is the only really necessary thing :-) */ - rel_info = ntohs(skb->h.icmph->un.frag.mtu); - if (rel_info < grehlen+68) + n = ntohs(skb->h.icmph->un.frag.mtu); + if (n < grehlen+68) return; - rel_info -= grehlen; + n -= grehlen; /* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */ - if (rel_info > ntohs(eiph->tot_len)) + if (n > ntohs(eiph->tot_len)) return; + rel_info = htonl(n); break; default: /* All others are translated to HOST_UNREACH. @@ -508,12 +512,11 @@ out: /* change mtu on this route */ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { - if (rel_info > dst_mtu(skb2->dst)) { + if (n > dst_mtu(skb2->dst)) { kfree_skb(skb2); return; } - skb2->dst->ops->update_pmtu(skb2->dst, rel_info); - rel_info = htonl(rel_info); + skb2->dst->ops->update_pmtu(skb2->dst, n); } else if (type == ICMP_TIME_EXCEEDED) { struct ip_tunnel *t = netdev_priv(skb2->dev); if (t->parms.iph.ttl) { @@ -576,7 +579,7 @@ static int ipgre_rcv(struct sk_buff *skb) if (flags&GRE_CSUM) { switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: csum = (u16)csum_fold(skb->csum); if (!csum) break; @@ -584,7 +587,7 @@ static int ipgre_rcv(struct sk_buff *skb) case CHECKSUM_NONE: skb->csum = 0; csum = __skb_checksum_complete(skb); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_COMPLETE; } offset += 4; } diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 406056edc02..e7437c09132 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -24,6 +24,7 @@ #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> +#include <net/cipso_ipv4.h> /* * Write options to IP header, record destination address to @@ -194,6 +195,13 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb) dopt->is_strictroute = sopt->is_strictroute; } } + if (sopt->cipso) { + optlen = sptr[sopt->cipso+1]; + dopt->cipso = dopt->optlen+sizeof(struct iphdr); + memcpy(dptr, sptr+sopt->cipso, optlen); + dptr += optlen; + dopt->optlen += optlen; + } while (dopt->optlen & 3) { *dptr++ = IPOPT_END; dopt->optlen++; @@ -434,6 +442,17 @@ int ip_options_compile(struct ip_options * opt, struct sk_buff * skb) if (optptr[2] == 0 && optptr[3] == 0) opt->router_alert = optptr - iph; break; + case IPOPT_CIPSO: + if (opt->cipso) { + pp_ptr = optptr; + goto error; + } + opt->cipso = optptr - iph; + if (cipso_v4_validate(&optptr)) { + pp_ptr = optptr; + goto error; + } + break; case IPOPT_SEC: case IPOPT_SID: default: @@ -506,7 +525,6 @@ static int ip_options_get_finish(struct ip_options **optp, opt->__data[optlen++] = IPOPT_END; opt->optlen = optlen; opt->is_data = 1; - opt->is_setbyuser = 1; if (optlen && ip_options_compile(opt, NULL)) { kfree(opt); return -EINVAL; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a2ede167e04..97aee76fb74 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -83,7 +83,7 @@ #include <linux/netlink.h> #include <linux/tcp.h> -int sysctl_ip_default_ttl = IPDEFTTL; +int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; /* Generate a checksum for an outgoing IP datagram. */ __inline__ void ip_send_check(struct iphdr *iph) @@ -328,6 +328,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) * keep trying until route appears or the connection times * itself out. */ + security_sk_classify_flow(sk, &fl); if (ip_route_output_flow(&rt, &fl, sk, 0)) goto no_route; } @@ -425,7 +426,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)) int ptr; struct net_device *dev; struct sk_buff *skb2; - unsigned int mtu, hlen, left, len, ll_rs; + unsigned int mtu, hlen, left, len, ll_rs, pad; int offset; __be16 not_last_frag; struct rtable *rt = (struct rtable*)skb->dst; @@ -555,14 +556,13 @@ slow_path: left = skb->len - hlen; /* Space per frame */ ptr = raw + hlen; /* Where to start from */ -#ifdef CONFIG_BRIDGE_NETFILTER /* for bridged IP traffic encapsulated inside f.e. a vlan header, - * we need to make room for the encapsulating header */ - ll_rs = LL_RESERVED_SPACE_EXTRA(rt->u.dst.dev, nf_bridge_pad(skb)); - mtu -= nf_bridge_pad(skb); -#else - ll_rs = LL_RESERVED_SPACE(rt->u.dst.dev); -#endif + * we need to make room for the encapsulating header + */ + pad = nf_bridge_pad(skb); + ll_rs = LL_RESERVED_SPACE_EXTRA(rt->u.dst.dev, pad); + mtu -= pad; + /* * Fragment the datagram. */ @@ -679,7 +679,7 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk { struct iovec *iov = from; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { if (memcpy_fromiovecend(to, iov, offset, len) < 0) return -EFAULT; } else { @@ -735,7 +735,7 @@ static inline int ip_ufo_append_data(struct sock *sk, /* initialize protocol header pointer */ skb->h.raw = skb->data + fragheaderlen; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; sk->sk_sndmsg_off = 0; } @@ -843,7 +843,7 @@ int ip_append_data(struct sock *sk, length + fragheaderlen <= mtu && rt->u.dst.dev->features & NETIF_F_ALL_CSUM && !exthdrlen) - csummode = CHECKSUM_HW; + csummode = CHECKSUM_PARTIAL; inet->cork.length += length; if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) && @@ -1366,6 +1366,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar { .sport = skb->h.th->dest, .dport = skb->h.th->source } }, .proto = sk->sk_protocol }; + security_skb_classify_flow(skb, &fl); if (ip_route_output_key(&rt, &fl)) return; } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 5bb9c9f03fb..17342430a84 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -176,7 +176,7 @@ static int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb) return 0; out_ok: - if (x->props.mode) + if (x->props.mode == XFRM_MODE_TUNNEL) ip_send_check(iph); return 0; } @@ -216,7 +216,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) t->id.daddr.a4 = x->id.daddr.a4; memcpy(&t->sel, &x->sel, sizeof(t->sel)); t->props.family = AF_INET; - t->props.mode = 1; + t->props.mode = XFRM_MODE_TUNNEL; t->props.saddr.a4 = x->props.saddr.a4; t->props.flags = x->props.flags; @@ -416,7 +416,7 @@ static int ipcomp_init_state(struct xfrm_state *x) goto out; x->props.header_len = 0; - if (x->props.mode) + if (x->props.mode == XFRM_MODE_TUNNEL) x->props.header_len += sizeof(struct iphdr); mutex_lock(&ipcomp_resource_mutex); @@ -428,7 +428,7 @@ static int ipcomp_init_state(struct xfrm_state *x) goto error; mutex_unlock(&ipcomp_resource_mutex); - if (x->props.mode) { + if (x->props.mode == XFRM_MODE_TUNNEL) { err = ipcomp_tunnel_attach(x); if (err) goto error_tunnel; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index cb8a92f18ef..1fbb38415b1 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -31,7 +31,6 @@ * -- Josef Siemes <jsiemes@web.de>, Aug 2002 */ -#include <linux/config.h> #include <linux/types.h> #include <linux/string.h> #include <linux/kernel.h> diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 76ab50b0d6e..0c455652922 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -341,7 +341,8 @@ out: int code = skb->h.icmph->code; int rel_type = 0; int rel_code = 0; - int rel_info = 0; + __be32 rel_info = 0; + __u32 n = 0; struct sk_buff *skb2; struct flowi fl; struct rtable *rt; @@ -354,14 +355,15 @@ out: default: return 0; case ICMP_PARAMETERPROB: - if (skb->h.icmph->un.gateway < hlen) + n = ntohl(skb->h.icmph->un.gateway) >> 24; + if (n < hlen) return 0; /* So... This guy found something strange INSIDE encapsulated packet. Well, he is fool, but what can we do ? */ rel_type = ICMP_PARAMETERPROB; - rel_info = skb->h.icmph->un.gateway - hlen; + rel_info = htonl((n - hlen) << 24); break; case ICMP_DEST_UNREACH: @@ -372,13 +374,14 @@ out: return 0; case ICMP_FRAG_NEEDED: /* And it is the only really necessary thing :-) */ - rel_info = ntohs(skb->h.icmph->un.frag.mtu); - if (rel_info < hlen+68) + n = ntohs(skb->h.icmph->un.frag.mtu); + if (n < hlen+68) return 0; - rel_info -= hlen; + n -= hlen; /* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */ - if (rel_info > ntohs(eiph->tot_len)) + if (n > ntohs(eiph->tot_len)) return 0; + rel_info = htonl(n); break; default: /* All others are translated to HOST_UNREACH. @@ -440,12 +443,11 @@ out: /* change mtu on this route */ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { - if (rel_info > dst_mtu(skb2->dst)) { + if (n > dst_mtu(skb2->dst)) { kfree_skb(skb2); return 0; } - skb2->dst->ops->update_pmtu(skb2->dst, rel_info); - rel_info = htonl(rel_info); + skb2->dst->ops->update_pmtu(skb2->dst, n); } else if (type == ICMP_TIME_EXCEEDED) { struct ip_tunnel *t = netdev_priv(skb2->dev); if (t->parms.iph.ttl) { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 85893eef6b1..ba49588da24 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -312,7 +312,8 @@ static void ipmr_destroy_unres(struct mfc_cache *c) e = NLMSG_DATA(nlh); e->error = -ETIMEDOUT; memset(&e->msg, 0, sizeof(e->msg)); - netlink_unicast(rtnl, skb, NETLINK_CB(skb).dst_pid, MSG_DONTWAIT); + + rtnl_unicast(skb, NETLINK_CB(skb).pid); } else kfree_skb(skb); } @@ -512,7 +513,6 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c) while((skb=__skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (skb->nh.iph->version == 0) { - int err; struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); if (ipmr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) { @@ -525,7 +525,8 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c) e->error = -EMSGSIZE; memset(&e->msg, 0, sizeof(e->msg)); } - err = netlink_unicast(rtnl, skb, NETLINK_CB(skb).dst_pid, MSG_DONTWAIT); + + rtnl_unicast(skb, NETLINK_CB(skb).pid); } else ip_mr_forward(skb, c, 0); } @@ -1899,11 +1900,8 @@ void __init ip_mr_init(void) { mrt_cachep = kmem_cache_create("ip_mrt_cache", sizeof(struct mfc_cache), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!mrt_cachep) - panic("cannot allocate ip_mrt_cache"); - init_timer(&ipmr_expire_timer); ipmr_expire_timer.function=ipmr_expire_process; register_netdevice_notifier(&ip_mr_notifier); diff --git a/net/ipv4/ipvs/ip_vs_proto_tcp.c b/net/ipv4/ipvs/ip_vs_proto_tcp.c index bc28b1160a3..820e8318d10 100644 --- a/net/ipv4/ipvs/ip_vs_proto_tcp.c +++ b/net/ipv4/ipvs/ip_vs_proto_tcp.c @@ -151,7 +151,7 @@ tcp_snat_handler(struct sk_buff **pskb, /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(tcph, cp->daddr, cp->vaddr, cp->dport, cp->vport); - if ((*pskb)->ip_summed == CHECKSUM_HW) + if ((*pskb)->ip_summed == CHECKSUM_COMPLETE) (*pskb)->ip_summed = CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -204,7 +204,7 @@ tcp_dnat_handler(struct sk_buff **pskb, /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(tcph, cp->vaddr, cp->daddr, cp->vport, cp->dport); - if ((*pskb)->ip_summed == CHECKSUM_HW) + if ((*pskb)->ip_summed == CHECKSUM_COMPLETE) (*pskb)->ip_summed = CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -229,7 +229,7 @@ tcp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) switch (skb->ip_summed) { case CHECKSUM_NONE: skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr, skb->len - tcphoff, skb->nh.iph->protocol, skb->csum)) { @@ -239,7 +239,7 @@ tcp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) } break; default: - /* CHECKSUM_UNNECESSARY */ + /* No need to checksum. */ break; } diff --git a/net/ipv4/ipvs/ip_vs_proto_udp.c b/net/ipv4/ipvs/ip_vs_proto_udp.c index 89d9175d8f2..90c8166c0ec 100644 --- a/net/ipv4/ipvs/ip_vs_proto_udp.c +++ b/net/ipv4/ipvs/ip_vs_proto_udp.c @@ -161,7 +161,7 @@ udp_snat_handler(struct sk_buff **pskb, /* Only port and addr are changed, do fast csum update */ udp_fast_csum_update(udph, cp->daddr, cp->vaddr, cp->dport, cp->vport); - if ((*pskb)->ip_summed == CHECKSUM_HW) + if ((*pskb)->ip_summed == CHECKSUM_COMPLETE) (*pskb)->ip_summed = CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -216,7 +216,7 @@ udp_dnat_handler(struct sk_buff **pskb, /* Only port and addr are changed, do fast csum update */ udp_fast_csum_update(udph, cp->vaddr, cp->daddr, cp->vport, cp->dport); - if ((*pskb)->ip_summed == CHECKSUM_HW) + if ((*pskb)->ip_summed == CHECKSUM_COMPLETE) (*pskb)->ip_summed = CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -250,7 +250,7 @@ udp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) case CHECKSUM_NONE: skb->csum = skb_checksum(skb, udphoff, skb->len - udphoff, 0); - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr, skb->len - udphoff, @@ -262,7 +262,7 @@ udp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp) } break; default: - /* CHECKSUM_UNNECESSARY */ + /* No need to checksum. */ break; } } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 6a9e34b794b..f88347de21a 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -168,7 +168,7 @@ unsigned int nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int csum = 0; switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (hook != NF_IP_PRE_ROUTING && hook != NF_IP_LOCAL_IN) break; if ((protocol == 0 && !(u16)csum_fold(skb->csum)) || diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index ef0b5aac583..a55b8ff70de 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -278,17 +278,6 @@ config IP_NF_MATCH_ECN To compile it as a module, choose M here. If unsure, say N. -config IP_NF_MATCH_DSCP - tristate "DSCP match support" - depends on IP_NF_IPTABLES - help - This option adds a `DSCP' match, which allows you to match against - the IPv4 header DSCP field (DSCP codepoint). - - The DSCP codepoint can have any value between 0x0 and 0x4f. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_AH tristate "AH match support" depends on IP_NF_IPTABLES @@ -568,17 +557,6 @@ config IP_NF_TARGET_ECN To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_DSCP - tristate "DSCP target support" - depends on IP_NF_MANGLE - help - This option adds a `DSCP' match, which allows you to match against - the IPv4 header DSCP field (DSCP codepoint). - - The DSCP codepoint can have any value between 0x0 and 0x4f. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_TARGET_TTL tristate 'TTL target support' depends on IP_NF_MANGLE diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 3ded4a3af59..09aaed1a806 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -59,7 +59,6 @@ obj-$(CONFIG_IP_NF_MATCH_OWNER) += ipt_owner.o obj-$(CONFIG_IP_NF_MATCH_TOS) += ipt_tos.o obj-$(CONFIG_IP_NF_MATCH_RECENT) += ipt_recent.o obj-$(CONFIG_IP_NF_MATCH_ECN) += ipt_ecn.o -obj-$(CONFIG_IP_NF_MATCH_DSCP) += ipt_dscp.o obj-$(CONFIG_IP_NF_MATCH_AH) += ipt_ah.o obj-$(CONFIG_IP_NF_MATCH_TTL) += ipt_ttl.o obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o @@ -68,7 +67,6 @@ obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o obj-$(CONFIG_IP_NF_TARGET_TOS) += ipt_TOS.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o -obj-$(CONFIG_IP_NF_TARGET_DSCP) += ipt_DSCP.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 8d1d7a6e72a..85f0d73ebfb 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -56,8 +56,6 @@ do { \ #define ARP_NF_ASSERT(x) #endif -#include <linux/netfilter_ipv4/listhelp.h> - static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, char *hdr_addr, int len) { @@ -208,8 +206,7 @@ static unsigned int arpt_error(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { if (net_ratelimit()) printk("arp_tables: error: '%s'\n", (char *)targinfo); @@ -226,8 +223,7 @@ unsigned int arpt_do_table(struct sk_buff **pskb, unsigned int hook, const struct net_device *in, const struct net_device *out, - struct arpt_table *table, - void *userdata) + struct arpt_table *table) { static const char nulldevname[IFNAMSIZ]; unsigned int verdict = NF_DROP; @@ -302,8 +298,7 @@ unsigned int arpt_do_table(struct sk_buff **pskb, in, out, hook, t->u.kernel.target, - t->data, - userdata); + t->data); /* Target might have changed stuff. */ arp = (*pskb)->nh.arph; @@ -490,12 +485,10 @@ static inline int check_entry(struct arpt_entry *e, const char *name, unsigned i if (t->u.kernel.target == &arpt_standard_target) { if (!standard_check(t, size)) { ret = -EINVAL; - goto out; + goto err; } } else if (t->u.kernel.target->checkentry && !t->u.kernel.target->checkentry(name, e, target, t->data, - t->u.target_size - - sizeof(*t), e->comefrom)) { duprintf("arp_tables: check failed for `%s'.\n", t->u.kernel.target->name); @@ -562,8 +555,7 @@ 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->u.kernel.target, t->data, - t->u.target_size - sizeof(*t)); + t->u.kernel.target->destroy(t->u.kernel.target, t->data); module_put(t->u.kernel.target->me); return 0; } diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index a58325c1ceb..d12b1df252a 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -11,7 +11,7 @@ static unsigned int 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 void *targinfo) { const struct arpt_mangle *mangle = targinfo; struct arphdr *arp; @@ -67,7 +67,7 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, const void *e, const struct xt_target *target, - void *targinfo, unsigned int targinfosize, unsigned int hook_mask) + void *targinfo, unsigned int hook_mask) { const struct arpt_mangle *mangle = targinfo; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index d7c472faa53..7edea2a1696 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -155,7 +155,7 @@ static unsigned int arpt_hook(unsigned int hook, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return arpt_do_table(pskb, hook, in, out, &packet_filter, NULL); + return arpt_do_table(pskb, hook, in, out, &packet_filter); } static struct nf_hook_ops arpt_ops[] = { diff --git a/net/ipv4/netfilter/ip_conntrack_core.c b/net/ipv4/netfilter/ip_conntrack_core.c index aa459177c3f..c432b316360 100644 --- a/net/ipv4/netfilter/ip_conntrack_core.c +++ b/net/ipv4/netfilter/ip_conntrack_core.c @@ -47,7 +47,6 @@ #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> #include <linux/netfilter_ipv4/ip_conntrack_helper.h> #include <linux/netfilter_ipv4/ip_conntrack_core.h> -#include <linux/netfilter_ipv4/listhelp.h> #define IP_CONNTRACK_VERSION "2.4" @@ -64,17 +63,17 @@ atomic_t ip_conntrack_count = ATOMIC_INIT(0); void (*ip_conntrack_destroyed)(struct ip_conntrack *conntrack) = NULL; LIST_HEAD(ip_conntrack_expect_list); -struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO]; +struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO] __read_mostly; static LIST_HEAD(helpers); -unsigned int ip_conntrack_htable_size = 0; -int ip_conntrack_max; -struct list_head *ip_conntrack_hash; +unsigned int ip_conntrack_htable_size __read_mostly = 0; +int ip_conntrack_max __read_mostly; +struct list_head *ip_conntrack_hash __read_mostly; static kmem_cache_t *ip_conntrack_cachep __read_mostly; static kmem_cache_t *ip_conntrack_expect_cachep __read_mostly; struct ip_conntrack ip_conntrack_untracked; -unsigned int ip_ct_log_invalid; +unsigned int ip_ct_log_invalid __read_mostly; static LIST_HEAD(unconfirmed); -static int ip_conntrack_vmalloc; +static int ip_conntrack_vmalloc __read_mostly; static unsigned int ip_conntrack_next_id; static unsigned int ip_conntrack_expect_next_id; @@ -294,15 +293,10 @@ void ip_ct_remove_expectations(struct ip_conntrack *ct) static void clean_from_lists(struct ip_conntrack *ct) { - unsigned int ho, hr; - DEBUGP("clean_from_lists(%p)\n", ct); ASSERT_WRITE_LOCK(&ip_conntrack_lock); - - ho = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - hr = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); - LIST_DELETE(&ip_conntrack_hash[ho], &ct->tuplehash[IP_CT_DIR_ORIGINAL]); - LIST_DELETE(&ip_conntrack_hash[hr], &ct->tuplehash[IP_CT_DIR_REPLY]); + list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list); + list_del(&ct->tuplehash[IP_CT_DIR_REPLY].list); /* Destroy all pending expectations */ ip_ct_remove_expectations(ct); @@ -313,6 +307,7 @@ destroy_conntrack(struct nf_conntrack *nfct) { struct ip_conntrack *ct = (struct ip_conntrack *)nfct; struct ip_conntrack_protocol *proto; + struct ip_conntrack_helper *helper; DEBUGP("destroy_conntrack(%p)\n", ct); IP_NF_ASSERT(atomic_read(&nfct->use) == 0); @@ -321,6 +316,10 @@ destroy_conntrack(struct nf_conntrack *nfct) ip_conntrack_event(IPCT_DESTROY, ct); set_bit(IPS_DYING_BIT, &ct->status); + helper = ct->helper; + if (helper && helper->destroy) + helper->destroy(ct); + /* To make sure we don't get any weird locking issues here: * destroy_conntrack() MUST NOT be called with a write lock * to ip_conntrack_lock!!! -HW */ @@ -367,16 +366,6 @@ static void death_by_timeout(unsigned long ul_conntrack) ip_conntrack_put(ct); } -static inline int -conntrack_tuple_cmp(const struct ip_conntrack_tuple_hash *i, - const struct ip_conntrack_tuple *tuple, - const struct ip_conntrack *ignored_conntrack) -{ - ASSERT_READ_LOCK(&ip_conntrack_lock); - return tuplehash_to_ctrack(i) != ignored_conntrack - && ip_ct_tuple_equal(tuple, &i->tuple); -} - struct ip_conntrack_tuple_hash * __ip_conntrack_find(const struct ip_conntrack_tuple *tuple, const struct ip_conntrack *ignored_conntrack) @@ -386,7 +375,8 @@ __ip_conntrack_find(const struct ip_conntrack_tuple *tuple, ASSERT_READ_LOCK(&ip_conntrack_lock); list_for_each_entry(h, &ip_conntrack_hash[hash], list) { - if (conntrack_tuple_cmp(h, tuple, ignored_conntrack)) { + if (tuplehash_to_ctrack(h) != ignored_conntrack && + ip_ct_tuple_equal(tuple, &h->tuple)) { CONNTRACK_STAT_INC(found); return h; } @@ -417,10 +407,10 @@ static void __ip_conntrack_hash_insert(struct ip_conntrack *ct, unsigned int repl_hash) { ct->id = ++ip_conntrack_next_id; - list_prepend(&ip_conntrack_hash[hash], - &ct->tuplehash[IP_CT_DIR_ORIGINAL].list); - list_prepend(&ip_conntrack_hash[repl_hash], - &ct->tuplehash[IP_CT_DIR_REPLY].list); + list_add(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list, + &ip_conntrack_hash[hash]); + list_add(&ct->tuplehash[IP_CT_DIR_REPLY].list, + &ip_conntrack_hash[repl_hash]); } void ip_conntrack_hash_insert(struct ip_conntrack *ct) @@ -440,6 +430,7 @@ int __ip_conntrack_confirm(struct sk_buff **pskb) { unsigned int hash, repl_hash; + struct ip_conntrack_tuple_hash *h; struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; @@ -470,43 +461,43 @@ __ip_conntrack_confirm(struct sk_buff **pskb) /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ - if (!LIST_FIND(&ip_conntrack_hash[hash], - conntrack_tuple_cmp, - struct ip_conntrack_tuple_hash *, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, NULL) - && !LIST_FIND(&ip_conntrack_hash[repl_hash], - conntrack_tuple_cmp, - struct ip_conntrack_tuple_hash *, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple, NULL)) { - /* Remove from unconfirmed list */ - list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list); + list_for_each_entry(h, &ip_conntrack_hash[hash], list) + if (ip_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &h->tuple)) + goto out; + list_for_each_entry(h, &ip_conntrack_hash[repl_hash], list) + if (ip_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, + &h->tuple)) + goto out; - __ip_conntrack_hash_insert(ct, hash, repl_hash); - /* Timer relative to confirmation time, not original - setting time, otherwise we'd get timer wrap in - weird delay cases. */ - ct->timeout.expires += jiffies; - add_timer(&ct->timeout); - atomic_inc(&ct->ct_general.use); - set_bit(IPS_CONFIRMED_BIT, &ct->status); - CONNTRACK_STAT_INC(insert); - write_unlock_bh(&ip_conntrack_lock); - if (ct->helper) - ip_conntrack_event_cache(IPCT_HELPER, *pskb); + /* Remove from unconfirmed list */ + list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list); + + __ip_conntrack_hash_insert(ct, hash, repl_hash); + /* Timer relative to confirmation time, not original + setting time, otherwise we'd get timer wrap in + weird delay cases. */ + ct->timeout.expires += jiffies; + add_timer(&ct->timeout); + atomic_inc(&ct->ct_general.use); + set_bit(IPS_CONFIRMED_BIT, &ct->status); + CONNTRACK_STAT_INC(insert); + write_unlock_bh(&ip_conntrack_lock); + if (ct->helper) + ip_conntrack_event_cache(IPCT_HELPER, *pskb); #ifdef CONFIG_IP_NF_NAT_NEEDED - if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) || - test_bit(IPS_DST_NAT_DONE_BIT, &ct->status)) - ip_conntrack_event_cache(IPCT_NATINFO, *pskb); + if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) || + test_bit(IPS_DST_NAT_DONE_BIT, &ct->status)) + ip_conntrack_event_cache(IPCT_NATINFO, *pskb); #endif - ip_conntrack_event_cache(master_ct(ct) ? - IPCT_RELATED : IPCT_NEW, *pskb); + ip_conntrack_event_cache(master_ct(ct) ? + IPCT_RELATED : IPCT_NEW, *pskb); - return NF_ACCEPT; - } + return NF_ACCEPT; +out: CONNTRACK_STAT_INC(insert_failed); write_unlock_bh(&ip_conntrack_lock); - return NF_DROP; } @@ -527,23 +518,21 @@ ip_conntrack_tuple_taken(const struct ip_conntrack_tuple *tuple, /* There's a small race here where we may free a just-assured connection. Too bad: we're in trouble anyway. */ -static inline int unreplied(const struct ip_conntrack_tuple_hash *i) -{ - return !(test_bit(IPS_ASSURED_BIT, &tuplehash_to_ctrack(i)->status)); -} - static int early_drop(struct list_head *chain) { /* Traverse backwards: gives us oldest, which is roughly LRU */ struct ip_conntrack_tuple_hash *h; - struct ip_conntrack *ct = NULL; + struct ip_conntrack *ct = NULL, *tmp; int dropped = 0; read_lock_bh(&ip_conntrack_lock); - h = LIST_FIND_B(chain, unreplied, struct ip_conntrack_tuple_hash *); - if (h) { - ct = tuplehash_to_ctrack(h); - atomic_inc(&ct->ct_general.use); + list_for_each_entry_reverse(h, chain, list) { + tmp = tuplehash_to_ctrack(h); + if (!test_bit(IPS_ASSURED_BIT, &tmp->status)) { + ct = tmp; + atomic_inc(&ct->ct_general.use); + break; + } } read_unlock_bh(&ip_conntrack_lock); @@ -559,18 +548,16 @@ static int early_drop(struct list_head *chain) return dropped; } -static inline int helper_cmp(const struct ip_conntrack_helper *i, - const struct ip_conntrack_tuple *rtuple) -{ - return ip_ct_tuple_mask_cmp(rtuple, &i->tuple, &i->mask); -} - static struct ip_conntrack_helper * __ip_conntrack_helper_find( const struct ip_conntrack_tuple *tuple) { - return LIST_FIND(&helpers, helper_cmp, - struct ip_conntrack_helper *, - tuple); + struct ip_conntrack_helper *h; + + list_for_each_entry(h, &helpers, list) { + if (ip_ct_tuple_mask_cmp(tuple, &h->tuple, &h->mask)) + return h; + } + return NULL; } struct ip_conntrack_helper * @@ -640,11 +627,15 @@ struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *orig, ip_conntrack_hash_rnd_initted = 1; } + /* We don't want any race condition at early drop stage */ + atomic_inc(&ip_conntrack_count); + if (ip_conntrack_max - && atomic_read(&ip_conntrack_count) >= ip_conntrack_max) { + && atomic_read(&ip_conntrack_count) > ip_conntrack_max) { unsigned int hash = hash_conntrack(orig); /* Try dropping from this hash chain. */ if (!early_drop(&ip_conntrack_hash[hash])) { + atomic_dec(&ip_conntrack_count); if (net_ratelimit()) printk(KERN_WARNING "ip_conntrack: table full, dropping" @@ -656,6 +647,7 @@ struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *orig, conntrack = kmem_cache_alloc(ip_conntrack_cachep, GFP_ATOMIC); if (!conntrack) { DEBUGP("Can't allocate conntrack.\n"); + atomic_dec(&ip_conntrack_count); return ERR_PTR(-ENOMEM); } @@ -669,8 +661,6 @@ struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *orig, conntrack->timeout.data = (unsigned long)conntrack; conntrack->timeout.function = death_by_timeout; - atomic_inc(&ip_conntrack_count); - return conntrack; } @@ -1062,7 +1052,7 @@ int ip_conntrack_helper_register(struct ip_conntrack_helper *me) { BUG_ON(me->timeout == 0); write_lock_bh(&ip_conntrack_lock); - list_prepend(&helpers, me); + list_add(&me->list, &helpers); write_unlock_bh(&ip_conntrack_lock); return 0; @@ -1081,24 +1071,24 @@ __ip_conntrack_helper_find_byname(const char *name) return NULL; } -static inline int unhelp(struct ip_conntrack_tuple_hash *i, - const struct ip_conntrack_helper *me) +static inline void unhelp(struct ip_conntrack_tuple_hash *i, + const struct ip_conntrack_helper *me) { if (tuplehash_to_ctrack(i)->helper == me) { ip_conntrack_event(IPCT_HELPER, tuplehash_to_ctrack(i)); tuplehash_to_ctrack(i)->helper = NULL; } - return 0; } void ip_conntrack_helper_unregister(struct ip_conntrack_helper *me) { unsigned int i; + struct ip_conntrack_tuple_hash *h; struct ip_conntrack_expect *exp, *tmp; /* Need write lock here, to delete helper. */ write_lock_bh(&ip_conntrack_lock); - LIST_DELETE(&helpers, me); + list_del(&me->list); /* Get rid of expectations */ list_for_each_entry_safe(exp, tmp, &ip_conntrack_expect_list, list) { @@ -1108,10 +1098,12 @@ void ip_conntrack_helper_unregister(struct ip_conntrack_helper *me) } } /* Get rid of expecteds, set helpers to NULL. */ - LIST_FIND_W(&unconfirmed, unhelp, struct ip_conntrack_tuple_hash*, me); - for (i = 0; i < ip_conntrack_htable_size; i++) - LIST_FIND_W(&ip_conntrack_hash[i], unhelp, - struct ip_conntrack_tuple_hash *, me); + list_for_each_entry(h, &unconfirmed, list) + unhelp(h, me); + for (i = 0; i < ip_conntrack_htable_size; i++) { + list_for_each_entry(h, &ip_conntrack_hash[i], list) + unhelp(h, me); + } write_unlock_bh(&ip_conntrack_lock); /* Someone could be still looking at the helper in a bh. */ @@ -1237,46 +1229,43 @@ static void ip_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb) nf_conntrack_get(nskb->nfct); } -static inline int -do_iter(const struct ip_conntrack_tuple_hash *i, - int (*iter)(struct ip_conntrack *i, void *data), - void *data) -{ - return iter(tuplehash_to_ctrack(i), data); -} - /* Bring out ya dead! */ -static struct ip_conntrack_tuple_hash * +static struct ip_conntrack * get_next_corpse(int (*iter)(struct ip_conntrack *i, void *data), void *data, unsigned int *bucket) { - struct ip_conntrack_tuple_hash *h = NULL; + struct ip_conntrack_tuple_hash *h; + struct ip_conntrack *ct; write_lock_bh(&ip_conntrack_lock); for (; *bucket < ip_conntrack_htable_size; (*bucket)++) { - h = LIST_FIND_W(&ip_conntrack_hash[*bucket], do_iter, - struct ip_conntrack_tuple_hash *, iter, data); - if (h) - break; + list_for_each_entry(h, &ip_conntrack_hash[*bucket], list) { + ct = tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; + } + } + list_for_each_entry(h, &unconfirmed, list) { + ct = tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; } - if (!h) - h = LIST_FIND_W(&unconfirmed, do_iter, - struct ip_conntrack_tuple_hash *, iter, data); - if (h) - atomic_inc(&tuplehash_to_ctrack(h)->ct_general.use); write_unlock_bh(&ip_conntrack_lock); + return NULL; - return h; +found: + atomic_inc(&ct->ct_general.use); + write_unlock_bh(&ip_conntrack_lock); + return ct; } void ip_ct_iterate_cleanup(int (*iter)(struct ip_conntrack *i, void *), void *data) { - struct ip_conntrack_tuple_hash *h; + struct ip_conntrack *ct; unsigned int bucket = 0; - while ((h = get_next_corpse(iter, data, &bucket)) != NULL) { - struct ip_conntrack *ct = tuplehash_to_ctrack(h); + while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { /* Time to push up daises... */ if (del_timer(&ct->timeout)) death_by_timeout((unsigned long)ct); diff --git a/net/ipv4/netfilter/ip_conntrack_helper_pptp.c b/net/ipv4/netfilter/ip_conntrack_helper_pptp.c index b020a33e65e..fb0aee69172 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_pptp.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_pptp.c @@ -20,11 +20,11 @@ * - We can only support one single call within each session * * TODO: - * - testing of incoming PPTP calls + * - testing of incoming PPTP calls * - * Changes: + * Changes: * 2002-02-05 - Version 1.3 - * - Call ip_conntrack_unexpect_related() from + * - Call ip_conntrack_unexpect_related() from * pptp_destroy_siblings() to destroy expectations in case * CALL_DISCONNECT_NOTIFY or tcp fin packet was seen * (Philip Craig <philipc@snapgear.com>) @@ -80,7 +80,7 @@ int struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq); -int +void (*ip_nat_pptp_hook_exp_gre)(struct ip_conntrack_expect *expect_orig, struct ip_conntrack_expect *expect_reply); @@ -141,7 +141,7 @@ static void pptp_expectfn(struct ip_conntrack *ct, invert_tuplepr(&inv_t, &exp->tuple); DEBUGP("trying to unexpect other dir: "); DUMP_TUPLE(&inv_t); - + exp_other = ip_conntrack_expect_find(&inv_t); if (exp_other) { /* delete other expectation. */ @@ -194,15 +194,16 @@ static void pptp_destroy_siblings(struct ip_conntrack *ct) { struct ip_conntrack_tuple t; - /* Since ct->sibling_list has literally rusted away in 2.6.11, + ip_ct_gre_keymap_destroy(ct); + /* Since ct->sibling_list has literally rusted away in 2.6.11, * we now need another way to find out about our sibling * contrack and expects... -HW */ /* try original (pns->pac) tuple */ memcpy(&t, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, sizeof(t)); t.dst.protonum = IPPROTO_GRE; - t.src.u.gre.key = htons(ct->help.ct_pptp_info.pns_call_id); - t.dst.u.gre.key = htons(ct->help.ct_pptp_info.pac_call_id); + t.src.u.gre.key = ct->help.ct_pptp_info.pns_call_id; + t.dst.u.gre.key = ct->help.ct_pptp_info.pac_call_id; if (!destroy_sibling_or_exp(&t)) DEBUGP("failed to timeout original pns->pac ct/exp\n"); @@ -210,8 +211,8 @@ static void pptp_destroy_siblings(struct ip_conntrack *ct) /* try reply (pac->pns) tuple */ memcpy(&t, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, sizeof(t)); t.dst.protonum = IPPROTO_GRE; - t.src.u.gre.key = htons(ct->help.ct_pptp_info.pac_call_id); - t.dst.u.gre.key = htons(ct->help.ct_pptp_info.pns_call_id); + t.src.u.gre.key = ct->help.ct_pptp_info.pac_call_id; + t.dst.u.gre.key = ct->help.ct_pptp_info.pns_call_id; if (!destroy_sibling_or_exp(&t)) DEBUGP("failed to timeout reply pac->pns ct/exp\n"); @@ -219,94 +220,63 @@ static void pptp_destroy_siblings(struct ip_conntrack *ct) /* expect GRE connections (PNS->PAC and PAC->PNS direction) */ static inline int -exp_gre(struct ip_conntrack *master, - u_int32_t seq, +exp_gre(struct ip_conntrack *ct, __be16 callid, __be16 peer_callid) { - struct ip_conntrack_tuple inv_tuple; - struct ip_conntrack_tuple exp_tuples[] = { - /* tuple in original direction, PNS->PAC */ - { .src = { .ip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip, - .u = { .gre = { .key = peer_callid } } - }, - .dst = { .ip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip, - .u = { .gre = { .key = callid } }, - .protonum = IPPROTO_GRE - }, - }, - /* tuple in reply direction, PAC->PNS */ - { .src = { .ip = master->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip, - .u = { .gre = { .key = callid } } - }, - .dst = { .ip = master->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip, - .u = { .gre = { .key = peer_callid } }, - .protonum = IPPROTO_GRE - }, - } - }; struct ip_conntrack_expect *exp_orig, *exp_reply; int ret = 1; - exp_orig = ip_conntrack_expect_alloc(master); + exp_orig = ip_conntrack_expect_alloc(ct); if (exp_orig == NULL) goto out; - exp_reply = ip_conntrack_expect_alloc(master); + exp_reply = ip_conntrack_expect_alloc(ct); if (exp_reply == NULL) goto out_put_orig; - memcpy(&exp_orig->tuple, &exp_tuples[0], sizeof(exp_orig->tuple)); + /* original direction, PNS->PAC */ + exp_orig->tuple.src.ip = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip; + exp_orig->tuple.src.u.gre.key = peer_callid; + exp_orig->tuple.dst.ip = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip; + exp_orig->tuple.dst.u.gre.key = callid; + exp_orig->tuple.dst.protonum = IPPROTO_GRE; exp_orig->mask.src.ip = 0xffffffff; exp_orig->mask.src.u.all = 0; - exp_orig->mask.dst.u.all = 0; exp_orig->mask.dst.u.gre.key = htons(0xffff); exp_orig->mask.dst.ip = 0xffffffff; exp_orig->mask.dst.protonum = 0xff; - - exp_orig->master = master; + + exp_orig->master = ct; exp_orig->expectfn = pptp_expectfn; exp_orig->flags = 0; /* both expectations are identical apart from tuple */ memcpy(exp_reply, exp_orig, sizeof(*exp_reply)); - memcpy(&exp_reply->tuple, &exp_tuples[1], sizeof(exp_reply->tuple)); - if (ip_nat_pptp_hook_exp_gre) - ret = ip_nat_pptp_hook_exp_gre(exp_orig, exp_reply); - else { - - DEBUGP("calling expect_related PNS->PAC"); - DUMP_TUPLE(&exp_orig->tuple); - - if (ip_conntrack_expect_related(exp_orig) != 0) { - DEBUGP("cannot expect_related()\n"); - goto out_put_both; - } + /* reply direction, PAC->PNS */ + exp_reply->tuple.src.ip = ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip; + exp_reply->tuple.src.u.gre.key = callid; + exp_reply->tuple.dst.ip = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip; + exp_reply->tuple.dst.u.gre.key = peer_callid; + exp_reply->tuple.dst.protonum = IPPROTO_GRE; - DEBUGP("calling expect_related PAC->PNS"); - DUMP_TUPLE(&exp_reply->tuple); - - if (ip_conntrack_expect_related(exp_reply) != 0) { - DEBUGP("cannot expect_related()\n"); - goto out_unexpect_orig; - } - - /* Add GRE keymap entries */ - if (ip_ct_gre_keymap_add(master, &exp_reply->tuple, 0) != 0) { - DEBUGP("cannot keymap_add() exp\n"); - goto out_unexpect_both; - } - - invert_tuplepr(&inv_tuple, &exp_reply->tuple); - if (ip_ct_gre_keymap_add(master, &inv_tuple, 1) != 0) { - ip_ct_gre_keymap_destroy(master); - DEBUGP("cannot keymap_add() exp_inv\n"); - goto out_unexpect_both; - } - ret = 0; + if (ip_nat_pptp_hook_exp_gre) + ip_nat_pptp_hook_exp_gre(exp_orig, exp_reply); + if (ip_conntrack_expect_related(exp_orig) != 0) + goto out_put_both; + if (ip_conntrack_expect_related(exp_reply) != 0) + goto out_unexpect_orig; + + /* Add GRE keymap entries */ + if (ip_ct_gre_keymap_add(ct, &exp_orig->tuple, 0) != 0) + goto out_unexpect_both; + if (ip_ct_gre_keymap_add(ct, &exp_reply->tuple, 1) != 0) { + ip_ct_gre_keymap_destroy(ct); + goto out_unexpect_both; } + ret = 0; out_put_both: ip_conntrack_expect_put(exp_reply); @@ -322,73 +292,36 @@ out_unexpect_orig: goto out_put_both; } -static inline int +static inline int pptp_inbound_pkt(struct sk_buff **pskb, - struct tcphdr *tcph, - unsigned int nexthdr_off, - unsigned int datalen, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq, + unsigned int reqlen, struct ip_conntrack *ct, enum ip_conntrack_info ctinfo) { - struct PptpControlHeader _ctlh, *ctlh; - unsigned int reqlen; - union pptp_ctrl_union _pptpReq, *pptpReq; struct ip_ct_pptp_master *info = &ct->help.ct_pptp_info; u_int16_t msg; - __be16 *cid, *pcid; - u_int32_t seq; - - ctlh = skb_header_pointer(*pskb, nexthdr_off, sizeof(_ctlh), &_ctlh); - if (!ctlh) { - DEBUGP("error during skb_header_pointer\n"); - return NF_ACCEPT; - } - nexthdr_off += sizeof(_ctlh); - datalen -= sizeof(_ctlh); - - reqlen = datalen; - if (reqlen > sizeof(*pptpReq)) - reqlen = sizeof(*pptpReq); - pptpReq = skb_header_pointer(*pskb, nexthdr_off, reqlen, &_pptpReq); - if (!pptpReq) { - DEBUGP("error during skb_header_pointer\n"); - return NF_ACCEPT; - } + __be16 cid = 0, pcid = 0; msg = ntohs(ctlh->messageType); DEBUGP("inbound control message %s\n", pptp_msg_name[msg]); switch (msg) { case PPTP_START_SESSION_REPLY: - if (reqlen < sizeof(_pptpReq.srep)) { - DEBUGP("%s: short packet\n", pptp_msg_name[msg]); - break; - } - /* server confirms new control session */ - if (info->sstate < PPTP_SESSION_REQUESTED) { - DEBUGP("%s without START_SESS_REQUEST\n", - pptp_msg_name[msg]); - break; - } + if (info->sstate < PPTP_SESSION_REQUESTED) + goto invalid; if (pptpReq->srep.resultCode == PPTP_START_OK) info->sstate = PPTP_SESSION_CONFIRMED; - else + else info->sstate = PPTP_SESSION_ERROR; break; case PPTP_STOP_SESSION_REPLY: - if (reqlen < sizeof(_pptpReq.strep)) { - DEBUGP("%s: short packet\n", pptp_msg_name[msg]); - break; - } - /* server confirms end of control session */ - if (info->sstate > PPTP_SESSION_STOPREQ) { - DEBUGP("%s without STOP_SESS_REQUEST\n", - pptp_msg_name[msg]); - break; - } + if (info->sstate > PPTP_SESSION_STOPREQ) + goto invalid; if (pptpReq->strep.resultCode == PPTP_STOP_OK) info->sstate = PPTP_SESSION_NONE; else @@ -396,116 +329,64 @@ pptp_inbound_pkt(struct sk_buff **pskb, break; case PPTP_OUT_CALL_REPLY: - if (reqlen < sizeof(_pptpReq.ocack)) { - DEBUGP("%s: short packet\n", pptp_msg_name[msg]); - break; - } - /* server accepted call, we now expect GRE frames */ - if (info->sstate != PPTP_SESSION_CONFIRMED) { - DEBUGP("%s but no session\n", pptp_msg_name[msg]); - break; - } + if (info->sstate != PPTP_SESSION_CONFIRMED) + goto invalid; if (info->cstate != PPTP_CALL_OUT_REQ && - info->cstate != PPTP_CALL_OUT_CONF) { - DEBUGP("%s without OUTCALL_REQ\n", pptp_msg_name[msg]); - break; - } - if (pptpReq->ocack.resultCode != PPTP_OUTCALL_CONNECT) { + info->cstate != PPTP_CALL_OUT_CONF) + goto invalid; + + cid = pptpReq->ocack.callID; + pcid = pptpReq->ocack.peersCallID; + if (info->pns_call_id != pcid) + goto invalid; + DEBUGP("%s, CID=%X, PCID=%X\n", pptp_msg_name[msg], + ntohs(cid), ntohs(pcid)); + + if (pptpReq->ocack.resultCode == PPTP_OUTCALL_CONNECT) { + info->cstate = PPTP_CALL_OUT_CONF; + info->pac_call_id = cid; + exp_gre(ct, cid, pcid); + } else info->cstate = PPTP_CALL_NONE; - break; - } - - cid = &pptpReq->ocack.callID; - pcid = &pptpReq->ocack.peersCallID; - - info->pac_call_id = ntohs(*cid); - - if (htons(info->pns_call_id) != *pcid) { - DEBUGP("%s for unknown callid %u\n", - pptp_msg_name[msg], ntohs(*pcid)); - break; - } - - DEBUGP("%s, CID=%X, PCID=%X\n", pptp_msg_name[msg], - ntohs(*cid), ntohs(*pcid)); - - info->cstate = PPTP_CALL_OUT_CONF; - - seq = ntohl(tcph->seq) + sizeof(struct pptp_pkt_hdr) - + sizeof(struct PptpControlHeader) - + ((void *)pcid - (void *)pptpReq); - - if (exp_gre(ct, seq, *cid, *pcid) != 0) - printk("ip_conntrack_pptp: error during exp_gre\n"); break; case PPTP_IN_CALL_REQUEST: - if (reqlen < sizeof(_pptpReq.icack)) { - DEBUGP("%s: short packet\n", pptp_msg_name[msg]); - break; - } - /* server tells us about incoming call request */ - if (info->sstate != PPTP_SESSION_CONFIRMED) { - DEBUGP("%s but no session\n", pptp_msg_name[msg]); - break; - } - pcid = &pptpReq->icack.peersCallID; - DEBUGP("%s, PCID=%X\n", pptp_msg_name[msg], ntohs(*pcid)); + if (info->sstate != PPTP_SESSION_CONFIRMED) + goto invalid; + + cid = pptpReq->icreq.callID; + DEBUGP("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid)); info->cstate = PPTP_CALL_IN_REQ; - info->pac_call_id = ntohs(*pcid); + info->pac_call_id = cid; break; case PPTP_IN_CALL_CONNECT: - if (reqlen < sizeof(_pptpReq.iccon)) { - DEBUGP("%s: short packet\n", pptp_msg_name[msg]); - break; - } - /* server tells us about incoming call established */ - if (info->sstate != PPTP_SESSION_CONFIRMED) { - DEBUGP("%s but no session\n", pptp_msg_name[msg]); - break; - } - if (info->cstate != PPTP_CALL_IN_REP - && info->cstate != PPTP_CALL_IN_CONF) { - DEBUGP("%s but never sent IN_CALL_REPLY\n", - pptp_msg_name[msg]); - break; - } + if (info->sstate != PPTP_SESSION_CONFIRMED) + goto invalid; + if (info->cstate != PPTP_CALL_IN_REP && + info->cstate != PPTP_CALL_IN_CONF) + goto invalid; - pcid = &pptpReq->iccon.peersCallID; - cid = &info->pac_call_id; + pcid = pptpReq->iccon.peersCallID; + cid = info->pac_call_id; - if (info->pns_call_id != ntohs(*pcid)) { - DEBUGP("%s for unknown CallID %u\n", - pptp_msg_name[msg], ntohs(*pcid)); - break; - } + if (info->pns_call_id != pcid) + goto invalid; - DEBUGP("%s, PCID=%X\n", pptp_msg_name[msg], ntohs(*pcid)); + DEBUGP("%s, PCID=%X\n", pptp_msg_name[msg], ntohs(pcid)); info->cstate = PPTP_CALL_IN_CONF; /* we expect a GRE connection from PAC to PNS */ - seq = ntohl(tcph->seq) + sizeof(struct pptp_pkt_hdr) - + sizeof(struct PptpControlHeader) - + ((void *)pcid - (void *)pptpReq); - - if (exp_gre(ct, seq, *cid, *pcid) != 0) - printk("ip_conntrack_pptp: error during exp_gre\n"); - + exp_gre(ct, cid, pcid); break; case PPTP_CALL_DISCONNECT_NOTIFY: - if (reqlen < sizeof(_pptpReq.disc)) { - DEBUGP("%s: short packet\n", pptp_msg_name[msg]); - break; - } - /* server confirms disconnect */ - cid = &pptpReq->disc.callID; - DEBUGP("%s, CID=%X\n", pptp_msg_name[msg], ntohs(*cid)); + cid = pptpReq->disc.callID; + DEBUGP("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid)); info->cstate = PPTP_CALL_NONE; /* untrack this call id, unexpect GRE packets */ @@ -513,54 +394,39 @@ pptp_inbound_pkt(struct sk_buff **pskb, break; case PPTP_WAN_ERROR_NOTIFY: - break; - case PPTP_ECHO_REQUEST: case PPTP_ECHO_REPLY: /* I don't have to explain these ;) */ break; default: - DEBUGP("invalid %s (TY=%d)\n", (msg <= PPTP_MSG_MAX) - ? pptp_msg_name[msg]:pptp_msg_name[0], msg); - break; + goto invalid; } - if (ip_nat_pptp_hook_inbound) return ip_nat_pptp_hook_inbound(pskb, ct, ctinfo, ctlh, pptpReq); - return NF_ACCEPT; +invalid: + DEBUGP("invalid %s: type=%d cid=%u pcid=%u " + "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n", + msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0], + msg, ntohs(cid), ntohs(pcid), info->cstate, info->sstate, + ntohs(info->pns_call_id), ntohs(info->pac_call_id)); + return NF_ACCEPT; } static inline int pptp_outbound_pkt(struct sk_buff **pskb, - struct tcphdr *tcph, - unsigned int nexthdr_off, - unsigned int datalen, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq, + unsigned int reqlen, struct ip_conntrack *ct, enum ip_conntrack_info ctinfo) { - struct PptpControlHeader _ctlh, *ctlh; - unsigned int reqlen; - union pptp_ctrl_union _pptpReq, *pptpReq; struct ip_ct_pptp_master *info = &ct->help.ct_pptp_info; u_int16_t msg; - __be16 *cid, *pcid; - - ctlh = skb_header_pointer(*pskb, nexthdr_off, sizeof(_ctlh), &_ctlh); - if (!ctlh) - return NF_ACCEPT; - nexthdr_off += sizeof(_ctlh); - datalen -= sizeof(_ctlh); - - reqlen = datalen; - if (reqlen > sizeof(*pptpReq)) - reqlen = sizeof(*pptpReq); - pptpReq = skb_header_pointer(*pskb, nexthdr_off, reqlen, &_pptpReq); - if (!pptpReq) - return NF_ACCEPT; + __be16 cid = 0, pcid = 0; msg = ntohs(ctlh->messageType); DEBUGP("outbound control message %s\n", pptp_msg_name[msg]); @@ -568,10 +434,8 @@ pptp_outbound_pkt(struct sk_buff **pskb, switch (msg) { case PPTP_START_SESSION_REQUEST: /* client requests for new control session */ - if (info->sstate != PPTP_SESSION_NONE) { - DEBUGP("%s but we already have one", - pptp_msg_name[msg]); - } + if (info->sstate != PPTP_SESSION_NONE) + goto invalid; info->sstate = PPTP_SESSION_REQUESTED; break; case PPTP_STOP_SESSION_REQUEST: @@ -580,123 +444,115 @@ pptp_outbound_pkt(struct sk_buff **pskb, break; case PPTP_OUT_CALL_REQUEST: - if (reqlen < sizeof(_pptpReq.ocreq)) { - DEBUGP("%s: short packet\n", pptp_msg_name[msg]); - /* FIXME: break; */ - } - /* client initiating connection to server */ - if (info->sstate != PPTP_SESSION_CONFIRMED) { - DEBUGP("%s but no session\n", - pptp_msg_name[msg]); - break; - } + if (info->sstate != PPTP_SESSION_CONFIRMED) + goto invalid; info->cstate = PPTP_CALL_OUT_REQ; /* track PNS call id */ - cid = &pptpReq->ocreq.callID; - DEBUGP("%s, CID=%X\n", pptp_msg_name[msg], ntohs(*cid)); - info->pns_call_id = ntohs(*cid); + cid = pptpReq->ocreq.callID; + DEBUGP("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid)); + info->pns_call_id = cid; break; case PPTP_IN_CALL_REPLY: - if (reqlen < sizeof(_pptpReq.icack)) { - DEBUGP("%s: short packet\n", pptp_msg_name[msg]); - break; - } - /* client answers incoming call */ - if (info->cstate != PPTP_CALL_IN_REQ - && info->cstate != PPTP_CALL_IN_REP) { - DEBUGP("%s without incall_req\n", - pptp_msg_name[msg]); - break; - } - if (pptpReq->icack.resultCode != PPTP_INCALL_ACCEPT) { + if (info->cstate != PPTP_CALL_IN_REQ && + info->cstate != PPTP_CALL_IN_REP) + goto invalid; + + cid = pptpReq->icack.callID; + pcid = pptpReq->icack.peersCallID; + if (info->pac_call_id != pcid) + goto invalid; + DEBUGP("%s, CID=%X PCID=%X\n", pptp_msg_name[msg], + ntohs(cid), ntohs(pcid)); + + if (pptpReq->icack.resultCode == PPTP_INCALL_ACCEPT) { + /* part two of the three-way handshake */ + info->cstate = PPTP_CALL_IN_REP; + info->pns_call_id = cid; + } else info->cstate = PPTP_CALL_NONE; - break; - } - pcid = &pptpReq->icack.peersCallID; - if (info->pac_call_id != ntohs(*pcid)) { - DEBUGP("%s for unknown call %u\n", - pptp_msg_name[msg], ntohs(*pcid)); - break; - } - DEBUGP("%s, CID=%X\n", pptp_msg_name[msg], ntohs(*pcid)); - /* part two of the three-way handshake */ - info->cstate = PPTP_CALL_IN_REP; - info->pns_call_id = ntohs(pptpReq->icack.callID); break; case PPTP_CALL_CLEAR_REQUEST: /* client requests hangup of call */ - if (info->sstate != PPTP_SESSION_CONFIRMED) { - DEBUGP("CLEAR_CALL but no session\n"); - break; - } + if (info->sstate != PPTP_SESSION_CONFIRMED) + goto invalid; /* FUTURE: iterate over all calls and check if * call ID is valid. We don't do this without newnat, * because we only know about last call */ info->cstate = PPTP_CALL_CLEAR_REQ; break; case PPTP_SET_LINK_INFO: - break; case PPTP_ECHO_REQUEST: case PPTP_ECHO_REPLY: /* I don't have to explain these ;) */ break; default: - DEBUGP("invalid %s (TY=%d)\n", (msg <= PPTP_MSG_MAX)? - pptp_msg_name[msg]:pptp_msg_name[0], msg); - /* unknown: no need to create GRE masq table entry */ - break; + goto invalid; } - + if (ip_nat_pptp_hook_outbound) return ip_nat_pptp_hook_outbound(pskb, ct, ctinfo, ctlh, pptpReq); + return NF_ACCEPT; +invalid: + DEBUGP("invalid %s: type=%d cid=%u pcid=%u " + "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n", + msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0], + msg, ntohs(cid), ntohs(pcid), info->cstate, info->sstate, + ntohs(info->pns_call_id), ntohs(info->pac_call_id)); return NF_ACCEPT; } +static const unsigned int pptp_msg_size[] = { + [PPTP_START_SESSION_REQUEST] = sizeof(struct PptpStartSessionRequest), + [PPTP_START_SESSION_REPLY] = sizeof(struct PptpStartSessionReply), + [PPTP_STOP_SESSION_REQUEST] = sizeof(struct PptpStopSessionRequest), + [PPTP_STOP_SESSION_REPLY] = sizeof(struct PptpStopSessionReply), + [PPTP_OUT_CALL_REQUEST] = sizeof(struct PptpOutCallRequest), + [PPTP_OUT_CALL_REPLY] = sizeof(struct PptpOutCallReply), + [PPTP_IN_CALL_REQUEST] = sizeof(struct PptpInCallRequest), + [PPTP_IN_CALL_REPLY] = sizeof(struct PptpInCallReply), + [PPTP_IN_CALL_CONNECT] = sizeof(struct PptpInCallConnected), + [PPTP_CALL_CLEAR_REQUEST] = sizeof(struct PptpClearCallRequest), + [PPTP_CALL_DISCONNECT_NOTIFY] = sizeof(struct PptpCallDisconnectNotify), + [PPTP_WAN_ERROR_NOTIFY] = sizeof(struct PptpWanErrorNotify), + [PPTP_SET_LINK_INFO] = sizeof(struct PptpSetLinkInfo), +}; /* track caller id inside control connection, call expect_related */ -static int +static int conntrack_pptp_help(struct sk_buff **pskb, struct ip_conntrack *ct, enum ip_conntrack_info ctinfo) { - struct pptp_pkt_hdr _pptph, *pptph; - struct tcphdr _tcph, *tcph; - u_int32_t tcplen = (*pskb)->len - (*pskb)->nh.iph->ihl * 4; - u_int32_t datalen; int dir = CTINFO2DIR(ctinfo); struct ip_ct_pptp_master *info = &ct->help.ct_pptp_info; - unsigned int nexthdr_off; - + struct tcphdr _tcph, *tcph; + struct pptp_pkt_hdr _pptph, *pptph; + struct PptpControlHeader _ctlh, *ctlh; + union pptp_ctrl_union _pptpReq, *pptpReq; + unsigned int tcplen = (*pskb)->len - (*pskb)->nh.iph->ihl * 4; + unsigned int datalen, reqlen, nexthdr_off; int oldsstate, oldcstate; int ret; + u_int16_t msg; /* don't do any tracking before tcp handshake complete */ - if (ctinfo != IP_CT_ESTABLISHED + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED+IP_CT_IS_REPLY) { DEBUGP("ctinfo = %u, skipping\n", ctinfo); return NF_ACCEPT; } - + nexthdr_off = (*pskb)->nh.iph->ihl*4; tcph = skb_header_pointer(*pskb, nexthdr_off, sizeof(_tcph), &_tcph); BUG_ON(!tcph); nexthdr_off += tcph->doff * 4; datalen = tcplen - tcph->doff * 4; - if (tcph->fin || tcph->rst) { - DEBUGP("RST/FIN received, timeouting GRE\n"); - /* can't do this after real newnat */ - info->cstate = PPTP_CALL_NONE; - - /* untrack this call id, unexpect GRE packets */ - pptp_destroy_siblings(ct); - } - pptph = skb_header_pointer(*pskb, nexthdr_off, sizeof(_pptph), &_pptph); if (!pptph) { DEBUGP("no full PPTP header, can't track\n"); @@ -712,6 +568,23 @@ conntrack_pptp_help(struct sk_buff **pskb, return NF_ACCEPT; } + ctlh = skb_header_pointer(*pskb, nexthdr_off, sizeof(_ctlh), &_ctlh); + if (!ctlh) + return NF_ACCEPT; + nexthdr_off += sizeof(_ctlh); + datalen -= sizeof(_ctlh); + + reqlen = datalen; + msg = ntohs(ctlh->messageType); + if (msg > 0 && msg <= PPTP_MSG_MAX && reqlen < pptp_msg_size[msg]) + return NF_ACCEPT; + if (reqlen > sizeof(*pptpReq)) + reqlen = sizeof(*pptpReq); + + pptpReq = skb_header_pointer(*pskb, nexthdr_off, reqlen, &_pptpReq); + if (!pptpReq) + return NF_ACCEPT; + oldsstate = info->sstate; oldcstate = info->cstate; @@ -721,11 +594,11 @@ conntrack_pptp_help(struct sk_buff **pskb, * established from PNS->PAC. However, RFC makes no guarantee */ if (dir == IP_CT_DIR_ORIGINAL) /* client -> server (PNS -> PAC) */ - ret = pptp_outbound_pkt(pskb, tcph, nexthdr_off, datalen, ct, + ret = pptp_outbound_pkt(pskb, ctlh, pptpReq, reqlen, ct, ctinfo); else /* server -> client (PAC -> PNS) */ - ret = pptp_inbound_pkt(pskb, tcph, nexthdr_off, datalen, ct, + ret = pptp_inbound_pkt(pskb, ctlh, pptpReq, reqlen, ct, ctinfo); DEBUGP("sstate: %d->%d, cstate: %d->%d\n", oldsstate, info->sstate, oldcstate, info->cstate); @@ -735,30 +608,31 @@ conntrack_pptp_help(struct sk_buff **pskb, } /* control protocol helper */ -static struct ip_conntrack_helper pptp = { +static struct ip_conntrack_helper pptp = { .list = { NULL, NULL }, - .name = "pptp", + .name = "pptp", .me = THIS_MODULE, .max_expected = 2, .timeout = 5 * 60, - .tuple = { .src = { .ip = 0, - .u = { .tcp = { .port = - __constant_htons(PPTP_CONTROL_PORT) } } - }, - .dst = { .ip = 0, + .tuple = { .src = { .ip = 0, + .u = { .tcp = { .port = + __constant_htons(PPTP_CONTROL_PORT) } } + }, + .dst = { .ip = 0, .u = { .all = 0 }, .protonum = IPPROTO_TCP - } + } }, - .mask = { .src = { .ip = 0, - .u = { .tcp = { .port = __constant_htons(0xffff) } } - }, - .dst = { .ip = 0, + .mask = { .src = { .ip = 0, + .u = { .tcp = { .port = __constant_htons(0xffff) } } + }, + .dst = { .ip = 0, .u = { .all = 0 }, - .protonum = 0xff - } + .protonum = 0xff + } }, - .help = conntrack_pptp_help + .help = conntrack_pptp_help, + .destroy = pptp_destroy_siblings, }; extern void ip_ct_proto_gre_fini(void); @@ -768,7 +642,7 @@ extern int __init ip_ct_proto_gre_init(void); static int __init ip_conntrack_helper_pptp_init(void) { int retcode; - + retcode = ip_ct_proto_gre_init(); if (retcode < 0) return retcode; diff --git a/net/ipv4/netfilter/ip_conntrack_netbios_ns.c b/net/ipv4/netfilter/ip_conntrack_netbios_ns.c index a566a81325b..3d0b438783d 100644 --- a/net/ipv4/netfilter/ip_conntrack_netbios_ns.c +++ b/net/ipv4/netfilter/ip_conntrack_netbios_ns.c @@ -21,6 +21,7 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> +#include <linux/if_addr.h> #include <linux/in.h> #include <linux/ip.h> #include <net/route.h> diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c index 0d4cc92391f..52eddea27e9 100644 --- a/net/ipv4/netfilter/ip_conntrack_netlink.c +++ b/net/ipv4/netfilter/ip_conntrack_netlink.c @@ -329,11 +329,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, /* dump everything */ events = ~0UL; group = NFNLGRP_CONNTRACK_NEW; - } else if (events & (IPCT_STATUS | - IPCT_PROTOINFO | - IPCT_HELPER | - IPCT_HELPINFO | - IPCT_NATINFO)) { + } else if (events & (IPCT_STATUS | IPCT_PROTOINFO)) { type = IPCTNL_MSG_CT_NEW; group = NFNLGRP_CONNTRACK_UPDATE; } else @@ -385,6 +381,10 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0) goto nfattr_failure; + if (events & IPCT_MARK + && ctnetlink_dump_mark(skb, ct) < 0) + goto nfattr_failure; + nlh->nlmsg_len = skb->tail - b; nfnetlink_send(skb, 0, group, 0); return NOTIFY_DONE; @@ -436,6 +436,11 @@ restart: cb->args[1] = (unsigned long)ct; goto out; } +#ifdef CONFIG_NF_CT_ACCT + if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == + IPCTNL_MSG_CT_GET_CTRZERO) + memset(&ct->counters, 0, sizeof(ct->counters)); +#endif } if (cb->args[1]) { cb->args[1] = 0; @@ -451,46 +456,6 @@ out: return skb->len; } -#ifdef CONFIG_IP_NF_CT_ACCT -static int -ctnetlink_dump_table_w(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct ip_conntrack *ct = NULL; - struct ip_conntrack_tuple_hash *h; - struct list_head *i; - u_int32_t *id = (u_int32_t *) &cb->args[1]; - - DEBUGP("entered %s, last bucket=%u id=%u\n", __FUNCTION__, - cb->args[0], *id); - - write_lock_bh(&ip_conntrack_lock); - for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++, *id = 0) { - list_for_each_prev(i, &ip_conntrack_hash[cb->args[0]]) { - h = (struct ip_conntrack_tuple_hash *) i; - if (DIRECTION(h) != IP_CT_DIR_ORIGINAL) - continue; - ct = tuplehash_to_ctrack(h); - if (ct->id <= *id) - continue; - if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - IPCTNL_MSG_CT_NEW, - 1, ct) < 0) - goto out; - *id = ct->id; - - memset(&ct->counters, 0, sizeof(ct->counters)); - } - } -out: - write_unlock_bh(&ip_conntrack_lock); - - DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id); - - return skb->len; -} -#endif - static const size_t cta_min_ip[CTA_IP_MAX] = { [CTA_IP_V4_SRC-1] = sizeof(u_int32_t), [CTA_IP_V4_DST-1] = sizeof(u_int32_t), @@ -775,22 +740,14 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, if (msg->nfgen_family != AF_INET) return -EAFNOSUPPORT; - if (NFNL_MSG_TYPE(nlh->nlmsg_type) == - IPCTNL_MSG_CT_GET_CTRZERO) { -#ifdef CONFIG_IP_NF_CT_ACCT - if ((*errp = netlink_dump_start(ctnl, skb, nlh, - ctnetlink_dump_table_w, - ctnetlink_done)) != 0) - return -EINVAL; -#else +#ifndef CONFIG_IP_NF_CT_ACCT + if (NFNL_MSG_TYPE(nlh->nlmsg_type) == IPCTNL_MSG_CT_GET_CTRZERO) return -ENOTSUPP; #endif - } else { - if ((*errp = netlink_dump_start(ctnl, skb, nlh, - ctnetlink_dump_table, - ctnetlink_done)) != 0) + if ((*errp = netlink_dump_start(ctnl, skb, nlh, + ctnetlink_dump_table, + ctnetlink_done)) != 0) return -EINVAL; - } rlen = NLMSG_ALIGN(nlh->nlmsg_len); if (rlen > skb->len) @@ -1253,6 +1210,9 @@ static int ctnetlink_expect_event(struct notifier_block *this, } else return NOTIFY_DONE; + if (!nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW)) + return NOTIFY_DONE; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb) return NOTIFY_DONE; diff --git a/net/ipv4/netfilter/ip_conntrack_proto_generic.c b/net/ipv4/netfilter/ip_conntrack_proto_generic.c index f891308b5e4..36f2b5e5d80 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_generic.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_generic.c @@ -12,7 +12,7 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> -unsigned int ip_ct_generic_timeout = 600*HZ; +unsigned int ip_ct_generic_timeout __read_mostly = 600*HZ; static int generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, diff --git a/net/ipv4/netfilter/ip_conntrack_proto_gre.c b/net/ipv4/netfilter/ip_conntrack_proto_gre.c index 4ee016c427b..5fe026f467d 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_gre.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_gre.c @@ -1,15 +1,15 @@ /* - * ip_conntrack_proto_gre.c - Version 3.0 + * ip_conntrack_proto_gre.c - Version 3.0 * * Connection tracking protocol helper module for GRE. * * GRE is a generic encapsulation protocol, which is generally not very * suited for NAT, as it has no protocol-specific part as port numbers. * - * It has an optional key field, which may help us distinguishing two + * It has an optional key field, which may help us distinguishing two * connections between the same two hosts. * - * GRE is defined in RFC 1701 and RFC 1702, as well as RFC 2784 + * GRE is defined in RFC 1701 and RFC 1702, as well as RFC 2784 * * PPTP is built on top of a modified version of GRE, and has a mandatory * field called "CallID", which serves us for the same purpose as the key @@ -37,7 +37,6 @@ static DEFINE_RWLOCK(ip_ct_gre_lock); #define ASSERT_READ_LOCK(x) #define ASSERT_WRITE_LOCK(x) -#include <linux/netfilter_ipv4/listhelp.h> #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> #include <linux/netfilter_ipv4/ip_conntrack_helper.h> #include <linux/netfilter_ipv4/ip_conntrack_core.h> @@ -62,7 +61,7 @@ MODULE_DESCRIPTION("netfilter connection tracking protocol helper for GRE"); #define DEBUGP(x, args...) #define DUMP_TUPLE_GRE(x) #endif - + /* GRE KEYMAP HANDLING FUNCTIONS */ static LIST_HEAD(gre_keymap_list); @@ -82,12 +81,14 @@ static __be16 gre_keymap_lookup(struct ip_conntrack_tuple *t) __be16 key = 0; read_lock_bh(&ip_ct_gre_lock); - km = LIST_FIND(&gre_keymap_list, gre_key_cmpfn, - struct ip_ct_gre_keymap *, t); - if (km) - key = km->tuple.src.u.gre.key; + list_for_each_entry(km, &gre_keymap_list, list) { + if (gre_key_cmpfn(km, t)) { + key = km->tuple.src.u.gre.key; + break; + } + } read_unlock_bh(&ip_ct_gre_lock); - + DEBUGP("lookup src key 0x%x up key for ", key); DUMP_TUPLE_GRE(t); @@ -99,28 +100,25 @@ int ip_ct_gre_keymap_add(struct ip_conntrack *ct, struct ip_conntrack_tuple *t, int reply) { - struct ip_ct_gre_keymap **exist_km, *km, *old; + struct ip_ct_gre_keymap **exist_km, *km; if (!ct->helper || strcmp(ct->helper->name, "pptp")) { DEBUGP("refusing to add GRE keymap to non-pptp session\n"); return -1; } - if (!reply) + if (!reply) exist_km = &ct->help.ct_pptp_info.keymap_orig; else exist_km = &ct->help.ct_pptp_info.keymap_reply; if (*exist_km) { /* check whether it's a retransmission */ - old = LIST_FIND(&gre_keymap_list, gre_key_cmpfn, - struct ip_ct_gre_keymap *, t); - if (old == *exist_km) { - DEBUGP("retransmission\n"); - return 0; + list_for_each_entry(km, &gre_keymap_list, list) { + if (gre_key_cmpfn(km, t) && km == *exist_km) + return 0; } - - DEBUGP("trying to override keymap_%s for ct %p\n", + DEBUGP("trying to override keymap_%s for ct %p\n", reply? "reply":"orig", ct); return -EEXIST; } @@ -136,7 +134,7 @@ ip_ct_gre_keymap_add(struct ip_conntrack *ct, DUMP_TUPLE_GRE(&km->tuple); write_lock_bh(&ip_ct_gre_lock); - list_append(&gre_keymap_list, km); + list_add_tail(&km->list, &gre_keymap_list); write_unlock_bh(&ip_ct_gre_lock); return 0; @@ -154,7 +152,7 @@ void ip_ct_gre_keymap_destroy(struct ip_conntrack *ct) write_lock_bh(&ip_ct_gre_lock); if (ct->help.ct_pptp_info.keymap_orig) { - DEBUGP("removing %p from list\n", + DEBUGP("removing %p from list\n", ct->help.ct_pptp_info.keymap_orig); list_del(&ct->help.ct_pptp_info.keymap_orig->list); kfree(ct->help.ct_pptp_info.keymap_orig); @@ -222,7 +220,7 @@ static int gre_pkt_to_tuple(const struct sk_buff *skb, static int gre_print_tuple(struct seq_file *s, const struct ip_conntrack_tuple *tuple) { - return seq_printf(s, "srckey=0x%x dstkey=0x%x ", + return seq_printf(s, "srckey=0x%x dstkey=0x%x ", ntohs(tuple->src.u.gre.key), ntohs(tuple->dst.u.gre.key)); } @@ -252,14 +250,14 @@ static int gre_packet(struct ip_conntrack *ct, } else ip_ct_refresh_acct(ct, conntrackinfo, skb, ct->proto.gre.timeout); - + return NF_ACCEPT; } /* Called when a new connection for this protocol found. */ static int gre_new(struct ip_conntrack *ct, const struct sk_buff *skb) -{ +{ DEBUGP(": "); DUMP_TUPLE_GRE(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); @@ -285,9 +283,9 @@ static void gre_destroy(struct ip_conntrack *ct) } /* protocol helper struct */ -static struct ip_conntrack_protocol gre = { +static struct ip_conntrack_protocol gre = { .proto = IPPROTO_GRE, - .name = "gre", + .name = "gre", .pkt_to_tuple = gre_pkt_to_tuple, .invert_tuple = gre_invert_tuple, .print_tuple = gre_print_tuple, @@ -325,7 +323,7 @@ void ip_ct_proto_gre_fini(void) } write_unlock_bh(&ip_ct_gre_lock); - ip_conntrack_protocol_unregister(&gre); + ip_conntrack_protocol_unregister(&gre); } EXPORT_SYMBOL(ip_ct_gre_keymap_add); diff --git a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c index 23f1c504586..09c40ebe334 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c @@ -21,7 +21,7 @@ #include <linux/netfilter_ipv4/ip_conntrack_core.h> #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> -unsigned int ip_ct_icmp_timeout = 30*HZ; +unsigned int ip_ct_icmp_timeout __read_mostly = 30*HZ; #if 0 #define DEBUGP printk diff --git a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c index 2d3612cd5f1..b908a4842e1 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c @@ -58,13 +58,13 @@ static const char *sctp_conntrack_names[] = { #define HOURS * 60 MINS #define DAYS * 24 HOURS -static unsigned int ip_ct_sctp_timeout_closed = 10 SECS; -static unsigned int ip_ct_sctp_timeout_cookie_wait = 3 SECS; -static unsigned int ip_ct_sctp_timeout_cookie_echoed = 3 SECS; -static unsigned int ip_ct_sctp_timeout_established = 5 DAYS; -static unsigned int ip_ct_sctp_timeout_shutdown_sent = 300 SECS / 1000; -static unsigned int ip_ct_sctp_timeout_shutdown_recd = 300 SECS / 1000; -static unsigned int ip_ct_sctp_timeout_shutdown_ack_sent = 3 SECS; +static unsigned int ip_ct_sctp_timeout_closed __read_mostly = 10 SECS; +static unsigned int ip_ct_sctp_timeout_cookie_wait __read_mostly = 3 SECS; +static unsigned int ip_ct_sctp_timeout_cookie_echoed __read_mostly = 3 SECS; +static unsigned int ip_ct_sctp_timeout_established __read_mostly = 5 DAYS; +static unsigned int ip_ct_sctp_timeout_shutdown_sent __read_mostly = 300 SECS / 1000; +static unsigned int ip_ct_sctp_timeout_shutdown_recd __read_mostly = 300 SECS / 1000; +static unsigned int ip_ct_sctp_timeout_shutdown_ack_sent __read_mostly = 3 SECS; static const unsigned int * sctp_timeouts[] = { NULL, /* SCTP_CONNTRACK_NONE */ diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c index fb920e76ec1..03ae9a04cb3 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c @@ -48,19 +48,19 @@ static DEFINE_RWLOCK(tcp_lock); /* "Be conservative in what you do, be liberal in what you accept from others." If it's non-zero, we mark only out of window RST segments as INVALID. */ -int ip_ct_tcp_be_liberal = 0; +int ip_ct_tcp_be_liberal __read_mostly = 0; /* When connection is picked up from the middle, how many packets are required to pass in each direction when we assume we are in sync - if any side uses window scaling, we lost the game. If it is set to zero, we disable picking up already established connections. */ -int ip_ct_tcp_loose = 3; +int ip_ct_tcp_loose __read_mostly = 3; /* Max number of the retransmitted packets without receiving an (acceptable) ACK from the destination. If this number is reached, a shorter timer will be started. */ -int ip_ct_tcp_max_retrans = 3; +int ip_ct_tcp_max_retrans __read_mostly = 3; /* FIXME: Examine ipfilter's timeouts and conntrack transitions more closely. They're more complex. --RR */ @@ -83,19 +83,19 @@ static const char *tcp_conntrack_names[] = { #define HOURS * 60 MINS #define DAYS * 24 HOURS -unsigned int ip_ct_tcp_timeout_syn_sent = 2 MINS; -unsigned int ip_ct_tcp_timeout_syn_recv = 60 SECS; -unsigned int ip_ct_tcp_timeout_established = 5 DAYS; -unsigned int ip_ct_tcp_timeout_fin_wait = 2 MINS; -unsigned int ip_ct_tcp_timeout_close_wait = 60 SECS; -unsigned int ip_ct_tcp_timeout_last_ack = 30 SECS; -unsigned int ip_ct_tcp_timeout_time_wait = 2 MINS; -unsigned int ip_ct_tcp_timeout_close = 10 SECS; +unsigned int ip_ct_tcp_timeout_syn_sent __read_mostly = 2 MINS; +unsigned int ip_ct_tcp_timeout_syn_recv __read_mostly = 60 SECS; +unsigned int ip_ct_tcp_timeout_established __read_mostly = 5 DAYS; +unsigned int ip_ct_tcp_timeout_fin_wait __read_mostly = 2 MINS; +unsigned int ip_ct_tcp_timeout_close_wait __read_mostly = 60 SECS; +unsigned int ip_ct_tcp_timeout_last_ack __read_mostly = 30 SECS; +unsigned int ip_ct_tcp_timeout_time_wait __read_mostly = 2 MINS; +unsigned int ip_ct_tcp_timeout_close __read_mostly = 10 SECS; /* RFC1122 says the R2 limit should be at least 100 seconds. Linux uses 15 packets as limit, which corresponds to ~13-30min depending on RTO. */ -unsigned int ip_ct_tcp_timeout_max_retrans = 5 MINS; +unsigned int ip_ct_tcp_timeout_max_retrans __read_mostly = 5 MINS; static const unsigned int * tcp_timeouts[] = { NULL, /* TCP_CONNTRACK_NONE */ @@ -731,13 +731,15 @@ static int tcp_in_window(struct ip_ct_tcp *state, if (state->last_dir == dir && state->last_seq == seq && state->last_ack == ack - && state->last_end == end) + && state->last_end == end + && state->last_win == win) state->retrans++; else { state->last_dir = dir; state->last_seq = seq; state->last_ack = ack; state->last_end = end; + state->last_win = win; state->retrans = 0; } } @@ -865,8 +867,7 @@ static int tcp_error(struct sk_buff *skb, /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path - * because the semantic of CHECKSUM_HW is different there - * and moreover root might send raw packets. + * because it is assumed to be correct. */ /* FIXME: Source route IP option packets --RR */ if (ip_conntrack_checksum && hooknum == NF_IP_PRE_ROUTING && diff --git a/net/ipv4/netfilter/ip_conntrack_proto_udp.c b/net/ipv4/netfilter/ip_conntrack_proto_udp.c index 9b2c16b4d2f..d0e8a16970e 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_udp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_udp.c @@ -18,8 +18,8 @@ #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> -unsigned int ip_ct_udp_timeout = 30*HZ; -unsigned int ip_ct_udp_timeout_stream = 180*HZ; +unsigned int ip_ct_udp_timeout __read_mostly = 30*HZ; +unsigned int ip_ct_udp_timeout_stream __read_mostly = 180*HZ; static int udp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, @@ -117,8 +117,7 @@ static int udp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path - * because the semantic of CHECKSUM_HW is different there - * and moreover root might send raw packets. + * because the checksum is assumed to be correct. * FIXME: Source route IP option packets --RR */ if (ip_conntrack_checksum && hooknum == NF_IP_PRE_ROUTING && nf_ip_checksum(skb, hooknum, iph->ihl * 4, IPPROTO_UDP)) { diff --git a/net/ipv4/netfilter/ip_conntrack_sip.c b/net/ipv4/netfilter/ip_conntrack_sip.c index 4f222d6be00..2893e9c7485 100644 --- a/net/ipv4/netfilter/ip_conntrack_sip.c +++ b/net/ipv4/netfilter/ip_conntrack_sip.c @@ -8,7 +8,6 @@ * published by the Free Software Foundation. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/skbuff.h> diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c index 7a9fa04a467..02135756562 100644 --- a/net/ipv4/netfilter/ip_conntrack_standalone.c +++ b/net/ipv4/netfilter/ip_conntrack_standalone.c @@ -35,7 +35,6 @@ #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> #include <linux/netfilter_ipv4/ip_conntrack_core.h> #include <linux/netfilter_ipv4/ip_conntrack_helper.h> -#include <linux/netfilter_ipv4/listhelp.h> #if 0 #define DEBUGP printk @@ -534,7 +533,7 @@ static struct nf_hook_ops ip_conntrack_ops[] = { /* Sysctl support */ -int ip_conntrack_checksum = 1; +int ip_conntrack_checksum __read_mostly = 1; #ifdef CONFIG_SYSCTL @@ -563,7 +562,7 @@ extern unsigned int ip_ct_udp_timeout_stream; /* From ip_conntrack_proto_icmp.c */ extern unsigned int ip_ct_icmp_timeout; -/* From ip_conntrack_proto_icmp.c */ +/* From ip_conntrack_proto_generic.c */ extern unsigned int ip_ct_generic_timeout; /* Log invalid packets of a given protocol */ diff --git a/net/ipv4/netfilter/ip_nat_core.c b/net/ipv4/netfilter/ip_nat_core.c index 1741d555ad0..71f3e09cbc8 100644 --- a/net/ipv4/netfilter/ip_nat_core.c +++ b/net/ipv4/netfilter/ip_nat_core.c @@ -22,9 +22,6 @@ #include <linux/udp.h> #include <linux/jhash.h> -#define ASSERT_READ_LOCK(x) -#define ASSERT_WRITE_LOCK(x) - #include <linux/netfilter_ipv4/ip_conntrack.h> #include <linux/netfilter_ipv4/ip_conntrack_core.h> #include <linux/netfilter_ipv4/ip_conntrack_protocol.h> @@ -33,7 +30,6 @@ #include <linux/netfilter_ipv4/ip_nat_core.h> #include <linux/netfilter_ipv4/ip_nat_helper.h> #include <linux/netfilter_ipv4/ip_conntrack_helper.h> -#include <linux/netfilter_ipv4/listhelp.h> #if 0 #define DEBUGP printk @@ -101,18 +97,6 @@ static void ip_nat_cleanup_conntrack(struct ip_conntrack *conn) write_unlock_bh(&ip_nat_lock); } -/* We do checksum mangling, so if they were wrong before they're still - * wrong. Also works for incomplete packets (eg. ICMP dest - * unreachables.) */ -u_int16_t -ip_nat_cheat_check(u_int32_t oldvalinv, u_int32_t newval, u_int16_t oldcheck) -{ - u_int32_t diffs[] = { oldvalinv, newval }; - return csum_fold(csum_partial((char *)diffs, sizeof(diffs), - oldcheck^0xFFFF)); -} -EXPORT_SYMBOL(ip_nat_cheat_check); - /* Is this tuple already taken? (not by us) */ int ip_nat_used_tuple(const struct ip_conntrack_tuple *tuple, @@ -378,12 +362,12 @@ manip_pkt(u_int16_t proto, iph = (void *)(*pskb)->data + iphdroff; if (maniptype == IP_NAT_MANIP_SRC) { - iph->check = ip_nat_cheat_check(~iph->saddr, target->src.ip, - iph->check); + iph->check = nf_csum_update(~iph->saddr, target->src.ip, + iph->check); iph->saddr = target->src.ip; } else { - iph->check = ip_nat_cheat_check(~iph->daddr, target->dst.ip, - iph->check); + iph->check = nf_csum_update(~iph->daddr, target->dst.ip, + iph->check); iph->daddr = target->dst.ip; } return 1; @@ -423,10 +407,10 @@ unsigned int ip_nat_packet(struct ip_conntrack *ct, EXPORT_SYMBOL_GPL(ip_nat_packet); /* Dir is direction ICMP is coming from (opposite to packet it contains) */ -int ip_nat_icmp_reply_translation(struct sk_buff **pskb, - struct ip_conntrack *ct, - enum ip_nat_manip_type manip, - enum ip_conntrack_dir dir) +int ip_nat_icmp_reply_translation(struct ip_conntrack *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum, + struct sk_buff **pskb) { struct { struct icmphdr icmp; @@ -434,7 +418,9 @@ int ip_nat_icmp_reply_translation(struct sk_buff **pskb, } *inside; struct ip_conntrack_tuple inner, target; int hdrlen = (*pskb)->nh.iph->ihl * 4; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); unsigned long statusbit; + enum ip_nat_manip_type manip = HOOK2MANIP(hooknum); if (!skb_make_writable(pskb, hdrlen + sizeof(*inside))) return 0; @@ -443,12 +429,8 @@ int ip_nat_icmp_reply_translation(struct sk_buff **pskb, /* We're actually going to mangle it beyond trivial checksum adjustment, so make sure the current checksum is correct. */ - if ((*pskb)->ip_summed != CHECKSUM_UNNECESSARY) { - hdrlen = (*pskb)->nh.iph->ihl * 4; - if ((u16)csum_fold(skb_checksum(*pskb, hdrlen, - (*pskb)->len - hdrlen, 0))) - return 0; - } + if (nf_ip_checksum(*pskb, hooknum, hdrlen, 0)) + return 0; /* Must be RELATED */ IP_NF_ASSERT((*pskb)->nfctinfo == IP_CT_RELATED || @@ -487,12 +469,14 @@ int ip_nat_icmp_reply_translation(struct sk_buff **pskb, !manip)) return 0; - /* Reloading "inside" here since manip_pkt inner. */ - inside = (void *)(*pskb)->data + (*pskb)->nh.iph->ihl*4; - inside->icmp.checksum = 0; - inside->icmp.checksum = csum_fold(skb_checksum(*pskb, hdrlen, - (*pskb)->len - hdrlen, - 0)); + if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { + /* Reloading "inside" here since manip_pkt inner. */ + inside = (void *)(*pskb)->data + (*pskb)->nh.iph->ihl*4; + inside->icmp.checksum = 0; + inside->icmp.checksum = csum_fold(skb_checksum(*pskb, hdrlen, + (*pskb)->len - hdrlen, + 0)); + } /* Change outer to look the reply to an incoming packet * (proto 0 means don't invert per-proto part). */ diff --git a/net/ipv4/netfilter/ip_nat_helper.c b/net/ipv4/netfilter/ip_nat_helper.c index cbcaa45370a..7f6a75984f6 100644 --- a/net/ipv4/netfilter/ip_nat_helper.c +++ b/net/ipv4/netfilter/ip_nat_helper.c @@ -27,16 +27,12 @@ #include <net/tcp.h> #include <net/udp.h> -#define ASSERT_READ_LOCK(x) -#define ASSERT_WRITE_LOCK(x) - #include <linux/netfilter_ipv4/ip_conntrack.h> #include <linux/netfilter_ipv4/ip_conntrack_helper.h> #include <linux/netfilter_ipv4/ip_nat.h> #include <linux/netfilter_ipv4/ip_nat_protocol.h> #include <linux/netfilter_ipv4/ip_nat_core.h> #include <linux/netfilter_ipv4/ip_nat_helper.h> -#include <linux/netfilter_ipv4/listhelp.h> #if 0 #define DEBUGP printk @@ -165,7 +161,7 @@ ip_nat_mangle_tcp_packet(struct sk_buff **pskb, { struct iphdr *iph; struct tcphdr *tcph; - int datalen; + int oldlen, datalen; if (!skb_make_writable(pskb, (*pskb)->len)) return 0; @@ -180,13 +176,22 @@ ip_nat_mangle_tcp_packet(struct sk_buff **pskb, iph = (*pskb)->nh.iph; tcph = (void *)iph + iph->ihl*4; + oldlen = (*pskb)->len - iph->ihl*4; mangle_contents(*pskb, iph->ihl*4 + tcph->doff*4, match_offset, match_len, rep_buffer, rep_len); datalen = (*pskb)->len - iph->ihl*4; - tcph->check = 0; - tcph->check = tcp_v4_check(tcph, datalen, iph->saddr, iph->daddr, - csum_partial((char *)tcph, datalen, 0)); + if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { + tcph->check = 0; + tcph->check = tcp_v4_check(tcph, datalen, + iph->saddr, iph->daddr, + csum_partial((char *)tcph, + datalen, 0)); + } else + tcph->check = nf_proto_csum_update(*pskb, + htons(oldlen) ^ 0xFFFF, + htons(datalen), + tcph->check, 1); if (rep_len != match_len) { set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); @@ -221,6 +226,7 @@ ip_nat_mangle_udp_packet(struct sk_buff **pskb, { struct iphdr *iph; struct udphdr *udph; + int datalen, oldlen; /* UDP helpers might accidentally mangle the wrong packet */ iph = (*pskb)->nh.iph; @@ -238,22 +244,32 @@ ip_nat_mangle_udp_packet(struct sk_buff **pskb, iph = (*pskb)->nh.iph; udph = (void *)iph + iph->ihl*4; + + oldlen = (*pskb)->len - iph->ihl*4; mangle_contents(*pskb, iph->ihl*4 + sizeof(*udph), match_offset, match_len, rep_buffer, rep_len); /* update the length of the UDP packet */ - udph->len = htons((*pskb)->len - iph->ihl*4); + datalen = (*pskb)->len - iph->ihl*4; + udph->len = htons(datalen); /* fix udp checksum if udp checksum was previously calculated */ - if (udph->check) { - int datalen = (*pskb)->len - iph->ihl * 4; + if (!udph->check && (*pskb)->ip_summed != CHECKSUM_PARTIAL) + return 1; + + if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { udph->check = 0; udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, IPPROTO_UDP, csum_partial((char *)udph, datalen, 0)); - } - + if (!udph->check) + udph->check = -1; + } else + udph->check = nf_proto_csum_update(*pskb, + htons(oldlen) ^ 0xFFFF, + htons(datalen), + udph->check, 1); return 1; } EXPORT_SYMBOL(ip_nat_mangle_udp_packet); @@ -293,11 +309,14 @@ sack_adjust(struct sk_buff *skb, ntohl(sack->start_seq), new_start_seq, ntohl(sack->end_seq), new_end_seq); - tcph->check = - ip_nat_cheat_check(~sack->start_seq, new_start_seq, - ip_nat_cheat_check(~sack->end_seq, - new_end_seq, - tcph->check)); + tcph->check = nf_proto_csum_update(skb, + ~sack->start_seq, + new_start_seq, + tcph->check, 0); + tcph->check = nf_proto_csum_update(skb, + ~sack->end_seq, + new_end_seq, + tcph->check, 0); sack->start_seq = new_start_seq; sack->end_seq = new_end_seq; sackoff += sizeof(*sack); @@ -381,10 +400,10 @@ ip_nat_seq_adjust(struct sk_buff **pskb, newack = ntohl(tcph->ack_seq) - other_way->offset_before; newack = htonl(newack); - tcph->check = ip_nat_cheat_check(~tcph->seq, newseq, - ip_nat_cheat_check(~tcph->ack_seq, - newack, - tcph->check)); + tcph->check = nf_proto_csum_update(*pskb, ~tcph->seq, newseq, + tcph->check, 0); + tcph->check = nf_proto_csum_update(*pskb, ~tcph->ack_seq, newack, + tcph->check, 0); DEBUGP("Adjusting sequence number from %u->%u, ack from %u->%u\n", ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), diff --git a/net/ipv4/netfilter/ip_nat_helper_pptp.c b/net/ipv4/netfilter/ip_nat_helper_pptp.c index 1d149964dc3..2ff57880712 100644 --- a/net/ipv4/netfilter/ip_nat_helper_pptp.c +++ b/net/ipv4/netfilter/ip_nat_helper_pptp.c @@ -32,7 +32,7 @@ * 2005-06-10 - Version 3.0 * - kernel >= 2.6.11 version, * funded by Oxcoda NetBox Blue (http://www.netboxblue.com/) - * + * */ #include <linux/module.h> @@ -85,19 +85,17 @@ static void pptp_nat_expected(struct ip_conntrack *ct, DEBUGP("we are PNS->PAC\n"); /* therefore, build tuple for PAC->PNS */ t.src.ip = master->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip; - t.src.u.gre.key = htons(master->help.ct_pptp_info.pac_call_id); + t.src.u.gre.key = master->help.ct_pptp_info.pac_call_id; t.dst.ip = master->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip; - t.dst.u.gre.key = htons(master->help.ct_pptp_info.pns_call_id); + t.dst.u.gre.key = master->help.ct_pptp_info.pns_call_id; t.dst.protonum = IPPROTO_GRE; } else { DEBUGP("we are PAC->PNS\n"); /* build tuple for PNS->PAC */ t.src.ip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip; - t.src.u.gre.key = - htons(master->nat.help.nat_pptp_info.pns_call_id); + t.src.u.gre.key = master->nat.help.nat_pptp_info.pns_call_id; t.dst.ip = master->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip; - t.dst.u.gre.key = - htons(master->nat.help.nat_pptp_info.pac_call_id); + t.dst.u.gre.key = master->nat.help.nat_pptp_info.pac_call_id; t.dst.protonum = IPPROTO_GRE; } @@ -149,51 +147,52 @@ pptp_outbound_pkt(struct sk_buff **pskb, { struct ip_ct_pptp_master *ct_pptp_info = &ct->help.ct_pptp_info; struct ip_nat_pptp *nat_pptp_info = &ct->nat.help.nat_pptp_info; - u_int16_t msg, new_callid; + u_int16_t msg; + __be16 new_callid; unsigned int cid_off; - new_callid = htons(ct_pptp_info->pns_call_id); - + new_callid = ct_pptp_info->pns_call_id; + switch (msg = ntohs(ctlh->messageType)) { - case PPTP_OUT_CALL_REQUEST: - cid_off = offsetof(union pptp_ctrl_union, ocreq.callID); - /* FIXME: ideally we would want to reserve a call ID - * here. current netfilter NAT core is not able to do - * this :( For now we use TCP source port. This breaks - * multiple calls within one control session */ - - /* save original call ID in nat_info */ - nat_pptp_info->pns_call_id = ct_pptp_info->pns_call_id; - - /* don't use tcph->source since we are at a DSTmanip - * hook (e.g. PREROUTING) and pkt is not mangled yet */ - new_callid = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port; - - /* save new call ID in ct info */ - ct_pptp_info->pns_call_id = ntohs(new_callid); - break; - case PPTP_IN_CALL_REPLY: - cid_off = offsetof(union pptp_ctrl_union, icreq.callID); - break; - case PPTP_CALL_CLEAR_REQUEST: - cid_off = offsetof(union pptp_ctrl_union, clrreq.callID); - break; - default: - DEBUGP("unknown outbound packet 0x%04x:%s\n", msg, - (msg <= PPTP_MSG_MAX)? - pptp_msg_name[msg]:pptp_msg_name[0]); - /* fall through */ - - case PPTP_SET_LINK_INFO: - /* only need to NAT in case PAC is behind NAT box */ - case PPTP_START_SESSION_REQUEST: - case PPTP_START_SESSION_REPLY: - case PPTP_STOP_SESSION_REQUEST: - case PPTP_STOP_SESSION_REPLY: - case PPTP_ECHO_REQUEST: - case PPTP_ECHO_REPLY: - /* no need to alter packet */ - return NF_ACCEPT; + case PPTP_OUT_CALL_REQUEST: + cid_off = offsetof(union pptp_ctrl_union, ocreq.callID); + /* FIXME: ideally we would want to reserve a call ID + * here. current netfilter NAT core is not able to do + * this :( For now we use TCP source port. This breaks + * multiple calls within one control session */ + + /* save original call ID in nat_info */ + nat_pptp_info->pns_call_id = ct_pptp_info->pns_call_id; + + /* don't use tcph->source since we are at a DSTmanip + * hook (e.g. PREROUTING) and pkt is not mangled yet */ + new_callid = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port; + + /* save new call ID in ct info */ + ct_pptp_info->pns_call_id = new_callid; + break; + case PPTP_IN_CALL_REPLY: + cid_off = offsetof(union pptp_ctrl_union, icack.callID); + break; + case PPTP_CALL_CLEAR_REQUEST: + cid_off = offsetof(union pptp_ctrl_union, clrreq.callID); + break; + default: + DEBUGP("unknown outbound packet 0x%04x:%s\n", msg, + (msg <= PPTP_MSG_MAX)? + pptp_msg_name[msg]:pptp_msg_name[0]); + /* fall through */ + + case PPTP_SET_LINK_INFO: + /* only need to NAT in case PAC is behind NAT box */ + case PPTP_START_SESSION_REQUEST: + case PPTP_START_SESSION_REPLY: + case PPTP_STOP_SESSION_REQUEST: + case PPTP_STOP_SESSION_REPLY: + case PPTP_ECHO_REQUEST: + case PPTP_ECHO_REPLY: + /* no need to alter packet */ + return NF_ACCEPT; } /* only OUT_CALL_REQUEST, IN_CALL_REPLY, CALL_CLEAR_REQUEST pass @@ -212,80 +211,28 @@ pptp_outbound_pkt(struct sk_buff **pskb, return NF_ACCEPT; } -static int +static void pptp_exp_gre(struct ip_conntrack_expect *expect_orig, struct ip_conntrack_expect *expect_reply) { - struct ip_ct_pptp_master *ct_pptp_info = - &expect_orig->master->help.ct_pptp_info; - struct ip_nat_pptp *nat_pptp_info = - &expect_orig->master->nat.help.nat_pptp_info; - struct ip_conntrack *ct = expect_orig->master; - - struct ip_conntrack_tuple inv_t; - struct ip_conntrack_tuple *orig_t, *reply_t; + struct ip_ct_pptp_master *ct_pptp_info = &ct->help.ct_pptp_info; + struct ip_nat_pptp *nat_pptp_info = &ct->nat.help.nat_pptp_info; /* save original PAC call ID in nat_info */ nat_pptp_info->pac_call_id = ct_pptp_info->pac_call_id; - /* alter expectation */ - orig_t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - reply_t = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - /* alter expectation for PNS->PAC direction */ - invert_tuplepr(&inv_t, &expect_orig->tuple); - expect_orig->saved_proto.gre.key = htons(ct_pptp_info->pns_call_id); - expect_orig->tuple.src.u.gre.key = htons(nat_pptp_info->pns_call_id); - expect_orig->tuple.dst.u.gre.key = htons(ct_pptp_info->pac_call_id); + expect_orig->saved_proto.gre.key = ct_pptp_info->pns_call_id; + expect_orig->tuple.src.u.gre.key = nat_pptp_info->pns_call_id; + expect_orig->tuple.dst.u.gre.key = ct_pptp_info->pac_call_id; expect_orig->dir = IP_CT_DIR_ORIGINAL; - inv_t.src.ip = reply_t->src.ip; - inv_t.dst.ip = reply_t->dst.ip; - inv_t.src.u.gre.key = htons(nat_pptp_info->pac_call_id); - inv_t.dst.u.gre.key = htons(ct_pptp_info->pns_call_id); - - if (!ip_conntrack_expect_related(expect_orig)) { - DEBUGP("successfully registered expect\n"); - } else { - DEBUGP("can't expect_related(expect_orig)\n"); - return 1; - } /* alter expectation for PAC->PNS direction */ - invert_tuplepr(&inv_t, &expect_reply->tuple); - expect_reply->saved_proto.gre.key = htons(nat_pptp_info->pns_call_id); - expect_reply->tuple.src.u.gre.key = htons(nat_pptp_info->pac_call_id); - expect_reply->tuple.dst.u.gre.key = htons(ct_pptp_info->pns_call_id); + expect_reply->saved_proto.gre.key = nat_pptp_info->pns_call_id; + expect_reply->tuple.src.u.gre.key = nat_pptp_info->pac_call_id; + expect_reply->tuple.dst.u.gre.key = ct_pptp_info->pns_call_id; expect_reply->dir = IP_CT_DIR_REPLY; - inv_t.src.ip = orig_t->src.ip; - inv_t.dst.ip = orig_t->dst.ip; - inv_t.src.u.gre.key = htons(nat_pptp_info->pns_call_id); - inv_t.dst.u.gre.key = htons(ct_pptp_info->pac_call_id); - - if (!ip_conntrack_expect_related(expect_reply)) { - DEBUGP("successfully registered expect\n"); - } else { - DEBUGP("can't expect_related(expect_reply)\n"); - ip_conntrack_unexpect_related(expect_orig); - return 1; - } - - if (ip_ct_gre_keymap_add(ct, &expect_reply->tuple, 0) < 0) { - DEBUGP("can't register original keymap\n"); - ip_conntrack_unexpect_related(expect_orig); - ip_conntrack_unexpect_related(expect_reply); - return 1; - } - - if (ip_ct_gre_keymap_add(ct, &inv_t, 1) < 0) { - DEBUGP("can't register reply keymap\n"); - ip_conntrack_unexpect_related(expect_orig); - ip_conntrack_unexpect_related(expect_reply); - ip_ct_gre_keymap_destroy(ct); - return 1; - } - - return 0; } /* inbound packets == from PAC to PNS */ @@ -297,15 +244,15 @@ pptp_inbound_pkt(struct sk_buff **pskb, union pptp_ctrl_union *pptpReq) { struct ip_nat_pptp *nat_pptp_info = &ct->nat.help.nat_pptp_info; - u_int16_t msg, new_cid = 0, new_pcid; - unsigned int pcid_off, cid_off = 0; + u_int16_t msg; + __be16 new_pcid; + unsigned int pcid_off; - new_pcid = htons(nat_pptp_info->pns_call_id); + new_pcid = nat_pptp_info->pns_call_id; switch (msg = ntohs(ctlh->messageType)) { case PPTP_OUT_CALL_REPLY: pcid_off = offsetof(union pptp_ctrl_union, ocack.peersCallID); - cid_off = offsetof(union pptp_ctrl_union, ocack.callID); break; case PPTP_IN_CALL_CONNECT: pcid_off = offsetof(union pptp_ctrl_union, iccon.peersCallID); @@ -324,7 +271,7 @@ pptp_inbound_pkt(struct sk_buff **pskb, break; default: - DEBUGP("unknown inbound packet %s\n", (msg <= PPTP_MSG_MAX)? + DEBUGP("unknown inbound packet %s\n", (msg <= PPTP_MSG_MAX)? pptp_msg_name[msg]:pptp_msg_name[0]); /* fall through */ @@ -351,17 +298,6 @@ pptp_inbound_pkt(struct sk_buff **pskb, sizeof(new_pcid), (char *)&new_pcid, sizeof(new_pcid)) == 0) return NF_DROP; - - if (new_cid) { - DEBUGP("altering call id from 0x%04x to 0x%04x\n", - 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), - sizeof(new_cid), (char *)&new_cid, - sizeof(new_cid)) == 0) - return NF_DROP; - } return NF_ACCEPT; } diff --git a/net/ipv4/netfilter/ip_nat_proto_gre.c b/net/ipv4/netfilter/ip_nat_proto_gre.c index 38acfdf540e..bf91f9312b3 100644 --- a/net/ipv4/netfilter/ip_nat_proto_gre.c +++ b/net/ipv4/netfilter/ip_nat_proto_gre.c @@ -6,10 +6,10 @@ * GRE is a generic encapsulation protocol, which is generally not very * suited for NAT, as it has no protocol-specific part as port numbers. * - * It has an optional key field, which may help us distinguishing two + * It has an optional key field, which may help us distinguishing two * connections between the same two hosts. * - * GRE is defined in RFC 1701 and RFC 1702, as well as RFC 2784 + * GRE is defined in RFC 1701 and RFC 1702, as well as RFC 2784 * * PPTP is built on top of a modified version of GRE, and has a mandatory * field called "CallID", which serves us for the same purpose as the key @@ -60,14 +60,14 @@ gre_in_range(const struct ip_conntrack_tuple *tuple, } /* generate unique tuple ... */ -static int +static int gre_unique_tuple(struct ip_conntrack_tuple *tuple, const struct ip_nat_range *range, enum ip_nat_manip_type maniptype, const struct ip_conntrack *conntrack) { static u_int16_t key; - u_int16_t *keyptr; + __be16 *keyptr; unsigned int min, i, range_size; if (maniptype == IP_NAT_MANIP_SRC) @@ -84,7 +84,7 @@ gre_unique_tuple(struct ip_conntrack_tuple *tuple, range_size = ntohs(range->max.gre.key) - min + 1; } - DEBUGP("min = %u, range_size = %u\n", min, range_size); + DEBUGP("min = %u, range_size = %u\n", min, range_size); for (i = 0; i < range_size; i++, key++) { *keyptr = htons(min + key % range_size); @@ -117,7 +117,7 @@ gre_manip_pkt(struct sk_buff **pskb, greh = (void *)(*pskb)->data + hdroff; pgreh = (struct gre_hdr_pptp *) greh; - /* we only have destination manip of a packet, since 'source key' + /* we only have destination manip of a packet, since 'source key' * is not present in the packet itself */ if (maniptype == IP_NAT_MANIP_DST) { /* key manipulation is always dest */ @@ -129,15 +129,16 @@ gre_manip_pkt(struct sk_buff **pskb, } if (greh->csum) { /* FIXME: Never tested this code... */ - *(gre_csum(greh)) = - ip_nat_cheat_check(~*(gre_key(greh)), + *(gre_csum(greh)) = + nf_proto_csum_update(*pskb, + ~*(gre_key(greh)), tuple->dst.u.gre.key, - *(gre_csum(greh))); + *(gre_csum(greh)), 0); } *(gre_key(greh)) = tuple->dst.u.gre.key; break; case GRE_VERSION_PPTP: - DEBUGP("call_id -> 0x%04x\n", + DEBUGP("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key)); pgreh->call_id = tuple->dst.u.gre.key; break; @@ -151,8 +152,8 @@ gre_manip_pkt(struct sk_buff **pskb, } /* nat helper struct */ -static struct ip_nat_protocol gre = { - .name = "GRE", +static struct ip_nat_protocol gre = { + .name = "GRE", .protonum = IPPROTO_GRE, .manip_pkt = gre_manip_pkt, .in_range = gre_in_range, @@ -163,7 +164,7 @@ static struct ip_nat_protocol gre = { .nfattr_to_range = ip_nat_port_nfattr_to_range, #endif }; - + int __init ip_nat_proto_gre_init(void) { return ip_nat_protocol_register(&gre); diff --git a/net/ipv4/netfilter/ip_nat_proto_icmp.c b/net/ipv4/netfilter/ip_nat_proto_icmp.c index 31a3f4ccb99..ec50cc29531 100644 --- a/net/ipv4/netfilter/ip_nat_proto_icmp.c +++ b/net/ipv4/netfilter/ip_nat_proto_icmp.c @@ -66,10 +66,10 @@ icmp_manip_pkt(struct sk_buff **pskb, return 0; hdr = (struct icmphdr *)((*pskb)->data + hdroff); - - hdr->checksum = ip_nat_cheat_check(hdr->un.echo.id ^ 0xFFFF, - tuple->src.u.icmp.id, - hdr->checksum); + hdr->checksum = nf_proto_csum_update(*pskb, + hdr->un.echo.id ^ 0xFFFF, + tuple->src.u.icmp.id, + hdr->checksum, 0); hdr->un.echo.id = tuple->src.u.icmp.id; return 1; } diff --git a/net/ipv4/netfilter/ip_nat_proto_tcp.c b/net/ipv4/netfilter/ip_nat_proto_tcp.c index a3d14079eba..72a6307bd2d 100644 --- a/net/ipv4/netfilter/ip_nat_proto_tcp.c +++ b/net/ipv4/netfilter/ip_nat_proto_tcp.c @@ -129,10 +129,9 @@ tcp_manip_pkt(struct sk_buff **pskb, if (hdrsize < sizeof(*hdr)) return 1; - hdr->check = ip_nat_cheat_check(~oldip, newip, - ip_nat_cheat_check(oldport ^ 0xFFFF, - newport, - hdr->check)); + hdr->check = nf_proto_csum_update(*pskb, ~oldip, newip, hdr->check, 1); + hdr->check = nf_proto_csum_update(*pskb, oldport ^ 0xFFFF, newport, + hdr->check, 0); return 1; } diff --git a/net/ipv4/netfilter/ip_nat_proto_udp.c b/net/ipv4/netfilter/ip_nat_proto_udp.c index ec6053fdc86..5da196ae758 100644 --- a/net/ipv4/netfilter/ip_nat_proto_udp.c +++ b/net/ipv4/netfilter/ip_nat_proto_udp.c @@ -113,11 +113,16 @@ udp_manip_pkt(struct sk_buff **pskb, newport = tuple->dst.u.udp.port; portptr = &hdr->dest; } - if (hdr->check) /* 0 is a special case meaning no checksum */ - hdr->check = ip_nat_cheat_check(~oldip, newip, - ip_nat_cheat_check(*portptr ^ 0xFFFF, - newport, - hdr->check)); + + if (hdr->check || (*pskb)->ip_summed == CHECKSUM_PARTIAL) { + hdr->check = nf_proto_csum_update(*pskb, ~oldip, newip, + hdr->check, 1); + hdr->check = nf_proto_csum_update(*pskb, + *portptr ^ 0xFFFF, newport, + hdr->check, 0); + if (!hdr->check) + hdr->check = -1; + } *portptr = newport; return 1; } diff --git a/net/ipv4/netfilter/ip_nat_rule.c b/net/ipv4/netfilter/ip_nat_rule.c index 1aba926c1cb..7b703839aa5 100644 --- a/net/ipv4/netfilter/ip_nat_rule.c +++ b/net/ipv4/netfilter/ip_nat_rule.c @@ -19,14 +19,10 @@ #include <net/route.h> #include <linux/bitops.h> -#define ASSERT_READ_LOCK(x) -#define ASSERT_WRITE_LOCK(x) - #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ip_nat.h> #include <linux/netfilter_ipv4/ip_nat_core.h> #include <linux/netfilter_ipv4/ip_nat_rule.h> -#include <linux/netfilter_ipv4/listhelp.h> #if 0 #define DEBUGP printk @@ -104,8 +100,7 @@ static unsigned int ipt_snat_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct ipt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; @@ -147,8 +142,7 @@ static unsigned int ipt_dnat_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct ipt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; @@ -174,7 +168,6 @@ 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) { struct ip_nat_multi_range_compat *mr = targinfo; @@ -191,7 +184,6 @@ 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) { struct ip_nat_multi_range_compat *mr = targinfo; @@ -255,7 +247,7 @@ int ip_nat_rule_find(struct sk_buff **pskb, { int ret; - ret = ipt_do_table(pskb, hooknum, in, out, &nat_table, NULL); + ret = ipt_do_table(pskb, hooknum, in, out, &nat_table); if (ret == NF_ACCEPT) { if (!ip_nat_initialized(ct, HOOK2MANIP(hooknum))) diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index 17de077a790..9c577db6204 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -30,9 +30,6 @@ #include <net/checksum.h> #include <linux/spinlock.h> -#define ASSERT_READ_LOCK(x) -#define ASSERT_WRITE_LOCK(x) - #include <linux/netfilter_ipv4/ip_nat.h> #include <linux/netfilter_ipv4/ip_nat_rule.h> #include <linux/netfilter_ipv4/ip_nat_protocol.h> @@ -40,7 +37,6 @@ #include <linux/netfilter_ipv4/ip_nat_helper.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ip_conntrack_core.h> -#include <linux/netfilter_ipv4/listhelp.h> #if 0 #define DEBUGP printk @@ -110,11 +106,6 @@ ip_nat_fn(unsigned int hooknum, IP_NF_ASSERT(!((*pskb)->nh.iph->frag_off & htons(IP_MF|IP_OFFSET))); - /* If we had a hardware checksum before, it's now invalid */ - if ((*pskb)->ip_summed == CHECKSUM_HW) - if (skb_checksum_help(*pskb, (out == NULL))) - return NF_DROP; - ct = ip_conntrack_get(*pskb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would have dropped it. Hence it's the user's responsibilty to @@ -145,8 +136,8 @@ ip_nat_fn(unsigned int hooknum, case IP_CT_RELATED: case IP_CT_RELATED+IP_CT_IS_REPLY: if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) { - if (!ip_nat_icmp_reply_translation(pskb, ct, maniptype, - CTINFO2DIR(ctinfo))) + if (!ip_nat_icmp_reply_translation(ct, ctinfo, + hooknum, pskb)) return NF_DROP; else return NF_ACCEPT; diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index 198ac36db86..7edad790478 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -52,15 +52,15 @@ struct ipq_queue_entry { typedef int (*ipq_cmpfn)(struct ipq_queue_entry *, unsigned long); -static unsigned char copy_mode = IPQ_COPY_NONE; -static unsigned int queue_maxlen = IPQ_QMAX_DEFAULT; +static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE; +static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT; static DEFINE_RWLOCK(queue_lock); -static int peer_pid; -static unsigned int copy_range; +static int peer_pid __read_mostly; +static unsigned int copy_range __read_mostly; static unsigned int queue_total; static unsigned int queue_dropped = 0; static unsigned int queue_user_dropped = 0; -static struct sock *ipqnl; +static struct sock *ipqnl __read_mostly; static LIST_HEAD(queue_list); static DEFINE_MUTEX(ipqnl_mutex); @@ -208,9 +208,9 @@ ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp) break; case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_HW && - (*errp = skb_checksum_help(entry->skb, - entry->info->outdev == NULL))) { + if ((entry->skb->ip_summed == CHECKSUM_PARTIAL || + entry->skb->ip_summed == CHECKSUM_COMPLETE) && + (*errp = skb_checksum_help(entry->skb))) { read_unlock_bh(&queue_lock); return NULL; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 048514f15f2..800067d69a9 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -180,8 +180,7 @@ ipt_error(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { if (net_ratelimit()) printk("ip_tables: error: `%s'\n", (char *)targinfo); @@ -217,8 +216,7 @@ ipt_do_table(struct sk_buff **pskb, unsigned int hook, const struct net_device *in, const struct net_device *out, - struct ipt_table *table, - void *userdata) + struct ipt_table *table) { static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); u_int16_t offset; @@ -308,8 +306,7 @@ ipt_do_table(struct sk_buff **pskb, in, out, hook, t->u.kernel.target, - t->data, - userdata); + t->data); #ifdef CONFIG_NETFILTER_DEBUG if (((struct ipt_entry *)table_base)->comefrom @@ -467,8 +464,7 @@ cleanup_match(struct ipt_entry_match *m, unsigned int *i) return 1; if (m->u.kernel.match->destroy) - m->u.kernel.match->destroy(m->u.kernel.match, m->data, - m->u.match_size - sizeof(*m)); + m->u.kernel.match->destroy(m->u.kernel.match, m->data); module_put(m->u.kernel.match->me); return 0; } @@ -521,7 +517,6 @@ check_match(struct ipt_entry_match *m, if (m->u.kernel.match->checkentry && !m->u.kernel.match->checkentry(name, ip, match, m->data, - m->u.match_size - sizeof(*m), hookmask)) { duprintf("ip_tables: check failed for `%s'.\n", m->u.kernel.match->name); @@ -578,12 +573,10 @@ check_entry(struct ipt_entry *e, const char *name, unsigned int size, if (t->u.kernel.target == &ipt_standard_target) { if (!standard_check(t, size)) { ret = -EINVAL; - goto cleanup_matches; + goto err; } } else if (t->u.kernel.target->checkentry && !t->u.kernel.target->checkentry(name, e, target, t->data, - t->u.target_size - - sizeof(*t), e->comefrom)) { duprintf("ip_tables: check failed for `%s'.\n", t->u.kernel.target->name); @@ -655,8 +648,7 @@ 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->u.kernel.target, t->data, - t->u.target_size - sizeof(*t)); + t->u.kernel.target->destroy(t->u.kernel.target, t->data); module_put(t->u.kernel.target->me); return 0; } @@ -950,73 +942,28 @@ static short compat_calc_jump(u_int16_t offset) return delta; } -struct compat_ipt_standard_target +static void compat_standard_from_user(void *dst, void *src) { - struct compat_xt_entry_target target; - compat_int_t verdict; -}; - -struct compat_ipt_standard -{ - struct compat_ipt_entry entry; - struct compat_ipt_standard_target target; -}; + int v = *(compat_int_t *)src; -#define IPT_ST_LEN XT_ALIGN(sizeof(struct ipt_standard_target)) -#define IPT_ST_COMPAT_LEN COMPAT_XT_ALIGN(sizeof(struct compat_ipt_standard_target)) -#define IPT_ST_OFFSET (IPT_ST_LEN - IPT_ST_COMPAT_LEN) + if (v > 0) + v += compat_calc_jump(v); + memcpy(dst, &v, sizeof(v)); +} -static int compat_ipt_standard_fn(void *target, - void **dstptr, int *size, int convert) +static int compat_standard_to_user(void __user *dst, void *src) { - struct compat_ipt_standard_target compat_st, *pcompat_st; - struct ipt_standard_target st, *pst; - int ret; + compat_int_t cv = *(int *)src; - ret = 0; - switch (convert) { - case COMPAT_TO_USER: - pst = target; - memcpy(&compat_st.target, &pst->target, - sizeof(compat_st.target)); - compat_st.verdict = pst->verdict; - if (compat_st.verdict > 0) - compat_st.verdict -= - compat_calc_jump(compat_st.verdict); - compat_st.target.u.user.target_size = IPT_ST_COMPAT_LEN; - if (copy_to_user(*dstptr, &compat_st, IPT_ST_COMPAT_LEN)) - ret = -EFAULT; - *size -= IPT_ST_OFFSET; - *dstptr += IPT_ST_COMPAT_LEN; - break; - case COMPAT_FROM_USER: - pcompat_st = target; - memcpy(&st.target, &pcompat_st->target, IPT_ST_COMPAT_LEN); - st.verdict = pcompat_st->verdict; - if (st.verdict > 0) - st.verdict += compat_calc_jump(st.verdict); - st.target.u.user.target_size = IPT_ST_LEN; - memcpy(*dstptr, &st, IPT_ST_LEN); - *size += IPT_ST_OFFSET; - *dstptr += IPT_ST_LEN; - break; - case COMPAT_CALC_SIZE: - *size += IPT_ST_OFFSET; - break; - default: - ret = -ENOPROTOOPT; - break; - } - return ret; + if (cv > 0) + cv -= compat_calc_jump(cv); + return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static inline int compat_calc_match(struct ipt_entry_match *m, int * size) { - if (m->u.kernel.match->compat) - m->u.kernel.match->compat(m, NULL, size, COMPAT_CALC_SIZE); - else - xt_compat_match(m, NULL, size, COMPAT_CALC_SIZE); + *size += xt_compat_match_offset(m->u.kernel.match); return 0; } @@ -1031,10 +978,7 @@ static int compat_calc_entry(struct ipt_entry *e, struct xt_table_info *info, entry_offset = (void *)e - base; IPT_MATCH_ITERATE(e, compat_calc_match, &off); t = ipt_get_target(e); - if (t->u.kernel.target->compat) - t->u.kernel.target->compat(t, NULL, &off, COMPAT_CALC_SIZE); - else - xt_compat_target(t, NULL, &off, COMPAT_CALC_SIZE); + off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = compat_add_offset(entry_offset, off); if (ret) @@ -1420,17 +1364,13 @@ struct compat_ipt_replace { }; static inline int compat_copy_match_to_user(struct ipt_entry_match *m, - void __user **dstptr, compat_uint_t *size) + void * __user *dstptr, compat_uint_t *size) { - if (m->u.kernel.match->compat) - return m->u.kernel.match->compat(m, dstptr, size, - COMPAT_TO_USER); - else - return xt_compat_match(m, dstptr, size, COMPAT_TO_USER); + return xt_compat_match_to_user(m, dstptr, size); } static int compat_copy_entry_to_user(struct ipt_entry *e, - void __user **dstptr, compat_uint_t *size) + void * __user *dstptr, compat_uint_t *size) { struct ipt_entry_target __user *t; struct compat_ipt_entry __user *ce; @@ -1450,11 +1390,7 @@ static int compat_copy_entry_to_user(struct ipt_entry *e, if (ret) goto out; t = ipt_get_target(e); - if (t->u.kernel.target->compat) - ret = t->u.kernel.target->compat(t, dstptr, size, - COMPAT_TO_USER); - else - ret = xt_compat_target(t, dstptr, size, COMPAT_TO_USER); + ret = xt_compat_target_to_user(t, dstptr, size); if (ret) goto out; ret = -EFAULT; @@ -1486,11 +1422,7 @@ compat_check_calc_match(struct ipt_entry_match *m, return match ? PTR_ERR(match) : -ENOENT; } m->u.kernel.match = match; - - if (m->u.kernel.match->compat) - m->u.kernel.match->compat(m, NULL, size, COMPAT_CALC_SIZE); - else - xt_compat_match(m, NULL, size, COMPAT_CALC_SIZE); + *size += xt_compat_match_offset(match); (*i)++; return 0; @@ -1537,7 +1469,7 @@ check_compat_entry_size_and_hooks(struct ipt_entry *e, ret = IPT_MATCH_ITERATE(e, compat_check_calc_match, name, &e->ip, e->comefrom, &off, &j); if (ret != 0) - goto out; + goto cleanup_matches; t = ipt_get_target(e); target = try_then_request_module(xt_find_target(AF_INET, @@ -1547,14 +1479,11 @@ check_compat_entry_size_and_hooks(struct ipt_entry *e, if (IS_ERR(target) || !target) { duprintf("check_entry: `%s' not found\n", t->u.user.name); ret = target ? PTR_ERR(target) : -ENOENT; - goto out; + goto cleanup_matches; } t->u.kernel.target = target; - if (t->u.kernel.target->compat) - t->u.kernel.target->compat(t, NULL, &off, COMPAT_CALC_SIZE); - else - xt_compat_target(t, NULL, &off, COMPAT_CALC_SIZE); + off += xt_compat_target_offset(target); *size += off; ret = compat_add_offset(entry_offset, off); if (ret) @@ -1574,14 +1503,17 @@ check_compat_entry_size_and_hooks(struct ipt_entry *e, (*i)++; return 0; + out: + module_put(t->u.kernel.target->me); +cleanup_matches: IPT_MATCH_ITERATE(e, cleanup_match, &j); return ret; } static inline int compat_copy_match_from_user(struct ipt_entry_match *m, void **dstptr, compat_uint_t *size, const char *name, - const struct ipt_ip *ip, unsigned int hookmask) + const struct ipt_ip *ip, unsigned int hookmask, int *i) { struct ipt_entry_match *dm; struct ipt_match *match; @@ -1589,26 +1521,28 @@ static inline int compat_copy_match_from_user(struct ipt_entry_match *m, dm = (struct ipt_entry_match *)*dstptr; match = m->u.kernel.match; - if (match->compat) - match->compat(m, dstptr, size, COMPAT_FROM_USER); - else - xt_compat_match(m, dstptr, size, COMPAT_FROM_USER); + xt_compat_match_from_user(m, dstptr, size); ret = xt_check_match(match, AF_INET, dm->u.match_size - sizeof(*dm), name, hookmask, ip->proto, ip->invflags & IPT_INV_PROTO); if (ret) - return ret; + goto err; if (m->u.kernel.match->checkentry && !m->u.kernel.match->checkentry(name, ip, match, dm->data, - dm->u.match_size - sizeof(*dm), hookmask)) { 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 int compat_copy_entry_from_user(struct ipt_entry *e, void **dstptr, @@ -1619,25 +1553,23 @@ static int compat_copy_entry_from_user(struct ipt_entry *e, void **dstptr, struct ipt_target *target; struct ipt_entry *de; unsigned int origsize; - int ret, h; + int ret, h, j; ret = 0; origsize = *size; de = (struct ipt_entry *)*dstptr; memcpy(de, e, sizeof(struct ipt_entry)); + j = 0; *dstptr += sizeof(struct compat_ipt_entry); ret = IPT_MATCH_ITERATE(e, compat_copy_match_from_user, dstptr, size, - name, &de->ip, de->comefrom); + name, &de->ip, de->comefrom, &j); if (ret) - goto out; + goto cleanup_matches; de->target_offset = e->target_offset - (origsize - *size); t = ipt_get_target(e); target = t->u.kernel.target; - if (target->compat) - target->compat(t, dstptr, size, COMPAT_FROM_USER); - else - xt_compat_target(t, dstptr, size, COMPAT_FROM_USER); + xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_IP_NUMHOOKS; h++) { @@ -1653,22 +1585,26 @@ static int compat_copy_entry_from_user(struct ipt_entry *e, void **dstptr, name, e->comefrom, e->ip.proto, e->ip.invflags & IPT_INV_PROTO); if (ret) - goto out; + goto err; ret = -EINVAL; if (t->u.kernel.target == &ipt_standard_target) { if (!standard_check(t, *size)) - goto out; + goto err; } else if (t->u.kernel.target->checkentry && !t->u.kernel.target->checkentry(name, de, target, - t->data, t->u.target_size - sizeof(*t), - de->comefrom)) { + t->data, de->comefrom)) { duprintf("ip_tables: compat: check failed for `%s'.\n", t->u.kernel.target->name); - goto out; + goto err; } ret = 0; -out: + return ret; + +err: + module_put(t->u.kernel.target->me); +cleanup_matches: + IPT_MATCH_ITERATE(e, cleanup_match, &j); return ret; } @@ -1989,6 +1925,8 @@ compat_get_entries(struct compat_ipt_get_entries __user *uptr, int *len) return ret; } +static int do_ipt_get_ctl(struct sock *, int, void __user *, int *); + static int compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { @@ -2002,8 +1940,7 @@ compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) ret = compat_get_entries(user, len); break; default: - duprintf("compat_do_ipt_get_ctl: unknown request %i\n", cmd); - ret = -EINVAL; + ret = do_ipt_get_ctl(sk, cmd, user, len); } return ret; } @@ -2185,7 +2122,6 @@ 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_icmp *icmpinfo = matchinfo; @@ -2200,7 +2136,9 @@ static struct ipt_target ipt_standard_target = { .targetsize = sizeof(int), .family = AF_INET, #ifdef CONFIG_COMPAT - .compat = &compat_ipt_standard_fn, + .compatsize = sizeof(compat_int_t), + .compat_from_user = compat_standard_from_user, + .compat_to_user = compat_standard_to_user, #endif }; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index d994c5f5744..41589665fc5 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -302,8 +302,7 @@ target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct ipt_clusterip_tgt_info *cipinfo = targinfo; enum ip_conntrack_info ctinfo; @@ -373,7 +372,6 @@ checkentry(const char *tablename, const void *e_void, const struct xt_target *target, void *targinfo, - unsigned int targinfosize, unsigned int hook_mask) { struct ipt_clusterip_tgt_info *cipinfo = targinfo; @@ -450,8 +448,7 @@ checkentry(const char *tablename, } /* drop reference count of cluster config when rule is deleted */ -static void destroy(const struct xt_target *target, void *targinfo, - unsigned int targinfosize) +static void destroy(const struct xt_target *target, void *targinfo) { struct ipt_clusterip_tgt_info *cipinfo = targinfo; diff --git a/net/ipv4/netfilter/ipt_DSCP.c b/net/ipv4/netfilter/ipt_DSCP.c deleted file mode 100644 index c8e971288df..00000000000 --- a/net/ipv4/netfilter/ipt_DSCP.c +++ /dev/null @@ -1,96 +0,0 @@ -/* iptables module for setting the IPv4 DSCP field, Version 1.8 - * - * (C) 2002 by Harald Welte <laforge@netfilter.org> - * based on ipt_FTOS.c (C) 2000 by Matthew G. Marsh <mgm@paktronix.com> - * - * 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. - * - * See RFC2474 for a description of the DSCP field within the IP Header. - * - * ipt_DSCP.c,v 1.8 2002/08/06 18:41:57 laforge Exp -*/ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <net/checksum.h> - -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_DSCP.h> - -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("iptables DSCP modification module"); -MODULE_LICENSE("GPL"); - -static unsigned int -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 ipt_DSCP_info *dinfo = targinfo; - u_int8_t sh_dscp = ((dinfo->dscp << IPT_DSCP_SHIFT) & IPT_DSCP_MASK); - - - if (((*pskb)->nh.iph->tos & IPT_DSCP_MASK) != sh_dscp) { - u_int16_t diffs[2]; - - if (!skb_make_writable(pskb, sizeof(struct iphdr))) - return NF_DROP; - - diffs[0] = htons((*pskb)->nh.iph->tos) ^ 0xFFFF; - (*pskb)->nh.iph->tos = ((*pskb)->nh.iph->tos & ~IPT_DSCP_MASK) - | sh_dscp; - diffs[1] = htons((*pskb)->nh.iph->tos); - (*pskb)->nh.iph->check - = csum_fold(csum_partial((char *)diffs, - sizeof(diffs), - (*pskb)->nh.iph->check - ^ 0xFFFF)); - } - return IPT_CONTINUE; -} - -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 ((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, -}; - -static int __init ipt_dscp_init(void) -{ - return ipt_register_target(&ipt_dscp_reg); -} - -static void __exit ipt_dscp_fini(void) -{ - ipt_unregister_target(&ipt_dscp_reg); -} - -module_init(ipt_dscp_init); -module_exit(ipt_dscp_fini); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 4adf5c9d34f..23f9c7ebe7e 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -27,32 +27,28 @@ MODULE_DESCRIPTION("iptables ECN modification module"); static inline int set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) { - if (((*pskb)->nh.iph->tos & IPT_ECN_IP_MASK) - != (einfo->ip_ect & IPT_ECN_IP_MASK)) { - u_int16_t diffs[2]; + struct iphdr *iph = (*pskb)->nh.iph; + u_int16_t oldtos; + if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) { if (!skb_make_writable(pskb, sizeof(struct iphdr))) return 0; - - diffs[0] = htons((*pskb)->nh.iph->tos) ^ 0xFFFF; - (*pskb)->nh.iph->tos &= ~IPT_ECN_IP_MASK; - (*pskb)->nh.iph->tos |= (einfo->ip_ect & IPT_ECN_IP_MASK); - diffs[1] = htons((*pskb)->nh.iph->tos); - (*pskb)->nh.iph->check - = csum_fold(csum_partial((char *)diffs, - sizeof(diffs), - (*pskb)->nh.iph->check - ^0xFFFF)); + iph = (*pskb)->nh.iph; + oldtos = iph->tos; + iph->tos &= ~IPT_ECN_IP_MASK; + iph->tos |= (einfo->ip_ect & IPT_ECN_IP_MASK); + iph->check = nf_csum_update(oldtos ^ 0xFFFF, iph->tos, + iph->check); } return 1; } /* Return 0 if there was an error. */ static inline int -set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo, int inward) +set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) { struct tcphdr _tcph, *tcph; - u_int16_t diffs[2]; + u_int16_t oldval; /* Not enought header? */ tcph = skb_header_pointer(*pskb, (*pskb)->nh.iph->ihl*4, @@ -70,22 +66,16 @@ set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo, int inward) return 0; tcph = (void *)(*pskb)->nh.iph + (*pskb)->nh.iph->ihl*4; - if ((*pskb)->ip_summed == CHECKSUM_HW && - skb_checksum_help(*pskb, inward)) - return 0; - - diffs[0] = ((u_int16_t *)tcph)[6]; + oldval = ((u_int16_t *)tcph)[6]; if (einfo->operation & IPT_ECN_OP_SET_ECE) tcph->ece = einfo->proto.tcp.ece; if (einfo->operation & IPT_ECN_OP_SET_CWR) tcph->cwr = einfo->proto.tcp.cwr; - diffs[1] = ((u_int16_t *)tcph)[6]; - diffs[0] = diffs[0] ^ 0xFFFF; - if ((*pskb)->ip_summed != CHECKSUM_UNNECESSARY) - tcph->check = csum_fold(csum_partial((char *)diffs, - sizeof(diffs), - tcph->check^0xFFFF)); + tcph->check = nf_proto_csum_update((*pskb), + oldval ^ 0xFFFF, + ((u_int16_t *)tcph)[6], + tcph->check, 0); return 1; } @@ -95,8 +85,7 @@ target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct ipt_ECN_info *einfo = targinfo; @@ -106,7 +95,7 @@ target(struct sk_buff **pskb, if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) && (*pskb)->nh.iph->protocol == IPPROTO_TCP) - if (!set_ect_tcp(pskb, einfo, (out == NULL))) + if (!set_ect_tcp(pskb, einfo)) return NF_DROP; return IPT_CONTINUE; @@ -117,7 +106,6 @@ checkentry(const char *tablename, const void *e_void, const struct xt_target *target, void *targinfo, - unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_ECN_info *einfo = (struct ipt_ECN_info *)targinfo; diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index b98f7b08b08..7dc820df8bc 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -416,8 +416,7 @@ ipt_log_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct ipt_log_info *loginfo = targinfo; struct nf_loginfo li; @@ -440,7 +439,6 @@ 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; diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index ebd94f2abf0..bc65168a343 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -42,7 +42,6 @@ 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; @@ -64,8 +63,7 @@ masquerade_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index 736c4b5a86a..beb2914225f 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -33,7 +33,6 @@ 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; @@ -55,8 +54,7 @@ target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index f290463232d..f03d43671c6 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -36,7 +36,6 @@ 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; @@ -58,8 +57,7 @@ redirect_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 269bc2067cb..b81821edd89 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -90,6 +90,7 @@ static inline struct rtable *route_reverse(struct sk_buff *skb, fl.proto = IPPROTO_TCP; fl.fl_ip_sport = tcph->dest; fl.fl_ip_dport = tcph->source; + security_skb_classify_flow(skb, &fl); xfrm_lookup((struct dst_entry **)&rt, &fl, NULL, 0); @@ -184,6 +185,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) tcph->urg_ptr = 0; /* Adjust TCP checksum */ + nskb->ip_summed = CHECKSUM_NONE; tcph->check = 0; tcph->check = tcp_v4_check(tcph, sizeof(struct tcphdr), nskb->nh.iph->saddr, @@ -226,8 +228,7 @@ static unsigned int reject(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct ipt_reject_info *reject = targinfo; @@ -275,7 +276,6 @@ static int check(const char *tablename, const void *e_void, const struct xt_target *target, void *targinfo, - unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_reject_info *rejinfo = targinfo; diff --git a/net/ipv4/netfilter/ipt_SAME.c b/net/ipv4/netfilter/ipt_SAME.c index 7169b09b5a6..efbcb119883 100644 --- a/net/ipv4/netfilter/ipt_SAME.c +++ b/net/ipv4/netfilter/ipt_SAME.c @@ -52,7 +52,6 @@ same_check(const char *tablename, const void *e, const struct xt_target *target, void *targinfo, - unsigned int targinfosize, unsigned int hook_mask) { unsigned int count, countess, rangeip, index = 0; @@ -116,8 +115,7 @@ same_check(const char *tablename, } static void -same_destroy(const struct xt_target *target, void *targinfo, - unsigned int targinfosize) +same_destroy(const struct xt_target *target, void *targinfo) { struct ipt_same_info *mr = targinfo; @@ -133,8 +131,7 @@ same_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; diff --git a/net/ipv4/netfilter/ipt_TCPMSS.c b/net/ipv4/netfilter/ipt_TCPMSS.c index ef2fe5b3f0d..4246c4321e5 100644 --- a/net/ipv4/netfilter/ipt_TCPMSS.c +++ b/net/ipv4/netfilter/ipt_TCPMSS.c @@ -21,26 +21,14 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); MODULE_DESCRIPTION("iptables TCP MSS modification module"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -static u_int16_t -cheat_check(u_int32_t oldvalinv, u_int32_t newval, u_int16_t oldcheck) -{ - u_int32_t diffs[] = { oldvalinv, newval }; - return csum_fold(csum_partial((char *)diffs, sizeof(diffs), - oldcheck^0xFFFF)); -} - static inline unsigned int optlen(const u_int8_t *opt, unsigned int offset) { /* Beware zero-length options: make finite progress */ - if (opt[offset] <= TCPOPT_NOP || opt[offset+1] == 0) return 1; - else return opt[offset+1]; + if (opt[offset] <= TCPOPT_NOP || opt[offset+1] == 0) + return 1; + else + return opt[offset+1]; } static unsigned int @@ -49,8 +37,7 @@ ipt_tcpmss_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct ipt_tcpmss_info *tcpmssinfo = targinfo; struct tcphdr *tcph; @@ -62,13 +49,8 @@ ipt_tcpmss_target(struct sk_buff **pskb, if (!skb_make_writable(pskb, (*pskb)->len)) return NF_DROP; - if ((*pskb)->ip_summed == CHECKSUM_HW && - skb_checksum_help(*pskb, out == NULL)) - return NF_DROP; - iph = (*pskb)->nh.iph; tcplen = (*pskb)->len - iph->ihl*4; - tcph = (void *)iph + iph->ihl*4; /* Since it passed flags test in tcp match, we know it is is @@ -84,54 +66,41 @@ ipt_tcpmss_target(struct sk_buff **pskb, return NF_DROP; } - if(tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU) { - if(!(*pskb)->dst) { + if (tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU) { + if (dst_mtu((*pskb)->dst) <= sizeof(struct iphdr) + + sizeof(struct tcphdr)) { if (net_ratelimit()) - printk(KERN_ERR - "ipt_tcpmss_target: no dst?! can't determine path-MTU\n"); + printk(KERN_ERR "ipt_tcpmss_target: " + "unknown or invalid path-MTU (%d)\n", + dst_mtu((*pskb)->dst)); return NF_DROP; /* or IPT_CONTINUE ?? */ } - if(dst_mtu((*pskb)->dst) <= (sizeof(struct iphdr) + sizeof(struct tcphdr))) { - if (net_ratelimit()) - printk(KERN_ERR - "ipt_tcpmss_target: unknown or invalid path-MTU (%d)\n", dst_mtu((*pskb)->dst)); - return NF_DROP; /* or IPT_CONTINUE ?? */ - } - - newmss = dst_mtu((*pskb)->dst) - sizeof(struct iphdr) - sizeof(struct tcphdr); + newmss = dst_mtu((*pskb)->dst) - sizeof(struct iphdr) - + sizeof(struct tcphdr); } else newmss = tcpmssinfo->mss; opt = (u_int8_t *)tcph; - for (i = sizeof(struct tcphdr); i < tcph->doff*4; i += optlen(opt, i)){ - if ((opt[i] == TCPOPT_MSS) && - ((tcph->doff*4 - i) >= TCPOLEN_MSS) && - (opt[i+1] == TCPOLEN_MSS)) { + for (i = sizeof(struct tcphdr); i < tcph->doff*4; i += optlen(opt, i)) { + if (opt[i] == TCPOPT_MSS && tcph->doff*4 - i >= TCPOLEN_MSS && + opt[i+1] == TCPOLEN_MSS) { u_int16_t oldmss; oldmss = (opt[i+2] << 8) | opt[i+3]; - if((tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU) && - (oldmss <= newmss)) - return IPT_CONTINUE; + if (tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU && + oldmss <= newmss) + return IPT_CONTINUE; opt[i+2] = (newmss & 0xff00) >> 8; opt[i+3] = (newmss & 0x00ff); - tcph->check = cheat_check(htons(oldmss)^0xFFFF, - htons(newmss), - tcph->check); - - DEBUGP(KERN_INFO "ipt_tcpmss_target: %u.%u.%u.%u:%hu" - "->%u.%u.%u.%u:%hu changed TCP MSS option" - " (from %u to %u)\n", - NIPQUAD((*pskb)->nh.iph->saddr), - ntohs(tcph->source), - NIPQUAD((*pskb)->nh.iph->daddr), - ntohs(tcph->dest), - oldmss, newmss); - goto retmodified; + tcph->check = nf_proto_csum_update(*pskb, + htons(oldmss)^0xFFFF, + htons(newmss), + tcph->check, 0); + return IPT_CONTINUE; } } @@ -143,13 +112,8 @@ ipt_tcpmss_target(struct sk_buff **pskb, newskb = skb_copy_expand(*pskb, skb_headroom(*pskb), TCPOLEN_MSS, GFP_ATOMIC); - if (!newskb) { - if (net_ratelimit()) - printk(KERN_ERR "ipt_tcpmss_target:" - " unable to allocate larger skb\n"); + if (!newskb) return NF_DROP; - } - kfree_skb(*pskb); *pskb = newskb; iph = (*pskb)->nh.iph; @@ -161,36 +125,29 @@ ipt_tcpmss_target(struct sk_buff **pskb, opt = (u_int8_t *)tcph + sizeof(struct tcphdr); memmove(opt + TCPOLEN_MSS, opt, tcplen - sizeof(struct tcphdr)); - tcph->check = cheat_check(htons(tcplen) ^ 0xFFFF, - htons(tcplen + TCPOLEN_MSS), tcph->check); - tcplen += TCPOLEN_MSS; - + tcph->check = nf_proto_csum_update(*pskb, + htons(tcplen) ^ 0xFFFF, + htons(tcplen + TCPOLEN_MSS), + tcph->check, 1); opt[0] = TCPOPT_MSS; opt[1] = TCPOLEN_MSS; opt[2] = (newmss & 0xff00) >> 8; opt[3] = (newmss & 0x00ff); - tcph->check = cheat_check(~0, *((u_int32_t *)opt), tcph->check); + tcph->check = nf_proto_csum_update(*pskb, ~0, *((u_int32_t *)opt), + tcph->check, 0); oldval = ((u_int16_t *)tcph)[6]; tcph->doff += TCPOLEN_MSS/4; - tcph->check = cheat_check(oldval ^ 0xFFFF, - ((u_int16_t *)tcph)[6], tcph->check); + tcph->check = nf_proto_csum_update(*pskb, + oldval ^ 0xFFFF, + ((u_int16_t *)tcph)[6], + tcph->check, 0); newtotlen = htons(ntohs(iph->tot_len) + TCPOLEN_MSS); - iph->check = cheat_check(iph->tot_len ^ 0xFFFF, - newtotlen, iph->check); + iph->check = nf_csum_update(iph->tot_len ^ 0xFFFF, + newtotlen, iph->check); iph->tot_len = newtotlen; - - DEBUGP(KERN_INFO "ipt_tcpmss_target: %u.%u.%u.%u:%hu" - "->%u.%u.%u.%u:%hu added TCP MSS option (%u)\n", - NIPQUAD((*pskb)->nh.iph->saddr), - ntohs(tcph->source), - NIPQUAD((*pskb)->nh.iph->daddr), - ntohs(tcph->dest), - newmss); - - retmodified: return IPT_CONTINUE; } @@ -200,9 +157,9 @@ static inline int find_syn_match(const struct ipt_entry_match *m) { const struct ipt_tcp *tcpinfo = (const struct ipt_tcp *)m->data; - if (strcmp(m->u.kernel.match->name, "tcp") == 0 - && (tcpinfo->flg_cmp & TH_SYN) - && !(tcpinfo->invflags & IPT_TCP_INV_FLAGS)) + if (strcmp(m->u.kernel.match->name, "tcp") == 0 && + tcpinfo->flg_cmp & TH_SYN && + !(tcpinfo->invflags & IPT_TCP_INV_FLAGS)) return 1; return 0; @@ -214,17 +171,17 @@ ipt_tcpmss_checkentry(const char *tablename, const void *e_void, const struct xt_target *target, void *targinfo, - unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_tcpmss_info *tcpmssinfo = targinfo; const struct ipt_entry *e = e_void; - if((tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU) && - ((hook_mask & ~((1 << NF_IP_FORWARD) - | (1 << NF_IP_LOCAL_OUT) - | (1 << NF_IP_POST_ROUTING))) != 0)) { - printk("TCPMSS: path-MTU clamping only supported in FORWARD, OUTPUT and POSTROUTING hooks\n"); + if (tcpmssinfo->mss == IPT_TCPMSS_CLAMP_PMTU && + (hook_mask & ~((1 << NF_IP_FORWARD) | + (1 << NF_IP_LOCAL_OUT) | + (1 << NF_IP_POST_ROUTING))) != 0) { + printk("TCPMSS: path-MTU clamping only supported in " + "FORWARD, OUTPUT and POSTROUTING hooks\n"); return 0; } diff --git a/net/ipv4/netfilter/ipt_TOS.c b/net/ipv4/netfilter/ipt_TOS.c index 1c7a5ca399b..471a4c438b0 100644 --- a/net/ipv4/netfilter/ipt_TOS.c +++ b/net/ipv4/netfilter/ipt_TOS.c @@ -26,27 +26,20 @@ target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct ipt_tos_target_info *tosinfo = targinfo; + struct iphdr *iph = (*pskb)->nh.iph; + u_int16_t oldtos; - if (((*pskb)->nh.iph->tos & IPTOS_TOS_MASK) != tosinfo->tos) { - u_int16_t diffs[2]; - + if ((iph->tos & IPTOS_TOS_MASK) != tosinfo->tos) { if (!skb_make_writable(pskb, sizeof(struct iphdr))) return NF_DROP; - - diffs[0] = htons((*pskb)->nh.iph->tos) ^ 0xFFFF; - (*pskb)->nh.iph->tos - = ((*pskb)->nh.iph->tos & IPTOS_PREC_MASK) - | tosinfo->tos; - diffs[1] = htons((*pskb)->nh.iph->tos); - (*pskb)->nh.iph->check - = csum_fold(csum_partial((char *)diffs, - sizeof(diffs), - (*pskb)->nh.iph->check - ^0xFFFF)); + iph = (*pskb)->nh.iph; + oldtos = iph->tos; + iph->tos = (iph->tos & IPTOS_PREC_MASK) | tosinfo->tos; + iph->check = nf_csum_update(oldtos ^ 0xFFFF, iph->tos, + iph->check); } return IPT_CONTINUE; } @@ -56,7 +49,6 @@ 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; diff --git a/net/ipv4/netfilter/ipt_TTL.c b/net/ipv4/netfilter/ipt_TTL.c index f48892ae0be..96e79cc6d0f 100644 --- a/net/ipv4/netfilter/ipt_TTL.c +++ b/net/ipv4/netfilter/ipt_TTL.c @@ -23,11 +23,10 @@ static unsigned int 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) + const void *targinfo) { struct iphdr *iph; const struct ipt_TTL_info *info = targinfo; - u_int16_t diffs[2]; int new_ttl; if (!skb_make_writable(pskb, (*pskb)->len)) @@ -55,12 +54,10 @@ ipt_ttl_target(struct sk_buff **pskb, } if (new_ttl != iph->ttl) { - diffs[0] = htons(((unsigned)iph->ttl) << 8) ^ 0xFFFF; + iph->check = nf_csum_update(ntohs((iph->ttl << 8)) ^ 0xFFFF, + ntohs(new_ttl << 8), + iph->check); iph->ttl = new_ttl; - diffs[1] = htons(((unsigned)iph->ttl) << 8); - iph->check = csum_fold(csum_partial((char *)diffs, - sizeof(diffs), - iph->check^0xFFFF)); } return IPT_CONTINUE; @@ -70,7 +67,6 @@ 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; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index d46fd677fa1..2b104ea54f4 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -308,7 +308,7 @@ static unsigned int ipt_ulog_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, void *userinfo) + const void *targinfo) { struct ipt_ulog_info *loginfo = (struct ipt_ulog_info *) targinfo; @@ -346,7 +346,6 @@ 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; diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c index 2927135873d..1798f86bc53 100644 --- a/net/ipv4/netfilter/ipt_ah.c +++ b/net/ipv4/netfilter/ipt_ah.c @@ -74,7 +74,6 @@ 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; diff --git a/net/ipv4/netfilter/ipt_dscp.c b/net/ipv4/netfilter/ipt_dscp.c deleted file mode 100644 index 47177591aeb..00000000000 --- a/net/ipv4/netfilter/ipt_dscp.c +++ /dev/null @@ -1,54 +0,0 @@ -/* IP tables module for matching the value of the IPv4 DSCP field - * - * ipt_dscp.c,v 1.3 2002/08/05 19:00:21 laforge Exp - * - * (C) 2002 by Harald Welte <laforge@netfilter.org> - * - * 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/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter_ipv4/ipt_dscp.h> -#include <linux/netfilter_ipv4/ip_tables.h> - -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 struct xt_match *match, const void *matchinfo, - int offset, unsigned int protoff, int *hotdrop) -{ - const struct ipt_dscp_info *info = matchinfo; - const struct iphdr *iph = skb->nh.iph; - - u_int8_t sh_dscp = ((info->dscp << IPT_DSCP_SHIFT) & IPT_DSCP_MASK); - - return ((iph->tos&IPT_DSCP_MASK) == sh_dscp) ^ info->invert; -} - -static struct ipt_match dscp_match = { - .name = "dscp", - .match = match, - .matchsize = sizeof(struct ipt_dscp_info), - .me = THIS_MODULE, -}; - -static int __init ipt_dscp_init(void) -{ - return ipt_register_match(&dscp_match); -} - -static void __exit ipt_dscp_fini(void) -{ - ipt_unregister_match(&dscp_match); - -} - -module_init(ipt_dscp_init); -module_exit(ipt_dscp_fini); diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index b2825041493..dafbdec0efc 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -88,8 +88,7 @@ static int 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 matchsize, - unsigned int hook_mask) + void *matchinfo, unsigned int hook_mask) { const struct ipt_ecn_info *info = matchinfo; const struct ipt_ip *ip = ip_void; diff --git a/net/ipv4/netfilter/ipt_hashlimit.c b/net/ipv4/netfilter/ipt_hashlimit.c index 3bd2368e1fc..4f73a61aa3d 100644 --- a/net/ipv4/netfilter/ipt_hashlimit.c +++ b/net/ipv4/netfilter/ipt_hashlimit.c @@ -478,7 +478,6 @@ 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; @@ -529,18 +528,46 @@ hashlimit_checkentry(const char *tablename, } static void -hashlimit_destroy(const struct xt_match *match, void *matchinfo, - unsigned int matchsize) +hashlimit_destroy(const struct xt_match *match, void *matchinfo) { struct ipt_hashlimit_info *r = matchinfo; htable_put(r->hinfo); } +#ifdef CONFIG_COMPAT +struct compat_ipt_hashlimit_info { + char name[IFNAMSIZ]; + struct hashlimit_cfg cfg; + compat_uptr_t hinfo; + compat_uptr_t master; +}; + +static void compat_from_user(void *dst, void *src) +{ + int off = offsetof(struct compat_ipt_hashlimit_info, hinfo); + + memcpy(dst, src, off); + memset(dst + off, 0, sizeof(struct compat_ipt_hashlimit_info) - off); +} + +static int compat_to_user(void __user *dst, void *src) +{ + int off = offsetof(struct compat_ipt_hashlimit_info, hinfo); + + return copy_to_user(dst, src, off) ? -EFAULT : 0; +} +#endif + static struct ipt_match ipt_hashlimit = { .name = "hashlimit", .match = hashlimit_match, .matchsize = sizeof(struct ipt_hashlimit_info), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct compat_ipt_hashlimit_info), + .compat_from_user = compat_from_user, + .compat_to_user = compat_to_user, +#endif .checkentry = hashlimit_checkentry, .destroy = hashlimit_destroy, .me = THIS_MODULE diff --git a/net/ipv4/netfilter/ipt_owner.c b/net/ipv4/netfilter/ipt_owner.c index 5ac6ac023b5..78c336f12a9 100644 --- a/net/ipv4/netfilter/ipt_owner.c +++ b/net/ipv4/netfilter/ipt_owner.c @@ -56,7 +56,6 @@ 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; diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 61a2139f9cf..32ae8d7ac50 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -35,14 +35,20 @@ static unsigned int ip_list_tot = 100; static unsigned int ip_pkt_list_tot = 20; static unsigned int ip_list_hash_size = 0; static unsigned int ip_list_perms = 0644; +static unsigned int ip_list_uid = 0; +static unsigned int ip_list_gid = 0; module_param(ip_list_tot, uint, 0400); module_param(ip_pkt_list_tot, uint, 0400); module_param(ip_list_hash_size, uint, 0400); module_param(ip_list_perms, uint, 0400); +module_param(ip_list_uid, uint, 0400); +module_param(ip_list_gid, uint, 0400); MODULE_PARM_DESC(ip_list_tot, "number of IPs to remember per list"); MODULE_PARM_DESC(ip_pkt_list_tot, "number of packets per IP to remember (max. 255)"); MODULE_PARM_DESC(ip_list_hash_size, "size of hash table used to look up IPs"); MODULE_PARM_DESC(ip_list_perms, "permissions on /proc/net/ipt_recent/* files"); +MODULE_PARM_DESC(ip_list_uid,"owner of /proc/net/ipt_recent/* files"); +MODULE_PARM_DESC(ip_list_gid,"owning group of /proc/net/ipt_recent/* files"); struct recent_entry { @@ -232,7 +238,7 @@ out: static int ipt_recent_checkentry(const char *tablename, const void *ip, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) + unsigned int hook_mask) { const struct ipt_recent_info *info = matchinfo; struct recent_table *t; @@ -274,6 +280,8 @@ ipt_recent_checkentry(const char *tablename, const void *ip, goto out; } t->proc->proc_fops = &recent_fops; + t->proc->uid = ip_list_uid; + t->proc->gid = ip_list_gid; t->proc->data = t; #endif spin_lock_bh(&recent_lock); @@ -286,8 +294,7 @@ out: } static void -ipt_recent_destroy(const struct xt_match *match, void *matchinfo, - unsigned int matchsize) +ipt_recent_destroy(const struct xt_match *match, void *matchinfo) { const struct ipt_recent_info *info = matchinfo; struct recent_table *t; diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 7f417484bfb..e2e7dd8d790 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -90,7 +90,7 @@ ipt_hook(unsigned int hook, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ipt_do_table(pskb, hook, in, out, &packet_filter, NULL); + return ipt_do_table(pskb, hook, in, out, &packet_filter); } static unsigned int @@ -108,7 +108,7 @@ ipt_local_out_hook(unsigned int hook, return NF_ACCEPT; } - return ipt_do_table(pskb, hook, in, out, &packet_filter, NULL); + return ipt_do_table(pskb, hook, in, out, &packet_filter); } static struct nf_hook_ops ipt_ops[] = { diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 4e7998beda6..79336cb4252 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -119,7 +119,7 @@ ipt_route_hook(unsigned int hook, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ipt_do_table(pskb, hook, in, out, &packet_mangler, NULL); + return ipt_do_table(pskb, hook, in, out, &packet_mangler); } static unsigned int @@ -148,7 +148,7 @@ ipt_local_hook(unsigned int hook, daddr = (*pskb)->nh.iph->daddr; tos = (*pskb)->nh.iph->tos; - ret = ipt_do_table(pskb, hook, in, out, &packet_mangler, NULL); + ret = ipt_do_table(pskb, hook, in, out, &packet_mangler); /* Reroute for ANY change. */ if (ret != NF_DROP && ret != NF_STOLEN && ret != NF_QUEUE && ((*pskb)->nh.iph->saddr != saddr diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 7912cce1e1b..bcbeb4aeacd 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -95,7 +95,7 @@ ipt_hook(unsigned int hook, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ipt_do_table(pskb, hook, in, out, &packet_raw, NULL); + return ipt_do_table(pskb, hook, in, out, &packet_raw); } /* 'raw' is the very first table. */ diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 663a73ee3f2..790f00d500c 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -25,7 +25,7 @@ #include <net/netfilter/nf_conntrack_protocol.h> #include <net/netfilter/nf_conntrack_core.h> -unsigned long nf_ct_icmp_timeout = 30*HZ; +unsigned long nf_ct_icmp_timeout __read_mostly = 30*HZ; #if 0 #define DEBUGP printk diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index d61e2a9d394..9c6cbe3d9fb 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -173,6 +173,8 @@ static const struct snmp_mib snmp4_udp_list[] = { SNMP_MIB_ITEM("NoPorts", UDP_MIB_NOPORTS), SNMP_MIB_ITEM("InErrors", UDP_MIB_INERRORS), SNMP_MIB_ITEM("OutDatagrams", UDP_MIB_OUTDATAGRAMS), + SNMP_MIB_ITEM("RcvbufErrors", UDP_MIB_RCVBUFERRORS), + SNMP_MIB_ITEM("SndbufErrors", UDP_MIB_SNDBUFERRORS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 62b2762a242..0e935b4c874 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -38,8 +38,7 @@ * 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/types.h> #include <asm/atomic.h> #include <asm/byteorder.h> @@ -484,6 +483,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (!inet->hdrincl) raw_probe_proto_opt(&fl, msg); + security_sk_classify_flow(sk, &fl); err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT)); } if (err) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b873cbcdd0b..20ffe8e88c0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2639,51 +2639,54 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, { struct rtable *rt = (struct rtable*)skb->dst; struct rtmsg *r; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; + struct nlmsghdr *nlh; struct rta_cacheinfo ci; -#ifdef CONFIG_IP_MROUTE - struct rtattr *eptr; -#endif - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*r), flags); - r = NLMSG_DATA(nlh); + + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); + if (nlh == NULL) + return -ENOBUFS; + + r = nlmsg_data(nlh); r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = rt->fl.fl4_tos; r->rtm_table = RT_TABLE_MAIN; + NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; - RTA_PUT(skb, RTA_DST, 4, &rt->rt_dst); + + NLA_PUT_U32(skb, RTA_DST, rt->rt_dst); + if (rt->fl.fl4_src) { r->rtm_src_len = 32; - RTA_PUT(skb, RTA_SRC, 4, &rt->fl.fl4_src); + NLA_PUT_U32(skb, RTA_SRC, rt->fl.fl4_src); } if (rt->u.dst.dev) - RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->u.dst.dev->ifindex); + NLA_PUT_U32(skb, RTA_OIF, rt->u.dst.dev->ifindex); #ifdef CONFIG_NET_CLS_ROUTE if (rt->u.dst.tclassid) - RTA_PUT(skb, RTA_FLOW, 4, &rt->u.dst.tclassid); + NLA_PUT_U32(skb, RTA_FLOW, rt->u.dst.tclassid); #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - if (rt->rt_multipath_alg != IP_MP_ALG_NONE) { - __u32 alg = rt->rt_multipath_alg; - - RTA_PUT(skb, RTA_MP_ALGO, 4, &alg); - } + if (rt->rt_multipath_alg != IP_MP_ALG_NONE) + NLA_PUT_U32(skb, RTA_MP_ALGO, rt->rt_multipath_alg); #endif if (rt->fl.iif) - RTA_PUT(skb, RTA_PREFSRC, 4, &rt->rt_spec_dst); + NLA_PUT_U32(skb, RTA_PREFSRC, rt->rt_spec_dst); else if (rt->rt_src != rt->fl.fl4_src) - RTA_PUT(skb, RTA_PREFSRC, 4, &rt->rt_src); + NLA_PUT_U32(skb, RTA_PREFSRC, rt->rt_src); + if (rt->rt_dst != rt->rt_gateway) - RTA_PUT(skb, RTA_GATEWAY, 4, &rt->rt_gateway); + NLA_PUT_U32(skb, RTA_GATEWAY, rt->rt_gateway); + if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) - goto rtattr_failure; + goto nla_put_failure; + ci.rta_lastuse = jiffies_to_clock_t(jiffies - rt->u.dst.lastuse); ci.rta_used = rt->u.dst.__use; ci.rta_clntref = atomic_read(&rt->u.dst.__refcnt); @@ -2700,10 +2703,7 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, ci.rta_tsage = xtime.tv_sec - rt->peer->tcp_ts_stamp; } } -#ifdef CONFIG_IP_MROUTE - eptr = (struct rtattr*)skb->tail; -#endif - RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); + if (rt->fl.iif) { #ifdef CONFIG_IP_MROUTE u32 dst = rt->rt_dst; @@ -2715,41 +2715,46 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, if (!nowait) { if (err == 0) return 0; - goto nlmsg_failure; + goto nla_put_failure; } else { if (err == -EMSGSIZE) - goto nlmsg_failure; - ((struct rta_cacheinfo*)RTA_DATA(eptr))->rta_error = err; + goto nla_put_failure; + ci.rta_error = err; } } } else #endif - RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fl.iif); + NLA_PUT_U32(skb, RTA_IIF, rt->fl.iif); } - nlh->nlmsg_len = skb->tail - b; - return skb->len; + NLA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); + + return nlmsg_end(skb, nlh); -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; +nla_put_failure: + return nlmsg_cancel(skb, nlh); } int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { - struct rtattr **rta = arg; - struct rtmsg *rtm = NLMSG_DATA(nlh); + struct rtmsg *rtm; + struct nlattr *tb[RTA_MAX+1]; struct rtable *rt = NULL; - u32 dst = 0; - u32 src = 0; - int iif = 0; - int err = -ENOBUFS; + u32 dst, src, iif; + int err; struct sk_buff *skb; + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy); + if (err < 0) + goto errout; + + rtm = nlmsg_data(nlh); + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - goto out; + if (skb == NULL) { + err = -ENOBUFS; + goto errout; + } /* Reserve room for dummy headers, this skb can pass through good chunk of routing engine. @@ -2760,62 +2765,61 @@ int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) skb->nh.iph->protocol = IPPROTO_ICMP; skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr)); - if (rta[RTA_SRC - 1]) - memcpy(&src, RTA_DATA(rta[RTA_SRC - 1]), 4); - if (rta[RTA_DST - 1]) - memcpy(&dst, RTA_DATA(rta[RTA_DST - 1]), 4); - if (rta[RTA_IIF - 1]) - memcpy(&iif, RTA_DATA(rta[RTA_IIF - 1]), sizeof(int)); + src = tb[RTA_SRC] ? nla_get_u32(tb[RTA_SRC]) : 0; + dst = tb[RTA_DST] ? nla_get_u32(tb[RTA_DST]) : 0; + iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; if (iif) { - struct net_device *dev = __dev_get_by_index(iif); - err = -ENODEV; - if (!dev) - goto out_free; + struct net_device *dev; + + dev = __dev_get_by_index(iif); + if (dev == NULL) { + err = -ENODEV; + goto errout_free; + } + skb->protocol = htons(ETH_P_IP); skb->dev = dev; local_bh_disable(); err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev); local_bh_enable(); - rt = (struct rtable*)skb->dst; - if (!err && rt->u.dst.error) + + rt = (struct rtable*) skb->dst; + if (err == 0 && rt->u.dst.error) err = -rt->u.dst.error; } else { - struct flowi fl = { .nl_u = { .ip4_u = { .daddr = dst, - .saddr = src, - .tos = rtm->rtm_tos } } }; - int oif = 0; - if (rta[RTA_OIF - 1]) - memcpy(&oif, RTA_DATA(rta[RTA_OIF - 1]), sizeof(int)); - fl.oif = oif; + struct flowi fl = { + .nl_u = { + .ip4_u = { + .daddr = dst, + .saddr = src, + .tos = rtm->rtm_tos, + }, + }, + .oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0, + }; err = ip_route_output_key(&rt, &fl); } + if (err) - goto out_free; + goto errout_free; skb->dst = &rt->u.dst; if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; - NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; - err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); - if (!err) - goto out_free; - if (err < 0) { - err = -EMSGSIZE; - goto out_free; - } + if (err <= 0) + goto errout_free; - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; -out: return err; + err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid); +errout: + return err; -out_free: +errout_free: kfree_skb(skb); - goto out; + goto errout; } int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) @@ -3143,13 +3147,9 @@ int __init ip_rt_init(void) } #endif - ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache", - sizeof(struct rtable), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - - if (!ipv4_dst_ops.kmem_cachep) - panic("IP: failed to allocate ip_dst_cache\n"); + ipv4_dst_ops.kmem_cachep = + kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); rt_hash_table = (struct rt_hash_bucket *) alloc_large_system_hash("IP route cache", diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index e20be3331f6..661e0a4bca7 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -214,6 +214,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, if (!req) goto out; + if (security_inet_conn_request(sk, skb, req)) { + reqsk_free(req); + goto out; + } ireq = inet_rsk(req); treq = tcp_rsk(req); treq->rcv_isn = htonl(skb->h.th->seq) - 1; @@ -259,6 +263,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, .uli_u = { .ports = { .sport = skb->h.th->dest, .dport = skb->h.th->source } } }; + security_req_classify_flow(req, &fl); if (ip_route_output_key(&rt, &fl)) { reqsk_free(req); goto out; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 70cea9d08a3..19b2071ff31 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -17,6 +17,7 @@ #include <net/ip.h> #include <net/route.h> #include <net/tcp.h> +#include <net/cipso_ipv4.h> /* From af_inet.c */ extern int sysctl_ip_nonlocal_bind; @@ -697,6 +698,40 @@ ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = &proc_dointvec }, +#ifdef CONFIG_NETLABEL + { + .ctl_name = NET_CIPSOV4_CACHE_ENABLE, + .procname = "cipso_cache_enable", + .data = &cipso_v4_cache_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = NET_CIPSOV4_CACHE_BUCKET_SIZE, + .procname = "cipso_cache_bucket_size", + .data = &cipso_v4_cache_bucketsize, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = NET_CIPSOV4_RBM_OPTFMT, + .procname = "cipso_rbm_optfmt", + .data = &cipso_v4_rbm_optfmt, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = NET_CIPSOV4_RBM_STRICTVALID, + .procname = "cipso_rbm_strictvalid", + .data = &cipso_v4_rbm_strictvalid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif /* CONFIG_NETLABEL */ { .ctl_name = 0 } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 934396bb137..66e9a729f6d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -268,7 +268,7 @@ #include <asm/uaccess.h> #include <asm/ioctls.h> -int sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; +int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; DEFINE_SNMP_STAT(struct tcp_mib, tcp_statistics) __read_mostly; @@ -568,7 +568,7 @@ new_segment: skb->truesize += copy; sk->sk_wmem_queued += copy; sk->sk_forward_alloc -= copy; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; tp->write_seq += copy; TCP_SKB_CB(skb)->end_seq += copy; skb_shinfo(skb)->gso_segs = 0; @@ -723,7 +723,7 @@ new_segment: * Check whether we can use HW checksum. */ if (sk->sk_route_caps & NETIF_F_ALL_CSUM) - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, tp, skb); copy = size_goal; @@ -955,8 +955,11 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) * receive buffer and there was a small segment * in queue. */ - (copied > 0 && (icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && - !icsk->icsk_ack.pingpong && !atomic_read(&sk->sk_rmem_alloc))) + (copied > 0 && + ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || + ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && + !icsk->icsk_ack.pingpong)) && + !atomic_read(&sk->sk_rmem_alloc))) time_to_ack = 1; } @@ -2205,7 +2208,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features) th->fin = th->psh = 0; th->check = ~csum_fold(th->check + delta); - if (skb->ip_summed != CHECKSUM_HW) + if (skb->ip_summed != CHECKSUM_PARTIAL) th->check = csum_fold(csum_partial(skb->h.raw, thlen, skb->csum)); @@ -2219,7 +2222,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features) delta = htonl(oldlen + (skb->tail - skb->h.raw) + skb->data_len); th->check = ~csum_fold(th->check + delta); - if (skb->ip_summed != CHECKSUM_HW) + if (skb->ip_summed != CHECKSUM_PARTIAL) th->check = csum_fold(csum_partial(skb->h.raw, thlen, skb->csum)); @@ -2254,9 +2257,7 @@ void __init tcp_init(void) tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, - SLAB_HWCACHE_ALIGN, NULL, NULL); - if (!tcp_hashinfo.bind_bucket_cachep) - panic("tcp_init: Cannot alloc tcp_bind_bucket cache."); + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); /* Size and allocate the main established and bind bucket * hash tables. diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index b0134ab0837..5730333cd0a 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -231,7 +231,7 @@ static struct tcp_congestion_ops bictcp = { static int __init bictcp_register(void) { - BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&bictcp); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 2be27980ca7..a60ef38d75c 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -358,7 +358,7 @@ static struct tcp_congestion_ops cubictcp = { static int __init cubictcp_register(void) { - BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); /* Precompute a bunch of the scaling factors that are used per-packet * based on SRTT of 100ms diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index fa3e1aad660..c4fc811bf37 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -189,7 +189,7 @@ static struct tcp_congestion_ops tcp_highspeed = { static int __init hstcp_register(void) { - BUG_ON(sizeof(struct hstcp) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct hstcp) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_highspeed); } diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 6edfe5e4510..682e7d5b6f2 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -286,7 +286,7 @@ static struct tcp_congestion_ops htcp = { static int __init htcp_register(void) { - BUG_ON(sizeof(struct htcp) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct htcp) > ICSK_CA_PRIV_SIZE); BUILD_BUG_ON(BETA_MIN >= BETA_MAX); return tcp_register_congestion_control(&htcp); } diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index 7406e0c5fb8..59e691d26f6 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -170,7 +170,7 @@ static struct tcp_congestion_ops tcp_hybla = { static int __init hybla_register(void) { - BUG_ON(sizeof(struct hybla) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct hybla) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_hybla); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 159fa3f1ba6..b3def0df14f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -72,24 +72,24 @@ #include <asm/unaligned.h> #include <net/netdma.h> -int sysctl_tcp_timestamps = 1; -int sysctl_tcp_window_scaling = 1; -int sysctl_tcp_sack = 1; -int sysctl_tcp_fack = 1; -int sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; -int sysctl_tcp_ecn; -int sysctl_tcp_dsack = 1; -int sysctl_tcp_app_win = 31; -int sysctl_tcp_adv_win_scale = 2; - -int sysctl_tcp_stdurg; -int sysctl_tcp_rfc1337; -int sysctl_tcp_max_orphans = NR_FILE; -int sysctl_tcp_frto; -int sysctl_tcp_nometrics_save; - -int sysctl_tcp_moderate_rcvbuf = 1; -int sysctl_tcp_abc; +int sysctl_tcp_timestamps __read_mostly = 1; +int sysctl_tcp_window_scaling __read_mostly = 1; +int sysctl_tcp_sack __read_mostly = 1; +int sysctl_tcp_fack __read_mostly = 1; +int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH; +int sysctl_tcp_ecn __read_mostly; +int sysctl_tcp_dsack __read_mostly = 1; +int sysctl_tcp_app_win __read_mostly = 31; +int sysctl_tcp_adv_win_scale __read_mostly = 2; + +int sysctl_tcp_stdurg __read_mostly; +int sysctl_tcp_rfc1337 __read_mostly; +int sysctl_tcp_max_orphans __read_mostly = NR_FILE; +int sysctl_tcp_frto __read_mostly; +int sysctl_tcp_nometrics_save __read_mostly; + +int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; +int sysctl_tcp_abc __read_mostly; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ @@ -127,7 +127,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, /* skb->len may jitter because of SACKs, even if peer * sends good full-sized frames. */ - len = skb->len; + len = skb_shinfo(skb)->gso_size ?: skb->len; if (len >= icsk->icsk_ack.rcv_mss) { icsk->icsk_ack.rcv_mss = len; } else { @@ -156,6 +156,8 @@ static void tcp_measure_rcv_mss(struct sock *sk, return; } } + if (icsk->icsk_ack.pending & ICSK_ACK_PUSHED) + icsk->icsk_ack.pending |= ICSK_ACK_PUSHED2; icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4b04c3edd4a..39b17985608 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -78,8 +78,8 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> -int sysctl_tcp_tw_reuse; -int sysctl_tcp_low_latency; +int sysctl_tcp_tw_reuse __read_mostly; +int sysctl_tcp_low_latency __read_mostly; /* Check TCP sequence numbers in ICMP packets. */ #define ICMP_MIN_LENGTH 8 @@ -484,7 +484,7 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) struct inet_sock *inet = inet_sk(sk); struct tcphdr *th = skb->h.th; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { th->check = ~tcp_v4_check(th, len, inet->saddr, inet->daddr, 0); skb->csum = offsetof(struct tcphdr, check); } else { @@ -509,7 +509,7 @@ int tcp_v4_gso_send_check(struct sk_buff *skb) th->check = 0; th->check = ~tcp_v4_check(th, skb->len, iph->saddr, iph->daddr, 0); skb->csum = offsetof(struct tcphdr, check); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; return 0; } @@ -798,6 +798,9 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_openreq_init(req, &tmp_opt, skb); + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_free; + ireq = inet_rsk(req); ireq->loc_addr = daddr; ireq->rmt_addr = saddr; @@ -948,9 +951,9 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) if (req) return tcp_check_req(sk, skb, req, prev); - nsk = __inet_lookup_established(&tcp_hashinfo, skb->nh.iph->saddr, - th->source, skb->nh.iph->daddr, - ntohs(th->dest), inet_iif(skb)); + nsk = inet_lookup_established(&tcp_hashinfo, skb->nh.iph->saddr, + th->source, skb->nh.iph->daddr, + th->dest, inet_iif(skb)); if (nsk) { if (nsk->sk_state != TCP_TIME_WAIT) { @@ -970,7 +973,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) static int tcp_v4_checksum_init(struct sk_buff *skb) { - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!tcp_v4_check(skb->h.th, skb->len, skb->nh.iph->saddr, skb->nh.iph->daddr, skb->csum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -1087,7 +1090,7 @@ int tcp_v4_rcv(struct sk_buff *skb) TCP_SKB_CB(skb)->sacked = 0; sk = __inet_lookup(&tcp_hashinfo, skb->nh.iph->saddr, th->source, - skb->nh.iph->daddr, ntohs(th->dest), + skb->nh.iph->daddr, th->dest, inet_iif(skb)); if (!sk) @@ -1101,7 +1104,7 @@ process: goto discard_and_relse; nf_reset(skb); - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard_and_relse; skb->dev = NULL; @@ -1165,7 +1168,7 @@ do_time_wait: case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(&tcp_hashinfo, skb->nh.iph->daddr, - ntohs(th->dest), + th->dest, inet_iif(skb)); if (sk2) { inet_twsk_deschedule((struct inet_timewait_sock *)sk, diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 48f28d617ce..308fb7e071c 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -35,7 +35,6 @@ * Version: $Id: tcp_lp.c,v 1.24 2006/09/05 20:22:53 hswong3i Exp $ */ -#include <linux/config.h> #include <linux/module.h> #include <net/tcp.h> @@ -328,7 +327,7 @@ static struct tcp_congestion_ops tcp_lp = { static int __init tcp_lp_register(void) { - BUG_ON(sizeof(struct lp) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct lp) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_lp); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 624e2b2c7f5..0163d982690 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -34,8 +34,8 @@ #define SYNC_INIT 1 #endif -int sysctl_tcp_syncookies = SYNC_INIT; -int sysctl_tcp_abort_on_overflow; +int sysctl_tcp_syncookies __read_mostly = SYNC_INIT; +int sysctl_tcp_abort_on_overflow __read_mostly; struct inet_timewait_death_row tcp_death_row = { .sysctl_max_tw_buckets = NR_FILE * 2, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b4f3ffe1b3b..061edfae0c2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -43,24 +43,24 @@ #include <linux/smp_lock.h> /* People can turn this off for buggy TCP's found in printers etc. */ -int sysctl_tcp_retrans_collapse = 1; +int sysctl_tcp_retrans_collapse __read_mostly = 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; +int sysctl_tcp_workaround_signed_windows __read_mostly = 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_tso_win_divisor __read_mostly = 3; -int sysctl_tcp_mtu_probing = 0; -int sysctl_tcp_base_mss = 512; +int sysctl_tcp_mtu_probing __read_mostly = 0; +int sysctl_tcp_base_mss __read_mostly = 512; /* By default, RFC2861 behavior. */ -int sysctl_tcp_slow_start_after_idle = 1; +int sysctl_tcp_slow_start_after_idle __read_mostly = 1; static void update_send_head(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb) @@ -577,7 +577,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; TCP_SKB_CB(skb)->sacked &= ~TCPCB_AT_TAIL; - if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_HW) { + if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { /* Copy and checksum data tail into the new buffer. */ buff->csum = csum_partial_copy_nocheck(skb->data + len, skb_put(buff, nsize), nsize, 0); @@ -586,7 +586,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss skb->csum = csum_block_sub(skb->csum, buff->csum, len); } else { - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); } @@ -689,7 +689,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) __pskb_trim_head(skb, len - skb_headlen(skb)); TCP_SKB_CB(skb)->seq += len; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb->truesize -= len; sk->sk_wmem_queued -= len; @@ -1062,7 +1062,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* This packet was never sent out yet, so no SACK bits. */ TCP_SKB_CB(buff)->sacked = 0; - buff->ip_summed = skb->ip_summed = CHECKSUM_HW; + buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); /* Fix up tso_factor for both original and new SKB. */ @@ -1206,8 +1206,7 @@ static int tcp_mtu_probe(struct sock *sk) 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; + nskb->ip_summed = skb->ip_summed; len = 0; while (len < probe_size) { @@ -1231,7 +1230,7 @@ static int tcp_mtu_probe(struct sock *sk) ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); - if (skb->ip_summed != CHECKSUM_HW) + if (skb->ip_summed != CHECKSUM_PARTIAL) skb->csum = csum_partial(skb->data, skb->len, 0); } else { __pskb_trim_head(skb, copy); @@ -1572,10 +1571,9 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int m memcpy(skb_put(skb, next_skb_size), next_skb->data, next_skb_size); - if (next_skb->ip_summed == CHECKSUM_HW) - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = next_skb->ip_summed; - if (skb->ip_summed != CHECKSUM_HW) + if (skb->ip_summed != CHECKSUM_PARTIAL) skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size); /* Update sequence range on original skb. */ diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 7c1bde3cd6c..fb09ade5897 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -23,14 +23,14 @@ #include <linux/module.h> #include <net/tcp.h> -int sysctl_tcp_syn_retries = TCP_SYN_RETRIES; -int sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; -int sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; -int sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; -int sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; -int sysctl_tcp_retries1 = TCP_RETR1; -int sysctl_tcp_retries2 = TCP_RETR2; -int sysctl_tcp_orphan_retries; +int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES; +int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES; +int sysctl_tcp_keepalive_time __read_mostly = TCP_KEEPALIVE_TIME; +int sysctl_tcp_keepalive_probes __read_mostly = TCP_KEEPALIVE_PROBES; +int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL; +int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; +int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; +int sysctl_tcp_orphan_retries __read_mostly; static void tcp_write_timer(unsigned long); static void tcp_delack_timer(unsigned long); diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 490360b5b4b..a3b7aa015a2 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -370,7 +370,7 @@ static struct tcp_congestion_ops tcp_vegas = { static int __init tcp_vegas_register(void) { - BUG_ON(sizeof(struct vegas) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct vegas) > ICSK_CA_PRIV_SIZE); tcp_register_congestion_control(&tcp_vegas); return 0; } diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 11b42a7135c..ce57bf302f6 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -9,7 +9,6 @@ * See http://www.ntu.edu.sg/home5/ZHOU0022/papers/CPFu03a.pdf */ -#include <linux/config.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/skbuff.h> @@ -213,7 +212,7 @@ static struct tcp_congestion_ops tcp_veno = { static int __init tcp_veno_register(void) { - BUG_ON(sizeof(struct veno) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct veno) > ICSK_CA_PRIV_SIZE); tcp_register_congestion_control(&tcp_veno); return 0; } diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index 5446312ffd2..4f42a86c77f 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -289,7 +289,7 @@ static struct tcp_congestion_ops tcp_westwood = { static int __init tcp_westwood_register(void) { - BUG_ON(sizeof(struct westwood) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct westwood) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_westwood); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f136cec96d9..77e265d7bb8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -118,14 +118,33 @@ DEFINE_SNMP_STAT(struct udp_mib, udp_statistics) __read_mostly; struct hlist_head udp_hash[UDP_HTABLE_SIZE]; DEFINE_RWLOCK(udp_hash_lock); -/* Shared by v4/v6 udp. */ -int udp_port_rover; +static int udp_port_rover; -static int udp_v4_get_port(struct sock *sk, unsigned short snum) +static inline int udp_lport_inuse(u16 num) +{ + struct sock *sk; + struct hlist_node *node; + + sk_for_each(sk, node, &udp_hash[num & (UDP_HTABLE_SIZE - 1)]) + if (inet_sk(sk)->num == num) + return 1; + return 0; +} + +/** + * udp_get_port - common port lookup for IPv4 and IPv6 + * + * @sk: socket struct in question + * @snum: port number to look up + * @saddr_comp: AF-dependent comparison of bound local IP addresses + */ +int udp_get_port(struct sock *sk, unsigned short snum, + int (*saddr_cmp)(const struct sock *sk1, const struct sock *sk2)) { struct hlist_node *node; + struct hlist_head *head; struct sock *sk2; - struct inet_sock *inet = inet_sk(sk); + int error = 1; write_lock_bh(&udp_hash_lock); if (snum == 0) { @@ -137,11 +156,10 @@ static int udp_v4_get_port(struct sock *sk, unsigned short snum) best_size_so_far = 32767; best = result = udp_port_rover; for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) { - struct hlist_head *list; int size; - list = &udp_hash[result & (UDP_HTABLE_SIZE - 1)]; - if (hlist_empty(list)) { + head = &udp_hash[result & (UDP_HTABLE_SIZE - 1)]; + if (hlist_empty(head)) { if (result > sysctl_local_port_range[1]) result = sysctl_local_port_range[0] + ((result - sysctl_local_port_range[0]) & @@ -149,12 +167,11 @@ static int udp_v4_get_port(struct sock *sk, unsigned short snum) goto gotit; } size = 0; - sk_for_each(sk2, node, list) - if (++size >= best_size_so_far) - goto next; - best_size_so_far = size; - best = result; - next:; + sk_for_each(sk2, node, head) + if (++size < best_size_so_far) { + best_size_so_far = size; + best = result; + } } result = best; for(i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++, result += UDP_HTABLE_SIZE) { @@ -170,38 +187,44 @@ static int udp_v4_get_port(struct sock *sk, unsigned short snum) gotit: udp_port_rover = snum = result; } else { - sk_for_each(sk2, node, - &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]) { - struct inet_sock *inet2 = inet_sk(sk2); - - if (inet2->num == snum && - sk2 != sk && - !ipv6_only_sock(sk2) && - (!sk2->sk_bound_dev_if || - !sk->sk_bound_dev_if || - sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && - (!inet2->rcv_saddr || - !inet->rcv_saddr || - inet2->rcv_saddr == inet->rcv_saddr) && - (!sk2->sk_reuse || !sk->sk_reuse)) + head = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]; + + sk_for_each(sk2, node, head) + if (inet_sk(sk2)->num == snum && + sk2 != sk && + (!sk2->sk_reuse || !sk->sk_reuse) && + (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if + || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (*saddr_cmp)(sk, sk2) ) goto fail; - } } - inet->num = snum; + inet_sk(sk)->num = snum; if (sk_unhashed(sk)) { - struct hlist_head *h = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]; - - sk_add_node(sk, h); + head = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]; + sk_add_node(sk, head); sock_prot_inc_use(sk->sk_prot); } - write_unlock_bh(&udp_hash_lock); - return 0; - + error = 0; fail: write_unlock_bh(&udp_hash_lock); - return 1; + return error; +} + +static inline int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) +{ + struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); + + return ( !ipv6_only_sock(sk2) && + (!inet1->rcv_saddr || !inet2->rcv_saddr || + inet1->rcv_saddr == inet2->rcv_saddr )); } +static inline int udp_v4_get_port(struct sock *sk, unsigned short snum) +{ + return udp_get_port(sk, snum, ipv4_rcv_saddr_equal); +} + + static void udp_v4_hash(struct sock *sk) { BUG(); @@ -429,7 +452,7 @@ static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up) /* * Only one fragment on the socket. */ - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { skb->csum = offsetof(struct udphdr, check); uh->check = ~csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len, IPPROTO_UDP, 0); @@ -448,7 +471,7 @@ static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up) * fragments on the socket so that all csums of sk_buffs * should be together. */ - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { int offset = (unsigned char *)uh - skb->data; skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); @@ -603,6 +626,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, .uli_u = { .ports = { .sport = inet->sport, .dport = dport } } }; + security_sk_classify_flow(sk, &fl); err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT)); if (err) goto out; @@ -661,6 +685,16 @@ out: UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS); return len; } + /* + * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting + * ENOBUFS might not be good (it's not tunable per se), but otherwise + * we don't have a good statistic (IpOutDiscards but it can be too many + * things). We could add another new stat but at least for now that + * seems like overkill. + */ + if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS); + } return err; do_confirm: @@ -980,6 +1014,7 @@ static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb) static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); + int rc; /* * Charge it to the socket, dropping if the queue is full. @@ -1026,7 +1061,10 @@ static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) skb->ip_summed = CHECKSUM_UNNECESSARY; } - if (sock_queue_rcv_skb(sk,skb)<0) { + if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { + /* Note that an ENOMEM error is charged twice */ + if (rc == -ENOMEM) + UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS); UDP_INC_STATS_BH(UDP_MIB_INERRORS); kfree_skb(skb); return -1; @@ -1087,7 +1125,7 @@ static void udp_checksum_init(struct sk_buff *skb, struct udphdr *uh, { if (uh->check == 0) { skb->ip_summed = CHECKSUM_UNNECESSARY; - } else if (skb->ip_summed == CHECKSUM_HW) { + } else if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!udp_check(uh, ulen, saddr, daddr, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -1581,7 +1619,7 @@ EXPORT_SYMBOL(udp_disconnect); EXPORT_SYMBOL(udp_hash); EXPORT_SYMBOL(udp_hash_lock); EXPORT_SYMBOL(udp_ioctl); -EXPORT_SYMBOL(udp_port_rover); +EXPORT_SYMBOL(udp_get_port); EXPORT_SYMBOL(udp_prot); EXPORT_SYMBOL(udp_sendmsg); EXPORT_SYMBOL(udp_poll); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 817ed84511a..040e8475f29 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -106,7 +106,7 @@ int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) if (x->mode->input(x, skb)) goto drop; - if (x->props.mode) { + if (x->props.mode == XFRM_MODE_TUNNEL) { decaps = 1; break; } diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c index a9e6b3dd19c..92676b7e403 100644 --- a/net/ipv4/xfrm4_mode_transport.c +++ b/net/ipv4/xfrm4_mode_transport.c @@ -21,9 +21,8 @@ * On exit, skb->h will be set to the start of the payload to be processed * by x->type->output and skb->nh will be set to the top IP header. */ -static int xfrm4_transport_output(struct sk_buff *skb) +static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb) { - struct xfrm_state *x; struct iphdr *iph; int ihl; @@ -33,7 +32,6 @@ static int xfrm4_transport_output(struct sk_buff *skb) ihl = iph->ihl * 4; skb->h.raw += ihl; - x = skb->dst->xfrm; skb->nh.raw = memmove(skb_push(skb, x->props.header_len), iph, ihl); return 0; } diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 13cafbe56ce..e23c21d31a5 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -33,10 +33,9 @@ static inline void ipip_ecn_decapsulate(struct sk_buff *skb) * On exit, skb->h will be set to the start of the payload to be processed * by x->type->output and skb->nh will be set to the top IP header. */ -static int xfrm4_tunnel_output(struct sk_buff *skb) +static int xfrm4_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { struct dst_entry *dst = skb->dst; - struct xfrm_state *x = dst->xfrm; struct iphdr *iph, *top_iph; int flags; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index d16f863cf68..04403fb01a5 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -48,13 +48,13 @@ static int xfrm4_output_one(struct sk_buff *skb) struct xfrm_state *x = dst->xfrm; int err; - if (skb->ip_summed == CHECKSUM_HW) { - err = skb_checksum_help(skb, 0); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); if (err) goto error_nolock; } - if (x->props.mode) { + if (x->props.mode == XFRM_MODE_TUNNEL) { err = xfrm4_tunnel_check_size(skb); if (err) goto error_nolock; @@ -66,7 +66,7 @@ static int xfrm4_output_one(struct sk_buff *skb) if (err) goto error; - err = x->mode->output(skb); + err = x->mode->output(x, skb); if (err) goto error; @@ -85,7 +85,7 @@ static int xfrm4_output_one(struct sk_buff *skb) } dst = skb->dst; x = dst->xfrm; - } while (x && !x->props.mode); + } while (x && (x->props.mode != XFRM_MODE_TUNNEL)); IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; err = 0; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 8f50eae47d0..eabcd27b176 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -21,6 +21,25 @@ static int xfrm4_dst_lookup(struct xfrm_dst **dst, struct flowi *fl) return __ip_route_output_key((struct rtable**)dst, fl); } +static int xfrm4_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr) +{ + struct rtable *rt; + struct flowi fl_tunnel = { + .nl_u = { + .ip4_u = { + .daddr = daddr->a4, + }, + }, + }; + + if (!xfrm4_dst_lookup((struct xfrm_dst **)&rt, &fl_tunnel)) { + saddr->a4 = rt->rt_src; + dst_release(&rt->u.dst); + return 0; + } + return -EHOSTUNREACH; +} + static struct dst_entry * __xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy) { @@ -33,7 +52,7 @@ __xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy) xdst->u.rt.fl.fl4_dst == fl->fl4_dst && xdst->u.rt.fl.fl4_src == fl->fl4_src && xdst->u.rt.fl.fl4_tos == fl->fl4_tos && - xfrm_bundle_ok(xdst, fl, AF_INET)) { + xfrm_bundle_ok(xdst, fl, AF_INET, 0)) { dst_clone(dst); break; } @@ -93,10 +112,11 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int xdst = (struct xfrm_dst *)dst1; xdst->route = &rt->u.dst; + xdst->genid = xfrm[i]->genid; dst1->next = dst_prev; dst_prev = dst1; - if (xfrm[i]->props.mode) { + if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { remote = xfrm[i]->id.daddr.a4; local = xfrm[i]->props.saddr.a4; tunnel = 1; @@ -135,6 +155,7 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int dst_prev->flags |= DST_HOST; dst_prev->lastuse = jiffies; dst_prev->header_len = header_len; + dst_prev->nfheader_len = 0; dst_prev->trailer_len = trailer_len; memcpy(&dst_prev->metrics, &x->route->metrics, sizeof(dst_prev->metrics)); @@ -296,6 +317,7 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .family = AF_INET, .dst_ops = &xfrm4_dst_ops, .dst_lookup = xfrm4_dst_lookup, + .get_saddr = xfrm4_get_saddr, .find_bundle = __xfrm4_find_bundle, .bundle_create = __xfrm4_bundle_create, .decode_session = _decode_session4, diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 81e1751c966..fe2034494d0 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -42,99 +42,15 @@ __xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->props.saddr = tmpl->saddr; if (x->props.saddr.a4 == 0) x->props.saddr.a4 = saddr->a4; - if (tmpl->mode && x->props.saddr.a4 == 0) { - struct rtable *rt; - struct flowi fl_tunnel = { - .nl_u = { - .ip4_u = { - .daddr = x->id.daddr.a4, - } - } - }; - if (!xfrm_dst_lookup((struct xfrm_dst **)&rt, - &fl_tunnel, AF_INET)) { - x->props.saddr.a4 = rt->rt_src; - dst_release(&rt->u.dst); - } - } x->props.mode = tmpl->mode; x->props.reqid = tmpl->reqid; x->props.family = AF_INET; } -static struct xfrm_state * -__xfrm4_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto) -{ - unsigned h = __xfrm4_spi_hash(daddr, spi, proto); - struct xfrm_state *x; - - list_for_each_entry(x, xfrm4_state_afinfo.state_byspi+h, byspi) { - if (x->props.family == AF_INET && - spi == x->id.spi && - daddr->a4 == x->id.daddr.a4 && - proto == x->id.proto) { - xfrm_state_hold(x); - return x; - } - } - return NULL; -} - -static struct xfrm_state * -__xfrm4_find_acq(u8 mode, u32 reqid, u8 proto, - xfrm_address_t *daddr, xfrm_address_t *saddr, - int create) -{ - struct xfrm_state *x, *x0; - unsigned h = __xfrm4_dst_hash(daddr); - - x0 = NULL; - - list_for_each_entry(x, xfrm4_state_afinfo.state_bydst+h, bydst) { - if (x->props.family == AF_INET && - daddr->a4 == x->id.daddr.a4 && - mode == x->props.mode && - proto == x->id.proto && - saddr->a4 == x->props.saddr.a4 && - reqid == x->props.reqid && - x->km.state == XFRM_STATE_ACQ && - !x->id.spi) { - x0 = x; - break; - } - } - if (!x0 && create && (x0 = xfrm_state_alloc()) != NULL) { - x0->sel.daddr.a4 = daddr->a4; - x0->sel.saddr.a4 = saddr->a4; - x0->sel.prefixlen_d = 32; - x0->sel.prefixlen_s = 32; - x0->props.saddr.a4 = saddr->a4; - x0->km.state = XFRM_STATE_ACQ; - x0->id.daddr.a4 = daddr->a4; - x0->id.proto = proto; - x0->props.family = AF_INET; - x0->props.mode = mode; - x0->props.reqid = reqid; - x0->props.family = AF_INET; - x0->lft.hard_add_expires_seconds = XFRM_ACQ_EXPIRES; - xfrm_state_hold(x0); - x0->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ; - add_timer(&x0->timer); - xfrm_state_hold(x0); - list_add_tail(&x0->bydst, xfrm4_state_afinfo.state_bydst+h); - wake_up(&km_waitq); - } - if (x0) - xfrm_state_hold(x0); - return x0; -} - static struct xfrm_state_afinfo xfrm4_state_afinfo = { .family = AF_INET, .init_flags = xfrm4_init_flags, .init_tempsel = __xfrm4_init_tempsel, - .state_lookup = __xfrm4_state_lookup, - .find_acq = __xfrm4_find_acq, }; void __init xfrm4_state_init(void) diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index f8ceaa127c8..f110af5b131 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -28,7 +28,7 @@ static int ipip_xfrm_rcv(struct xfrm_state *x, struct sk_buff *skb) static int ipip_init_state(struct xfrm_state *x) { - if (!x->props.mode) + if (x->props.mode != XFRM_MODE_TUNNEL) return -EINVAL; if (x->encap) diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 0ba06c0c5d3..a2d211da2ab 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -98,6 +98,15 @@ config INET6_IPCOMP If unsure, say Y. +config IPV6_MIP6 + bool "IPv6: Mobility (EXPERIMENTAL)" + depends on IPV6 && EXPERIMENTAL + select XFRM + ---help--- + Support for IPv6 Mobility described in RFC 3775. + + If unsure, say N. + config INET6_XFRM_TUNNEL tristate select INET6_TUNNEL @@ -127,6 +136,13 @@ config INET6_XFRM_MODE_TUNNEL If unsure, say Y. +config INET6_XFRM_MODE_ROUTEOPTIMIZATION + tristate "IPv6: MIPv6 route optimization mode (EXPERIMENTAL)" + depends on IPV6 && EXPERIMENTAL + select XFRM + ---help--- + Support for MIPv6 route optimization mode. + config IPV6_TUNNEL tristate "IPv6: IPv6-in-IPv6 tunnel" select INET6_TUNNEL @@ -136,3 +152,31 @@ config IPV6_TUNNEL If unsure, say N. +config IPV6_SUBTREES + bool "IPv6: source address based routing" + depends on IPV6 && EXPERIMENTAL + ---help--- + Enable routing by source address or prefix. + + The destination address is still the primary routing key, so mixing + normal and source prefix specific routes in the same routing table + may sometimes lead to unintended routing behavior. This can be + avoided by defining different routing tables for the normal and + source prefix specific routes. + + If unsure, say N. + +config IPV6_MULTIPLE_TABLES + bool "IPv6: Multiple Routing Tables" + depends on IPV6 && EXPERIMENTAL + select FIB_RULES + ---help--- + Support multiple routing tables. + +config IPV6_ROUTE_FWMARK + bool "IPv6: use netfilter MARK value as routing key" + depends on IPV6_MULTIPLE_TABLES && NETFILTER + ---help--- + If you say Y here, you will be able to specify different routes for + packets with different mark values (see iptables(8), MARK target). + diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 386e0a62694..0213c6612b5 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -13,6 +13,9 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \ ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ xfrm6_output.o ipv6-$(CONFIG_NETFILTER) += netfilter.o +ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o +ipv6-$(CONFIG_IPV6_MIP6) += mip6.o + ipv6-objs += $(ipv6-y) obj-$(CONFIG_INET6_AH) += ah6.o @@ -22,6 +25,7 @@ obj-$(CONFIG_INET6_XFRM_TUNNEL) += xfrm6_tunnel.o obj-$(CONFIG_INET6_TUNNEL) += tunnel6.o obj-$(CONFIG_INET6_XFRM_MODE_TRANSPORT) += xfrm6_mode_transport.o obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o +obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c7852b38e03..c1867635239 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -48,6 +48,7 @@ #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> +#include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/if_arcnet.h> #include <linux/if_infiniband.h> @@ -72,6 +73,7 @@ #include <net/addrconf.h> #include <net/tcp.h> #include <net/ip.h> +#include <net/netlink.h> #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> @@ -117,9 +119,6 @@ static int ipv6_count_addresses(struct inet6_dev *idev); static struct inet6_ifaddr *inet6_addr_lst[IN6_ADDR_HSIZE]; static DEFINE_RWLOCK(addrconf_hash_lock); -/* Protects inet6 devices */ -DEFINE_RWLOCK(addrconf_lock); - static void addrconf_verify(unsigned long); static DEFINE_TIMER(addr_chk_timer, addrconf_verify, 0, 0); @@ -144,7 +143,7 @@ static int ipv6_chk_same_addr(const struct in6_addr *addr, struct net_device *de static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); -struct ipv6_devconf ipv6_devconf = { +struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, @@ -173,9 +172,10 @@ struct ipv6_devconf ipv6_devconf = { .accept_ra_rt_info_max_plen = 0, #endif #endif + .proxy_ndp = 0, }; -static struct ipv6_devconf ipv6_devconf_dflt = { +static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, @@ -203,6 +203,7 @@ static struct ipv6_devconf ipv6_devconf_dflt = { .accept_ra_rt_info_max_plen = 0, #endif #endif + .proxy_ndp = 0, }; /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ @@ -314,6 +315,12 @@ static void addrconf_mod_timer(struct inet6_ifaddr *ifp, /* Nobody refers to this device, we may destroy it. */ +static void in6_dev_finish_destroy_rcu(struct rcu_head *head) +{ + struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu); + kfree(idev); +} + void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; @@ -328,7 +335,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) return; } snmp6_free_dev(idev); - kfree(idev); + call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu); } static struct inet6_dev * ipv6_add_dev(struct net_device *dev) @@ -404,9 +411,8 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) if (netif_carrier_ok(dev)) ndev->if_flags |= IF_READY; - write_lock_bh(&addrconf_lock); - dev->ip6_ptr = ndev; - write_unlock_bh(&addrconf_lock); + /* protected by rtnl_lock */ + rcu_assign_pointer(dev->ip6_ptr, ndev); ipv6_mc_init_dev(ndev); ndev->tstamp = jiffies; @@ -470,7 +476,7 @@ static void addrconf_forward_change(void) read_lock(&dev_base_lock); for (dev=dev_base; dev; dev=dev->next) { - read_lock(&addrconf_lock); + rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!ipv6_devconf.forwarding); @@ -478,7 +484,7 @@ static void addrconf_forward_change(void) if (changed) dev_forward_change(idev); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); } read_unlock(&dev_base_lock); } @@ -539,7 +545,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, int hash; int err = 0; - read_lock_bh(&addrconf_lock); + rcu_read_lock_bh(); if (idev->dead) { err = -ENODEV; /*XXX*/ goto out2; @@ -608,7 +614,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, in6_ifa_hold(ifa); write_unlock(&idev->lock); out2: - read_unlock_bh(&addrconf_lock); + rcu_read_unlock_bh(); if (likely(err == 0)) atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa); @@ -734,7 +740,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) { if (onlink == 0) { - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); rt = NULL; } else if (!(rt->rt6i_flags & RTF_EXPIRES)) { rt->rt6i_expires = expires; @@ -911,7 +917,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, memset(&hiscore, 0, sizeof(hiscore)); read_lock(&dev_base_lock); - read_lock(&addrconf_lock); + rcu_read_lock(); for (dev = dev_base; dev; dev=dev->next) { struct inet6_dev *idev; @@ -1032,9 +1038,27 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, continue; } - /* Rule 4: Prefer home address -- not implemented yet */ + /* Rule 4: Prefer home address */ +#ifdef CONFIG_IPV6_MIP6 + if (hiscore.rule < 4) { + if (ifa_result->flags & IFA_F_HOMEADDRESS) + hiscore.attrs |= IPV6_SADDR_SCORE_HOA; + hiscore.rule++; + } + if (ifa->flags & IFA_F_HOMEADDRESS) { + score.attrs |= IPV6_SADDR_SCORE_HOA; + if (!(ifa_result->flags & IFA_F_HOMEADDRESS)) { + score.rule = 4; + goto record_it; + } + } else { + if (hiscore.attrs & IPV6_SADDR_SCORE_HOA) + continue; + } +#else if (hiscore.rule < 4) hiscore.rule++; +#endif /* Rule 5: Prefer outgoing interface */ if (hiscore.rule < 5) { @@ -1123,7 +1147,7 @@ record_it: } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); read_unlock(&dev_base_lock); if (!ifa_result) @@ -1147,7 +1171,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr) struct inet6_dev *idev; int err = -EADDRNOTAVAIL; - read_lock(&addrconf_lock); + rcu_read_lock(); if ((idev = __in6_dev_get(dev)) != NULL) { struct inet6_ifaddr *ifp; @@ -1161,7 +1185,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr) } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); return err; } @@ -1462,7 +1486,7 @@ static void ipv6_regen_rndid(unsigned long data) struct inet6_dev *idev = (struct inet6_dev *) data; unsigned long expires; - read_lock_bh(&addrconf_lock); + rcu_read_lock_bh(); write_lock_bh(&idev->lock); if (idev->dead) @@ -1486,7 +1510,7 @@ static void ipv6_regen_rndid(unsigned long data) out: write_unlock_bh(&idev->lock); - read_unlock_bh(&addrconf_lock); + rcu_read_unlock_bh(); in6_dev_put(idev); } @@ -1507,59 +1531,56 @@ static void addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, unsigned long expires, u32 flags) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_PREFIX, + .fc_metric = IP6_RT_PRIO_ADDRCONF, + .fc_ifindex = dev->ifindex, + .fc_expires = expires, + .fc_dst_len = plen, + .fc_flags = RTF_UP | flags, + }; - memset(&rtmsg, 0, sizeof(rtmsg)); - ipv6_addr_copy(&rtmsg.rtmsg_dst, pfx); - rtmsg.rtmsg_dst_len = plen; - rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF; - rtmsg.rtmsg_ifindex = dev->ifindex; - rtmsg.rtmsg_info = expires; - rtmsg.rtmsg_flags = RTF_UP|flags; - rtmsg.rtmsg_type = RTMSG_NEWROUTE; + ipv6_addr_copy(&cfg.fc_dst, pfx); /* Prevent useless cloning on PtP SIT. This thing is done here expecting that the whole class of non-broadcast devices need not cloning. */ - if (dev->type == ARPHRD_SIT && (dev->flags&IFF_POINTOPOINT)) - rtmsg.rtmsg_flags |= RTF_NONEXTHOP; + if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT)) + cfg.fc_flags |= RTF_NONEXTHOP; - ip6_route_add(&rtmsg, NULL, NULL, NULL); + ip6_route_add(&cfg); } /* Create "default" multicast route to the interface */ static void addrconf_add_mroute(struct net_device *dev) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_LOCAL, + .fc_metric = IP6_RT_PRIO_ADDRCONF, + .fc_ifindex = dev->ifindex, + .fc_dst_len = 8, + .fc_flags = RTF_UP, + }; + + ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - memset(&rtmsg, 0, sizeof(rtmsg)); - ipv6_addr_set(&rtmsg.rtmsg_dst, - htonl(0xFF000000), 0, 0, 0); - rtmsg.rtmsg_dst_len = 8; - rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF; - rtmsg.rtmsg_ifindex = dev->ifindex; - rtmsg.rtmsg_flags = RTF_UP; - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - ip6_route_add(&rtmsg, NULL, NULL, NULL); + ip6_route_add(&cfg); } static void sit_route_add(struct net_device *dev) { - struct in6_rtmsg rtmsg; - - memset(&rtmsg, 0, sizeof(rtmsg)); - - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_MAIN, + .fc_metric = IP6_RT_PRIO_ADDRCONF, + .fc_ifindex = dev->ifindex, + .fc_dst_len = 96, + .fc_flags = RTF_UP | RTF_NONEXTHOP, + }; /* prefix length - 96 bits "::d.d.d.d" */ - rtmsg.rtmsg_dst_len = 96; - rtmsg.rtmsg_flags = RTF_UP|RTF_NONEXTHOP; - rtmsg.rtmsg_ifindex = dev->ifindex; - - ip6_route_add(&rtmsg, NULL, NULL, NULL); + ip6_route_add(&cfg); } static void addrconf_add_lroute(struct net_device *dev) @@ -1660,7 +1681,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) { if (rt->rt6i_flags&RTF_EXPIRES) { if (valid_lft == 0) { - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); rt = NULL; } else { rt->rt6i_expires = jiffies + rt_expires; @@ -1870,12 +1891,11 @@ err_exit: * Manual configuration of address on an interface */ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen, - __u32 prefered_lft, __u32 valid_lft) + __u8 ifa_flags, __u32 prefered_lft, __u32 valid_lft) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; - __u8 ifa_flags = 0; int scope; ASSERT_RTNL(); @@ -1887,9 +1907,6 @@ static int inet6_addr_add(int ifindex, struct in6_addr *pfx, int plen, if ((dev = __dev_get_by_index(ifindex)) == NULL) return -ENODEV; - if (!(dev->flags&IFF_UP)) - return -ENETDOWN; - if ((idev = addrconf_add_dev(dev)) == NULL) return -ENOBUFS; @@ -1971,7 +1988,7 @@ int addrconf_add_ifaddr(void __user *arg) rtnl_lock(); err = inet6_addr_add(ireq.ifr6_ifindex, &ireq.ifr6_addr, ireq.ifr6_prefixlen, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + IFA_F_PERMANENT, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); rtnl_unlock(); return err; } @@ -2344,10 +2361,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) Do not dev_put! */ if (how == 1) { - write_lock_bh(&addrconf_lock); - dev->ip6_ptr = NULL; idev->dead = 1; - write_unlock_bh(&addrconf_lock); + + /* protected by rtnl_lock */ + rcu_assign_pointer(dev->ip6_ptr, NULL); /* Step 1.5: remove snmp6 entry */ snmp6_unregister_dev(idev); @@ -2514,7 +2531,8 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) spin_lock_bh(&ifp->lock); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || - !(ifp->flags&IFA_F_TENTATIVE)) { + !(ifp->flags&IFA_F_TENTATIVE) || + ifp->flags & IFA_F_NODAD) { ifp->flags &= ~IFA_F_TENTATIVE; spin_unlock_bh(&ifp->lock); read_unlock_bh(&idev->lock); @@ -2759,6 +2777,26 @@ void if6_proc_exit(void) } #endif /* CONFIG_PROC_FS */ +#ifdef CONFIG_IPV6_MIP6 +/* Check if address is a home address configured on any interface. */ +int ipv6_chk_home_addr(struct in6_addr *addr) +{ + int ret = 0; + struct inet6_ifaddr * ifp; + u8 hash = ipv6_addr_hash(addr); + read_lock_bh(&addrconf_hash_lock); + for (ifp = inet6_addr_lst[hash]; ifp; ifp = ifp->lst_next) { + if (ipv6_addr_cmp(&ifp->addr, addr) == 0 && + (ifp->flags & IFA_F_HOMEADDRESS)) { + ret = 1; + break; + } + } + read_unlock_bh(&addrconf_hash_lock); + return ret; +} +#endif + /* * Periodic address status verification */ @@ -2869,66 +2907,68 @@ restart: spin_unlock_bh(&addrconf_verify_lock); } +static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local) +{ + struct in6_addr *pfx = NULL; + + if (addr) + pfx = nla_data(addr); + + if (local) { + if (pfx && nla_memcmp(local, pfx, sizeof(*pfx))) + pfx = NULL; + else + pfx = nla_data(local); + } + + return pfx; +} + +static struct nla_policy ifa_ipv6_policy[IFA_MAX+1] __read_mostly = { + [IFA_ADDRESS] = { .len = sizeof(struct in6_addr) }, + [IFA_LOCAL] = { .len = sizeof(struct in6_addr) }, + [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, +}; + static int inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct rtattr **rta = arg; - struct ifaddrmsg *ifm = NLMSG_DATA(nlh); + struct ifaddrmsg *ifm; + struct nlattr *tb[IFA_MAX+1]; struct in6_addr *pfx; + int err; - pfx = NULL; - if (rta[IFA_ADDRESS-1]) { - if (RTA_PAYLOAD(rta[IFA_ADDRESS-1]) < sizeof(*pfx)) - return -EINVAL; - pfx = RTA_DATA(rta[IFA_ADDRESS-1]); - } - if (rta[IFA_LOCAL-1]) { - if (RTA_PAYLOAD(rta[IFA_LOCAL-1]) < sizeof(*pfx) || - (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx)))) - return -EINVAL; - pfx = RTA_DATA(rta[IFA_LOCAL-1]); - } + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); + if (err < 0) + return err; + + ifm = nlmsg_data(nlh); + pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]); if (pfx == NULL) return -EINVAL; return inet6_addr_del(ifm->ifa_index, pfx, ifm->ifa_prefixlen); } -static int -inet6_addr_modify(int ifindex, struct in6_addr *pfx, - __u32 prefered_lft, __u32 valid_lft) +static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, + u32 prefered_lft, u32 valid_lft) { - struct inet6_ifaddr *ifp = NULL; - struct net_device *dev; - int ifa_flags = 0; - - if ((dev = __dev_get_by_index(ifindex)) == NULL) - return -ENODEV; - - if (!(dev->flags&IFF_UP)) - return -ENETDOWN; - if (!valid_lft || (prefered_lft > valid_lft)) return -EINVAL; - ifp = ipv6_get_ifaddr(pfx, dev, 1); - if (ifp == NULL) - return -ENOENT; - if (valid_lft == INFINITY_LIFE_TIME) - ifa_flags = IFA_F_PERMANENT; + ifa_flags |= IFA_F_PERMANENT; else if (valid_lft >= 0x7FFFFFFF/HZ) valid_lft = 0x7FFFFFFF/HZ; if (prefered_lft == 0) - ifa_flags = IFA_F_DEPRECATED; + ifa_flags |= IFA_F_DEPRECATED; else if ((prefered_lft >= 0x7FFFFFFF/HZ) && (prefered_lft != INFINITY_LIFE_TIME)) prefered_lft = 0x7FFFFFFF/HZ; spin_lock_bh(&ifp->lock); - ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED|IFA_F_PERMANENT)) | ifa_flags; - + ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags; ifp->tstamp = jiffies; ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; @@ -2936,7 +2976,6 @@ inet6_addr_modify(int ifindex, struct in6_addr *pfx, spin_unlock_bh(&ifp->lock); if (!(ifp->flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); - in6_ifa_put(ifp); addrconf_verify(0); @@ -2946,172 +2985,189 @@ inet6_addr_modify(int ifindex, struct in6_addr *pfx, static int inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct rtattr **rta = arg; - struct ifaddrmsg *ifm = NLMSG_DATA(nlh); + struct ifaddrmsg *ifm; + struct nlattr *tb[IFA_MAX+1]; struct in6_addr *pfx; - __u32 valid_lft = INFINITY_LIFE_TIME, prefered_lft = INFINITY_LIFE_TIME; + struct inet6_ifaddr *ifa; + struct net_device *dev; + u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME; + u8 ifa_flags; + int err; - pfx = NULL; - if (rta[IFA_ADDRESS-1]) { - if (RTA_PAYLOAD(rta[IFA_ADDRESS-1]) < sizeof(*pfx)) - return -EINVAL; - pfx = RTA_DATA(rta[IFA_ADDRESS-1]); - } - if (rta[IFA_LOCAL-1]) { - if (RTA_PAYLOAD(rta[IFA_LOCAL-1]) < sizeof(*pfx) || - (pfx && memcmp(pfx, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*pfx)))) - return -EINVAL; - pfx = RTA_DATA(rta[IFA_LOCAL-1]); - } + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); + if (err < 0) + return err; + + ifm = nlmsg_data(nlh); + pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]); if (pfx == NULL) return -EINVAL; - if (rta[IFA_CACHEINFO-1]) { + if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; - if (RTA_PAYLOAD(rta[IFA_CACHEINFO-1]) < sizeof(*ci)) - return -EINVAL; - ci = RTA_DATA(rta[IFA_CACHEINFO-1]); + + ci = nla_data(tb[IFA_CACHEINFO]); valid_lft = ci->ifa_valid; - prefered_lft = ci->ifa_prefered; + preferred_lft = ci->ifa_prefered; + } else { + preferred_lft = INFINITY_LIFE_TIME; + valid_lft = INFINITY_LIFE_TIME; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) { - int ret; - ret = inet6_addr_modify(ifm->ifa_index, pfx, - prefered_lft, valid_lft); - if (ret == 0 || !(nlh->nlmsg_flags & NLM_F_CREATE)) - return ret; + dev = __dev_get_by_index(ifm->ifa_index); + if (dev == NULL) + return -ENODEV; + + /* We ignore other flags so far. */ + ifa_flags = ifm->ifa_flags & (IFA_F_NODAD | IFA_F_HOMEADDRESS); + + ifa = ipv6_get_ifaddr(pfx, dev, 1); + if (ifa == NULL) { + /* + * It would be best to check for !NLM_F_CREATE here but + * userspace alreay relies on not having to provide this. + */ + return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen, + ifa_flags, preferred_lft, valid_lft); } - return inet6_addr_add(ifm->ifa_index, pfx, ifm->ifa_prefixlen, - prefered_lft, valid_lft); + if (nlh->nlmsg_flags & NLM_F_EXCL || + !(nlh->nlmsg_flags & NLM_F_REPLACE)) + err = -EEXIST; + else + err = inet6_addr_modify(ifa, ifa_flags, preferred_lft, valid_lft); + + in6_ifa_put(ifa); + + return err; +} + +static void put_ifaddrmsg(struct nlmsghdr *nlh, u8 prefixlen, u8 flags, + u8 scope, int ifindex) +{ + struct ifaddrmsg *ifm; + ifm = nlmsg_data(nlh); + ifm->ifa_family = AF_INET6; + ifm->ifa_prefixlen = prefixlen; + ifm->ifa_flags = flags; + ifm->ifa_scope = scope; + ifm->ifa_index = ifindex; } -/* Maximum length of ifa_cacheinfo attributes */ -#define INET6_IFADDR_RTA_SPACE \ - RTA_SPACE(16) /* IFA_ADDRESS */ + \ - RTA_SPACE(sizeof(struct ifa_cacheinfo)) /* CACHEINFO */ +static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, + unsigned long tstamp, u32 preferred, u32 valid) +{ + struct ifa_cacheinfo ci; + + ci.cstamp = (u32)(TIME_DELTA(cstamp, INITIAL_JIFFIES) / HZ * 100 + + TIME_DELTA(cstamp, INITIAL_JIFFIES) % HZ * 100 / HZ); + ci.tstamp = (u32)(TIME_DELTA(tstamp, INITIAL_JIFFIES) / HZ * 100 + + TIME_DELTA(tstamp, INITIAL_JIFFIES) % HZ * 100 / HZ); + ci.ifa_prefered = preferred; + ci.ifa_valid = valid; + + return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); +} + +static inline int rt_scope(int ifa_scope) +{ + if (ifa_scope & IFA_HOST) + return RT_SCOPE_HOST; + else if (ifa_scope & IFA_LINK) + return RT_SCOPE_LINK; + else if (ifa_scope & IFA_SITE) + return RT_SCOPE_SITE; + else + return RT_SCOPE_UNIVERSE; +} + +static inline int inet6_ifaddr_msgsize(void) +{ + return nlmsg_total_size(sizeof(struct ifaddrmsg) + + nla_total_size(16) + + nla_total_size(sizeof(struct ifa_cacheinfo)) + + 128); +} static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, u32 pid, u32 seq, int event, unsigned int flags) { - struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - struct ifa_cacheinfo ci; - unsigned char *b = skb->tail; + u32 preferred, valid; + + nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags); + if (nlh == NULL) + return -ENOBUFS; + + put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), + ifa->idev->dev->ifindex); - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); - ifm = NLMSG_DATA(nlh); - ifm->ifa_family = AF_INET6; - ifm->ifa_prefixlen = ifa->prefix_len; - ifm->ifa_flags = ifa->flags; - ifm->ifa_scope = RT_SCOPE_UNIVERSE; - if (ifa->scope&IFA_HOST) - ifm->ifa_scope = RT_SCOPE_HOST; - else if (ifa->scope&IFA_LINK) - ifm->ifa_scope = RT_SCOPE_LINK; - else if (ifa->scope&IFA_SITE) - ifm->ifa_scope = RT_SCOPE_SITE; - ifm->ifa_index = ifa->idev->dev->ifindex; - RTA_PUT(skb, IFA_ADDRESS, 16, &ifa->addr); if (!(ifa->flags&IFA_F_PERMANENT)) { - ci.ifa_prefered = ifa->prefered_lft; - ci.ifa_valid = ifa->valid_lft; - if (ci.ifa_prefered != INFINITY_LIFE_TIME) { + preferred = ifa->prefered_lft; + valid = ifa->valid_lft; + if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - ifa->tstamp)/HZ; - ci.ifa_prefered -= tval; - if (ci.ifa_valid != INFINITY_LIFE_TIME) - ci.ifa_valid -= tval; + preferred -= tval; + if (valid != INFINITY_LIFE_TIME) + valid -= tval; } } else { - ci.ifa_prefered = INFINITY_LIFE_TIME; - ci.ifa_valid = INFINITY_LIFE_TIME; - } - ci.cstamp = (__u32)(TIME_DELTA(ifa->cstamp, INITIAL_JIFFIES) / HZ * 100 - + TIME_DELTA(ifa->cstamp, INITIAL_JIFFIES) % HZ * 100 / HZ); - ci.tstamp = (__u32)(TIME_DELTA(ifa->tstamp, INITIAL_JIFFIES) / HZ * 100 - + TIME_DELTA(ifa->tstamp, INITIAL_JIFFIES) % HZ * 100 / HZ); - RTA_PUT(skb, IFA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + preferred = INFINITY_LIFE_TIME; + valid = INFINITY_LIFE_TIME; + } -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0 || + put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) + return nlmsg_cancel(skb, nlh); + + return nlmsg_end(skb, nlh); } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, u32 pid, u32 seq, int event, u16 flags) { - struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - struct ifa_cacheinfo ci; - unsigned char *b = skb->tail; - - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); - ifm = NLMSG_DATA(nlh); - ifm->ifa_family = AF_INET6; - ifm->ifa_prefixlen = 128; - ifm->ifa_flags = IFA_F_PERMANENT; - ifm->ifa_scope = RT_SCOPE_UNIVERSE; - if (ipv6_addr_scope(&ifmca->mca_addr)&IFA_SITE) - ifm->ifa_scope = RT_SCOPE_SITE; - ifm->ifa_index = ifmca->idev->dev->ifindex; - RTA_PUT(skb, IFA_MULTICAST, 16, &ifmca->mca_addr); - ci.cstamp = (__u32)(TIME_DELTA(ifmca->mca_cstamp, INITIAL_JIFFIES) / HZ - * 100 + TIME_DELTA(ifmca->mca_cstamp, INITIAL_JIFFIES) % HZ - * 100 / HZ); - ci.tstamp = (__u32)(TIME_DELTA(ifmca->mca_tstamp, INITIAL_JIFFIES) / HZ - * 100 + TIME_DELTA(ifmca->mca_tstamp, INITIAL_JIFFIES) % HZ - * 100 / HZ); - ci.ifa_prefered = INFINITY_LIFE_TIME; - ci.ifa_valid = INFINITY_LIFE_TIME; - RTA_PUT(skb, IFA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + u8 scope = RT_SCOPE_UNIVERSE; + int ifindex = ifmca->idev->dev->ifindex; -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) + scope = RT_SCOPE_SITE; + + nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags); + if (nlh == NULL) + return -ENOBUFS; + + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); + if (nla_put(skb, IFA_MULTICAST, 16, &ifmca->mca_addr) < 0 || + put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) + return nlmsg_cancel(skb, nlh); + + return nlmsg_end(skb, nlh); } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, u32 pid, u32 seq, int event, unsigned int flags) { - struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - struct ifa_cacheinfo ci; - unsigned char *b = skb->tail; - - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*ifm), flags); - ifm = NLMSG_DATA(nlh); - ifm->ifa_family = AF_INET6; - ifm->ifa_prefixlen = 128; - ifm->ifa_flags = IFA_F_PERMANENT; - ifm->ifa_scope = RT_SCOPE_UNIVERSE; - if (ipv6_addr_scope(&ifaca->aca_addr)&IFA_SITE) - ifm->ifa_scope = RT_SCOPE_SITE; - ifm->ifa_index = ifaca->aca_idev->dev->ifindex; - RTA_PUT(skb, IFA_ANYCAST, 16, &ifaca->aca_addr); - ci.cstamp = (__u32)(TIME_DELTA(ifaca->aca_cstamp, INITIAL_JIFFIES) / HZ - * 100 + TIME_DELTA(ifaca->aca_cstamp, INITIAL_JIFFIES) % HZ - * 100 / HZ); - ci.tstamp = (__u32)(TIME_DELTA(ifaca->aca_tstamp, INITIAL_JIFFIES) / HZ - * 100 + TIME_DELTA(ifaca->aca_tstamp, INITIAL_JIFFIES) % HZ - * 100 / HZ); - ci.ifa_prefered = INFINITY_LIFE_TIME; - ci.ifa_valid = INFINITY_LIFE_TIME; - RTA_PUT(skb, IFA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + u8 scope = RT_SCOPE_UNIVERSE; + int ifindex = ifaca->aca_idev->dev->ifindex; -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) + scope = RT_SCOPE_SITE; + + nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags); + if (nlh == NULL) + return -ENOBUFS; + + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); + if (nla_put(skb, IFA_ANYCAST, 16, &ifaca->aca_addr) < 0 || + put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) + return nlmsg_cancel(skb, nlh); + + return nlmsg_end(skb, nlh); } enum addr_type_t @@ -3222,79 +3278,74 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb) return inet6_dump_addr(skb, cb, type); } -static int inet6_rtm_getaddr(struct sk_buff *in_skb, - struct nlmsghdr* nlh, void *arg) +static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh, + void *arg) { - struct rtattr **rta = arg; - struct ifaddrmsg *ifm = NLMSG_DATA(nlh); + struct ifaddrmsg *ifm; + struct nlattr *tb[IFA_MAX+1]; struct in6_addr *addr = NULL; struct net_device *dev = NULL; struct inet6_ifaddr *ifa; struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct ifaddrmsg) + INET6_IFADDR_RTA_SPACE); int err; - if (rta[IFA_ADDRESS-1]) { - if (RTA_PAYLOAD(rta[IFA_ADDRESS-1]) < sizeof(*addr)) - return -EINVAL; - addr = RTA_DATA(rta[IFA_ADDRESS-1]); - } - if (rta[IFA_LOCAL-1]) { - if (RTA_PAYLOAD(rta[IFA_LOCAL-1]) < sizeof(*addr) || - (addr && memcmp(addr, RTA_DATA(rta[IFA_LOCAL-1]), sizeof(*addr)))) - return -EINVAL; - addr = RTA_DATA(rta[IFA_LOCAL-1]); + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy); + if (err < 0) + goto errout; + + addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]); + if (addr == NULL) { + err = -EINVAL; + goto errout; } - if (addr == NULL) - return -EINVAL; + ifm = nlmsg_data(nlh); if (ifm->ifa_index) dev = __dev_get_by_index(ifm->ifa_index); - if ((ifa = ipv6_get_ifaddr(addr, dev, 1)) == NULL) - return -EADDRNOTAVAIL; + if ((ifa = ipv6_get_ifaddr(addr, dev, 1)) == NULL) { + err = -EADDRNOTAVAIL; + goto errout; + } - if ((skb = alloc_skb(size, GFP_KERNEL)) == NULL) { + if ((skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_KERNEL)) == NULL) { err = -ENOBUFS; - goto out; + goto errout_ifa; } - NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWADDR, 0); if (err < 0) { - err = -EMSGSIZE; - goto out_free; + kfree_skb(skb); + goto errout_ifa; } - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; -out: + err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid); +errout_ifa: in6_ifa_put(ifa); +errout: return err; -out_free: - kfree_skb(skb); - goto out; } static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct ifaddrmsg) + INET6_IFADDR_RTA_SPACE); + int err = -ENOBUFS; - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFADDR, ENOBUFS); - return; - } - if (inet6_fill_ifaddr(skb, ifa, current->pid, 0, event, 0) < 0) { + skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0); + if (err < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFADDR, EINVAL); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_IFADDR; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_IFADDR, GFP_ATOMIC); + + err = rtnl_notify(skb, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_IPV6_IFADDR, err); } static void inline ipv6_store_devconf(struct ipv6_devconf *cnf, @@ -3329,6 +3380,7 @@ static void inline ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen; #endif #endif + array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp; } /* Maximum length of ifinfomsg attributes */ @@ -3435,20 +3487,23 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) void inet6_ifinfo_notify(int event, struct inet6_dev *idev) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct ifinfomsg) + INET6_IFINFO_RTA_SPACE); + int payload = sizeof(struct ifinfomsg) + INET6_IFINFO_RTA_SPACE; + int err = -ENOBUFS; - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFINFO, ENOBUFS); - return; - } - if (inet6_fill_ifinfo(skb, idev, current->pid, 0, event, 0) < 0) { + skb = nlmsg_new(nlmsg_total_size(payload), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_fill_ifinfo(skb, idev, 0, 0, event, 0); + if (err < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_IFINFO, EINVAL); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_IFINFO; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_IFINFO, GFP_ATOMIC); + + err = rtnl_notify(skb, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_IPV6_IFADDR, err); } /* Maximum length of prefix_cacheinfo attributes */ @@ -3500,20 +3555,23 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct prefixmsg) + INET6_PREFIX_RTA_SPACE); + int payload = sizeof(struct prefixmsg) + INET6_PREFIX_RTA_SPACE; + int err = -ENOBUFS; - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_PREFIX, ENOBUFS); - return; - } - if (inet6_fill_prefix(skb, idev, pinfo, current->pid, 0, event, 0) < 0) { + skb = nlmsg_new(nlmsg_total_size(payload), GFP_ATOMIC); + if (skb == NULL) + goto errout; + + err = inet6_fill_prefix(skb, idev, pinfo, 0, 0, event, 0); + if (err < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_PREFIX, EINVAL); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_PREFIX; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_PREFIX, GFP_ATOMIC); + + err = rtnl_notify(skb, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_IPV6_PREFIX, err); } static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = { @@ -3528,6 +3586,9 @@ static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = { [RTM_DELROUTE - RTM_BASE] = { .doit = inet6_rtm_delroute, }, [RTM_GETROUTE - RTM_BASE] = { .doit = inet6_rtm_getroute, .dumpit = inet6_dump_fib, }, +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + [RTM_GETRULE - RTM_BASE] = { .dumpit = fib6_rules_dump, }, +#endif }; static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) @@ -3536,7 +3597,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) switch (event) { case RTM_NEWADDR: - ip6_ins_rt(ifp->rt, NULL, NULL, NULL); + ip6_ins_rt(ifp->rt); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); break; @@ -3545,7 +3606,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); dst_hold(&ifp->rt->u.dst); - if (ip6_del_rt(ifp->rt, NULL, NULL, NULL)) + if (ip6_del_rt(ifp->rt)) dst_free(&ifp->rt->u.dst); break; } @@ -3553,10 +3614,10 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { - read_lock_bh(&addrconf_lock); + rcu_read_lock_bh(); if (likely(ifp->idev->dead == 0)) __ipv6_ifa_notify(event, ifp); - read_unlock_bh(&addrconf_lock); + rcu_read_unlock_bh(); } #ifdef CONFIG_SYSCTL @@ -3653,7 +3714,7 @@ static struct addrconf_sysctl_table ctl_table addrconf_conf_dir[2]; ctl_table addrconf_proto_dir[2]; ctl_table addrconf_root_dir[2]; -} addrconf_sysctl = { +} addrconf_sysctl __read_mostly = { .sysctl_header = NULL, .addrconf_vars = { { @@ -3843,6 +3904,14 @@ static struct addrconf_sysctl_table #endif #endif { + .ctl_name = NET_IPV6_PROXY_NDP, + .procname = "proxy_ndp", + .data = &ipv6_devconf.proxy_ndp, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { .ctl_name = 0, /* sentinel */ } }, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index ac85e9c532c..bf6e8aff19d 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -59,6 +59,9 @@ #ifdef CONFIG_IPV6_TUNNEL #include <net/ip6_tunnel.h> #endif +#ifdef CONFIG_IPV6_MIP6 +#include <net/mip6.h> +#endif #include <asm/uaccess.h> #include <asm/system.h> @@ -67,7 +70,7 @@ MODULE_AUTHOR("Cast of dozens"); MODULE_DESCRIPTION("IPv6 protocol stack for Linux"); MODULE_LICENSE("GPL"); -int sysctl_ipv6_bindv6only; +int sysctl_ipv6_bindv6only __read_mostly; /* The inetsw table contains everything that inet_create needs to * build a new socket. @@ -637,6 +640,7 @@ int inet6_sk_rebuild_header(struct sock *sk) fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; + security_sk_classify_flow(sk, &fl); if (np->opt && np->opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt; @@ -658,7 +662,7 @@ int inet6_sk_rebuild_header(struct sock *sk) return err; } - __ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL, NULL); } return 0; @@ -757,6 +761,8 @@ static int __init inet6_init(void) struct list_head *r; int err; + BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)); + #ifdef MODULE #if 0 /* FIXME --RR */ if (!mod_member_present(&__this_module, can_unload)) @@ -766,11 +772,6 @@ static int __init inet6_init(void) #endif #endif - if (sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)) { - printk(KERN_CRIT "inet6_proto_init: size fault\n"); - return -EINVAL; - } - err = proto_register(&tcpv6_prot, 1); if (err) goto out; @@ -856,6 +857,9 @@ static int __init inet6_init(void) ipv6_frag_init(); ipv6_nodata_init(); ipv6_destopt_init(); +#ifdef CONFIG_IPV6_MIP6 + mip6_init(); +#endif /* Init v6 transport protocols. */ udpv6_init(); @@ -919,6 +923,9 @@ static void __exit inet6_exit(void) tcp6_proc_exit(); raw6_proc_exit(); #endif +#ifdef CONFIG_IPV6_MIP6 + mip6_fini(); +#endif /* Cleanup code parts. */ sit_cleanup(); ip6_flowlabel_cleanup(); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 00ffa7bc6c9..b0d83e8e425 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -74,6 +74,66 @@ bad: return 0; } +#ifdef CONFIG_IPV6_MIP6 +/** + * ipv6_rearrange_destopt - rearrange IPv6 destination options header + * @iph: IPv6 header + * @destopt: destionation options header + */ +static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *destopt) +{ + u8 *opt = (u8 *)destopt; + int len = ipv6_optlen(destopt); + int off = 0; + int optlen = 0; + + off += 2; + len -= 2; + + while (len > 0) { + + switch (opt[off]) { + + case IPV6_TLV_PAD0: + optlen = 1; + break; + default: + if (len < 2) + goto bad; + optlen = opt[off+1]+2; + if (len < optlen) + goto bad; + + /* Rearrange the source address in @iph and the + * addresses in home address option for final source. + * See 11.3.2 of RFC 3775 for details. + */ + if (opt[off] == IPV6_TLV_HAO) { + struct in6_addr final_addr; + struct ipv6_destopt_hao *hao; + + hao = (struct ipv6_destopt_hao *)&opt[off]; + if (hao->length != sizeof(hao->addr)) { + if (net_ratelimit()) + printk(KERN_WARNING "destopt hao: invalid header length: %u\n", hao->length); + goto bad; + } + ipv6_addr_copy(&final_addr, &hao->addr); + ipv6_addr_copy(&hao->addr, &iph->saddr); + ipv6_addr_copy(&iph->saddr, &final_addr); + } + break; + } + + off += optlen; + len -= optlen; + } + /* Note: ok if len == 0 */ +bad: + return; +} +#endif + /** * ipv6_rearrange_rthdr - rearrange IPv6 routing header * @iph: IPv6 header @@ -113,7 +173,7 @@ static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr) ipv6_addr_copy(&iph->daddr, &final_addr); } -static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len) +static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) { union { struct ipv6hdr *iph; @@ -128,8 +188,12 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len) while (exthdr.raw < end) { switch (nexthdr) { - case NEXTHDR_HOP: case NEXTHDR_DEST: +#ifdef CONFIG_IPV6_MIP6 + if (dir == XFRM_POLICY_OUT) + ipv6_rearrange_destopt(iph, exthdr.opth); +#endif + case NEXTHDR_HOP: if (!zero_out_mutable_opts(exthdr.opth)) { LIMIT_NETDEBUG( KERN_WARNING "overrun %sopts\n", @@ -164,6 +228,9 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) u8 nexthdr; char tmp_base[8]; struct { +#ifdef CONFIG_IPV6_MIP6 + struct in6_addr saddr; +#endif struct in6_addr daddr; char hdrs[0]; } *tmp_ext; @@ -188,10 +255,15 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) err = -ENOMEM; goto error; } +#ifdef CONFIG_IPV6_MIP6 + memcpy(tmp_ext, &top_iph->saddr, extlen); +#else memcpy(tmp_ext, &top_iph->daddr, extlen); +#endif err = ipv6_clear_mutable_options(top_iph, extlen - sizeof(*tmp_ext) + - sizeof(*top_iph)); + sizeof(*top_iph), + XFRM_POLICY_OUT); if (err) goto error_free_iph; } @@ -222,7 +294,11 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(top_iph, tmp_base, sizeof(tmp_base)); if (tmp_ext) { +#ifdef CONFIG_IPV6_MIP6 + memcpy(&top_iph->saddr, tmp_ext, extlen); +#else memcpy(&top_iph->daddr, tmp_ext, extlen); +#endif error_free_iph: kfree(tmp_ext); } @@ -282,7 +358,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (!tmp_hdr) goto out; memcpy(tmp_hdr, skb->nh.raw, hdr_len); - if (ipv6_clear_mutable_options(skb->nh.ipv6h, hdr_len)) + if (ipv6_clear_mutable_options(skb->nh.ipv6h, hdr_len, XFRM_POLICY_IN)) goto free_out; skb->nh.ipv6h->priority = 0; skb->nh.ipv6h->flow_lbl[0] = 0; @@ -398,7 +474,7 @@ static int ah6_init_state(struct xfrm_state *x) goto error; x->props.header_len = XFRM_ALIGN8(sizeof(struct ipv6_auth_hdr) + ahp->icv_trunc_len); - if (x->props.mode) + if (x->props.mode == XFRM_MODE_TUNNEL) x->props.header_len += sizeof(struct ipv6hdr); x->data = ahp; @@ -435,7 +511,8 @@ static struct xfrm_type ah6_type = .init_state = ah6_init_state, .destructor = ah6_destroy, .input = ah6_input, - .output = ah6_output + .output = ah6_output, + .hdr_offset = xfrm6_find_1stfragopt, }; static struct inet6_protocol ah6_protocol = { diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index f6881d7a038..a9604764e01 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -56,7 +56,7 @@ ip6_onlink(struct in6_addr *addr, struct net_device *dev) int onlink; onlink = 0; - read_lock(&addrconf_lock); + rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); @@ -68,7 +68,7 @@ ip6_onlink(struct in6_addr *addr, struct net_device *dev) } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); return onlink; } @@ -335,7 +335,7 @@ int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) write_unlock_bh(&idev->lock); dst_hold(&rt->u.dst); - if (ip6_ins_rt(rt, NULL, NULL, NULL)) + if (ip6_ins_rt(rt)) dst_release(&rt->u.dst); addrconf_join_solict(dev, &aca->aca_addr); @@ -378,7 +378,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr) addrconf_leave_solict(idev, &aca->aca_addr); dst_hold(&aca->aca_rt->u.dst); - if (ip6_del_rt(aca->aca_rt, NULL, NULL, NULL)) + if (ip6_del_rt(aca->aca_rt)) dst_free(&aca->aca_rt->u.dst); else dst_release(&aca->aca_rt->u.dst); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 3b55b4c8e2d..7206747022f 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -156,6 +156,8 @@ ipv4_connected: if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST)) fl.oif = np->mcast_oif; + security_sk_classify_flow(sk, &fl); + if (flowlabel) { if (flowlabel->opt && flowlabel->opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *) flowlabel->opt->srcrt; @@ -191,7 +193,12 @@ ipv4_connected: ip6_dst_store(sk, dst, ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? - &np->daddr : NULL); + &np->daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl.fl6_src, &np->saddr) ? + &np->saddr : +#endif + NULL); sk->sk_state = TCP_ESTABLISHED; out: @@ -641,10 +648,13 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg); - /* - * TYPE 0 - */ - if (rthdr->type) { + switch (rthdr->type) { + case IPV6_SRCRT_TYPE_0: +#ifdef CONFIG_IPV6_MIP6 + case IPV6_SRCRT_TYPE_2: +#endif + break; + default: err = -EINVAL; goto exit_f; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 2ebfd281e72..e78680a9985 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -99,8 +99,13 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) esph->seq_no = htonl(++x->replay.oseq); xfrm_aevent_doreplay(x); - if (esp->conf.ivlen) + if (esp->conf.ivlen) { + if (unlikely(!esp->conf.ivinitted)) { + get_random_bytes(esp->conf.ivec, esp->conf.ivlen); + esp->conf.ivinitted = 1; + } crypto_blkcipher_set_iv(tfm, esp->conf.ivec, esp->conf.ivlen); + } do { struct scatterlist *sg = &esp->sgbuf[0]; @@ -237,7 +242,7 @@ static u32 esp6_get_max_size(struct xfrm_state *x, int mtu) struct esp_data *esp = x->data; u32 blksize = ALIGN(crypto_blkcipher_blocksize(esp->conf.tfm), 4); - if (x->props.mode) { + if (x->props.mode == XFRM_MODE_TUNNEL) { mtu = ALIGN(mtu + 2, blksize); } else { /* The worst case. */ @@ -353,12 +358,12 @@ static int esp6_init_state(struct xfrm_state *x) esp->conf.ivec = kmalloc(esp->conf.ivlen, GFP_KERNEL); if (unlikely(esp->conf.ivec == NULL)) goto error; - get_random_bytes(esp->conf.ivec, esp->conf.ivlen); + esp->conf.ivinitted = 0; } if (crypto_blkcipher_setkey(tfm, esp->conf.key, esp->conf.key_len)) goto error; x->props.header_len = sizeof(struct ipv6_esp_hdr) + esp->conf.ivlen; - if (x->props.mode) + if (x->props.mode == XFRM_MODE_TUNNEL) x->props.header_len += sizeof(struct ipv6hdr); x->data = esp; return 0; @@ -379,7 +384,8 @@ static struct xfrm_type esp6_type = .destructor = esp6_destroy, .get_max_size = esp6_get_max_size, .input = esp6_input, - .output = esp6_output + .output = esp6_output, + .hdr_offset = xfrm6_find_1stfragopt, }; static struct inet6_protocol esp6_protocol = { diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 86dac106873..88c96b10684 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -43,9 +43,54 @@ #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> +#ifdef CONFIG_IPV6_MIP6 +#include <net/xfrm.h> +#endif #include <asm/uaccess.h> +int ipv6_find_tlv(struct sk_buff *skb, int offset, int type) +{ + int packet_len = skb->tail - skb->nh.raw; + struct ipv6_opt_hdr *hdr; + int len; + + if (offset + 2 > packet_len) + goto bad; + hdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset); + len = ((hdr->hdrlen + 1) << 3); + + if (offset + len > packet_len) + goto bad; + + offset += 2; + len -= 2; + + while (len > 0) { + int opttype = skb->nh.raw[offset]; + int optlen; + + if (opttype == type) + return offset; + + switch (opttype) { + case IPV6_TLV_PAD0: + optlen = 1; + break; + default: + optlen = skb->nh.raw[offset + 1] + 2; + if (optlen > len) + goto bad; + break; + } + offset += optlen; + len -= optlen; + } + /* not_found */ + bad: + return -1; +} + /* * Parsing tlv encoded headers. * @@ -56,7 +101,7 @@ struct tlvtype_proc { int type; - int (*func)(struct sk_buff *skb, int offset); + int (*func)(struct sk_buff **skbp, int offset); }; /********************* @@ -65,8 +110,10 @@ struct tlvtype_proc { /* An unknown option is detected, decide what to do */ -static int ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) +static int ip6_tlvopt_unknown(struct sk_buff **skbp, int optoff) { + struct sk_buff *skb = *skbp; + switch ((skb->nh.raw[optoff] & 0xC0) >> 6) { case 0: /* ignore */ return 1; @@ -91,8 +138,9 @@ static int ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) /* Parse tlv encoded option header (hop-by-hop or destination) */ -static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff *skb) +static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff **skbp) { + struct sk_buff *skb = *skbp; struct tlvtype_proc *curr; int off = skb->h.raw - skb->nh.raw; int len = ((skb->h.raw[1]+1)<<3); @@ -122,13 +170,13 @@ static int ip6_parse_tlv(struct tlvtype_proc *procs, struct sk_buff *skb) /* type specific length/alignment checks will be performed in the func(). */ - if (curr->func(skb, off) == 0) + if (curr->func(skbp, off) == 0) return 0; break; } } if (curr->type < 0) { - if (ip6_tlvopt_unknown(skb, off) == 0) + if (ip6_tlvopt_unknown(skbp, off) == 0) return 0; } break; @@ -147,8 +195,85 @@ bad: Destination options header. *****************************/ +#ifdef CONFIG_IPV6_MIP6 +static int ipv6_dest_hao(struct sk_buff **skbp, int optoff) +{ + struct sk_buff *skb = *skbp; + struct ipv6_destopt_hao *hao; + struct inet6_skb_parm *opt = IP6CB(skb); + struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->nh.raw; + struct in6_addr tmp_addr; + int ret; + + if (opt->dsthao) { + LIMIT_NETDEBUG(KERN_DEBUG "hao duplicated\n"); + goto discard; + } + opt->dsthao = opt->dst1; + opt->dst1 = 0; + + hao = (struct ipv6_destopt_hao *)(skb->nh.raw + optoff); + + if (hao->length != 16) { + LIMIT_NETDEBUG( + KERN_DEBUG "hao invalid option length = %d\n", hao->length); + goto discard; + } + + if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) { + LIMIT_NETDEBUG( + KERN_DEBUG "hao is not an unicast addr: " NIP6_FMT "\n", NIP6(hao->addr)); + goto discard; + } + + ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr, + (xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS); + if (unlikely(ret < 0)) + goto discard; + + if (skb_cloned(skb)) { + struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC); + struct inet6_skb_parm *opt2; + + if (skb2 == NULL) + goto discard; + + opt2 = IP6CB(skb2); + memcpy(opt2, opt, sizeof(*opt2)); + + kfree_skb(skb); + + /* update all variable using below by copied skbuff */ + *skbp = skb = skb2; + hao = (struct ipv6_destopt_hao *)(skb2->nh.raw + optoff); + ipv6h = (struct ipv6hdr *)skb2->nh.raw; + } + + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->ip_summed = CHECKSUM_NONE; + + ipv6_addr_copy(&tmp_addr, &ipv6h->saddr); + ipv6_addr_copy(&ipv6h->saddr, &hao->addr); + ipv6_addr_copy(&hao->addr, &tmp_addr); + + if (skb->tstamp.off_sec == 0) + __net_timestamp(skb); + + return 1; + + discard: + kfree_skb(skb); + return 0; +} +#endif + static struct tlvtype_proc tlvprocdestopt_lst[] = { - /* No destination options are defined now */ +#ifdef CONFIG_IPV6_MIP6 + { + .type = IPV6_TLV_HAO, + .func = ipv6_dest_hao, + }, +#endif {-1, NULL} }; @@ -156,6 +281,9 @@ static int ipv6_destopt_rcv(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; struct inet6_skb_parm *opt = IP6CB(skb); +#ifdef CONFIG_IPV6_MIP6 + __u16 dstbuf; +#endif if (!pskb_may_pull(skb, (skb->h.raw-skb->data)+8) || !pskb_may_pull(skb, (skb->h.raw-skb->data)+((skb->h.raw[1]+1)<<3))) { @@ -166,10 +294,19 @@ static int ipv6_destopt_rcv(struct sk_buff **skbp) opt->lastopt = skb->h.raw - skb->nh.raw; opt->dst1 = skb->h.raw - skb->nh.raw; +#ifdef CONFIG_IPV6_MIP6 + dstbuf = opt->dst1; +#endif - if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { + if (ip6_parse_tlv(tlvprocdestopt_lst, skbp)) { + skb = *skbp; skb->h.raw += ((skb->h.raw[1]+1)<<3); + opt = IP6CB(skb); +#ifdef CONFIG_IPV6_MIP6 + opt->nhoff = dstbuf; +#else opt->nhoff = opt->dst1; +#endif return 1; } @@ -219,7 +356,7 @@ static int ipv6_rthdr_rcv(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; struct inet6_skb_parm *opt = IP6CB(skb); - struct in6_addr *addr; + struct in6_addr *addr = NULL; struct in6_addr daddr; int n, i; @@ -244,6 +381,23 @@ static int ipv6_rthdr_rcv(struct sk_buff **skbp) looped_back: if (hdr->segments_left == 0) { + switch (hdr->type) { +#ifdef CONFIG_IPV6_MIP6 + case IPV6_SRCRT_TYPE_2: + /* Silently discard type 2 header unless it was + * processed by own + */ + if (!addr) { + IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + kfree_skb(skb); + return -1; + } + break; +#endif + default: + break; + } + opt->lastopt = skb->h.raw - skb->nh.raw; opt->srcrt = skb->h.raw - skb->nh.raw; skb->h.raw += (hdr->hdrlen + 1) << 3; @@ -253,17 +407,29 @@ looped_back: return 1; } - if (hdr->type != IPV6_SRCRT_TYPE_0) { + switch (hdr->type) { + case IPV6_SRCRT_TYPE_0: + if (hdr->hdrlen & 0x01) { + IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->hdrlen) - skb->nh.raw); + return -1; + } + break; +#ifdef CONFIG_IPV6_MIP6 + case IPV6_SRCRT_TYPE_2: + /* Silently discard invalid RTH type 2 */ + if (hdr->hdrlen != 2 || hdr->segments_left != 1) { + IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); + kfree_skb(skb); + return -1; + } + break; +#endif + default: IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb->nh.raw); return -1; } - - if (hdr->hdrlen & 0x01) { - IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->hdrlen) - skb->nh.raw); - return -1; - } /* * This is the routing header forwarding algorithm from @@ -294,7 +460,7 @@ looped_back: hdr = (struct ipv6_rt_hdr *) skb2->h.raw; } - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; i = n - --hdr->segments_left; @@ -303,6 +469,27 @@ looped_back: addr = rthdr->addr; addr += i - 1; + switch (hdr->type) { +#ifdef CONFIG_IPV6_MIP6 + case IPV6_SRCRT_TYPE_2: + if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, + (xfrm_address_t *)&skb->nh.ipv6h->saddr, + IPPROTO_ROUTING) < 0) { + IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + kfree_skb(skb); + return -1; + } + if (!ipv6_chk_home_addr(addr)) { + IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); + kfree_skb(skb); + return -1; + } + break; +#endif + default: + break; + } + if (ipv6_addr_is_multicast(addr)) { IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); @@ -421,8 +608,10 @@ EXPORT_SYMBOL_GPL(ipv6_invert_rthdr); /* Router Alert as of RFC 2711 */ -static int ipv6_hop_ra(struct sk_buff *skb, int optoff) +static int ipv6_hop_ra(struct sk_buff **skbp, int optoff) { + struct sk_buff *skb = *skbp; + if (skb->nh.raw[optoff+1] == 2) { IP6CB(skb)->ra = optoff; return 1; @@ -435,8 +624,9 @@ static int ipv6_hop_ra(struct sk_buff *skb, int optoff) /* Jumbo payload */ -static int ipv6_hop_jumbo(struct sk_buff *skb, int optoff) +static int ipv6_hop_jumbo(struct sk_buff **skbp, int optoff) { + struct sk_buff *skb = *skbp; u32 pkt_len; if (skb->nh.raw[optoff+1] != 4 || (optoff&3) != 2) { @@ -485,8 +675,9 @@ static struct tlvtype_proc tlvprochopopt_lst[] = { { -1, } }; -int ipv6_parse_hopopts(struct sk_buff *skb) +int ipv6_parse_hopopts(struct sk_buff **skbp) { + struct sk_buff *skb = *skbp; struct inet6_skb_parm *opt = IP6CB(skb); /* @@ -502,8 +693,10 @@ int ipv6_parse_hopopts(struct sk_buff *skb) } opt->hop = sizeof(struct ipv6hdr); - if (ip6_parse_tlv(tlvprochopopt_lst, skb)) { + if (ip6_parse_tlv(tlvprochopopt_lst, skbp)) { + skb = *skbp; skb->h.raw += (skb->h.raw[1]+1)<<3; + opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); return 1; } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c new file mode 100644 index 00000000000..34f5bfaddfc --- /dev/null +++ b/net/ipv6/fib6_rules.c @@ -0,0 +1,305 @@ +/* + * net/ipv6/fib6_rules.c IPv6 Routing Policy Rules + * + * Copyright (C)2003-2006 Helsinki University of Technology + * Copyright (C)2003-2006 USAGI/WIDE Project + * + * 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, version 2. + * + * Authors + * Thomas Graf <tgraf@suug.ch> + * Ville Nuorvala <vnuorval@tcs.hut.fi> + */ + +#include <linux/config.h> +#include <linux/netdevice.h> + +#include <net/fib_rules.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/netlink.h> + +struct fib6_rule +{ + struct fib_rule common; + struct rt6key src; + struct rt6key dst; +#ifdef CONFIG_IPV6_ROUTE_FWMARK + u32 fwmark; + u32 fwmask; +#endif + u8 tclass; +}; + +static struct fib_rules_ops fib6_rules_ops; + +static struct fib6_rule main_rule = { + .common = { + .refcnt = ATOMIC_INIT(2), + .pref = 0x7FFE, + .action = FR_ACT_TO_TBL, + .table = RT6_TABLE_MAIN, + }, +}; + +static struct fib6_rule local_rule = { + .common = { + .refcnt = ATOMIC_INIT(2), + .pref = 0, + .action = FR_ACT_TO_TBL, + .table = RT6_TABLE_LOCAL, + .flags = FIB_RULE_PERMANENT, + }, +}; + +static LIST_HEAD(fib6_rules); + +struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags, + pol_lookup_t lookup) +{ + struct fib_lookup_arg arg = { + .lookup_ptr = lookup, + }; + + fib_rules_lookup(&fib6_rules_ops, fl, flags, &arg); + if (arg.rule) + fib_rule_put(arg.rule); + + if (arg.result) + return (struct dst_entry *) arg.result; + + dst_hold(&ip6_null_entry.u.dst); + return &ip6_null_entry.u.dst; +} + +static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct rt6_info *rt = NULL; + struct fib6_table *table; + pol_lookup_t lookup = arg->lookup_ptr; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + rt = &ip6_null_entry; + goto discard_pkt; + default: + case FR_ACT_BLACKHOLE: + rt = &ip6_blk_hole_entry; + goto discard_pkt; + case FR_ACT_PROHIBIT: + rt = &ip6_prohibit_entry; + goto discard_pkt; + } + + table = fib6_get_table(rule->table); + if (table) + rt = lookup(table, flp, flags); + + if (rt != &ip6_null_entry) + goto out; + dst_release(&rt->u.dst); + rt = NULL; + goto out; + +discard_pkt: + dst_hold(&rt->u.dst); +out: + arg->result = rt; + return rt == NULL ? -EAGAIN : 0; +} + + +static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) +{ + struct fib6_rule *r = (struct fib6_rule *) rule; + + if (!ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen)) + return 0; + + if ((flags & RT6_LOOKUP_F_HAS_SADDR) && + !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen)) + return 0; + + if (r->tclass && r->tclass != ((ntohl(fl->fl6_flowlabel) >> 20) & 0xff)) + return 0; + +#ifdef CONFIG_IPV6_ROUTE_FWMARK + if ((r->fwmark ^ fl->fl6_fwmark) & r->fwmask) + return 0; +#endif + + return 1; +} + +static struct nla_policy fib6_rule_policy[FRA_MAX+1] __read_mostly = { + [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, + [FRA_PRIORITY] = { .type = NLA_U32 }, + [FRA_SRC] = { .len = sizeof(struct in6_addr) }, + [FRA_DST] = { .len = sizeof(struct in6_addr) }, + [FRA_FWMARK] = { .type = NLA_U32 }, + [FRA_FWMASK] = { .type = NLA_U32 }, + [FRA_TABLE] = { .type = NLA_U32 }, +}; + +static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct nlmsghdr *nlh, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + int err = -EINVAL; + struct fib6_rule *rule6 = (struct fib6_rule *) rule; + + if (frh->src_len > 128 || frh->dst_len > 128 || + (frh->tos & ~IPV6_FLOWINFO_MASK)) + goto errout; + + if (rule->action == FR_ACT_TO_TBL) { + if (rule->table == RT6_TABLE_UNSPEC) + goto errout; + + if (fib6_new_table(rule->table) == NULL) { + err = -ENOBUFS; + goto errout; + } + } + + if (tb[FRA_SRC]) + nla_memcpy(&rule6->src.addr, tb[FRA_SRC], + sizeof(struct in6_addr)); + + if (tb[FRA_DST]) + nla_memcpy(&rule6->dst.addr, tb[FRA_DST], + sizeof(struct in6_addr)); + +#ifdef CONFIG_IPV6_ROUTE_FWMARK + if (tb[FRA_FWMARK]) { + rule6->fwmark = nla_get_u32(tb[FRA_FWMARK]); + if (rule6->fwmark) { + /* + * if the mark value is non-zero, + * all bits are compared by default + * unless a mask is explicitly specified. + */ + rule6->fwmask = 0xFFFFFFFF; + } + } + + if (tb[FRA_FWMASK]) + rule6->fwmask = nla_get_u32(tb[FRA_FWMASK]); +#endif + + rule6->src.plen = frh->src_len; + rule6->dst.plen = frh->dst_len; + rule6->tclass = frh->tos; + + err = 0; +errout: + return err; +} + +static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + struct fib6_rule *rule6 = (struct fib6_rule *) rule; + + if (frh->src_len && (rule6->src.plen != frh->src_len)) + return 0; + + if (frh->dst_len && (rule6->dst.plen != frh->dst_len)) + return 0; + + if (frh->tos && (rule6->tclass != frh->tos)) + return 0; + + if (tb[FRA_SRC] && + nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr))) + return 0; + + if (tb[FRA_DST] && + nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr))) + return 0; + +#ifdef CONFIG_IPV6_ROUTE_FWMARK + if (tb[FRA_FWMARK] && (rule6->fwmark != nla_get_u32(tb[FRA_FWMARK]))) + return 0; + + if (tb[FRA_FWMASK] && (rule6->fwmask != nla_get_u32(tb[FRA_FWMASK]))) + return 0; +#endif + + return 1; +} + +static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct nlmsghdr *nlh, struct fib_rule_hdr *frh) +{ + struct fib6_rule *rule6 = (struct fib6_rule *) rule; + + frh->family = AF_INET6; + frh->dst_len = rule6->dst.plen; + frh->src_len = rule6->src.plen; + frh->tos = rule6->tclass; + + if (rule6->dst.plen) + NLA_PUT(skb, FRA_DST, sizeof(struct in6_addr), + &rule6->dst.addr); + + if (rule6->src.plen) + NLA_PUT(skb, FRA_SRC, sizeof(struct in6_addr), + &rule6->src.addr); + +#ifdef CONFIG_IPV6_ROUTE_FWMARK + if (rule6->fwmark) + NLA_PUT_U32(skb, FRA_FWMARK, rule6->fwmark); + + if (rule6->fwmask || rule6->fwmark) + NLA_PUT_U32(skb, FRA_FWMASK, rule6->fwmask); +#endif + + return 0; + +nla_put_failure: + return -ENOBUFS; +} + +int fib6_rules_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + return fib_rules_dump(skb, cb, AF_INET6); +} + +static u32 fib6_rule_default_pref(void) +{ + return 0x3FFF; +} + +static struct fib_rules_ops fib6_rules_ops = { + .family = AF_INET6, + .rule_size = sizeof(struct fib6_rule), + .action = fib6_rule_action, + .match = fib6_rule_match, + .configure = fib6_rule_configure, + .compare = fib6_rule_compare, + .fill = fib6_rule_fill, + .default_pref = fib6_rule_default_pref, + .nlgroup = RTNLGRP_IPV6_RULE, + .policy = fib6_rule_policy, + .rules_list = &fib6_rules, + .owner = THIS_MODULE, +}; + +void __init fib6_rules_init(void) +{ + list_add_tail(&local_rule.common.list, &fib6_rules); + list_add_tail(&main_rule.common.list, &fib6_rules); + + fib_rules_register(&fib6_rules_ops); +} + +void fib6_rules_cleanup(void) +{ + fib_rules_unregister(&fib6_rules_ops); +} diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 356a8a7ef22..4ec876066b3 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -151,7 +151,7 @@ static int is_ineligible(struct sk_buff *skb) return 0; } -static int sysctl_icmpv6_time = 1*HZ; +static int sysctl_icmpv6_time __read_mostly = 1*HZ; /* * Check the ICMP output rate limit @@ -273,6 +273,29 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st return 0; } +#ifdef CONFIG_IPV6_MIP6 +static void mip6_addr_swap(struct sk_buff *skb) +{ + struct ipv6hdr *iph = skb->nh.ipv6h; + struct inet6_skb_parm *opt = IP6CB(skb); + struct ipv6_destopt_hao *hao; + struct in6_addr tmp; + int off; + + if (opt->dsthao) { + off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO); + if (likely(off >= 0)) { + hao = (struct ipv6_destopt_hao *)(skb->nh.raw + off); + ipv6_addr_copy(&tmp, &iph->saddr); + ipv6_addr_copy(&iph->saddr, &hao->addr); + ipv6_addr_copy(&hao->addr, &tmp); + } + } +} +#else +static inline void mip6_addr_swap(struct sk_buff *skb) {} +#endif + /* * Send an ICMP message in response to a packet in error */ @@ -350,6 +373,8 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, return; } + mip6_addr_swap(skb); + memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_ICMPV6; ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr); @@ -358,6 +383,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, fl.oif = iif; fl.fl_icmp_type = type; fl.fl_icmp_code = code; + security_skb_classify_flow(skb, &fl); if (icmpv6_xmit_lock()) return; @@ -472,6 +498,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ipv6_addr_copy(&fl.fl6_src, saddr); fl.oif = skb->dev->ifindex; fl.fl_icmp_type = ICMPV6_ECHO_REPLY; + security_skb_classify_flow(skb, &fl); if (icmpv6_xmit_lock()) return; @@ -604,7 +631,7 @@ static int icmpv6_rcv(struct sk_buff **pskb) /* Perform checksum. */ switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, skb->csum)) break; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index bf491077b82..827f41d1478 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -157,6 +157,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) fl.oif = sk->sk_bound_dev_if; fl.fl_ip_sport = inet->sport; fl.fl_ip_dport = inet->dport; + security_sk_classify_flow(sk, &fl); if (np->opt && np->opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; @@ -185,7 +186,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) return err; } - __ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL, NULL); } skb->dst = dst_clone(dst); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 764221220af..8fcae7a6510 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -18,6 +18,7 @@ * Yuji SEKIYA @USAGI: Support default route on router node; * remove ip6_null_entry from the top of * routing table. + * Ville Nuorvala: Fixed routing subtrees. */ #include <linux/errno.h> #include <linux/types.h> @@ -26,6 +27,7 @@ #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/init.h> +#include <linux/list.h> #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> @@ -68,19 +70,19 @@ struct fib6_cleaner_t void *arg; }; -DEFINE_RWLOCK(fib6_walker_lock); - +static DEFINE_RWLOCK(fib6_walker_lock); #ifdef CONFIG_IPV6_SUBTREES #define FWS_INIT FWS_S -#define SUBTREE(fn) ((fn)->subtree) #else #define FWS_INIT FWS_L -#define SUBTREE(fn) NULL #endif static void fib6_prune_clones(struct fib6_node *fn, struct rt6_info *rt); +static struct rt6_info * fib6_find_prefix(struct fib6_node *fn); static struct fib6_node * fib6_repair_tree(struct fib6_node *fn); +static int fib6_walk(struct fib6_walker_t *w); +static int fib6_walk_continue(struct fib6_walker_t *w); /* * A routing update causes an increase of the serial number on the @@ -93,13 +95,31 @@ static __u32 rt_sernum; static DEFINE_TIMER(ip6_fib_timer, fib6_run_gc, 0, 0); -struct fib6_walker_t fib6_walker_list = { +static struct fib6_walker_t fib6_walker_list = { .prev = &fib6_walker_list, .next = &fib6_walker_list, }; #define FOR_WALKERS(w) for ((w)=fib6_walker_list.next; (w) != &fib6_walker_list; (w)=(w)->next) +static inline void fib6_walker_link(struct fib6_walker_t *w) +{ + write_lock_bh(&fib6_walker_lock); + w->next = fib6_walker_list.next; + w->prev = &fib6_walker_list; + w->next->prev = w; + w->prev->next = w; + write_unlock_bh(&fib6_walker_lock); +} + +static inline void fib6_walker_unlink(struct fib6_walker_t *w) +{ + write_lock_bh(&fib6_walker_lock); + w->next->prev = w->prev; + w->prev->next = w->next; + w->prev = w->next = w; + write_unlock_bh(&fib6_walker_lock); +} static __inline__ u32 fib6_new_sernum(void) { u32 n = ++rt_sernum; @@ -147,6 +167,253 @@ static __inline__ void rt6_release(struct rt6_info *rt) dst_free(&rt->u.dst); } +static struct fib6_table fib6_main_tbl = { + .tb6_id = RT6_TABLE_MAIN, + .tb6_lock = RW_LOCK_UNLOCKED, + .tb6_root = { + .leaf = &ip6_null_entry, + .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO, + }, +}; + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +#define FIB_TABLE_HASHSZ 256 +#else +#define FIB_TABLE_HASHSZ 1 +#endif +static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; + +static void fib6_link_table(struct fib6_table *tb) +{ + unsigned int h; + + h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1); + + /* + * No protection necessary, this is the only list mutatation + * operation, tables never disappear once they exist. + */ + hlist_add_head_rcu(&tb->tb6_hlist, &fib_table_hash[h]); +} + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +static struct fib6_table fib6_local_tbl = { + .tb6_id = RT6_TABLE_LOCAL, + .tb6_lock = RW_LOCK_UNLOCKED, + .tb6_root = { + .leaf = &ip6_null_entry, + .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO, + }, +}; + +static struct fib6_table *fib6_alloc_table(u32 id) +{ + struct fib6_table *table; + + table = kzalloc(sizeof(*table), GFP_ATOMIC); + if (table != NULL) { + table->tb6_id = id; + table->tb6_lock = RW_LOCK_UNLOCKED; + table->tb6_root.leaf = &ip6_null_entry; + table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; + } + + return table; +} + +struct fib6_table *fib6_new_table(u32 id) +{ + struct fib6_table *tb; + + if (id == 0) + id = RT6_TABLE_MAIN; + tb = fib6_get_table(id); + if (tb) + return tb; + + tb = fib6_alloc_table(id); + if (tb != NULL) + fib6_link_table(tb); + + return tb; +} + +struct fib6_table *fib6_get_table(u32 id) +{ + struct fib6_table *tb; + struct hlist_node *node; + unsigned int h; + + if (id == 0) + id = RT6_TABLE_MAIN; + h = id & (FIB_TABLE_HASHSZ - 1); + rcu_read_lock(); + hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb6_hlist) { + if (tb->tb6_id == id) { + rcu_read_unlock(); + return tb; + } + } + rcu_read_unlock(); + + return NULL; +} + +static void __init fib6_tables_init(void) +{ + fib6_link_table(&fib6_main_tbl); + fib6_link_table(&fib6_local_tbl); +} + +#else + +struct fib6_table *fib6_new_table(u32 id) +{ + return fib6_get_table(id); +} + +struct fib6_table *fib6_get_table(u32 id) +{ + return &fib6_main_tbl; +} + +struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags, + pol_lookup_t lookup) +{ + return (struct dst_entry *) lookup(&fib6_main_tbl, fl, flags); +} + +static void __init fib6_tables_init(void) +{ + fib6_link_table(&fib6_main_tbl); +} + +#endif + +static int fib6_dump_node(struct fib6_walker_t *w) +{ + int res; + struct rt6_info *rt; + + for (rt = w->leaf; rt; rt = rt->u.next) { + res = rt6_dump_route(rt, w->args); + if (res < 0) { + /* Frame is full, suspend walking */ + w->leaf = rt; + return 1; + } + BUG_TRAP(res!=0); + } + w->leaf = NULL; + return 0; +} + +static void fib6_dump_end(struct netlink_callback *cb) +{ + struct fib6_walker_t *w = (void*)cb->args[2]; + + if (w) { + cb->args[2] = 0; + kfree(w); + } + cb->done = (void*)cb->args[3]; + cb->args[1] = 3; +} + +static int fib6_dump_done(struct netlink_callback *cb) +{ + fib6_dump_end(cb); + return cb->done ? cb->done(cb) : 0; +} + +static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct fib6_walker_t *w; + int res; + + w = (void *)cb->args[2]; + w->root = &table->tb6_root; + + if (cb->args[4] == 0) { + read_lock_bh(&table->tb6_lock); + res = fib6_walk(w); + read_unlock_bh(&table->tb6_lock); + if (res > 0) + cb->args[4] = 1; + } else { + read_lock_bh(&table->tb6_lock); + res = fib6_walk_continue(w); + read_unlock_bh(&table->tb6_lock); + if (res != 0) { + if (res < 0) + fib6_walker_unlink(w); + goto end; + } + fib6_walker_unlink(w); + cb->args[4] = 0; + } +end: + return res; +} + +int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) +{ + unsigned int h, s_h; + unsigned int e = 0, s_e; + struct rt6_rtnl_dump_arg arg; + struct fib6_walker_t *w; + struct fib6_table *tb; + struct hlist_node *node; + int res = 0; + + s_h = cb->args[0]; + s_e = cb->args[1]; + + w = (void *)cb->args[2]; + if (w == NULL) { + /* New dump: + * + * 1. hook callback destructor. + */ + cb->args[3] = (long)cb->done; + cb->done = fib6_dump_done; + + /* + * 2. allocate and initialize walker. + */ + w = kzalloc(sizeof(*w), GFP_ATOMIC); + if (w == NULL) + return -ENOMEM; + w->func = fib6_dump_node; + cb->args[2] = (long)w; + } + + arg.skb = skb; + arg.cb = cb; + w->args = &arg; + + for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { + e = 0; + hlist_for_each_entry(tb, node, &fib_table_hash[h], tb6_hlist) { + if (e < s_e) + goto next; + res = fib6_dump_table(tb, skb, cb); + if (res != 0) + goto out; +next: + e++; + } + } +out: + cb->args[1] = e; + cb->args[0] = h; + + res = res < 0 ? res : skb->len; + if (res <= 0) + fib6_dump_end(cb); + return res; +} /* * Routing Table @@ -343,7 +610,7 @@ insert_above: */ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nlmsghdr *nlh, struct netlink_skb_parms *req) + struct nl_info *info) { struct rt6_info *iter = NULL; struct rt6_info **ins; @@ -398,7 +665,7 @@ out: *ins = rt; rt->rt6i_node = fn; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, nlh, req); + inet6_rt_notify(RTM_NEWROUTE, rt, info); rt6_stats.fib_rt_entries++; if ((fn->fn_flags & RTN_RTINFO) == 0) { @@ -428,10 +695,9 @@ void fib6_force_start_gc(void) * with source addr info in sub-trees */ -int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) { - struct fib6_node *fn; + struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), @@ -440,6 +706,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (fn == NULL) goto out; + pn = fn; + #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen) { struct fib6_node *sn; @@ -485,10 +753,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, /* Now link new subtree to main tree */ sfn->parent = fn; fn->subtree = sfn; - if (fn->leaf == NULL) { - fn->leaf = rt; - atomic_inc(&rt->rt6i_ref); - } } else { sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, sizeof(struct in6_addr), rt->rt6i_src.plen, @@ -498,21 +762,42 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, goto st_failure; } + if (fn->leaf == NULL) { + fn->leaf = rt; + atomic_inc(&rt->rt6i_ref); + } fn = sn; } #endif - err = fib6_add_rt2node(fn, rt, nlh, req); + err = fib6_add_rt2node(fn, rt, info); if (err == 0) { fib6_start_gc(rt); if (!(rt->rt6i_flags&RTF_CACHE)) - fib6_prune_clones(fn, rt); + fib6_prune_clones(pn, rt); } out: - if (err) + if (err) { +#ifdef CONFIG_IPV6_SUBTREES + /* + * If fib6_add_1 has cleared the old leaf pointer in the + * super-tree leaf node we have to find a new one for it. + */ + if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) { + pn->leaf = fib6_find_prefix(pn); +#if RT6_DEBUG >= 2 + if (!pn->leaf) { + BUG_TRAP(pn->leaf != NULL); + pn->leaf = &ip6_null_entry; + } +#endif + atomic_inc(&pn->leaf->rt6i_ref); + } +#endif dst_free(&rt->u.dst); + } return err; #ifdef CONFIG_IPV6_SUBTREES @@ -543,6 +828,9 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, struct fib6_node *fn; int dir; + if (unlikely(args->offset == 0)) + return NULL; + /* * Descend on a tree */ @@ -564,33 +852,26 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, break; } - while ((fn->fn_flags & RTN_ROOT) == 0) { -#ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) { - struct fib6_node *st; - struct lookup_args *narg; - - narg = args + 1; - - if (narg->addr) { - st = fib6_lookup_1(fn->subtree, narg); - - if (st && !(st->fn_flags & RTN_ROOT)) - return st; - } - } -#endif - - if (fn->fn_flags & RTN_RTINFO) { + while(fn) { + if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) { struct rt6key *key; key = (struct rt6key *) ((u8 *) fn->leaf + args->offset); - if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) - return fn; + if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { +#ifdef CONFIG_IPV6_SUBTREES + if (fn->subtree) + fn = fib6_lookup_1(fn->subtree, args + 1); +#endif + if (!fn || fn->fn_flags & RTN_RTINFO) + return fn; + } } + if (fn->fn_flags & RTN_ROOT) + break; + fn = fn->parent; } @@ -600,18 +881,24 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, struct fib6_node * fib6_lookup(struct fib6_node *root, struct in6_addr *daddr, struct in6_addr *saddr) { - struct lookup_args args[2]; struct fib6_node *fn; - - args[0].offset = offsetof(struct rt6_info, rt6i_dst); - args[0].addr = daddr; - + struct lookup_args args[] = { + { + .offset = offsetof(struct rt6_info, rt6i_dst), + .addr = daddr, + }, #ifdef CONFIG_IPV6_SUBTREES - args[1].offset = offsetof(struct rt6_info, rt6i_src); - args[1].addr = saddr; + { + .offset = offsetof(struct rt6_info, rt6i_src), + .addr = saddr, + }, #endif + { + .offset = 0, /* sentinel */ + } + }; - fn = fib6_lookup_1(root, args); + fn = fib6_lookup_1(root, daddr ? args : args + 1); if (fn == NULL || fn->fn_flags & RTN_TL_ROOT) fn = root; @@ -667,10 +954,8 @@ struct fib6_node * fib6_locate(struct fib6_node *root, #ifdef CONFIG_IPV6_SUBTREES if (src_len) { BUG_TRAP(saddr!=NULL); - if (fn == NULL) - fn = fn->subtree; - if (fn) - fn = fib6_locate_1(fn, saddr, src_len, + if (fn && fn->subtree) + fn = fib6_locate_1(fn->subtree, saddr, src_len, offsetof(struct rt6_info, rt6i_src)); } #endif @@ -699,7 +984,7 @@ static struct rt6_info * fib6_find_prefix(struct fib6_node *fn) if(fn->right) return fn->right->leaf; - fn = SUBTREE(fn); + fn = FIB6_SUBTREE(fn); } return NULL; } @@ -730,7 +1015,7 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) if (fn->right) child = fn->right, children |= 1; if (fn->left) child = fn->left, children |= 2; - if (children == 3 || SUBTREE(fn) + if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES /* Subtree root (i.e. fn) may have one child */ || (children && fn->fn_flags&RTN_ROOT) @@ -749,9 +1034,9 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) pn = fn->parent; #ifdef CONFIG_IPV6_SUBTREES - if (SUBTREE(pn) == fn) { + if (FIB6_SUBTREE(pn) == fn) { BUG_TRAP(fn->fn_flags&RTN_ROOT); - SUBTREE(pn) = NULL; + FIB6_SUBTREE(pn) = NULL; nstate = FWS_L; } else { BUG_TRAP(!(fn->fn_flags&RTN_ROOT)); @@ -799,7 +1084,7 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) read_unlock(&fib6_walker_lock); node_free(fn); - if (pn->fn_flags&RTN_RTINFO || SUBTREE(pn)) + if (pn->fn_flags&RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; rt6_release(pn->leaf); @@ -809,7 +1094,7 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) } static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, - struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) + struct nl_info *info) { struct fib6_walker_t *w; struct rt6_info *rt = *rtp; @@ -865,11 +1150,11 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, if (atomic_read(&rt->rt6i_ref) != 1) BUG(); } - inet6_rt_notify(RTM_DELROUTE, rt, nlh, req); + inet6_rt_notify(RTM_DELROUTE, rt, info); rt6_release(rt); } -int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +int fib6_del(struct rt6_info *rt, struct nl_info *info) { struct fib6_node *fn = rt->rt6i_node; struct rt6_info **rtp; @@ -885,8 +1170,18 @@ int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct ne BUG_TRAP(fn->fn_flags&RTN_RTINFO); - if (!(rt->rt6i_flags&RTF_CACHE)) - fib6_prune_clones(fn, rt); + if (!(rt->rt6i_flags&RTF_CACHE)) { + struct fib6_node *pn = fn; +#ifdef CONFIG_IPV6_SUBTREES + /* clones of this route might be in another subtree */ + if (rt->rt6i_src.plen) { + while (!(pn->fn_flags&RTN_ROOT)) + pn = pn->parent; + pn = pn->parent; + } +#endif + fib6_prune_clones(pn, rt); + } /* * Walk the leaf entries looking for ourself @@ -894,7 +1189,7 @@ int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct ne for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->u.next) { if (*rtp == rt) { - fib6_del_route(fn, rtp, nlh, _rtattr, req); + fib6_del_route(fn, rtp, info); return 0; } } @@ -925,7 +1220,7 @@ int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct ne * <0 -> walk is terminated by an error. */ -int fib6_walk_continue(struct fib6_walker_t *w) +static int fib6_walk_continue(struct fib6_walker_t *w) { struct fib6_node *fn, *pn; @@ -942,8 +1237,8 @@ int fib6_walk_continue(struct fib6_walker_t *w) switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: - if (SUBTREE(fn)) { - w->node = SUBTREE(fn); + if (FIB6_SUBTREE(fn)) { + w->node = FIB6_SUBTREE(fn); continue; } w->state = FWS_L; @@ -977,7 +1272,7 @@ int fib6_walk_continue(struct fib6_walker_t *w) pn = fn->parent; w->node = pn; #ifdef CONFIG_IPV6_SUBTREES - if (SUBTREE(pn) == fn) { + if (FIB6_SUBTREE(pn) == fn) { BUG_TRAP(fn->fn_flags&RTN_ROOT); w->state = FWS_L; continue; @@ -999,7 +1294,7 @@ int fib6_walk_continue(struct fib6_walker_t *w) } } -int fib6_walk(struct fib6_walker_t *w) +static int fib6_walk(struct fib6_walker_t *w) { int res; @@ -1023,7 +1318,7 @@ static int fib6_clean_node(struct fib6_walker_t *w) res = c->func(rt, c->arg); if (res < 0) { w->leaf = rt; - res = fib6_del(rt, NULL, NULL, NULL); + res = fib6_del(rt, NULL); if (res) { #if RT6_DEBUG >= 2 printk(KERN_DEBUG "fib6_clean_node: del failed: rt=%p@%p err=%d\n", rt, rt->rt6i_node, res); @@ -1049,9 +1344,9 @@ static int fib6_clean_node(struct fib6_walker_t *w) * ignoring pure split nodes) will be scanned. */ -void fib6_clean_tree(struct fib6_node *root, - int (*func)(struct rt6_info *, void *arg), - int prune, void *arg) +static void fib6_clean_tree(struct fib6_node *root, + int (*func)(struct rt6_info *, void *arg), + int prune, void *arg) { struct fib6_cleaner_t c; @@ -1064,6 +1359,25 @@ void fib6_clean_tree(struct fib6_node *root, fib6_walk(&c.w); } +void fib6_clean_all(int (*func)(struct rt6_info *, void *arg), + int prune, void *arg) +{ + struct fib6_table *table; + struct hlist_node *node; + unsigned int h; + + rcu_read_lock(); + for (h = 0; h < FIB_TABLE_HASHSZ; h++) { + hlist_for_each_entry_rcu(table, node, &fib_table_hash[h], + tb6_hlist) { + write_lock_bh(&table->tb6_lock); + fib6_clean_tree(&table->tb6_root, func, prune, arg); + write_unlock_bh(&table->tb6_lock); + } + } + rcu_read_unlock(); +} + static int fib6_prune_clone(struct rt6_info *rt, void *arg) { if (rt->rt6i_flags & RTF_CACHE) { @@ -1142,11 +1456,8 @@ void fib6_run_gc(unsigned long dummy) } gc_args.more = 0; - - write_lock_bh(&rt6_lock); ndisc_dst_gc(&gc_args.more); - fib6_clean_tree(&ip6_routing_table, fib6_age, 0, NULL); - write_unlock_bh(&rt6_lock); + fib6_clean_all(fib6_age, 0, NULL); if (gc_args.more) mod_timer(&ip6_fib_timer, jiffies + ip6_rt_gc_interval); @@ -1161,10 +1472,10 @@ void __init fib6_init(void) { fib6_node_kmem = kmem_cache_create("fib6_nodes", sizeof(struct fib6_node), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!fib6_node_kmem) - panic("cannot create fib6_nodes cache"); + + fib6_tables_init(); } void fib6_gc_cleanup(void) diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 25c2a9e0389..6b8e6d76a58 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -111,7 +111,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt } if (hdr->nexthdr == NEXTHDR_HOP) { - if (ipv6_parse_hopopts(skb) < 0) { + if (ipv6_parse_hopopts(&skb) < 0) { IP6_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS); return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4fb47a25291..66716911962 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -308,6 +308,56 @@ static int ip6_call_ra_chain(struct sk_buff *skb, int sel) return 0; } +static int ip6_forward_proxy_check(struct sk_buff *skb) +{ + struct ipv6hdr *hdr = skb->nh.ipv6h; + u8 nexthdr = hdr->nexthdr; + int offset; + + if (ipv6_ext_hdr(nexthdr)) { + offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr); + if (offset < 0) + return 0; + } else + offset = sizeof(struct ipv6hdr); + + if (nexthdr == IPPROTO_ICMPV6) { + struct icmp6hdr *icmp6; + + if (!pskb_may_pull(skb, skb->nh.raw + offset + 1 - skb->data)) + return 0; + + icmp6 = (struct icmp6hdr *)(skb->nh.raw + offset); + + switch (icmp6->icmp6_type) { + case NDISC_ROUTER_SOLICITATION: + case NDISC_ROUTER_ADVERTISEMENT: + case NDISC_NEIGHBOUR_SOLICITATION: + case NDISC_NEIGHBOUR_ADVERTISEMENT: + case NDISC_REDIRECT: + /* For reaction involving unicast neighbor discovery + * message destined to the proxied address, pass it to + * input function. + */ + return 1; + default: + break; + } + } + + /* + * The proxying router can't forward traffic sent to a link-local + * address, so signal the sender and discard the packet. This + * behavior is clarified by the MIPv6 specification. + */ + if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) { + dst_link_failure(skb); + return -1; + } + + return 0; +} + static inline int ip6_forward_finish(struct sk_buff *skb) { return dst_output(skb); @@ -362,6 +412,18 @@ int ip6_forward(struct sk_buff *skb) return -ETIMEDOUT; } + /* XXX: idev->cnf.proxy_ndp? */ + if (ipv6_devconf.proxy_ndp && + pneigh_lookup(&nd_tbl, &hdr->daddr, skb->dev, 0)) { + int proxied = ip6_forward_proxy_check(skb); + if (proxied > 0) + return ip6_input(skb); + else if (proxied < 0) { + IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); + goto drop; + } + } + if (!xfrm6_route_forward(skb)) { IP6_INC_STATS(IPSTATS_MIB_INDISCARDS); goto drop; @@ -475,17 +537,25 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) switch (**nexthdr) { case NEXTHDR_HOP: + break; case NEXTHDR_ROUTING: + found_rhdr = 1; + break; case NEXTHDR_DEST: - if (**nexthdr == NEXTHDR_ROUTING) found_rhdr = 1; - if (**nexthdr == NEXTHDR_DEST && found_rhdr) return offset; - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset); +#ifdef CONFIG_IPV6_MIP6 + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) + break; +#endif + if (found_rhdr) + return offset; break; default : return offset; } + + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; + exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset); } return offset; @@ -726,6 +796,14 @@ fail: return err; } +static inline int ip6_rt_check(struct rt6key *rt_key, + struct in6_addr *fl_addr, + struct in6_addr *addr_cache) +{ + return ((rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && + (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache))); +} + static struct dst_entry *ip6_sk_dst_check(struct sock *sk, struct dst_entry *dst, struct flowi *fl) @@ -741,8 +819,8 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, * 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. + * 1. ip6_rt_check(): 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. @@ -753,11 +831,11 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, * sockets. * 2. oif also should be the same. */ - if (((rt->rt6i_dst.plen != 128 || - !ipv6_addr_equal(&fl->fl6_dst, &rt->rt6i_dst.addr)) - && (np->daddr_cache == NULL || - !ipv6_addr_equal(&fl->fl6_dst, np->daddr_cache))) - || (fl->oif && fl->oif != dst->dev->ifindex)) { + if (ip6_rt_check(&rt->rt6i_dst, &fl->fl6_dst, np->daddr_cache) || +#ifdef CONFIG_IPV6_SUBTREES + ip6_rt_check(&rt->rt6i_src, &fl->fl6_src, np->saddr_cache) || +#endif + (fl->oif && fl->oif != dst->dev->ifindex)) { dst_release(dst); dst = NULL; } @@ -866,7 +944,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, /* initialize protocol header pointer */ skb->h.raw = skb->data + fragheaderlen; - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; sk->sk_sndmsg_off = 0; } @@ -963,7 +1041,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); - fragheaderlen = sizeof(struct ipv6hdr) + (opt ? opt->opt_nflen : 0); + fragheaderlen = sizeof(struct ipv6hdr) + rt->u.dst.nfheader_len + (opt ? opt->opt_nflen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) { diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index a81e9e9d93b..ad9c6e824e6 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -212,7 +212,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) memcpy(t->id.daddr.a6, x->id.daddr.a6, sizeof(struct in6_addr)); memcpy(&t->sel, &x->sel, sizeof(t->sel)); t->props.family = AF_INET6; - t->props.mode = 1; + t->props.mode = XFRM_MODE_TUNNEL; memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr)); if (xfrm_init_state(t)) @@ -417,7 +417,7 @@ static int ipcomp6_init_state(struct xfrm_state *x) goto out; x->props.header_len = 0; - if (x->props.mode) + if (x->props.mode == XFRM_MODE_TUNNEL) x->props.header_len += sizeof(struct ipv6hdr); mutex_lock(&ipcomp6_resource_mutex); @@ -429,7 +429,7 @@ static int ipcomp6_init_state(struct xfrm_state *x) goto error; mutex_unlock(&ipcomp6_resource_mutex); - if (x->props.mode) { + if (x->props.mode == XFRM_MODE_TUNNEL) { err = ipcomp6_tunnel_attach(x); if (err) goto error_tunnel; @@ -461,6 +461,7 @@ static struct xfrm_type ipcomp6_type = .destructor = ipcomp6_destroy, .input = ipcomp6_input, .output = ipcomp6_output, + .hdr_offset = xfrm6_find_1stfragopt, }; static struct inet6_protocol ipcomp6_protocol = diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a5eaaf693ab..4f3bb7fcc8b 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -407,8 +407,16 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, /* routing header option needs extra check */ if (optname == IPV6_RTHDR && opt->srcrt) { struct ipv6_rt_hdr *rthdr = opt->srcrt; - if (rthdr->type) + switch (rthdr->type) { + case IPV6_SRCRT_TYPE_0: +#ifdef CONFIG_IPV6_MIP6 + case IPV6_SRCRT_TYPE_2: +#endif + break; + default: goto sticky_done; + } + if ((rthdr->hdrlen & 1) || (rthdr->hdrlen >> 1) != rthdr->segments_left) goto sticky_done; diff --git a/net/ipv6/ipv6_syms.c b/net/ipv6/ipv6_syms.c index dd4d1ce7776..0e8e0676a03 100644 --- a/net/ipv6/ipv6_syms.c +++ b/net/ipv6/ipv6_syms.c @@ -14,7 +14,6 @@ EXPORT_SYMBOL(ndisc_mc_map); EXPORT_SYMBOL(register_inet6addr_notifier); EXPORT_SYMBOL(unregister_inet6addr_notifier); EXPORT_SYMBOL(ip6_route_output); -EXPORT_SYMBOL(addrconf_lock); EXPORT_SYMBOL(ipv6_setsockopt); EXPORT_SYMBOL(ipv6_getsockopt); EXPORT_SYMBOL(inet6_register_protosw); @@ -31,6 +30,8 @@ EXPORT_SYMBOL(ipv6_chk_addr); EXPORT_SYMBOL(in6_dev_finish_destroy); #ifdef CONFIG_XFRM EXPORT_SYMBOL(xfrm6_rcv); +EXPORT_SYMBOL(xfrm6_input_addr); +EXPORT_SYMBOL(xfrm6_find_1stfragopt); #endif EXPORT_SYMBOL(rt6_lookup); EXPORT_SYMBOL(ipv6_push_nfrag_opts); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 639eb20c9f1..3b114e3fa2f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -171,7 +171,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, #define IPV6_MLD_MAX_MSF 64 -int sysctl_mld_max_msf = IPV6_MLD_MAX_MSF; +int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; /* * socket join on multicast group diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c new file mode 100644 index 00000000000..99d116caecd --- /dev/null +++ b/net/ipv6/mip6.c @@ -0,0 +1,519 @@ +/* + * Copyright (C)2003-2006 Helsinki University of Technology + * Copyright (C)2003-2006 USAGI/WIDE Project + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +/* + * Authors: + * Noriaki TAKAMIYA @USAGI + * Masahide NAKAMURA @USAGI + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/time.h> +#include <linux/ipv6.h> +#include <linux/icmpv6.h> +#include <net/sock.h> +#include <net/ipv6.h> +#include <net/ip6_checksum.h> +#include <net/xfrm.h> +#include <net/mip6.h> + +static xfrm_address_t *mip6_xfrm_addr(struct xfrm_state *x, xfrm_address_t *addr) +{ + return x->coaddr; +} + +static inline unsigned int calc_padlen(unsigned int len, unsigned int n) +{ + return (n - len + 16) & 0x7; +} + +static inline void *mip6_padn(__u8 *data, __u8 padlen) +{ + if (!data) + return NULL; + if (padlen == 1) { + data[0] = MIP6_OPT_PAD_1; + } else if (padlen > 1) { + data[0] = MIP6_OPT_PAD_N; + data[1] = padlen - 2; + if (padlen > 2) + memset(data+2, 0, data[1]); + } + return data + padlen; +} + +static inline void mip6_param_prob(struct sk_buff *skb, int code, int pos) +{ + icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev); +} + +static int mip6_mh_len(int type) +{ + int len = 0; + + switch (type) { + case IP6_MH_TYPE_BRR: + len = 0; + break; + case IP6_MH_TYPE_HOTI: + case IP6_MH_TYPE_COTI: + case IP6_MH_TYPE_BU: + case IP6_MH_TYPE_BACK: + len = 1; + break; + case IP6_MH_TYPE_HOT: + case IP6_MH_TYPE_COT: + case IP6_MH_TYPE_BERROR: + len = 2; + break; + } + return len; +} + +int mip6_mh_filter(struct sock *sk, struct sk_buff *skb) +{ + struct ip6_mh *mh; + int mhlen; + + if (!pskb_may_pull(skb, (skb->h.raw - skb->data) + 8) || + !pskb_may_pull(skb, (skb->h.raw - skb->data) + ((skb->h.raw[1] + 1) << 3))) + return -1; + + mh = (struct ip6_mh *)skb->h.raw; + + if (mh->ip6mh_hdrlen < mip6_mh_len(mh->ip6mh_type)) { + LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH message too short: %d vs >=%d\n", + mh->ip6mh_hdrlen, mip6_mh_len(mh->ip6mh_type)); + mip6_param_prob(skb, 0, (&mh->ip6mh_hdrlen) - skb->nh.raw); + return -1; + } + mhlen = (mh->ip6mh_hdrlen + 1) << 3; + + if (skb->ip_summed == CHECKSUM_COMPLETE) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + if (csum_ipv6_magic(&skb->nh.ipv6h->saddr, + &skb->nh.ipv6h->daddr, + mhlen, IPPROTO_MH, + skb->csum)) { + LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH hw checksum failed\n"); + skb->ip_summed = CHECKSUM_NONE; + } + } + if (skb->ip_summed == CHECKSUM_NONE) { + if (csum_ipv6_magic(&skb->nh.ipv6h->saddr, + &skb->nh.ipv6h->daddr, + mhlen, IPPROTO_MH, + skb_checksum(skb, 0, mhlen, 0))) { + LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH checksum failed " + "[" NIP6_FMT " > " NIP6_FMT "]\n", + NIP6(skb->nh.ipv6h->saddr), + NIP6(skb->nh.ipv6h->daddr)); + return -1; + } + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + + if (mh->ip6mh_proto != IPPROTO_NONE) { + LIMIT_NETDEBUG(KERN_DEBUG "mip6: MH invalid payload proto = %d\n", + mh->ip6mh_proto); + mip6_param_prob(skb, 0, (&mh->ip6mh_proto) - skb->nh.raw); + return -1; + } + + return 0; +} + +struct mip6_report_rate_limiter { + spinlock_t lock; + struct timeval stamp; + int iif; + struct in6_addr src; + struct in6_addr dst; +}; + +static struct mip6_report_rate_limiter mip6_report_rl = { + .lock = SPIN_LOCK_UNLOCKED +}; + +static int mip6_destopt_input(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *iph = skb->nh.ipv6h; + struct ipv6_destopt_hdr *destopt = (struct ipv6_destopt_hdr *)skb->data; + + if (!ipv6_addr_equal(&iph->saddr, (struct in6_addr *)x->coaddr) && + !ipv6_addr_any((struct in6_addr *)x->coaddr)) + return -ENOENT; + + return destopt->nexthdr; +} + +/* Destination Option Header is inserted. + * IP Header's src address is replaced with Home Address Option in + * Destination Option Header. + */ +static int mip6_destopt_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *iph; + struct ipv6_destopt_hdr *dstopt; + struct ipv6_destopt_hao *hao; + u8 nexthdr; + int len; + + iph = (struct ipv6hdr *)skb->data; + iph->payload_len = htons(skb->len - sizeof(*iph)); + + nexthdr = *skb->nh.raw; + *skb->nh.raw = IPPROTO_DSTOPTS; + + dstopt = (struct ipv6_destopt_hdr *)skb->h.raw; + dstopt->nexthdr = nexthdr; + + hao = mip6_padn((char *)(dstopt + 1), + calc_padlen(sizeof(*dstopt), 6)); + + hao->type = IPV6_TLV_HAO; + hao->length = sizeof(*hao) - 2; + BUG_TRAP(hao->length == 16); + + len = ((char *)hao - (char *)dstopt) + sizeof(*hao); + + memcpy(&hao->addr, &iph->saddr, sizeof(hao->addr)); + memcpy(&iph->saddr, x->coaddr, sizeof(iph->saddr)); + + BUG_TRAP(len == x->props.header_len); + dstopt->hdrlen = (x->props.header_len >> 3) - 1; + + return 0; +} + +static inline int mip6_report_rl_allow(struct timeval *stamp, + struct in6_addr *dst, + struct in6_addr *src, int iif) +{ + int allow = 0; + + spin_lock_bh(&mip6_report_rl.lock); + if (mip6_report_rl.stamp.tv_sec != stamp->tv_sec || + mip6_report_rl.stamp.tv_usec != stamp->tv_usec || + mip6_report_rl.iif != iif || + !ipv6_addr_equal(&mip6_report_rl.src, src) || + !ipv6_addr_equal(&mip6_report_rl.dst, dst)) { + mip6_report_rl.stamp.tv_sec = stamp->tv_sec; + mip6_report_rl.stamp.tv_usec = stamp->tv_usec; + mip6_report_rl.iif = iif; + ipv6_addr_copy(&mip6_report_rl.src, src); + ipv6_addr_copy(&mip6_report_rl.dst, dst); + allow = 1; + } + spin_unlock_bh(&mip6_report_rl.lock); + return allow; +} + +static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct flowi *fl) +{ + struct inet6_skb_parm *opt = (struct inet6_skb_parm *)skb->cb; + struct ipv6_destopt_hao *hao = NULL; + struct xfrm_selector sel; + int offset; + struct timeval stamp; + int err = 0; + + if (unlikely(fl->proto == IPPROTO_MH && + fl->fl_mh_type <= IP6_MH_TYPE_MAX)) + goto out; + + if (likely(opt->dsthao)) { + offset = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO); + if (likely(offset >= 0)) + hao = (struct ipv6_destopt_hao *)(skb->nh.raw + offset); + } + + skb_get_timestamp(skb, &stamp); + + if (!mip6_report_rl_allow(&stamp, &skb->nh.ipv6h->daddr, + hao ? &hao->addr : &skb->nh.ipv6h->saddr, + opt->iif)) + goto out; + + memset(&sel, 0, sizeof(sel)); + memcpy(&sel.daddr, (xfrm_address_t *)&skb->nh.ipv6h->daddr, + sizeof(sel.daddr)); + sel.prefixlen_d = 128; + memcpy(&sel.saddr, (xfrm_address_t *)&skb->nh.ipv6h->saddr, + sizeof(sel.saddr)); + sel.prefixlen_s = 128; + sel.family = AF_INET6; + sel.proto = fl->proto; + sel.dport = xfrm_flowi_dport(fl); + if (sel.dport) + sel.dport_mask = ~((__u16)0); + sel.sport = xfrm_flowi_sport(fl); + if (sel.sport) + sel.sport_mask = ~((__u16)0); + sel.ifindex = fl->oif; + + err = km_report(IPPROTO_DSTOPTS, &sel, + (hao ? (xfrm_address_t *)&hao->addr : NULL)); + + out: + return err; +} + +static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb, + u8 **nexthdr) +{ + u16 offset = sizeof(struct ipv6hdr); + struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr*)(skb->nh.ipv6h + 1); + unsigned int packet_len = skb->tail - skb->nh.raw; + int found_rhdr = 0; + + *nexthdr = &skb->nh.ipv6h->nexthdr; + + while (offset + 1 <= packet_len) { + + switch (**nexthdr) { + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + found_rhdr = 1; + break; + case NEXTHDR_DEST: + /* + * HAO MUST NOT appear more than once. + * XXX: It is better to try to find by the end of + * XXX: packet if HAO exists. + */ + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) { + LIMIT_NETDEBUG(KERN_WARNING "mip6: hao exists already, override\n"); + return offset; + } + + if (found_rhdr) + return offset; + + break; + default: + return offset; + } + + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; + exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset); + } + + return offset; +} + +static int mip6_destopt_init_state(struct xfrm_state *x) +{ + if (x->id.spi) { + printk(KERN_INFO "%s: spi is not 0: %u\n", __FUNCTION__, + x->id.spi); + return -EINVAL; + } + if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) { + printk(KERN_INFO "%s: state's mode is not %u: %u\n", + __FUNCTION__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode); + return -EINVAL; + } + + x->props.header_len = sizeof(struct ipv6_destopt_hdr) + + calc_padlen(sizeof(struct ipv6_destopt_hdr), 6) + + sizeof(struct ipv6_destopt_hao); + BUG_TRAP(x->props.header_len == 24); + + return 0; +} + +/* + * Do nothing about destroying since it has no specific operation for + * destination options header unlike IPsec protocols. + */ +static void mip6_destopt_destroy(struct xfrm_state *x) +{ +} + +static struct xfrm_type mip6_destopt_type = +{ + .description = "MIP6DESTOPT", + .owner = THIS_MODULE, + .proto = IPPROTO_DSTOPTS, + .flags = XFRM_TYPE_NON_FRAGMENT, + .init_state = mip6_destopt_init_state, + .destructor = mip6_destopt_destroy, + .input = mip6_destopt_input, + .output = mip6_destopt_output, + .reject = mip6_destopt_reject, + .hdr_offset = mip6_destopt_offset, + .local_addr = mip6_xfrm_addr, +}; + +static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb) +{ + struct rt2_hdr *rt2 = (struct rt2_hdr *)skb->data; + + if (!ipv6_addr_equal(&rt2->addr, (struct in6_addr *)x->coaddr) && + !ipv6_addr_any((struct in6_addr *)x->coaddr)) + return -ENOENT; + + return rt2->rt_hdr.nexthdr; +} + +/* Routing Header type 2 is inserted. + * IP Header's dst address is replaced with Routing Header's Home Address. + */ +static int mip6_rthdr_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *iph; + struct rt2_hdr *rt2; + u8 nexthdr; + + iph = (struct ipv6hdr *)skb->data; + iph->payload_len = htons(skb->len - sizeof(*iph)); + + nexthdr = *skb->nh.raw; + *skb->nh.raw = IPPROTO_ROUTING; + + rt2 = (struct rt2_hdr *)skb->h.raw; + rt2->rt_hdr.nexthdr = nexthdr; + rt2->rt_hdr.hdrlen = (x->props.header_len >> 3) - 1; + rt2->rt_hdr.type = IPV6_SRCRT_TYPE_2; + rt2->rt_hdr.segments_left = 1; + memset(&rt2->reserved, 0, sizeof(rt2->reserved)); + + BUG_TRAP(rt2->rt_hdr.hdrlen == 2); + + memcpy(&rt2->addr, &iph->daddr, sizeof(rt2->addr)); + memcpy(&iph->daddr, x->coaddr, sizeof(iph->daddr)); + + return 0; +} + +static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb, + u8 **nexthdr) +{ + u16 offset = sizeof(struct ipv6hdr); + struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr*)(skb->nh.ipv6h + 1); + unsigned int packet_len = skb->tail - skb->nh.raw; + int found_rhdr = 0; + + *nexthdr = &skb->nh.ipv6h->nexthdr; + + while (offset + 1 <= packet_len) { + + switch (**nexthdr) { + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + if (offset + 3 <= packet_len) { + struct ipv6_rt_hdr *rt; + rt = (struct ipv6_rt_hdr *)(skb->nh.raw + offset); + if (rt->type != 0) + return offset; + } + found_rhdr = 1; + break; + case NEXTHDR_DEST: + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) + return offset; + + if (found_rhdr) + return offset; + + break; + default: + return offset; + } + + offset += ipv6_optlen(exthdr); + *nexthdr = &exthdr->nexthdr; + exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset); + } + + return offset; +} + +static int mip6_rthdr_init_state(struct xfrm_state *x) +{ + if (x->id.spi) { + printk(KERN_INFO "%s: spi is not 0: %u\n", __FUNCTION__, + x->id.spi); + return -EINVAL; + } + if (x->props.mode != XFRM_MODE_ROUTEOPTIMIZATION) { + printk(KERN_INFO "%s: state's mode is not %u: %u\n", + __FUNCTION__, XFRM_MODE_ROUTEOPTIMIZATION, x->props.mode); + return -EINVAL; + } + + x->props.header_len = sizeof(struct rt2_hdr); + + return 0; +} + +/* + * Do nothing about destroying since it has no specific operation for routing + * header type 2 unlike IPsec protocols. + */ +static void mip6_rthdr_destroy(struct xfrm_state *x) +{ +} + +static struct xfrm_type mip6_rthdr_type = +{ + .description = "MIP6RT", + .owner = THIS_MODULE, + .proto = IPPROTO_ROUTING, + .flags = XFRM_TYPE_NON_FRAGMENT, + .init_state = mip6_rthdr_init_state, + .destructor = mip6_rthdr_destroy, + .input = mip6_rthdr_input, + .output = mip6_rthdr_output, + .hdr_offset = mip6_rthdr_offset, + .remote_addr = mip6_xfrm_addr, +}; + +int __init mip6_init(void) +{ + printk(KERN_INFO "Mobile IPv6\n"); + + if (xfrm_register_type(&mip6_destopt_type, AF_INET6) < 0) { + printk(KERN_INFO "%s: can't add xfrm type(destopt)\n", __FUNCTION__); + goto mip6_destopt_xfrm_fail; + } + if (xfrm_register_type(&mip6_rthdr_type, AF_INET6) < 0) { + printk(KERN_INFO "%s: can't add xfrm type(rthdr)\n", __FUNCTION__); + goto mip6_rthdr_xfrm_fail; + } + return 0; + + mip6_rthdr_xfrm_fail: + xfrm_unregister_type(&mip6_destopt_type, AF_INET6); + mip6_destopt_xfrm_fail: + return -EAGAIN; +} + +void __exit mip6_fini(void) +{ + if (xfrm_unregister_type(&mip6_rthdr_type, AF_INET6) < 0) + printk(KERN_INFO "%s: can't remove xfrm type(rthdr)\n", __FUNCTION__); + if (xfrm_unregister_type(&mip6_destopt_type, AF_INET6) < 0) + printk(KERN_INFO "%s: can't remove xfrm type(destopt)\n", __FUNCTION__); +} diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b50055b9278..0304b5fe8d6 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -62,6 +62,7 @@ #include <linux/sysctl.h> #endif +#include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> @@ -411,7 +412,8 @@ static void pndisc_destructor(struct pneigh_entry *n) */ static inline void ndisc_flow_init(struct flowi *fl, u8 type, - struct in6_addr *saddr, struct in6_addr *daddr) + struct in6_addr *saddr, struct in6_addr *daddr, + int oif) { memset(fl, 0, sizeof(*fl)); ipv6_addr_copy(&fl->fl6_src, saddr); @@ -419,6 +421,8 @@ static inline void ndisc_flow_init(struct flowi *fl, u8 type, fl->proto = IPPROTO_ICMPV6; fl->fl_icmp_type = type; fl->fl_icmp_code = 0; + fl->oif = oif; + security_sk_classify_flow(ndisc_socket->sk, fl); } static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, @@ -450,7 +454,8 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, src_addr = &tmpaddr; } - ndisc_flow_init(&fl, NDISC_NEIGHBOUR_ADVERTISEMENT, src_addr, daddr); + ndisc_flow_init(&fl, NDISC_NEIGHBOUR_ADVERTISEMENT, src_addr, daddr, + dev->ifindex); dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output); if (!dst) @@ -491,7 +496,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, msg->icmph.icmp6_unused = 0; msg->icmph.icmp6_router = router; msg->icmph.icmp6_solicited = solicited; - msg->icmph.icmp6_override = !!override; + msg->icmph.icmp6_override = override; /* Set the target address. */ ipv6_addr_copy(&msg->target, solicited_addr); @@ -540,7 +545,8 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, saddr = &addr_buf; } - ndisc_flow_init(&fl, NDISC_NEIGHBOUR_SOLICITATION, saddr, daddr); + ndisc_flow_init(&fl, NDISC_NEIGHBOUR_SOLICITATION, saddr, daddr, + dev->ifindex); dst = ndisc_dst_alloc(dev, neigh, daddr, ip6_output); if (!dst) @@ -615,7 +621,8 @@ void ndisc_send_rs(struct net_device *dev, struct in6_addr *saddr, int len; int err; - ndisc_flow_init(&fl, NDISC_ROUTER_SOLICITATION, saddr, daddr); + ndisc_flow_init(&fl, NDISC_ROUTER_SOLICITATION, saddr, daddr, + dev->ifindex); dst = ndisc_dst_alloc(dev, NULL, daddr, ip6_output); if (!dst) @@ -729,8 +736,10 @@ static void ndisc_recv_ns(struct sk_buff *skb) struct inet6_ifaddr *ifp; struct inet6_dev *idev = NULL; struct neighbour *neigh; + struct pneigh_entry *pneigh = NULL; int dad = ipv6_addr_any(saddr); int inc; + int is_router; if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK2(KERN_WARNING @@ -815,7 +824,9 @@ static void ndisc_recv_ns(struct sk_buff *skb) if (ipv6_chk_acast_addr(dev, &msg->target) || (idev->cnf.forwarding && - pneigh_lookup(&nd_tbl, &msg->target, dev, 0))) { + (ipv6_devconf.proxy_ndp || idev->cnf.proxy_ndp) && + (pneigh = pneigh_lookup(&nd_tbl, + &msg->target, dev, 0)) != NULL)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc != 0 && @@ -836,12 +847,14 @@ static void ndisc_recv_ns(struct sk_buff *skb) goto out; } + is_router = !!(pneigh ? pneigh->flags & NTF_ROUTER : idev->cnf.forwarding); + if (dad) { struct in6_addr maddr; ipv6_addr_all_nodes(&maddr); ndisc_send_na(dev, NULL, &maddr, &msg->target, - idev->cnf.forwarding, 0, (ifp != NULL), 1); + is_router, 0, (ifp != NULL), 1); goto out; } @@ -862,7 +875,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) NEIGH_UPDATE_F_OVERRIDE); if (neigh || !dev->hard_header) { ndisc_send_na(dev, neigh, saddr, &msg->target, - idev->cnf.forwarding, + is_router, 1, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); @@ -945,6 +958,20 @@ static void ndisc_recv_na(struct sk_buff *skb) if (neigh->nud_state & NUD_FAILED) goto out; + /* + * Don't update the neighbor cache entry on a proxy NA from + * ourselves because either the proxied node is off link or it + * has already sent a NA to us. + */ + if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && + ipv6_devconf.forwarding && ipv6_devconf.proxy_ndp && + pneigh_lookup(&nd_tbl, &msg->target, dev, 0)) { + /* XXX: idev->cnf.prixy_ndp */ + WARN_ON(skb->dst != NULL && + ((struct rt6_info *)skb->dst)->rt6i_idev); + goto out; + } + neigh_update(neigh, lladdr, msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| @@ -959,7 +986,7 @@ static void ndisc_recv_na(struct sk_buff *skb) struct rt6_info *rt; rt = rt6_get_dflt_router(saddr, dev); if (rt) - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); } out: @@ -1112,7 +1139,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt && lifetime == 0) { neigh_clone(neigh); - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); rt = NULL; } @@ -1344,7 +1371,8 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); if (neigh) { - rt6_redirect(dest, &skb->nh.ipv6h->saddr, neigh, lladdr, + rt6_redirect(dest, &skb->nh.ipv6h->daddr, + &skb->nh.ipv6h->saddr, neigh, lladdr, on_link); neigh_release(neigh); } @@ -1380,7 +1408,8 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, return; } - ndisc_flow_init(&fl, NDISC_REDIRECT, &saddr_buf, &skb->nh.ipv6h->saddr); + ndisc_flow_init(&fl, NDISC_REDIRECT, &saddr_buf, &skb->nh.ipv6h->saddr, + dev->ifindex); dst = ip6_route_output(NULL, &fl); if (dst == NULL) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 395a417ba95..580b1aba672 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -87,7 +87,7 @@ unsigned int nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int csum = 0; switch (skb->ip_summed) { - case CHECKSUM_HW: + case CHECKSUM_COMPLETE: if (hook != NF_IP6_PRE_ROUTING && hook != NF_IP6_LOCAL_IN) break; if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index eeeb57d4c9c..ac1dfebde17 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -5,7 +5,7 @@ # Link order matters here. obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o -obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o ip6t_dst.o +obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 968a14be0d0..9510c24ca8d 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -56,15 +56,15 @@ struct ipq_queue_entry { typedef int (*ipq_cmpfn)(struct ipq_queue_entry *, unsigned long); -static unsigned char copy_mode = IPQ_COPY_NONE; -static unsigned int queue_maxlen = IPQ_QMAX_DEFAULT; +static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE; +static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT; static DEFINE_RWLOCK(queue_lock); -static int peer_pid; -static unsigned int copy_range; +static int peer_pid __read_mostly; +static unsigned int copy_range __read_mostly; static unsigned int queue_total; static unsigned int queue_dropped = 0; static unsigned int queue_user_dropped = 0; -static struct sock *ipqnl; +static struct sock *ipqnl __read_mostly; static LIST_HEAD(queue_list); static DEFINE_MUTEX(ipqnl_mutex); @@ -206,9 +206,9 @@ ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp) break; case IPQ_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_HW && - (*errp = skb_checksum_help(entry->skb, - entry->info->outdev == NULL))) { + if ((entry->skb->ip_summed == CHECKSUM_PARTIAL || + entry->skb->ip_summed == CHECKSUM_COMPLETE) && + (*errp = skb_checksum_help(entry->skb))) { read_unlock_bh(&queue_lock); return NULL; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index c9d6b23cd3f..4ab368fa0b8 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -70,9 +70,6 @@ do { \ #define IP_NF_ASSERT(x) #endif - -#include <linux/netfilter_ipv4/listhelp.h> - #if 0 /* All the better to debug you with... */ #define static @@ -220,8 +217,7 @@ ip6t_error(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { if (net_ratelimit()) printk("ip6_tables: error: `%s'\n", (char *)targinfo); @@ -258,8 +254,7 @@ ip6t_do_table(struct sk_buff **pskb, unsigned int hook, const struct net_device *in, const struct net_device *out, - struct xt_table *table, - void *userdata) + struct xt_table *table) { static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); int offset = 0; @@ -349,8 +344,7 @@ ip6t_do_table(struct sk_buff **pskb, in, out, hook, t->u.kernel.target, - t->data, - userdata); + t->data); #ifdef CONFIG_NETFILTER_DEBUG if (((struct ip6t_entry *)table_base)->comefrom @@ -507,8 +501,7 @@ cleanup_match(struct ip6t_entry_match *m, unsigned int *i) return 1; if (m->u.kernel.match->destroy) - m->u.kernel.match->destroy(m->u.kernel.match, m->data, - m->u.match_size - sizeof(*m)); + m->u.kernel.match->destroy(m->u.kernel.match, m->data); module_put(m->u.kernel.match->me); return 0; } @@ -561,7 +554,6 @@ check_match(struct ip6t_entry_match *m, if (m->u.kernel.match->checkentry && !m->u.kernel.match->checkentry(name, ipv6, match, m->data, - m->u.match_size - sizeof(*m), hookmask)) { duprintf("ip_tables: check failed for `%s'.\n", m->u.kernel.match->name); @@ -618,12 +610,10 @@ check_entry(struct ip6t_entry *e, const char *name, unsigned int size, if (t->u.kernel.target == &ip6t_standard_target) { if (!standard_check(t, size)) { ret = -EINVAL; - goto cleanup_matches; + goto err; } } else if (t->u.kernel.target->checkentry && !t->u.kernel.target->checkentry(name, e, target, t->data, - t->u.target_size - - sizeof(*t), e->comefrom)) { duprintf("ip_tables: check failed for `%s'.\n", t->u.kernel.target->name); @@ -695,8 +685,7 @@ 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->u.kernel.target, t->data, - t->u.target_size - sizeof(*t)); + t->u.kernel.target->destroy(t->u.kernel.target, t->data); module_put(t->u.kernel.target->me); return 0; } @@ -1352,7 +1341,6 @@ 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_icmp *icmpinfo = matchinfo; diff --git a/net/ipv6/netfilter/ip6t_HL.c b/net/ipv6/netfilter/ip6t_HL.c index b8eff8ee69b..435750f664d 100644 --- a/net/ipv6/netfilter/ip6t_HL.c +++ b/net/ipv6/netfilter/ip6t_HL.c @@ -22,11 +22,10 @@ static unsigned int ip6t_hl_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, void *userinfo) + const void *targinfo) { struct ipv6hdr *ip6h; const struct ip6t_HL_info *info = targinfo; - u_int16_t diffs[2]; int new_hl; if (!skb_make_writable(pskb, (*pskb)->len)) @@ -53,11 +52,8 @@ static unsigned int ip6t_hl_target(struct sk_buff **pskb, break; } - if (new_hl != ip6h->hop_limit) { - diffs[0] = htons(((unsigned)ip6h->hop_limit) << 8) ^ 0xFFFF; + if (new_hl != ip6h->hop_limit) ip6h->hop_limit = new_hl; - diffs[1] = htons(((unsigned)ip6h->hop_limit) << 8); - } return IP6T_CONTINUE; } @@ -66,7 +62,6 @@ 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; diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 73c6300109d..0cf537d3018 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -427,8 +427,7 @@ ip6t_log_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct ip6t_log_info *loginfo = targinfo; struct nf_loginfo li; @@ -452,7 +451,6 @@ 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; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 8629ba195d2..311eae82feb 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -96,6 +96,7 @@ static void send_reset(struct sk_buff *oldskb) ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr); fl.fl_ip_sport = otcph.dest; fl.fl_ip_dport = otcph.source; + security_skb_classify_flow(oldskb, &fl); dst = ip6_route_output(NULL, &fl); if (dst == NULL) return; @@ -179,8 +180,7 @@ static unsigned int reject6_target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct ip6t_reject_info *reject = targinfo; @@ -223,7 +223,6 @@ static int check(const char *tablename, const void *entry, const struct xt_target *target, void *targinfo, - unsigned int targinfosize, unsigned int hook_mask) { const struct ip6t_reject_info *rejinfo = targinfo; @@ -256,9 +255,7 @@ static struct ip6t_target ip6t_reject_reg = { static int __init ip6t_reject_init(void) { - if (ip6t_register_target(&ip6t_reject_reg)) - return -EINVAL; - return 0; + return ip6t_register_target(&ip6t_reject_reg); } static void __exit ip6t_reject_fini(void) diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 2f7bb20c758..ec1b1608156 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -102,7 +102,6 @@ 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; diff --git a/net/ipv6/netfilter/ip6t_dst.c b/net/ipv6/netfilter/ip6t_dst.c deleted file mode 100644 index 9422413d057..00000000000 --- a/net/ipv6/netfilter/ip6t_dst.c +++ /dev/null @@ -1,220 +0,0 @@ -/* Kernel module to match Hop-by-Hop and Destination parameters. */ - -/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> - * - * 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/module.h> -#include <linux/skbuff.h> -#include <linux/ipv6.h> -#include <linux/types.h> -#include <net/checksum.h> -#include <net/ipv6.h> - -#include <asm/byteorder.h> - -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv6/ip6t_opts.h> - -#define HOPBYHOP 0 - -MODULE_LICENSE("GPL"); -#if HOPBYHOP -MODULE_DESCRIPTION("IPv6 HbH match"); -#else -MODULE_DESCRIPTION("IPv6 DST match"); -#endif -MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); - -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -/* - * (Type & 0xC0) >> 6 - * 0 -> ignorable - * 1 -> must drop the packet - * 2 -> send ICMP PARM PROB regardless and drop packet - * 3 -> Send ICMP if not a multicast address and drop packet - * (Type & 0x20) >> 5 - * 0 -> invariant - * 1 -> can change the routing - * (Type & 0x1F) Type - * 0 -> Pad1 (only 1 byte!) - * 1 -> PadN LENGTH info (total length = length + 2) - * C0 | 2 -> JUMBO 4 x x x x ( xxxx > 64k ) - * 5 -> RTALERT 2 x x - */ - -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) -{ - struct ipv6_opt_hdr _optsh, *oh; - const struct ip6t_opts *optinfo = matchinfo; - unsigned int temp; - unsigned int ptr; - unsigned int hdrlen = 0; - unsigned int ret = 0; - u8 _opttype, *tp = NULL; - u8 _optlen, *lp = NULL; - unsigned int optlen; - -#if HOPBYHOP - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP, NULL) < 0) -#else - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST, NULL) < 0) -#endif - return 0; - - oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh); - if (oh == NULL) { - *hotdrop = 1; - return 0; - } - - hdrlen = ipv6_optlen(oh); - if (skb->len - ptr < hdrlen) { - /* Packet smaller than it's length field */ - return 0; - } - - DEBUGP("IPv6 OPTS LEN %u %u ", hdrlen, oh->hdrlen); - - DEBUGP("len %02X %04X %02X ", - optinfo->hdrlen, hdrlen, - (!(optinfo->flags & IP6T_OPTS_LEN) || - ((optinfo->hdrlen == hdrlen) ^ - !!(optinfo->invflags & IP6T_OPTS_INV_LEN)))); - - ret = (oh != NULL) && - (!(optinfo->flags & IP6T_OPTS_LEN) || - ((optinfo->hdrlen == hdrlen) ^ - !!(optinfo->invflags & IP6T_OPTS_INV_LEN))); - - ptr += 2; - hdrlen -= 2; - if (!(optinfo->flags & IP6T_OPTS_OPTS)) { - return ret; - } else if (optinfo->flags & IP6T_OPTS_NSTRICT) { - DEBUGP("Not strict - not implemented"); - } else { - DEBUGP("Strict "); - DEBUGP("#%d ", optinfo->optsnr); - for (temp = 0; temp < optinfo->optsnr; temp++) { - /* type field exists ? */ - if (hdrlen < 1) - break; - tp = skb_header_pointer(skb, ptr, sizeof(_opttype), - &_opttype); - if (tp == NULL) - break; - - /* Type check */ - if (*tp != (optinfo->opts[temp] & 0xFF00) >> 8) { - DEBUGP("Tbad %02X %02X\n", - *tp, - (optinfo->opts[temp] & 0xFF00) >> 8); - return 0; - } else { - DEBUGP("Tok "); - } - /* Length check */ - if (*tp) { - u16 spec_len; - - /* length field exists ? */ - if (hdrlen < 2) - break; - lp = skb_header_pointer(skb, ptr + 1, - sizeof(_optlen), - &_optlen); - if (lp == NULL) - break; - spec_len = optinfo->opts[temp] & 0x00FF; - - if (spec_len != 0x00FF && spec_len != *lp) { - DEBUGP("Lbad %02X %04X\n", *lp, - spec_len); - return 0; - } - DEBUGP("Lok "); - optlen = *lp + 2; - } else { - DEBUGP("Pad1\n"); - optlen = 1; - } - - /* Step to the next */ - DEBUGP("len%04X \n", optlen); - - if ((ptr > skb->len - optlen || hdrlen < optlen) && - (temp < optinfo->optsnr - 1)) { - DEBUGP("new pointer is too large! \n"); - break; - } - ptr += optlen; - hdrlen -= optlen; - } - if (temp == optinfo->optsnr) - return ret; - else - return 0; - } - - return 0; -} - -/* Called when user tries to insert an entry of this type. */ -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 (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) { - DEBUGP("ip6t_opts: unknown flags %X\n", optsinfo->invflags); - return 0; - } - return 1; -} - -static struct ip6t_match opts_match = { -#if HOPBYHOP - .name = "hbh", -#else - .name = "dst", -#endif - .match = match, - .matchsize = sizeof(struct ip6t_opts), - .checkentry = checkentry, - .me = THIS_MODULE, -}; - -static int __init ip6t_dst_init(void) -{ - return ip6t_register_match(&opts_match); -} - -static void __exit ip6t_dst_fini(void) -{ - ip6t_unregister_match(&opts_match); -} - -module_init(ip6t_dst_init); -module_exit(ip6t_dst_fini); diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index 06768c84bd3..78d9c8b9e28 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -119,7 +119,6 @@ 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; diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index 374f1be85c0..d32a205e3af 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -19,15 +19,10 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_opts.h> -#define HOPBYHOP 1 - MODULE_LICENSE("GPL"); -#if HOPBYHOP -MODULE_DESCRIPTION("IPv6 HbH match"); -#else -MODULE_DESCRIPTION("IPv6 DST match"); -#endif +MODULE_DESCRIPTION("IPv6 opts match"); MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); +MODULE_ALIAS("ip6t_dst"); #if 0 #define DEBUGP printk @@ -71,11 +66,7 @@ match(const struct sk_buff *skb, u8 _optlen, *lp = NULL; unsigned int optlen; -#if HOPBYHOP - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_HOP, NULL) < 0) -#else - if (ipv6_find_hdr(skb, &ptr, NEXTHDR_DEST, NULL) < 0) -#endif + if (ipv6_find_hdr(skb, &ptr, match->data, NULL) < 0) return 0; oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh); @@ -182,7 +173,6 @@ 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; @@ -194,26 +184,35 @@ checkentry(const char *tablename, return 1; } -static struct ip6t_match opts_match = { -#if HOPBYHOP - .name = "hbh", -#else - .name = "dst", -#endif - .match = match, - .matchsize = sizeof(struct ip6t_opts), - .checkentry = checkentry, - .me = THIS_MODULE, +static struct xt_match opts_match[] = { + { + .name = "hbh", + .family = AF_INET6, + .match = match, + .matchsize = sizeof(struct ip6t_opts), + .checkentry = checkentry, + .me = THIS_MODULE, + .data = NEXTHDR_HOP, + }, + { + .name = "dst", + .family = AF_INET6, + .match = match, + .matchsize = sizeof(struct ip6t_opts), + .checkentry = checkentry, + .me = THIS_MODULE, + .data = NEXTHDR_DEST, + }, }; static int __init ip6t_hbh_init(void) { - return ip6t_register_match(&opts_match); + return xt_register_matches(opts_match, ARRAY_SIZE(opts_match)); } static void __exit ip6t_hbh_fini(void) { - ip6t_unregister_match(&opts_match); + xt_unregister_matches(opts_match, ARRAY_SIZE(opts_match)); } module_init(ip6t_hbh_init); diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c index 9375eeb1369..3093c398002 100644 --- a/net/ipv6/netfilter/ip6t_ipv6header.c +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -128,7 +128,6 @@ 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; diff --git a/net/ipv6/netfilter/ip6t_owner.c b/net/ipv6/netfilter/ip6t_owner.c index 5d047990cd4..4eb9bbc4ebc 100644 --- a/net/ipv6/netfilter/ip6t_owner.c +++ b/net/ipv6/netfilter/ip6t_owner.c @@ -57,7 +57,6 @@ 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; diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index fbb0184a41d..bcb2e168a5b 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -197,7 +197,6 @@ 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; diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 60976c0c58e..2fc07c74dec 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -108,7 +108,7 @@ ip6t_hook(unsigned int hook, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip6t_do_table(pskb, hook, in, out, &packet_filter, NULL); + return ip6t_do_table(pskb, hook, in, out, &packet_filter); } static unsigned int @@ -128,7 +128,7 @@ ip6t_local_out_hook(unsigned int hook, } #endif - return ip6t_do_table(pskb, hook, in, out, &packet_filter, NULL); + return ip6t_do_table(pskb, hook, in, out, &packet_filter); } static struct nf_hook_ops ip6t_ops[] = { diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 03a13eab1da..386ea260e76 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -138,7 +138,7 @@ ip6t_route_hook(unsigned int hook, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip6t_do_table(pskb, hook, in, out, &packet_mangler, NULL); + return ip6t_do_table(pskb, hook, in, out, &packet_mangler); } static unsigned int @@ -174,18 +174,14 @@ ip6t_local_hook(unsigned int hook, /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *) (*pskb)->nh.ipv6h); - ret = ip6t_do_table(pskb, hook, in, out, &packet_mangler, NULL); + ret = ip6t_do_table(pskb, hook, in, out, &packet_mangler); if (ret != NF_DROP && ret != NF_STOLEN && (memcmp(&(*pskb)->nh.ipv6h->saddr, &saddr, sizeof(saddr)) || memcmp(&(*pskb)->nh.ipv6h->daddr, &daddr, sizeof(daddr)) || (*pskb)->nfmark != nfmark - || (*pskb)->nh.ipv6h->hop_limit != hop_limit)) { - - /* something which could affect routing has changed */ - - DEBUGP("ip6table_mangle: we'd need to re-route a packet\n"); - } + || (*pskb)->nh.ipv6h->hop_limit != hop_limit)) + return ip6_route_me_harder(*pskb) == 0 ? ret : NF_DROP; return ret; } diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 61a7c58e99f..b4154da575c 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -122,7 +122,7 @@ ip6t_hook(unsigned int hook, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip6t_do_table(pskb, hook, in, out, &packet_raw, NULL); + return ip6t_do_table(pskb, hook, in, out, &packet_raw); } static struct nf_hook_ops ip6t_ops[] = { diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index c2ab38ff46a..e5e53fff9e3 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -335,7 +335,7 @@ static struct nf_hook_ops ipv6_conntrack_ops[] = { /* From nf_conntrack_proto_icmpv6.c */ extern unsigned int nf_ct_icmpv6_timeout; -/* From nf_conntrack_frag6.c */ +/* From nf_conntrack_reasm.c */ extern unsigned int nf_ct_frag6_timeout; extern unsigned int nf_ct_frag6_low_thresh; extern unsigned int nf_ct_frag6_high_thresh; diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index ef18a7b7014..34d447208ff 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -33,7 +33,7 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/ipv6/nf_conntrack_icmpv6.h> -unsigned long nf_ct_icmpv6_timeout = 30*HZ; +unsigned long nf_ct_icmpv6_timeout __read_mostly = 30*HZ; #if 0 #define DEBUGP printk diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 00d5583807f..bf93c1ea6be 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -54,9 +54,9 @@ #define NF_CT_FRAG6_LOW_THRESH 196608 /* == 192*1024 */ #define NF_CT_FRAG6_TIMEOUT IPV6_FRAG_TIMEOUT -unsigned int nf_ct_frag6_high_thresh = 256*1024; -unsigned int nf_ct_frag6_low_thresh = 192*1024; -unsigned long nf_ct_frag6_timeout = IPV6_FRAG_TIMEOUT; +unsigned int nf_ct_frag6_high_thresh __read_mostly = 256*1024; +unsigned int nf_ct_frag6_low_thresh __read_mostly = 192*1024; +unsigned long nf_ct_frag6_timeout __read_mostly = IPV6_FRAG_TIMEOUT; struct nf_ct_frag6_skb_cb { @@ -408,7 +408,7 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb, return -1; } - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(skb->nh.raw, (u8*)(fhdr + 1) - skb->nh.raw, @@ -640,7 +640,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) head->len += fp->len; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_HW) + else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; atomic_sub(fp->truesize, &nf_ct_frag6_mem); @@ -652,7 +652,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev) head->nh.ipv6h->payload_len = htons(payload_len); /* Yes, and fold redundant checksum back. 8) */ - if (head->ip_summed == CHECKSUM_HW) + if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum); fq->fragments = NULL; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 15b862d8aca..d09329ca326 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -50,6 +50,9 @@ #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> +#ifdef CONFIG_IPV6_MIP6 +#include <net/mip6.h> +#endif #include <net/rawv6.h> #include <net/xfrm.h> @@ -169,8 +172,32 @@ int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr, IP6CB(skb)->iif); while (sk) { + int filtered; + delivered = 1; - if (nexthdr != IPPROTO_ICMPV6 || !icmpv6_filter(sk, skb)) { + switch (nexthdr) { + case IPPROTO_ICMPV6: + filtered = icmpv6_filter(sk, skb); + break; +#ifdef CONFIG_IPV6_MIP6 + case IPPROTO_MH: + /* XXX: To validate MH only once for each packet, + * this is placed here. It should be after checking + * xfrm policy, however it doesn't. The checking xfrm + * policy is placed in rawv6_rcv() because it is + * required for each socket. + */ + filtered = mip6_mh_filter(sk, skb); + break; +#endif + default: + filtered = 0; + break; + } + + if (filtered < 0) + break; + if (filtered == 0) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ @@ -334,7 +361,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_COMPLETE) { skb_postpull_rcsum(skb, skb->nh.raw, skb->h.raw - skb->nh.raw); if (!csum_ipv6_magic(&skb->nh.ipv6h->saddr, @@ -582,6 +609,9 @@ static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) struct iovec *iov; u8 __user *type = NULL; u8 __user *code = NULL; +#ifdef CONFIG_IPV6_MIP6 + u8 len = 0; +#endif int probed = 0; int i; @@ -613,6 +643,20 @@ static void rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg) probed = 1; } break; +#ifdef CONFIG_IPV6_MIP6 + case IPPROTO_MH: + if (iov->iov_base && iov->iov_len < 1) + break; + /* check if type field is readable or not. */ + if (iov->iov_len > 2 - len) { + u8 __user *p = iov->iov_base; + get_user(fl->fl_mh_type, &p[2 - len]); + probed = 1; + } else + len += iov->iov_len; + + break; +#endif default: probed = 1; break; @@ -759,6 +803,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) fl.oif = np->mcast_oif; + security_sk_classify_flow(sk, &fl); err = ip6_dst_lookup(sk, &dst, &fl); if (err) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 4e299c69e1c..f39bbedd132 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -53,10 +53,10 @@ #include <net/ndisc.h> #include <net/addrconf.h> -int sysctl_ip6frag_high_thresh = 256*1024; -int sysctl_ip6frag_low_thresh = 192*1024; +int sysctl_ip6frag_high_thresh __read_mostly = 256*1024; +int sysctl_ip6frag_low_thresh __read_mostly = 192*1024; -int sysctl_ip6frag_time = IPV6_FRAG_TIMEOUT; +int sysctl_ip6frag_time __read_mostly = IPV6_FRAG_TIMEOUT; struct ip6frag_skb_cb { @@ -152,7 +152,7 @@ static unsigned int ip6qhashfn(u32 id, struct in6_addr *saddr, } static struct timer_list ip6_frag_secret_timer; -int sysctl_ip6frag_secret_interval = 10 * 60 * HZ; +int sysctl_ip6frag_secret_interval __read_mostly = 10 * 60 * HZ; static void ip6_frag_secret_rebuild(unsigned long dummy) { @@ -433,7 +433,7 @@ static void ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, return; } - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(skb->nh.raw, (u8*)(fhdr+1)-skb->nh.raw, 0)); @@ -647,7 +647,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in, head->len += fp->len; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_HW) + else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; atomic_sub(fp->truesize, &ip6_frag_mem); @@ -662,7 +662,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff **skb_in, *skb_in = head; /* Yes, and fold redundant checksum back. 8) */ - if (head->ip_summed == CHECKSUM_HW) + if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_partial(head->nh.raw, head->h.raw-head->nh.raw, head->csum); IP6_INC_STATS_BH(IPSTATS_MIB_REASMOKS); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d9baca062d2..d6b4b4f48d1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -22,6 +22,8 @@ * routers in REACHABLE, STALE, DELAY or PROBE states). * - always select the same router if it is (probably) * reachable. otherwise, round-robin the list. + * Ville Nuorvala + * Fixed routing subtrees. */ #include <linux/capability.h> @@ -35,7 +37,6 @@ #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/init.h> -#include <linux/netlink.h> #include <linux/if_arp.h> #ifdef CONFIG_PROC_FS @@ -54,6 +55,7 @@ #include <net/dst.h> #include <net/xfrm.h> #include <net/netevent.h> +#include <net/netlink.h> #include <asm/uaccess.h> @@ -74,9 +76,6 @@ #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; static int ip6_rt_gc_timeout = 60*HZ; @@ -140,15 +139,49 @@ struct rt6_info ip6_null_entry = { .rt6i_ref = ATOMIC_INIT(1), }; -struct fib6_node ip6_routing_table = { - .leaf = &ip6_null_entry, - .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO, -}; +#ifdef CONFIG_IPV6_MULTIPLE_TABLES -/* Protects all the ip6 fib */ +struct rt6_info ip6_prohibit_entry = { + .u = { + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .dev = &loopback_dev, + .obsolete = -1, + .error = -EACCES, + .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, + .input = ip6_pkt_discard, + .output = ip6_pkt_discard_out, + .ops = &ip6_dst_ops, + .path = (struct dst_entry*)&ip6_prohibit_entry, + } + }, + .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_metric = ~(u32) 0, + .rt6i_ref = ATOMIC_INIT(1), +}; -DEFINE_RWLOCK(rt6_lock); +struct rt6_info ip6_blk_hole_entry = { + .u = { + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .dev = &loopback_dev, + .obsolete = -1, + .error = -EINVAL, + .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, + .input = ip6_pkt_discard, + .output = ip6_pkt_discard_out, + .ops = &ip6_dst_ops, + .path = (struct dst_entry*)&ip6_blk_hole_entry, + } + }, + .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_metric = ~(u32) 0, + .rt6i_ref = ATOMIC_INIT(1), +}; +#endif /* allocate dst with ip6_dst_ops */ static __inline__ struct rt6_info *ip6_dst_alloc(void) @@ -188,8 +221,14 @@ static __inline__ int rt6_check_expired(const struct rt6_info *rt) time_after(jiffies, rt->rt6i_expires)); } +static inline int rt6_need_strict(struct in6_addr *daddr) +{ + return (ipv6_addr_type(daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); +} + /* - * Route lookup. Any rt6_lock is implied. + * Route lookup. Any table->tb6_lock is implied. */ static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt, @@ -298,7 +337,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif, int m, n; m = rt6_check_dev(rt, oif); - if (!m && (strict & RT6_SELECT_F_IFACE)) + if (!m && (strict & RT6_LOOKUP_F_IFACE)) return -1; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; @@ -306,7 +345,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif, n = rt6_check_neigh(rt); if (n > 1) m |= 16; - else if (!n && strict & RT6_SELECT_F_REACHABLE) + else if (!n && strict & RT6_LOOKUP_F_REACHABLE) return -1; return m; } @@ -346,7 +385,7 @@ static struct rt6_info *rt6_select(struct rt6_info **head, int oif, } if (!match && - (strict & RT6_SELECT_F_REACHABLE) && + (strict & RT6_LOOKUP_F_REACHABLE) && last && last != rt0) { /* no entries matched; do round-robin */ static DEFINE_SPINLOCK(lock); @@ -417,7 +456,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, rt = rt6_get_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex); if (rt && !lifetime) { - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); rt = NULL; } @@ -441,44 +480,95 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, } #endif -struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, - int oif, int strict) +#define BACKTRACK(saddr) \ +do { \ + if (rt == &ip6_null_entry) { \ + struct fib6_node *pn; \ + while (fn) { \ + if (fn->fn_flags & RTN_TL_ROOT) \ + goto out; \ + pn = fn->parent; \ + if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \ + fn = fib6_lookup(pn->subtree, NULL, saddr); \ + else \ + fn = pn; \ + if (fn->fn_flags & RTN_RTINFO) \ + goto restart; \ + } \ + } \ +} while(0) + +static struct rt6_info *ip6_pol_route_lookup(struct fib6_table *table, + struct flowi *fl, int flags) { struct fib6_node *fn; struct rt6_info *rt; - read_lock_bh(&rt6_lock); - fn = fib6_lookup(&ip6_routing_table, daddr, saddr); - rt = rt6_device_match(fn->leaf, oif, strict); + read_lock_bh(&table->tb6_lock); + fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); +restart: + rt = fn->leaf; + rt = rt6_device_match(rt, fl->oif, flags); + BACKTRACK(&fl->fl6_src); +out: dst_hold(&rt->u.dst); - rt->u.dst.__use++; - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); rt->u.dst.lastuse = jiffies; - if (rt->u.dst.error == 0) - return rt; - dst_release(&rt->u.dst); + rt->u.dst.__use++; + + return rt; + +} + +struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, + int oif, int strict) +{ + struct flowi fl = { + .oif = oif, + .nl_u = { + .ip6_u = { + .daddr = *daddr, + /* TODO: saddr */ + }, + }, + }; + struct dst_entry *dst; + int flags = strict ? RT6_LOOKUP_F_IFACE : 0; + + dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup); + if (dst->error == 0) + return (struct rt6_info *) dst; + + dst_release(dst); + return NULL; } -/* ip6_ins_rt is called with FREE rt6_lock. +/* ip6_ins_rt is called with FREE table->tb6_lock. It takes new route entry, the addition fails by any reason the route is freed. In any case, if caller does not hold it, it may be destroyed. */ -int ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req) +static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info) { int err; + struct fib6_table *table; - write_lock_bh(&rt6_lock); - err = fib6_add(&ip6_routing_table, rt, nlh, _rtattr, req); - write_unlock_bh(&rt6_lock); + table = rt->rt6i_table; + write_lock_bh(&table->tb6_lock); + err = fib6_add(&table->tb6_root, rt, info); + write_unlock_bh(&table->tb6_lock); return err; } +int ip6_ins_rt(struct rt6_info *rt) +{ + return __ip6_ins_rt(rt, NULL); +} + static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr, struct in6_addr *saddr) { @@ -532,51 +622,39 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d return rt; } -#define BACKTRACK() \ -if (rt == &ip6_null_entry) { \ - while ((fn = fn->parent) != NULL) { \ - if (fn->fn_flags & RTN_ROOT) { \ - goto out; \ - } \ - if (fn->fn_flags & RTN_RTINFO) \ - goto restart; \ - } \ -} - - -void ip6_route_input(struct sk_buff *skb) +static struct rt6_info *ip6_pol_route_input(struct fib6_table *table, + struct flowi *fl, int flags) { struct fib6_node *fn; struct rt6_info *rt, *nrt; - int strict; + int strict = 0; int attempts = 3; int err; - int reachable = RT6_SELECT_F_REACHABLE; + int reachable = RT6_LOOKUP_F_REACHABLE; - strict = ipv6_addr_type(&skb->nh.ipv6h->daddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0; + strict |= flags & RT6_LOOKUP_F_IFACE; relookup: - read_lock_bh(&rt6_lock); + read_lock_bh(&table->tb6_lock); restart_2: - fn = fib6_lookup(&ip6_routing_table, &skb->nh.ipv6h->daddr, - &skb->nh.ipv6h->saddr); + fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); restart: - rt = rt6_select(&fn->leaf, skb->dev->ifindex, strict | reachable); - BACKTRACK(); + rt = rt6_select(&fn->leaf, fl->iif, strict | reachable); + BACKTRACK(&fl->fl6_src); if (rt == &ip6_null_entry || rt->rt6i_flags & RTF_CACHE) goto out; dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) - nrt = rt6_alloc_cow(rt, &skb->nh.ipv6h->daddr, &skb->nh.ipv6h->saddr); + nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src); else { #if CLONE_OFFLINK_ROUTE - nrt = rt6_alloc_clone(rt, &skb->nh.ipv6h->daddr); + nrt = rt6_alloc_clone(rt, &fl->fl6_dst); #else goto out2; #endif @@ -587,7 +665,7 @@ restart: dst_hold(&rt->u.dst); if (nrt) { - err = ip6_ins_rt(nrt, NULL, NULL, &NETLINK_CB(skb)); + err = ip6_ins_rt(nrt); if (!err) goto out2; } @@ -596,7 +674,7 @@ restart: goto out2; /* - * Race condition! In the gap, when rt6_lock was + * Race condition! In the gap, when table->tb6_lock was * released someone could insert this route. Relookup. */ dst_release(&rt->u.dst); @@ -608,40 +686,63 @@ out: goto restart_2; } dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); out2: rt->u.dst.lastuse = jiffies; rt->u.dst.__use++; - skb->dst = (struct dst_entry *) rt; - return; + + return rt; } -struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl) +void ip6_route_input(struct sk_buff *skb) +{ + struct ipv6hdr *iph = skb->nh.ipv6h; + struct flowi fl = { + .iif = skb->dev->ifindex, + .nl_u = { + .ip6_u = { + .daddr = iph->daddr, + .saddr = iph->saddr, +#ifdef CONFIG_IPV6_ROUTE_FWMARK + .fwmark = skb->nfmark, +#endif + .flowlabel = (* (u32 *) iph)&IPV6_FLOWINFO_MASK, + }, + }, + .proto = iph->nexthdr, + }; + int flags = rt6_need_strict(&iph->daddr) ? RT6_LOOKUP_F_IFACE : 0; + + skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input); +} + +static struct rt6_info *ip6_pol_route_output(struct fib6_table *table, + struct flowi *fl, int flags) { struct fib6_node *fn; struct rt6_info *rt, *nrt; - int strict; + int strict = 0; int attempts = 3; int err; - int reachable = RT6_SELECT_F_REACHABLE; + int reachable = RT6_LOOKUP_F_REACHABLE; - strict = ipv6_addr_type(&fl->fl6_dst) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0; + strict |= flags & RT6_LOOKUP_F_IFACE; relookup: - read_lock_bh(&rt6_lock); + read_lock_bh(&table->tb6_lock); restart_2: - fn = fib6_lookup(&ip6_routing_table, &fl->fl6_dst, &fl->fl6_src); + fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); restart: rt = rt6_select(&fn->leaf, fl->oif, strict | reachable); - BACKTRACK(); + BACKTRACK(&fl->fl6_src); if (rt == &ip6_null_entry || rt->rt6i_flags & RTF_CACHE) goto out; dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src); @@ -658,7 +759,7 @@ restart: dst_hold(&rt->u.dst); if (nrt) { - err = ip6_ins_rt(nrt, NULL, NULL, NULL); + err = ip6_ins_rt(nrt); if (!err) goto out2; } @@ -667,7 +768,7 @@ restart: goto out2; /* - * Race condition! In the gap, when rt6_lock was + * Race condition! In the gap, when table->tb6_lock was * released someone could insert this route. Relookup. */ dst_release(&rt->u.dst); @@ -679,11 +780,21 @@ out: goto restart_2; } dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); out2: rt->u.dst.lastuse = jiffies; rt->u.dst.__use++; - return &rt->u.dst; + return rt; +} + +struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl) +{ + int flags = 0; + + if (rt6_need_strict(&fl->fl6_dst)) + flags |= RT6_LOOKUP_F_IFACE; + + return fib6_rule_lookup(fl, flags, ip6_pol_route_output); } @@ -709,7 +820,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) if (rt) { if (rt->rt6i_flags & RTF_CACHE) - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); else dst_release(dst); } @@ -747,8 +858,6 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) } } -/* Protected by rt6_lock. */ -static struct dst_entry *ndisc_dst_gc_list; static int ipv6_get_mtu(struct net_device *dev); static inline unsigned int ipv6_advmss(unsigned int mtu) @@ -769,6 +878,9 @@ static inline unsigned int ipv6_advmss(unsigned int mtu) return mtu; } +static struct dst_entry *ndisc_dst_gc_list; +static DEFINE_SPINLOCK(ndisc_lock); + struct dst_entry *ndisc_dst_alloc(struct net_device *dev, struct neighbour *neigh, struct in6_addr *addr, @@ -809,10 +921,10 @@ struct dst_entry *ndisc_dst_alloc(struct net_device *dev, rt->rt6i_dst.plen = 128; #endif - write_lock_bh(&rt6_lock); + spin_lock_bh(&ndisc_lock); rt->u.dst.next = ndisc_dst_gc_list; ndisc_dst_gc_list = &rt->u.dst; - write_unlock_bh(&rt6_lock); + spin_unlock_bh(&ndisc_lock); fib6_force_start_gc(); @@ -826,8 +938,11 @@ int ndisc_dst_gc(int *more) int freed; next = NULL; + freed = 0; + + spin_lock_bh(&ndisc_lock); pprev = &ndisc_dst_gc_list; - freed = 0; + while ((dst = *pprev) != NULL) { if (!atomic_read(&dst->__refcnt)) { *pprev = dst->next; @@ -839,6 +954,8 @@ int ndisc_dst_gc(int *more) } } + spin_unlock_bh(&ndisc_lock); + return freed; } @@ -899,28 +1016,24 @@ int ipv6_get_hoplimit(struct net_device *dev) * */ -int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req) +int ip6_route_add(struct fib6_config *cfg) { int err; - struct rtmsg *r; - struct rtattr **rta; struct rt6_info *rt = NULL; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; + struct fib6_table *table; int addr_type; - rta = (struct rtattr **) _rtattr; - - if (rtmsg->rtmsg_dst_len > 128 || rtmsg->rtmsg_src_len > 128) + if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) return -EINVAL; #ifndef CONFIG_IPV6_SUBTREES - if (rtmsg->rtmsg_src_len) + if (cfg->fc_src_len) return -EINVAL; #endif - if (rtmsg->rtmsg_ifindex) { + if (cfg->fc_ifindex) { err = -ENODEV; - dev = dev_get_by_index(rtmsg->rtmsg_ifindex); + dev = dev_get_by_index(cfg->fc_ifindex); if (!dev) goto out; idev = in6_dev_get(dev); @@ -928,8 +1041,14 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, goto out; } - if (rtmsg->rtmsg_metric == 0) - rtmsg->rtmsg_metric = IP6_RT_PRIO_USER; + if (cfg->fc_metric == 0) + cfg->fc_metric = IP6_RT_PRIO_USER; + + table = fib6_new_table(cfg->fc_table); + if (table == NULL) { + err = -ENOBUFS; + goto out; + } rt = ip6_dst_alloc(); @@ -939,14 +1058,13 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, } rt->u.dst.obsolete = -1; - rt->rt6i_expires = jiffies + clock_t_to_jiffies(rtmsg->rtmsg_info); - if (nlh && (r = NLMSG_DATA(nlh))) { - rt->rt6i_protocol = r->rtm_protocol; - } else { - rt->rt6i_protocol = RTPROT_BOOT; - } + rt->rt6i_expires = jiffies + clock_t_to_jiffies(cfg->fc_expires); - addr_type = ipv6_addr_type(&rtmsg->rtmsg_dst); + if (cfg->fc_protocol == RTPROT_UNSPEC) + cfg->fc_protocol = RTPROT_BOOT; + rt->rt6i_protocol = cfg->fc_protocol; + + addr_type = ipv6_addr_type(&cfg->fc_dst); if (addr_type & IPV6_ADDR_MULTICAST) rt->u.dst.input = ip6_mc_input; @@ -955,24 +1073,22 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, rt->u.dst.output = ip6_output; - ipv6_addr_prefix(&rt->rt6i_dst.addr, - &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len); - rt->rt6i_dst.plen = rtmsg->rtmsg_dst_len; + ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); + rt->rt6i_dst.plen = cfg->fc_dst_len; if (rt->rt6i_dst.plen == 128) rt->u.dst.flags = DST_HOST; #ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_prefix(&rt->rt6i_src.addr, - &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len); - rt->rt6i_src.plen = rtmsg->rtmsg_src_len; + ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); + rt->rt6i_src.plen = cfg->fc_src_len; #endif - rt->rt6i_metric = rtmsg->rtmsg_metric; + rt->rt6i_metric = cfg->fc_metric; /* We cannot add true routes via loopback here, they would result in kernel looping; promote them to reject routes */ - if ((rtmsg->rtmsg_flags&RTF_REJECT) || + if ((cfg->fc_flags & RTF_REJECT) || (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) { /* hold loopback dev/idev if we haven't done so. */ if (dev != &loopback_dev) { @@ -995,12 +1111,12 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, goto install_route; } - if (rtmsg->rtmsg_flags & RTF_GATEWAY) { + if (cfg->fc_flags & RTF_GATEWAY) { struct in6_addr *gw_addr; int gwa_type; - gw_addr = &rtmsg->rtmsg_gateway; - ipv6_addr_copy(&rt->rt6i_gateway, &rtmsg->rtmsg_gateway); + gw_addr = &cfg->fc_gateway; + ipv6_addr_copy(&rt->rt6i_gateway, gw_addr); gwa_type = ipv6_addr_type(gw_addr); if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { @@ -1017,7 +1133,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, if (!(gwa_type&IPV6_ADDR_UNICAST)) goto out; - grt = rt6_lookup(gw_addr, NULL, rtmsg->rtmsg_ifindex, 1); + grt = rt6_lookup(gw_addr, NULL, cfg->fc_ifindex, 1); err = -EHOSTUNREACH; if (grt == NULL) @@ -1049,7 +1165,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, if (dev == NULL) goto out; - if (rtmsg->rtmsg_flags & (RTF_GATEWAY|RTF_NONEXTHOP)) { + if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) { rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev); if (IS_ERR(rt->rt6i_nexthop)) { err = PTR_ERR(rt->rt6i_nexthop); @@ -1058,24 +1174,24 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, } } - rt->rt6i_flags = rtmsg->rtmsg_flags; + rt->rt6i_flags = cfg->fc_flags; install_route: - if (rta && rta[RTA_METRICS-1]) { - int attrlen = RTA_PAYLOAD(rta[RTA_METRICS-1]); - struct rtattr *attr = RTA_DATA(rta[RTA_METRICS-1]); - - while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; - if (flavor) { - if (flavor > RTAX_MAX) { + if (cfg->fc_mx) { + struct nlattr *nla; + int remaining; + + nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { + int type = nla->nla_type; + + if (type) { + if (type > RTAX_MAX) { err = -EINVAL; goto out; } - rt->u.dst.metrics[flavor-1] = - *(u32 *)RTA_DATA(attr); + + rt->u.dst.metrics[type - 1] = nla_get_u32(nla); } - attr = RTA_NEXT(attr, attrlen); } } @@ -1087,7 +1203,8 @@ install_route: rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst)); rt->u.dst.dev = dev; rt->rt6i_idev = idev; - return ip6_ins_rt(rt, nlh, _rtattr, req); + rt->rt6i_table = table; + return __ip6_ins_rt(rt, &cfg->fc_nlinfo); out: if (dev) @@ -1099,51 +1216,65 @@ out: return err; } -int ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) { int err; + struct fib6_table *table; - write_lock_bh(&rt6_lock); + if (rt == &ip6_null_entry) + return -ENOENT; - err = fib6_del(rt, nlh, _rtattr, req); + table = rt->rt6i_table; + write_lock_bh(&table->tb6_lock); + + err = fib6_del(rt, info); dst_release(&rt->u.dst); - write_unlock_bh(&rt6_lock); + write_unlock_bh(&table->tb6_lock); return err; } -static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +int ip6_del_rt(struct rt6_info *rt) { + return __ip6_del_rt(rt, NULL); +} + +static int ip6_route_del(struct fib6_config *cfg) +{ + struct fib6_table *table; struct fib6_node *fn; struct rt6_info *rt; int err = -ESRCH; - read_lock_bh(&rt6_lock); + table = fib6_get_table(cfg->fc_table); + if (table == NULL) + return err; - fn = fib6_locate(&ip6_routing_table, - &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len, - &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len); + read_lock_bh(&table->tb6_lock); + + fn = fib6_locate(&table->tb6_root, + &cfg->fc_dst, cfg->fc_dst_len, + &cfg->fc_src, cfg->fc_src_len); if (fn) { for (rt = fn->leaf; rt; rt = rt->u.next) { - if (rtmsg->rtmsg_ifindex && + if (cfg->fc_ifindex && (rt->rt6i_dev == NULL || - rt->rt6i_dev->ifindex != rtmsg->rtmsg_ifindex)) + rt->rt6i_dev->ifindex != cfg->fc_ifindex)) continue; - if (rtmsg->rtmsg_flags&RTF_GATEWAY && - !ipv6_addr_equal(&rtmsg->rtmsg_gateway, &rt->rt6i_gateway)) + if (cfg->fc_flags & RTF_GATEWAY && + !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) continue; - if (rtmsg->rtmsg_metric && - rtmsg->rtmsg_metric != rt->rt6i_metric) + if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric) continue; dst_hold(&rt->u.dst); - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); - return ip6_del_rt(rt, nlh, _rtattr, req); + return __ip6_del_rt(rt, &cfg->fc_nlinfo); } } - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); return err; } @@ -1151,13 +1282,18 @@ static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_r /* * Handle redirects */ -void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr, - struct neighbour *neigh, u8 *lladdr, int on_link) +struct ip6rd_flowi { + struct flowi fl; + struct in6_addr gateway; +}; + +static struct rt6_info *__ip6_route_redirect(struct fib6_table *table, + struct flowi *fl, + int flags) { - struct rt6_info *rt, *nrt = NULL; - int strict; + struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl; + struct rt6_info *rt; struct fib6_node *fn; - struct netevent_redirect netevent; /* * Get the "current" route for this destination and @@ -1169,10 +1305,9 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr, * is a bit fuzzy and one might need to check all possible * routes. */ - strict = ipv6_addr_type(dest) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL); - read_lock_bh(&rt6_lock); - fn = fib6_lookup(&ip6_routing_table, dest, NULL); + read_lock_bh(&table->tb6_lock); + fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); restart: for (rt = fn->leaf; rt; rt = rt->u.next) { /* @@ -1187,29 +1322,60 @@ restart: continue; if (!(rt->rt6i_flags & RTF_GATEWAY)) continue; - if (neigh->dev != rt->rt6i_dev) + if (fl->oif != rt->rt6i_dev->ifindex) continue; - if (!ipv6_addr_equal(saddr, &rt->rt6i_gateway)) + if (!ipv6_addr_equal(&rdfl->gateway, &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 (!rt) + rt = &ip6_null_entry; + BACKTRACK(&fl->fl6_src); +out: + dst_hold(&rt->u.dst); + + read_unlock_bh(&table->tb6_lock); + + return rt; +}; + +static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, + struct in6_addr *src, + struct in6_addr *gateway, + struct net_device *dev) +{ + struct ip6rd_flowi rdfl = { + .fl = { + .oif = dev->ifindex, + .nl_u = { + .ip6_u = { + .daddr = *dest, + .saddr = *src, + }, + }, + }, + .gateway = *gateway, + }; + int flags = rt6_need_strict(dest) ? RT6_LOOKUP_F_IFACE : 0; + + return (struct rt6_info *)fib6_rule_lookup((struct flowi *)&rdfl, flags, __ip6_route_redirect); +} + +void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, + struct in6_addr *saddr, + struct neighbour *neigh, u8 *lladdr, int on_link) +{ + struct rt6_info *rt, *nrt = NULL; + struct netevent_redirect netevent; + + rt = ip6_route_redirect(dest, src, saddr, neigh->dev); + + if (rt == &ip6_null_entry) { if (net_ratelimit()) printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop " "for redirect target\n"); - return; + goto out; } /* @@ -1252,7 +1418,7 @@ restart: nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev); nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&nrt->u.dst)); - if (ip6_ins_rt(nrt, NULL, NULL, NULL)) + if (ip6_ins_rt(nrt)) goto out; netevent.old = &rt->u.dst; @@ -1260,7 +1426,7 @@ restart: call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); if (rt->rt6i_flags&RTF_CACHE) { - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); return; } @@ -1342,7 +1508,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires); nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES; - ip6_ins_rt(nrt, NULL, NULL, NULL); + ip6_ins_rt(nrt); } out: dst_release(&rt->u.dst); @@ -1378,6 +1544,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif + rt->rt6i_table = ort->rt6i_table; } return rt; } @@ -1388,9 +1555,14 @@ static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixle { struct fib6_node *fn; struct rt6_info *rt = NULL; + struct fib6_table *table; + + table = fib6_get_table(RT6_TABLE_INFO); + if (table == NULL) + return NULL; - write_lock_bh(&rt6_lock); - fn = fib6_locate(&ip6_routing_table, prefix ,prefixlen, NULL, 0); + write_lock_bh(&table->tb6_lock); + fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0); if (!fn) goto out; @@ -1405,7 +1577,7 @@ static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixle break; } out: - write_unlock_bh(&rt6_lock); + write_unlock_bh(&table->tb6_lock); return rt; } @@ -1413,21 +1585,23 @@ static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixle struct in6_addr *gwaddr, int ifindex, unsigned pref) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_INFO, + .fc_metric = 1024, + .fc_ifindex = ifindex, + .fc_dst_len = prefixlen, + .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | + RTF_UP | RTF_PREF(pref), + }; + + ipv6_addr_copy(&cfg.fc_dst, prefix); + ipv6_addr_copy(&cfg.fc_gateway, gwaddr); - 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; + cfg.fc_flags |= RTF_DEFAULT; - ip6_route_add(&rtmsg, NULL, NULL, NULL); + ip6_route_add(&cfg); return rt6_get_route_info(prefix, prefixlen, gwaddr, ifindex); } @@ -1436,12 +1610,14 @@ static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixle struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev) { struct rt6_info *rt; - struct fib6_node *fn; + struct fib6_table *table; - fn = &ip6_routing_table; + table = fib6_get_table(RT6_TABLE_DFLT); + if (table == NULL) + return NULL; - write_lock_bh(&rt6_lock); - for (rt = fn->leaf; rt; rt=rt->u.next) { + write_lock_bh(&table->tb6_lock); + for (rt = table->tb6_root.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)) @@ -1449,7 +1625,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d } if (rt) dst_hold(&rt->u.dst); - write_unlock_bh(&rt6_lock); + write_unlock_bh(&table->tb6_lock); return rt; } @@ -1457,43 +1633,65 @@ struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_DFLT, + .fc_metric = 1024, + .fc_ifindex = dev->ifindex, + .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | + RTF_UP | RTF_EXPIRES | RTF_PREF(pref), + }; - memset(&rtmsg, 0, sizeof(struct in6_rtmsg)); - 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 | - RTF_PREF(pref); + ipv6_addr_copy(&cfg.fc_gateway, gwaddr); - rtmsg.rtmsg_ifindex = dev->ifindex; + ip6_route_add(&cfg); - ip6_route_add(&rtmsg, NULL, NULL, NULL); return rt6_get_dflt_router(gwaddr, dev); } void rt6_purge_dflt_routers(void) { struct rt6_info *rt; + struct fib6_table *table; + + /* NOTE: Keep consistent with rt6_get_dflt_router */ + table = fib6_get_table(RT6_TABLE_DFLT); + if (table == NULL) + return; restart: - read_lock_bh(&rt6_lock); - for (rt = ip6_routing_table.leaf; rt; rt = rt->u.next) { + read_lock_bh(&table->tb6_lock); + for (rt = table->tb6_root.leaf; rt; rt = rt->u.next) { if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { dst_hold(&rt->u.dst); - - read_unlock_bh(&rt6_lock); - - ip6_del_rt(rt, NULL, NULL, NULL); - + read_unlock_bh(&table->tb6_lock); + ip6_del_rt(rt); goto restart; } } - read_unlock_bh(&rt6_lock); + read_unlock_bh(&table->tb6_lock); +} + +static void rtmsg_to_fib6_config(struct in6_rtmsg *rtmsg, + struct fib6_config *cfg) +{ + memset(cfg, 0, sizeof(*cfg)); + + cfg->fc_table = RT6_TABLE_MAIN; + cfg->fc_ifindex = rtmsg->rtmsg_ifindex; + cfg->fc_metric = rtmsg->rtmsg_metric; + cfg->fc_expires = rtmsg->rtmsg_info; + cfg->fc_dst_len = rtmsg->rtmsg_dst_len; + cfg->fc_src_len = rtmsg->rtmsg_src_len; + cfg->fc_flags = rtmsg->rtmsg_flags; + + ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst); + ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src); + ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway); } int ipv6_route_ioctl(unsigned int cmd, void __user *arg) { + struct fib6_config cfg; struct in6_rtmsg rtmsg; int err; @@ -1506,14 +1704,16 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg) sizeof(struct in6_rtmsg)); if (err) return -EFAULT; - + + rtmsg_to_fib6_config(&rtmsg, &cfg); + rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&rtmsg, NULL, NULL, NULL); + err = ip6_route_add(&cfg); break; case SIOCDELRT: - err = ip6_route_del(&rtmsg, NULL, NULL, NULL); + err = ip6_route_del(&cfg); break; default: err = -EINVAL; @@ -1587,6 +1787,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, ipv6_addr_copy(&rt->rt6i_dst.addr, addr); rt->rt6i_dst.plen = 128; + rt->rt6i_table = fib6_get_table(RT6_TABLE_LOCAL); atomic_set(&rt->u.dst.__refcnt, 1); @@ -1605,9 +1806,7 @@ static int fib6_ifdown(struct rt6_info *rt, void *arg) void rt6_ifdown(struct net_device *dev) { - write_lock_bh(&rt6_lock); - fib6_clean_tree(&ip6_routing_table, fib6_ifdown, 0, dev); - write_unlock_bh(&rt6_lock); + fib6_clean_all(fib6_ifdown, 0, dev); } struct rt6_mtu_change_arg @@ -1657,80 +1856,114 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) void rt6_mtu_change(struct net_device *dev, unsigned mtu) { - struct rt6_mtu_change_arg arg; + struct rt6_mtu_change_arg arg = { + .dev = dev, + .mtu = mtu, + }; - arg.dev = dev; - arg.mtu = mtu; - read_lock_bh(&rt6_lock); - fib6_clean_tree(&ip6_routing_table, rt6_mtu_change_route, 0, &arg); - read_unlock_bh(&rt6_lock); + fib6_clean_all(rt6_mtu_change_route, 0, &arg); } -static int inet6_rtm_to_rtmsg(struct rtmsg *r, struct rtattr **rta, - struct in6_rtmsg *rtmsg) +static struct nla_policy rtm_ipv6_policy[RTA_MAX+1] __read_mostly = { + [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, + [RTA_OIF] = { .type = NLA_U32 }, + [RTA_IIF] = { .type = NLA_U32 }, + [RTA_PRIORITY] = { .type = NLA_U32 }, + [RTA_METRICS] = { .type = NLA_NESTED }, +}; + +static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, + struct fib6_config *cfg) { - memset(rtmsg, 0, sizeof(*rtmsg)); + struct rtmsg *rtm; + struct nlattr *tb[RTA_MAX+1]; + int err; - rtmsg->rtmsg_dst_len = r->rtm_dst_len; - rtmsg->rtmsg_src_len = r->rtm_src_len; - rtmsg->rtmsg_flags = RTF_UP; - if (r->rtm_type == RTN_UNREACHABLE) - rtmsg->rtmsg_flags |= RTF_REJECT; + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); + if (err < 0) + goto errout; - if (rta[RTA_GATEWAY-1]) { - if (rta[RTA_GATEWAY-1]->rta_len != RTA_LENGTH(16)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_gateway, RTA_DATA(rta[RTA_GATEWAY-1]), 16); - rtmsg->rtmsg_flags |= RTF_GATEWAY; - } - if (rta[RTA_DST-1]) { - if (RTA_PAYLOAD(rta[RTA_DST-1]) < ((r->rtm_dst_len+7)>>3)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_dst, RTA_DATA(rta[RTA_DST-1]), ((r->rtm_dst_len+7)>>3)); + err = -EINVAL; + rtm = nlmsg_data(nlh); + memset(cfg, 0, sizeof(*cfg)); + + cfg->fc_table = rtm->rtm_table; + cfg->fc_dst_len = rtm->rtm_dst_len; + cfg->fc_src_len = rtm->rtm_src_len; + cfg->fc_flags = RTF_UP; + cfg->fc_protocol = rtm->rtm_protocol; + + if (rtm->rtm_type == RTN_UNREACHABLE) + cfg->fc_flags |= RTF_REJECT; + + cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; + cfg->fc_nlinfo.nlh = nlh; + + if (tb[RTA_GATEWAY]) { + nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16); + cfg->fc_flags |= RTF_GATEWAY; } - if (rta[RTA_SRC-1]) { - if (RTA_PAYLOAD(rta[RTA_SRC-1]) < ((r->rtm_src_len+7)>>3)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_src, RTA_DATA(rta[RTA_SRC-1]), ((r->rtm_src_len+7)>>3)); + + if (tb[RTA_DST]) { + int plen = (rtm->rtm_dst_len + 7) >> 3; + + if (nla_len(tb[RTA_DST]) < plen) + goto errout; + + nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen); } - if (rta[RTA_OIF-1]) { - if (rta[RTA_OIF-1]->rta_len != RTA_LENGTH(sizeof(int))) - return -EINVAL; - memcpy(&rtmsg->rtmsg_ifindex, RTA_DATA(rta[RTA_OIF-1]), sizeof(int)); + + if (tb[RTA_SRC]) { + int plen = (rtm->rtm_src_len + 7) >> 3; + + if (nla_len(tb[RTA_SRC]) < plen) + goto errout; + + nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } - if (rta[RTA_PRIORITY-1]) { - if (rta[RTA_PRIORITY-1]->rta_len != RTA_LENGTH(4)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_metric, RTA_DATA(rta[RTA_PRIORITY-1]), 4); + + if (tb[RTA_OIF]) + cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); + + if (tb[RTA_PRIORITY]) + cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]); + + if (tb[RTA_METRICS]) { + cfg->fc_mx = nla_data(tb[RTA_METRICS]); + cfg->fc_mx_len = nla_len(tb[RTA_METRICS]); } - return 0; + + if (tb[RTA_TABLE]) + cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); + + err = 0; +errout: + return err; } int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct rtmsg *r = NLMSG_DATA(nlh); - struct in6_rtmsg rtmsg; + struct fib6_config cfg; + int err; - if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) - return -EINVAL; - return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb)); + err = rtm_to_fib6_config(skb, nlh, &cfg); + if (err < 0) + return err; + + return ip6_route_del(&cfg); } int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct rtmsg *r = NLMSG_DATA(nlh); - struct in6_rtmsg rtmsg; + struct fib6_config cfg; + int err; - if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) - return -EINVAL; - return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb)); -} + err = rtm_to_fib6_config(skb, nlh, &cfg); + if (err < 0) + return err; -struct rt6_rtnl_dump_arg -{ - struct sk_buff *skb; - struct netlink_callback *cb; -}; + return ip6_route_add(&cfg); +} static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, @@ -1738,9 +1971,9 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, int prefix, unsigned int flags) { struct rtmsg *rtm; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; + struct nlmsghdr *nlh; struct rta_cacheinfo ci; + u32 table; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -1749,13 +1982,21 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, } } - nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*rtm), flags); - rtm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags); + if (nlh == NULL) + return -ENOBUFS; + + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt->rt6i_dst.plen; rtm->rtm_src_len = rt->rt6i_src.plen; rtm->rtm_tos = 0; - rtm->rtm_table = RT_TABLE_MAIN; + if (rt->rt6i_table) + table = rt->rt6i_table->tb6_id; + else + table = RT6_TABLE_UNSPEC; + rtm->rtm_table = table; + NLA_PUT_U32(skb, RTA_TABLE, table); if (rt->rt6i_flags&RTF_REJECT) rtm->rtm_type = RTN_UNREACHABLE; else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK)) @@ -1776,31 +2017,35 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, rtm->rtm_flags |= RTM_F_CLONED; if (dst) { - RTA_PUT(skb, RTA_DST, 16, dst); + NLA_PUT(skb, RTA_DST, 16, dst); rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - RTA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr); + NLA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (src) { - RTA_PUT(skb, RTA_SRC, 16, src); + NLA_PUT(skb, RTA_SRC, 16, src); rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len) - RTA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr); + NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr); #endif if (iif) - RTA_PUT(skb, RTA_IIF, 4, &iif); + NLA_PUT_U32(skb, RTA_IIF, iif); else if (dst) { struct in6_addr saddr_buf; if (ipv6_get_saddr(&rt->u.dst, dst, &saddr_buf) == 0) - RTA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); + NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } + if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) - goto rtattr_failure; + goto nla_put_failure; + if (rt->u.dst.neighbour) - RTA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key); + NLA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key); + if (rt->u.dst.dev) - RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->rt6i_dev->ifindex); - RTA_PUT(skb, RTA_PRIORITY, 4, &rt->rt6i_metric); + NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex); + + NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric); ci.rta_lastuse = jiffies_to_clock_t(jiffies - rt->u.dst.lastuse); if (rt->rt6i_expires) ci.rta_expires = jiffies_to_clock_t(rt->rt6i_expires - jiffies); @@ -1812,23 +2057,21 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, ci.rta_id = 0; ci.rta_ts = 0; ci.rta_tsage = 0; - RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + NLA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); } -static int rt6_dump_route(struct rt6_info *rt, void *p_arg) +int rt6_dump_route(struct rt6_info *rt, void *p_arg) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; int prefix; - if (arg->cb->nlh->nlmsg_len >= NLMSG_LENGTH(sizeof(struct rtmsg))) { - struct rtmsg *rtm = NLMSG_DATA(arg->cb->nlh); + if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) { + struct rtmsg *rtm = nlmsg_data(arg->cb->nlh); prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0; } else prefix = 0; @@ -1838,189 +2081,108 @@ static int rt6_dump_route(struct rt6_info *rt, void *p_arg) prefix, NLM_F_MULTI); } -static int fib6_dump_node(struct fib6_walker_t *w) +int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { - int res; + struct nlattr *tb[RTA_MAX+1]; struct rt6_info *rt; + struct sk_buff *skb; + struct rtmsg *rtm; + struct flowi fl; + int err, iif = 0; - for (rt = w->leaf; rt; rt = rt->u.next) { - res = rt6_dump_route(rt, w->args); - if (res < 0) { - /* Frame is full, suspend walking */ - w->leaf = rt; - return 1; - } - BUG_TRAP(res!=0); - } - w->leaf = NULL; - return 0; -} - -static void fib6_dump_end(struct netlink_callback *cb) -{ - struct fib6_walker_t *w = (void*)cb->args[0]; - - if (w) { - cb->args[0] = 0; - fib6_walker_unlink(w); - kfree(w); - } - cb->done = (void*)cb->args[1]; - cb->args[1] = 0; -} - -static int fib6_dump_done(struct netlink_callback *cb) -{ - fib6_dump_end(cb); - return cb->done ? cb->done(cb) : 0; -} - -int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct rt6_rtnl_dump_arg arg; - struct fib6_walker_t *w; - int res; + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); + if (err < 0) + goto errout; - arg.skb = skb; - arg.cb = cb; + err = -EINVAL; + memset(&fl, 0, sizeof(fl)); - w = (void*)cb->args[0]; - if (w == NULL) { - /* New dump: - * - * 1. hook callback destructor. - */ - cb->args[1] = (long)cb->done; - cb->done = fib6_dump_done; + if (tb[RTA_SRC]) { + if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) + goto errout; - /* - * 2. allocate and initialize walker. - */ - w = kzalloc(sizeof(*w), GFP_ATOMIC); - if (w == NULL) - return -ENOMEM; - RT6_TRACE("dump<%p", w); - w->root = &ip6_routing_table; - w->func = fib6_dump_node; - w->args = &arg; - cb->args[0] = (long)w; - read_lock_bh(&rt6_lock); - res = fib6_walk(w); - read_unlock_bh(&rt6_lock); - } else { - w->args = &arg; - read_lock_bh(&rt6_lock); - res = fib6_walk_continue(w); - read_unlock_bh(&rt6_lock); + ipv6_addr_copy(&fl.fl6_src, nla_data(tb[RTA_SRC])); } -#if RT6_DEBUG >= 3 - if (res <= 0 && skb->len == 0) - RT6_TRACE("%p>dump end\n", w); -#endif - res = res < 0 ? res : skb->len; - /* res < 0 is an error. (really, impossible) - res == 0 means that dump is complete, but skb still can contain data. - res > 0 dump is not complete, but frame is full. - */ - /* Destroy walker, if dump of this table is complete. */ - if (res <= 0) - fib6_dump_end(cb); - return res; -} - -int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) -{ - struct rtattr **rta = arg; - int iif = 0; - int err = -ENOBUFS; - struct sk_buff *skb; - struct flowi fl; - struct rt6_info *rt; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (skb == NULL) - goto out; + if (tb[RTA_DST]) { + if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) + goto errout; - /* Reserve room for dummy headers, this skb can pass - through good chunk of routing engine. - */ - skb->mac.raw = skb->data; - skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); + ipv6_addr_copy(&fl.fl6_dst, nla_data(tb[RTA_DST])); + } - memset(&fl, 0, sizeof(fl)); - if (rta[RTA_SRC-1]) - ipv6_addr_copy(&fl.fl6_src, - (struct in6_addr*)RTA_DATA(rta[RTA_SRC-1])); - if (rta[RTA_DST-1]) - ipv6_addr_copy(&fl.fl6_dst, - (struct in6_addr*)RTA_DATA(rta[RTA_DST-1])); + if (tb[RTA_IIF]) + iif = nla_get_u32(tb[RTA_IIF]); - if (rta[RTA_IIF-1]) - memcpy(&iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int)); + if (tb[RTA_OIF]) + fl.oif = nla_get_u32(tb[RTA_OIF]); if (iif) { struct net_device *dev; dev = __dev_get_by_index(iif); if (!dev) { err = -ENODEV; - goto out_free; + goto errout; } } - fl.oif = 0; - if (rta[RTA_OIF-1]) - memcpy(&fl.oif, RTA_DATA(rta[RTA_OIF-1]), sizeof(int)); + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) { + err = -ENOBUFS; + goto errout; + } - rt = (struct rt6_info*)ip6_route_output(NULL, &fl); + /* Reserve room for dummy headers, this skb can pass + through good chunk of routing engine. + */ + skb->mac.raw = skb->data; + skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); + rt = (struct rt6_info*) ip6_route_output(NULL, &fl); skb->dst = &rt->u.dst; - NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; - err = rt6_fill_node(skb, rt, - &fl.fl6_dst, &fl.fl6_src, - iif, + err = rt6_fill_node(skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, 0); if (err < 0) { - err = -EMSGSIZE; - goto out_free; + kfree_skb(skb); + goto errout; } - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; -out: + err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid); +errout: return err; -out_free: - kfree_skb(skb); - goto out; } -void inet6_rt_notify(int event, struct rt6_info *rt, struct nlmsghdr *nlh, - struct netlink_skb_parms *req) +void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct rtmsg)+256); - u32 pid = current->pid; - u32 seq = 0; - - if (req) - pid = req->pid; - if (nlh) - seq = nlh->nlmsg_seq; - - skb = alloc_skb(size, gfp_any()); - if (!skb) { - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, ENOBUFS); - return; + u32 pid = 0, seq = 0; + struct nlmsghdr *nlh = NULL; + int payload = sizeof(struct rtmsg) + 256; + int err = -ENOBUFS; + + if (info) { + pid = info->pid; + nlh = info->nlh; + if (nlh) + seq = nlh->nlmsg_seq; } - if (rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0) < 0) { + + skb = nlmsg_new(nlmsg_total_size(payload), gfp_any()); + if (skb == NULL) + goto errout; + + err = rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0); + if (err < 0) { kfree_skb(skb); - netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, EINVAL); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_ROUTE; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_ROUTE, gfp_any()); + + err = rtnl_notify(skb, pid, RTNLGRP_IPV6_ROUTE, nlh, gfp_any()); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_IPV6_ROUTE, err); } /* @@ -2096,16 +2258,13 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) static int rt6_proc_info(char *buffer, char **start, off_t offset, int length) { - struct rt6_proc_arg arg; - arg.buffer = buffer; - arg.offset = offset; - arg.length = length; - arg.skip = 0; - arg.len = 0; + struct rt6_proc_arg arg = { + .buffer = buffer, + .offset = offset, + .length = length, + }; - read_lock_bh(&rt6_lock); - fib6_clean_tree(&ip6_routing_table, rt6_info_route, 0, &arg); - read_unlock_bh(&rt6_lock); + fib6_clean_all(rt6_info_route, 0, &arg); *start = buffer; if (offset) @@ -2260,13 +2419,9 @@ void __init ip6_route_init(void) { struct proc_dir_entry *p; - ip6_dst_ops.kmem_cachep = kmem_cache_create("ip6_dst_cache", - sizeof(struct rt6_info), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - if (!ip6_dst_ops.kmem_cachep) - panic("cannot create ip6_dst_cache"); - + ip6_dst_ops.kmem_cachep = + kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); fib6_init(); #ifdef CONFIG_PROC_FS p = proc_net_create("ipv6_route", 0, rt6_proc_info); @@ -2278,10 +2433,16 @@ void __init ip6_route_init(void) #ifdef CONFIG_XFRM xfrm6_init(); #endif +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + fib6_rules_init(); +#endif } void ip6_route_cleanup(void) { +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + fib6_rules_cleanup(); +#endif #ifdef CONFIG_PROC_FS proc_net_remove("ipv6_route"); proc_net_remove("rt6_stats"); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 802a1a6b103..2546fc9f0a7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -251,6 +251,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, final_p = &final; } + security_sk_classify_flow(sk, &fl); + err = ip6_dst_lookup(sk, &dst, &fl); if (err) goto failure; @@ -270,7 +272,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, inet->rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; - __ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (np->opt) @@ -374,6 +376,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; + security_skb_classify_flow(skb, &fl); if ((err = ip6_dst_lookup(sk, &dst, &fl))) { sk->sk_err_soft = -err; @@ -467,6 +470,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, fl.oif = treq->iif; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; + security_req_classify_flow(req, &fl); if (dst == NULL) { opt = np->opt; @@ -541,7 +545,7 @@ static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) struct ipv6_pinfo *np = inet6_sk(sk); struct tcphdr *th = skb->h.th; - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 0); skb->csum = offsetof(struct tcphdr, check); } else { @@ -566,7 +570,7 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb) th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, IPPROTO_TCP, 0); skb->csum = offsetof(struct tcphdr, check); - skb->ip_summed = CHECKSUM_HW; + skb->ip_summed = CHECKSUM_PARTIAL; return 0; } @@ -625,6 +629,7 @@ static void tcp_v6_send_reset(struct sk_buff *skb) fl.oif = inet6_iif(skb); fl.fl_ip_dport = t1->dest; fl.fl_ip_sport = t1->source; + security_skb_classify_flow(skb, &fl); /* sk = NULL, but it is safe for now. RST socket required. */ if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) { @@ -691,6 +696,7 @@ static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 fl.oif = inet6_iif(skb); fl.fl_ip_dport = t1->dest; fl.fl_ip_sport = t1->source; + security_skb_classify_flow(skb, &fl); if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) { if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) { @@ -820,6 +826,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->snt_isn = isn; + security_inet_conn_request(sk, skb, req); + if (tcp_v6_send_synack(sk, req, NULL)) goto drop; @@ -923,6 +931,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; + security_req_classify_flow(req, &fl); if (ip6_dst_lookup(sk, &dst, &fl)) goto out; @@ -945,7 +954,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ newsk->sk_gso_type = SKB_GSO_TCPV6; - __ip6_dst_store(newsk, dst, NULL); + __ip6_dst_store(newsk, dst, NULL, NULL); newtcp6sk = (struct tcp6_sock *)newsk; inet_sk(newsk)->pinet6 = &newtcp6sk->inet6; @@ -1024,7 +1033,7 @@ out: static int tcp_v6_checksum_init(struct sk_buff *skb) { - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr,skb->csum)) { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -1066,7 +1075,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard; /* @@ -1223,7 +1232,7 @@ process: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard_and_relse; skb->dev = NULL; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3d54f246411..9662561701d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -61,81 +61,9 @@ DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly; -/* Grrr, addr_type already calculated by caller, but I don't want - * to add some silly "cookie" argument to this method just for that. - */ -static int udp_v6_get_port(struct sock *sk, unsigned short snum) +static inline int udp_v6_get_port(struct sock *sk, unsigned short snum) { - struct sock *sk2; - struct hlist_node *node; - - write_lock_bh(&udp_hash_lock); - if (snum == 0) { - int best_size_so_far, best, result, i; - - if (udp_port_rover > sysctl_local_port_range[1] || - udp_port_rover < sysctl_local_port_range[0]) - udp_port_rover = sysctl_local_port_range[0]; - best_size_so_far = 32767; - best = result = udp_port_rover; - for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) { - int size; - struct hlist_head *list; - - list = &udp_hash[result & (UDP_HTABLE_SIZE - 1)]; - if (hlist_empty(list)) { - if (result > sysctl_local_port_range[1]) - result = sysctl_local_port_range[0] + - ((result - sysctl_local_port_range[0]) & - (UDP_HTABLE_SIZE - 1)); - goto gotit; - } - size = 0; - sk_for_each(sk2, node, list) - if (++size >= best_size_so_far) - goto next; - best_size_so_far = size; - best = result; - next:; - } - result = best; - for(i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++, result += UDP_HTABLE_SIZE) { - if (result > sysctl_local_port_range[1]) - result = sysctl_local_port_range[0] - + ((result - sysctl_local_port_range[0]) & - (UDP_HTABLE_SIZE - 1)); - if (!udp_lport_inuse(result)) - break; - } - if (i >= (1 << 16) / UDP_HTABLE_SIZE) - goto fail; -gotit: - udp_port_rover = snum = result; - } else { - sk_for_each(sk2, node, - &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]) { - if (inet_sk(sk2)->num == snum && - sk2 != sk && - (!sk2->sk_bound_dev_if || - !sk->sk_bound_dev_if || - sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && - (!sk2->sk_reuse || !sk->sk_reuse) && - ipv6_rcv_saddr_equal(sk, sk2)) - goto fail; - } - } - - inet_sk(sk)->num = snum; - if (sk_unhashed(sk)) { - sk_add_node(sk, &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]); - sock_prot_inc_use(sk->sk_prot); - } - write_unlock_bh(&udp_hash_lock); - return 0; - -fail: - write_unlock_bh(&udp_hash_lock); - return 1; + return udp_get_port(sk, snum, ipv6_rcv_saddr_equal); } static void udp_v6_hash(struct sock *sk) @@ -345,6 +273,8 @@ out: static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) { + int rc; + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { kfree_skb(skb); return -1; @@ -356,7 +286,10 @@ static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) return 0; } - if (sock_queue_rcv_skb(sk,skb)<0) { + if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { + /* Note that an ENOMEM error is charged twice */ + if (rc == -ENOMEM) + UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS); UDP6_INC_STATS_BH(UDP_MIB_INERRORS); kfree_skb(skb); return 0; @@ -475,7 +408,7 @@ static int udpv6_rcv(struct sk_buff **pskb) uh = skb->h.uh; } - if (skb->ip_summed == CHECKSUM_HW && + if (skb->ip_summed == CHECKSUM_COMPLETE && !csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -782,6 +715,8 @@ do_udp_sendmsg: connected = 0; } + security_sk_classify_flow(sk, fl); + err = ip6_sk_dst_lookup(sk, &dst, fl); if (err) goto out; @@ -840,7 +775,12 @@ do_append_data: if (connected) { ip6_dst_store(sk, dst, ipv6_addr_equal(&fl->fl6_dst, &np->daddr) ? - &np->daddr : NULL); + &np->daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl->fl6_src, &np->saddr) ? + &np->saddr : +#endif + NULL); } else { dst_release(dst); } @@ -855,6 +795,16 @@ out: UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS); return len; } + /* + * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting + * ENOBUFS might not be good (it's not tunable per se), but otherwise + * we don't have a good statistic (IpOutDiscards but it can be too many + * things). We could add another new stat but at least for now that + * seems like overkill. + */ + if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS); + } return err; do_confirm: diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 0405d74ff91..a40a0578901 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -72,7 +72,7 @@ int xfrm6_rcv_spi(struct sk_buff *skb, u32 spi) if (x->mode->input(x, skb)) goto drop; - if (x->props.mode) { /* XXX */ + if (x->props.mode == XFRM_MODE_TUNNEL) { /* XXX */ decaps = 1; break; } @@ -138,3 +138,111 @@ int xfrm6_rcv(struct sk_buff **pskb) { return xfrm6_rcv_spi(*pskb, 0); } + +int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, + xfrm_address_t *saddr, u8 proto) +{ + struct xfrm_state *x = NULL; + int wildcard = 0; + struct in6_addr any; + xfrm_address_t *xany; + struct xfrm_state *xfrm_vec_one = NULL; + int nh = 0; + int i = 0; + + ipv6_addr_set(&any, 0, 0, 0, 0); + xany = (xfrm_address_t *)&any; + + for (i = 0; i < 3; i++) { + xfrm_address_t *dst, *src; + switch (i) { + case 0: + dst = daddr; + src = saddr; + break; + case 1: + /* lookup state with wild-card source address */ + wildcard = 1; + dst = daddr; + src = xany; + break; + case 2: + default: + /* lookup state with wild-card addresses */ + wildcard = 1; /* XXX */ + dst = xany; + src = xany; + break; + } + + x = xfrm_state_lookup_byaddr(dst, src, proto, AF_INET6); + if (!x) + continue; + + spin_lock(&x->lock); + + if (wildcard) { + if ((x->props.flags & XFRM_STATE_WILDRECV) == 0) { + spin_unlock(&x->lock); + xfrm_state_put(x); + x = NULL; + continue; + } + } + + if (unlikely(x->km.state != XFRM_STATE_VALID)) { + spin_unlock(&x->lock); + xfrm_state_put(x); + x = NULL; + continue; + } + if (xfrm_state_check_expire(x)) { + spin_unlock(&x->lock); + xfrm_state_put(x); + x = NULL; + continue; + } + + nh = x->type->input(x, skb); + if (nh <= 0) { + spin_unlock(&x->lock); + xfrm_state_put(x); + x = NULL; + continue; + } + + x->curlft.bytes += skb->len; + x->curlft.packets++; + + spin_unlock(&x->lock); + + xfrm_vec_one = x; + break; + } + + if (!xfrm_vec_one) + goto drop; + + /* Allocate new secpath or COW existing one. */ + if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) { + struct sec_path *sp; + sp = secpath_dup(skb->sp); + if (!sp) + goto drop; + if (skb->sp) + secpath_put(skb->sp); + skb->sp = sp; + } + + if (1 + skb->sp->len > XFRM_MAX_DEPTH) + goto drop; + + skb->sp->xvec[skb->sp->len] = xfrm_vec_one; + skb->sp->len ++; + + return 1; +drop: + if (xfrm_vec_one) + xfrm_state_put(xfrm_vec_one); + return -1; +} diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c new file mode 100644 index 00000000000..6031c16d46c --- /dev/null +++ b/net/ipv6/xfrm6_mode_ro.c @@ -0,0 +1,93 @@ +/* + * xfrm6_mode_ro.c - Route optimization mode for IPv6. + * + * Copyright (C)2003-2006 Helsinki University of Technology + * Copyright (C)2003-2006 USAGI/WIDE Project + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +/* + * Authors: + * Noriaki TAKAMIYA @USAGI + * Masahide NAKAMURA @USAGI + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/stringify.h> +#include <net/ipv6.h> +#include <net/xfrm.h> + +/* Add route optimization header space. + * + * The IP header and mutable extension headers will be moved forward to make + * space for the route optimization header. + * + * On exit, skb->h will be set to the start of the encapsulation header to be + * filled in by x->type->output and skb->nh will be set to the nextheader field + * of the extension header directly preceding the encapsulation header, or in + * its absence, that of the top IP header. The value of skb->data will always + * point to the top IP header. + */ +static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) +{ + struct ipv6hdr *iph; + u8 *prevhdr; + int hdr_len; + + skb_push(skb, x->props.header_len); + iph = skb->nh.ipv6h; + + hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + skb->nh.raw = prevhdr - x->props.header_len; + skb->h.raw = skb->data + hdr_len; + memmove(skb->data, iph, hdr_len); + return 0; +} + +/* + * Do nothing about routing optimization header unlike IPsec. + */ +static int xfrm6_ro_input(struct xfrm_state *x, struct sk_buff *skb) +{ + return 0; +} + +static struct xfrm_mode xfrm6_ro_mode = { + .input = xfrm6_ro_input, + .output = xfrm6_ro_output, + .owner = THIS_MODULE, + .encap = XFRM_MODE_ROUTEOPTIMIZATION, +}; + +static int __init xfrm6_ro_init(void) +{ + return xfrm_register_mode(&xfrm6_ro_mode, AF_INET6); +} + +static void __exit xfrm6_ro_exit(void) +{ + int err; + + err = xfrm_unregister_mode(&xfrm6_ro_mode, AF_INET6); + BUG_ON(err); +} + +module_init(xfrm6_ro_init); +module_exit(xfrm6_ro_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_ROUTEOPTIMIZATION); diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c index 711d713e36d..3a4b39b12ba 100644 --- a/net/ipv6/xfrm6_mode_transport.c +++ b/net/ipv6/xfrm6_mode_transport.c @@ -25,9 +25,8 @@ * its absence, that of the top IP header. The value of skb->data will always * point to the top IP header. */ -static int xfrm6_transport_output(struct sk_buff *skb) +static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) { - struct xfrm_state *x = skb->dst->xfrm; struct ipv6hdr *iph; u8 *prevhdr; int hdr_len; @@ -35,7 +34,7 @@ static int xfrm6_transport_output(struct sk_buff *skb) skb_push(skb, x->props.header_len); iph = skb->nh.ipv6h; - hdr_len = ip6_find_1stfragopt(skb, &prevhdr); + hdr_len = x->type->hdr_offset(x, skb, &prevhdr); skb->nh.raw = prevhdr - x->props.header_len; skb->h.raw = skb->data + hdr_len; memmove(skb->data, iph, hdr_len); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 8af79be2edc..5e7d8a7d641 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -37,10 +37,9 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) * its absence, that of the top IP header. The value of skb->data will always * point to the top IP header. */ -static int xfrm6_tunnel_output(struct sk_buff *skb) +static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) { struct dst_entry *dst = skb->dst; - struct xfrm_state *x = dst->xfrm; struct ipv6hdr *iph, *top_iph; int dsfield; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index c8c8b44a0f5..c260ea104c5 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -17,6 +17,12 @@ #include <net/ipv6.h> #include <net/xfrm.h> +int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, + u8 **prevhdr) +{ + return ip6_find_1stfragopt(skb, prevhdr); +} + static int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; @@ -41,13 +47,13 @@ static int xfrm6_output_one(struct sk_buff *skb) struct xfrm_state *x = dst->xfrm; int err; - if (skb->ip_summed == CHECKSUM_HW) { - err = skb_checksum_help(skb, 0); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); if (err) goto error_nolock; } - if (x->props.mode) { + if (x->props.mode == XFRM_MODE_TUNNEL) { err = xfrm6_tunnel_check_size(skb); if (err) goto error_nolock; @@ -59,7 +65,7 @@ static int xfrm6_output_one(struct sk_buff *skb) if (err) goto error; - err = x->mode->output(skb); + err = x->mode->output(x, skb); if (err) goto error; @@ -69,6 +75,8 @@ static int xfrm6_output_one(struct sk_buff *skb) x->curlft.bytes += skb->len; x->curlft.packets++; + if (x->props.mode == XFRM_MODE_ROUTEOPTIMIZATION) + x->lastused = (u64)xtime.tv_sec; spin_unlock_bh(&x->lock); @@ -80,7 +88,7 @@ static int xfrm6_output_one(struct sk_buff *skb) } dst = skb->dst; x = dst->xfrm; - } while (x && !x->props.mode); + } while (x && (x->props.mode != XFRM_MODE_TUNNEL)); IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; err = 0; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 73cd250aecb..6a252e2134d 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -18,6 +18,9 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> +#ifdef CONFIG_IPV6_MIP6 +#include <net/mip6.h> +#endif static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; @@ -31,6 +34,26 @@ static int xfrm6_dst_lookup(struct xfrm_dst **dst, struct flowi *fl) return err; } +static int xfrm6_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr) +{ + struct rt6_info *rt; + struct flowi fl_tunnel = { + .nl_u = { + .ip6_u = { + .daddr = *(struct in6_addr *)&daddr->a6, + }, + }, + }; + + if (!xfrm6_dst_lookup((struct xfrm_dst **)&rt, &fl_tunnel)) { + ipv6_get_saddr(&rt->u.dst, (struct in6_addr *)&daddr->a6, + (struct in6_addr *)&saddr->a6); + dst_release(&rt->u.dst); + return 0; + } + return -EHOSTUNREACH; +} + static struct dst_entry * __xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy) { @@ -50,7 +73,9 @@ __xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy) xdst->u.rt6.rt6i_src.plen); if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) && ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) && - xfrm_bundle_ok(xdst, fl, AF_INET6)) { + xfrm_bundle_ok(xdst, fl, AF_INET6, + (xdst->u.rt6.rt6i_dst.plen != 128 || + xdst->u.rt6.rt6i_src.plen != 128))) { dst_clone(dst); break; } @@ -59,6 +84,40 @@ __xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy) return dst; } +static inline struct in6_addr* +__xfrm6_bundle_addr_remote(struct xfrm_state *x, struct in6_addr *addr) +{ + return (x->type->remote_addr) ? + (struct in6_addr*)x->type->remote_addr(x, (xfrm_address_t *)addr) : + (struct in6_addr*)&x->id.daddr; +} + +static inline struct in6_addr* +__xfrm6_bundle_addr_local(struct xfrm_state *x, struct in6_addr *addr) +{ + return (x->type->local_addr) ? + (struct in6_addr*)x->type->local_addr(x, (xfrm_address_t *)addr) : + (struct in6_addr*)&x->props.saddr; +} + +static inline void +__xfrm6_bundle_len_inc(int *len, int *nflen, struct xfrm_state *x) +{ + if (x->type->flags & XFRM_TYPE_NON_FRAGMENT) + *nflen += x->props.header_len; + else + *len += x->props.header_len; +} + +static inline void +__xfrm6_bundle_len_dec(int *len, int *nflen, struct xfrm_state *x) +{ + if (x->type->flags & XFRM_TYPE_NON_FRAGMENT) + *nflen -= x->props.header_len; + else + *len -= x->props.header_len; +} + /* Allocate chain of dst_entry's, attach known xfrm's, calculate * all the metrics... Shortly, bundle a bundle. */ @@ -83,6 +142,7 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int int i; int err = 0; int header_len = 0; + int nfheader_len = 0; int trailer_len = 0; dst = dst_prev = NULL; @@ -109,17 +169,18 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int xdst = (struct xfrm_dst *)dst1; xdst->route = &rt->u.dst; + xdst->genid = xfrm[i]->genid; if (rt->rt6i_node) xdst->route_cookie = rt->rt6i_node->fn_sernum; dst1->next = dst_prev; dst_prev = dst1; - if (xfrm[i]->props.mode) { - remote = (struct in6_addr*)&xfrm[i]->id.daddr; - local = (struct in6_addr*)&xfrm[i]->props.saddr; + if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { + remote = __xfrm6_bundle_addr_remote(xfrm[i], remote); + local = __xfrm6_bundle_addr_local(xfrm[i], local); tunnel = 1; } - header_len += xfrm[i]->props.header_len; + __xfrm6_bundle_len_inc(&header_len, &nfheader_len, xfrm[i]); trailer_len += xfrm[i]->props.trailer_len; if (tunnel) { @@ -154,6 +215,7 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int dst_prev->flags |= DST_HOST; dst_prev->lastuse = jiffies; dst_prev->header_len = header_len; + dst_prev->nfheader_len = nfheader_len; dst_prev->trailer_len = trailer_len; memcpy(&dst_prev->metrics, &x->route->metrics, sizeof(dst_prev->metrics)); @@ -172,7 +234,7 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int x->u.rt6.rt6i_src = rt0->rt6i_src; x->u.rt6.rt6i_idev = rt0->rt6i_idev; in6_dev_hold(rt0->rt6i_idev); - header_len -= x->u.dst.xfrm->props.header_len; + __xfrm6_bundle_len_dec(&header_len, &nfheader_len, x->u.dst.xfrm); trailer_len -= x->u.dst.xfrm->props.trailer_len; } @@ -232,6 +294,18 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl) fl->proto = nexthdr; return; +#ifdef CONFIG_IPV6_MIP6 + case IPPROTO_MH: + if (pskb_may_pull(skb, skb->nh.raw + offset + 3 - skb->data)) { + struct ip6_mh *mh; + mh = (struct ip6_mh *)exthdr; + + fl->fl_mh_type = mh->ip6mh_type; + } + fl->proto = nexthdr; + return; +#endif + /* XXX Why are there these headers? */ case IPPROTO_AH: case IPPROTO_ESP: @@ -308,6 +382,7 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .family = AF_INET6, .dst_ops = &xfrm6_dst_ops, .dst_lookup = xfrm6_dst_lookup, + .get_saddr = xfrm6_get_saddr, .find_bundle = __xfrm6_find_bundle, .bundle_create = __xfrm6_bundle_create, .decode_session = _decode_session6, diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index b33296b3f6d..711bfafb247 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -42,102 +42,135 @@ __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr)); if (ipv6_addr_any((struct in6_addr*)&x->props.saddr)) memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr)); - if (tmpl->mode && ipv6_addr_any((struct in6_addr*)&x->props.saddr)) { - struct rt6_info *rt; - struct flowi fl_tunnel = { - .nl_u = { - .ip6_u = { - .daddr = *(struct in6_addr *)daddr, - } - } - }; - if (!xfrm_dst_lookup((struct xfrm_dst **)&rt, - &fl_tunnel, AF_INET6)) { - ipv6_get_saddr(&rt->u.dst, (struct in6_addr *)daddr, - (struct in6_addr *)&x->props.saddr); - dst_release(&rt->u.dst); - } - } x->props.mode = tmpl->mode; x->props.reqid = tmpl->reqid; x->props.family = AF_INET6; } -static struct xfrm_state * -__xfrm6_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto) +static int +__xfrm6_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n) { - unsigned h = __xfrm6_spi_hash(daddr, spi, proto); - struct xfrm_state *x; - - list_for_each_entry(x, xfrm6_state_afinfo.state_byspi+h, byspi) { - if (x->props.family == AF_INET6 && - spi == x->id.spi && - ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)x->id.daddr.a6) && - proto == x->id.proto) { - xfrm_state_hold(x); - return x; + int i; + int j = 0; + + /* Rule 1: select IPsec transport except AH */ + for (i = 0; i < n; i++) { + if (src[i]->props.mode == XFRM_MODE_TRANSPORT && + src[i]->id.proto != IPPROTO_AH) { + dst[j++] = src[i]; + src[i] = NULL; + } + } + if (j == n) + goto end; + + /* Rule 2: select MIPv6 RO or inbound trigger */ +#ifdef CONFIG_IPV6_MIP6 + for (i = 0; i < n; i++) { + if (src[i] && + (src[i]->props.mode == XFRM_MODE_ROUTEOPTIMIZATION || + src[i]->props.mode == XFRM_MODE_IN_TRIGGER)) { + dst[j++] = src[i]; + src[i] = NULL; + } + } + if (j == n) + goto end; +#endif + + /* Rule 3: select IPsec transport AH */ + for (i = 0; i < n; i++) { + if (src[i] && + src[i]->props.mode == XFRM_MODE_TRANSPORT && + src[i]->id.proto == IPPROTO_AH) { + dst[j++] = src[i]; + src[i] = NULL; } } - return NULL; + if (j == n) + goto end; + + /* Rule 4: select IPsec tunnel */ + for (i = 0; i < n; i++) { + if (src[i] && + src[i]->props.mode == XFRM_MODE_TUNNEL) { + dst[j++] = src[i]; + src[i] = NULL; + } + } + if (likely(j == n)) + goto end; + + /* Final rule */ + for (i = 0; i < n; i++) { + if (src[i]) { + dst[j++] = src[i]; + src[i] = NULL; + } + } + + end: + return 0; } -static struct xfrm_state * -__xfrm6_find_acq(u8 mode, u32 reqid, u8 proto, - xfrm_address_t *daddr, xfrm_address_t *saddr, - int create) +static int +__xfrm6_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n) { - struct xfrm_state *x, *x0; - unsigned h = __xfrm6_dst_hash(daddr); - - x0 = NULL; - - list_for_each_entry(x, xfrm6_state_afinfo.state_bydst+h, bydst) { - if (x->props.family == AF_INET6 && - ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)x->id.daddr.a6) && - mode == x->props.mode && - proto == x->id.proto && - ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)x->props.saddr.a6) && - reqid == x->props.reqid && - x->km.state == XFRM_STATE_ACQ && - !x->id.spi) { - x0 = x; - break; - } + int i; + int j = 0; + + /* Rule 1: select IPsec transport */ + for (i = 0; i < n; i++) { + if (src[i]->mode == XFRM_MODE_TRANSPORT) { + dst[j++] = src[i]; + src[i] = NULL; + } } - if (!x0 && create && (x0 = xfrm_state_alloc()) != NULL) { - ipv6_addr_copy((struct in6_addr *)x0->sel.daddr.a6, - (struct in6_addr *)daddr); - ipv6_addr_copy((struct in6_addr *)x0->sel.saddr.a6, - (struct in6_addr *)saddr); - x0->sel.prefixlen_d = 128; - x0->sel.prefixlen_s = 128; - ipv6_addr_copy((struct in6_addr *)x0->props.saddr.a6, - (struct in6_addr *)saddr); - x0->km.state = XFRM_STATE_ACQ; - ipv6_addr_copy((struct in6_addr *)x0->id.daddr.a6, - (struct in6_addr *)daddr); - x0->id.proto = proto; - x0->props.family = AF_INET6; - x0->props.mode = mode; - x0->props.reqid = reqid; - x0->lft.hard_add_expires_seconds = XFRM_ACQ_EXPIRES; - xfrm_state_hold(x0); - x0->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ; - add_timer(&x0->timer); - xfrm_state_hold(x0); - list_add_tail(&x0->bydst, xfrm6_state_afinfo.state_bydst+h); - wake_up(&km_waitq); + if (j == n) + goto end; + + /* Rule 2: select MIPv6 RO or inbound trigger */ +#ifdef CONFIG_IPV6_MIP6 + for (i = 0; i < n; i++) { + if (src[i] && + (src[i]->mode == XFRM_MODE_ROUTEOPTIMIZATION || + src[i]->mode == XFRM_MODE_IN_TRIGGER)) { + dst[j++] = src[i]; + src[i] = NULL; + } } - if (x0) - xfrm_state_hold(x0); - return x0; + if (j == n) + goto end; +#endif + + /* Rule 3: select IPsec tunnel */ + for (i = 0; i < n; i++) { + if (src[i] && + src[i]->mode == XFRM_MODE_TUNNEL) { + dst[j++] = src[i]; + src[i] = NULL; + } + } + if (likely(j == n)) + goto end; + + /* Final rule */ + for (i = 0; i < n; i++) { + if (src[i]) { + dst[j++] = src[i]; + src[i] = NULL; + } + } + + end: + return 0; } static struct xfrm_state_afinfo xfrm6_state_afinfo = { .family = AF_INET6, .init_tempsel = __xfrm6_init_tempsel, - .state_lookup = __xfrm6_state_lookup, - .find_acq = __xfrm6_find_acq, + .tmpl_sort = __xfrm6_tmpl_sort, + .state_sort = __xfrm6_state_sort, }; void __init xfrm6_state_init(void) diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index c8f9369c2a8..59685ee8f70 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -307,7 +307,7 @@ static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, static int xfrm6_tunnel_init_state(struct xfrm_state *x) { - if (!x->props.mode) + if (x->props.mode != XFRM_MODE_TUNNEL) return -EINVAL; if (x->encap) diff --git a/net/key/af_key.c b/net/key/af_key.c index 3a95b2ee469..83b443ddc72 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1731,7 +1731,8 @@ static u32 gen_reqid(void) ++reqid; if (reqid == 0) reqid = IPSEC_MANUAL_REQID_MAX+1; - if (xfrm_policy_walk(check_reqid, (void*)&reqid) != -EEXIST) + if (xfrm_policy_walk(XFRM_POLICY_TYPE_MAIN, check_reqid, + (void*)&reqid) != -EEXIST) return reqid; } while (reqid != start); return 0; @@ -1765,7 +1766,7 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) } /* addresses present only in tunnel mode */ - if (t->mode) { + if (t->mode == XFRM_MODE_TUNNEL) { switch (xp->family) { case AF_INET: sin = (void*)(rq+1); @@ -1997,7 +1998,7 @@ static void pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, i int req_size; req_size = sizeof(struct sadb_x_ipsecrequest); - if (t->mode) + if (t->mode == XFRM_MODE_TUNNEL) req_size += 2*socklen; else size -= 2*socklen; @@ -2013,7 +2014,7 @@ static void pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, i if (t->optional) rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_USE; rq->sadb_x_ipsecrequest_reqid = t->reqid; - if (t->mode) { + if (t->mode == XFRM_MODE_TUNNEL) { switch (xp->family) { case AF_INET: sin = (void*)(rq+1); @@ -2268,7 +2269,8 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg return err; } - xp = xfrm_policy_bysel_ctx(pol->sadb_x_policy_dir-1, &sel, tmp.security, 1); + xp = xfrm_policy_bysel_ctx(XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir-1, + &sel, tmp.security, 1); security_xfrm_policy_free(&tmp); if (xp == NULL) return -ENOENT; @@ -2330,7 +2332,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h if (dir >= XFRM_POLICY_MAX) return -EINVAL; - xp = xfrm_policy_byid(dir, pol->sadb_x_policy_id, + xp = xfrm_policy_byid(XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, hdr->sadb_msg_type == SADB_X_SPDDELETE2); if (xp == NULL) return -ENOENT; @@ -2378,7 +2380,7 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, struct sadb_msg * { struct pfkey_dump_data data = { .skb = skb, .hdr = hdr, .sk = sk }; - return xfrm_policy_walk(dump_sp, &data); + return xfrm_policy_walk(XFRM_POLICY_TYPE_MAIN, dump_sp, &data); } static int key_notify_policy_flush(struct km_event *c) @@ -2405,7 +2407,8 @@ static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, struct sadb_msg { struct km_event c; - xfrm_policy_flush(); + xfrm_policy_flush(XFRM_POLICY_TYPE_MAIN); + c.data.type = XFRM_POLICY_TYPE_MAIN; c.event = XFRM_MSG_FLUSHPOLICY; c.pid = hdr->sadb_msg_pid; c.seq = hdr->sadb_msg_seq; @@ -2667,6 +2670,9 @@ static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c) static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) { + if (xp && xp->type != XFRM_POLICY_TYPE_MAIN) + return 0; + switch (c->event) { case XFRM_MSG_POLEXPIRE: return key_notify_policy_expire(xp, c); @@ -2675,6 +2681,8 @@ static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_e case XFRM_MSG_UPDPOLICY: return key_notify_policy(xp, dir, c); case XFRM_MSG_FLUSHPOLICY: + if (c->data.type != XFRM_POLICY_TYPE_MAIN) + break; return key_notify_policy_flush(c); default: printk("pfkey: Unknown policy event %d\n", c->event); @@ -2708,6 +2716,9 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct #endif int sockaddr_size; int size; + struct sadb_x_sec_ctx *sec_ctx; + struct xfrm_sec_ctx *xfrm_ctx; + int ctx_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) @@ -2723,6 +2734,11 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct else if (x->id.proto == IPPROTO_ESP) size += count_esp_combs(t); + if ((xfrm_ctx = x->security)) { + ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); + size += sizeof(struct sadb_x_sec_ctx) + ctx_size; + } + skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; @@ -2818,17 +2834,31 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct else if (x->id.proto == IPPROTO_ESP) dump_esp_combs(skb, t); + /* security context */ + if (xfrm_ctx) { + sec_ctx = (struct sadb_x_sec_ctx *) skb_put(skb, + sizeof(struct sadb_x_sec_ctx) + ctx_size); + sec_ctx->sadb_x_sec_len = + (sizeof(struct sadb_x_sec_ctx) + ctx_size) / sizeof(uint64_t); + sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; + sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; + sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; + sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; + memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, + xfrm_ctx->ctx_len); + } + return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL); } -static struct xfrm_policy *pfkey_compile_policy(u16 family, int opt, +static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt, u8 *data, int len, int *dir) { struct xfrm_policy *xp; struct sadb_x_policy *pol = (struct sadb_x_policy*)data; struct sadb_x_sec_ctx *sec_ctx; - switch (family) { + switch (sk->sk_family) { case AF_INET: if (opt != IP_IPSEC_POLICY) { *dir = -EOPNOTSUPP; @@ -2869,7 +2899,7 @@ static struct xfrm_policy *pfkey_compile_policy(u16 family, int opt, xp->lft.hard_byte_limit = XFRM_INF; xp->lft.soft_packet_limit = XFRM_INF; xp->lft.hard_packet_limit = XFRM_INF; - xp->family = family; + xp->family = sk->sk_family; xp->xfrm_nr = 0; if (pol->sadb_x_policy_type == IPSEC_POLICY_IPSEC && @@ -2885,8 +2915,10 @@ static struct xfrm_policy *pfkey_compile_policy(u16 family, int opt, p += pol->sadb_x_policy_len*8; sec_ctx = (struct sadb_x_sec_ctx *)p; if (len < pol->sadb_x_policy_len*8 + - sec_ctx->sadb_x_sec_len) + sec_ctx->sadb_x_sec_len) { + *dir = -EINVAL; goto out; + } if ((*dir = verify_sec_ctx_len(p))) goto out; uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx); @@ -2896,6 +2928,11 @@ static struct xfrm_policy *pfkey_compile_policy(u16 family, int opt, if (*dir) goto out; } + else { + *dir = security_xfrm_sock_policy_alloc(xp, sk); + if (*dir) + goto out; + } *dir = pol->sadb_x_policy_dir-1; return xp; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index a9894ddfd72..0a28d2c5c44 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -148,6 +148,18 @@ config NETFILTER_XT_TARGET_CONNMARK <file:Documentation/modules.txt>. The module will be called ipt_CONNMARK.o. If unsure, say `N'. +config NETFILTER_XT_TARGET_DSCP + tristate '"DSCP" target support' + depends on NETFILTER_XTABLES + depends on IP_NF_MANGLE || IP6_NF_MANGLE + help + This option adds a `DSCP' target, which allows you to manipulate + the IPv4/IPv6 header DSCP field (differentiated services codepoint). + + The DSCP field can have any value between 0x0 and 0x3f inclusive. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_MARK tristate '"MARK" target support' depends on NETFILTER_XTABLES @@ -263,6 +275,17 @@ config NETFILTER_XT_MATCH_DCCP If you want to compile it as a module, say M here and read <file:Documentation/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_DSCP + tristate '"DSCP" match support' + depends on NETFILTER_XTABLES + help + This option adds a `DSCP' match, which allows you to match against + the IPv4/IPv6 header DSCP field (differentiated services codepoint). + + The DSCP field can have any value between 0x0 and 0x3f inclusive. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_MATCH_ESP tristate '"ESP" match support' depends on NETFILTER_XTABLES diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 6fa4b758045..a74be492fd0 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o # targets obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o obj-$(CONFIG_NETFILTER_XT_TARGET_CONNMARK) += xt_CONNMARK.o +obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o obj-$(CONFIG_NETFILTER_XT_TARGET_MARK) += xt_MARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o obj-$(CONFIG_NETFILTER_XT_TARGET_NOTRACK) += xt_NOTRACK.o @@ -37,6 +38,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNMARK) += xt_connmark.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o +obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 5d29d5e2362..d80b935b3a9 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -182,7 +182,7 @@ next_hook: ret = -EPERM; } else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) { NFDEBUG("nf_hook: Verdict = QUEUE.\n"); - if (!nf_queue(pskb, elem, pf, hook, indev, outdev, okfn, + if (!nf_queue(*pskb, elem, pf, hook, indev, outdev, okfn, verdict >> NF_VERDICT_BITS)) goto next_hook; } @@ -222,6 +222,28 @@ copy_skb: } EXPORT_SYMBOL(skb_make_writable); +u_int16_t nf_csum_update(u_int32_t oldval, u_int32_t newval, u_int32_t csum) +{ + u_int32_t diff[] = { oldval, newval }; + + return csum_fold(csum_partial((char *)diff, sizeof(diff), ~csum)); +} +EXPORT_SYMBOL(nf_csum_update); + +u_int16_t nf_proto_csum_update(struct sk_buff *skb, + u_int32_t oldval, u_int32_t newval, + u_int16_t csum, int pseudohdr) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) { + csum = nf_csum_update(oldval, newval, csum); + if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) + skb->csum = nf_csum_update(oldval, newval, skb->csum); + } else if (pseudohdr) + csum = ~nf_csum_update(oldval, newval, ~csum); + + return csum; +} +EXPORT_SYMBOL(nf_proto_csum_update); /* This does not belong here, but locally generated errors need it if connection tracking in use: without this, connection may not be in hash table, and hence diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 8f2261965a6..093b3ddc513 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -57,7 +57,6 @@ #include <net/netfilter/nf_conntrack_protocol.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_core.h> -#include <linux/netfilter_ipv4/listhelp.h> #define NF_CONNTRACK_VERSION "0.5.0" @@ -74,17 +73,17 @@ atomic_t nf_conntrack_count = ATOMIC_INIT(0); void (*nf_conntrack_destroyed)(struct nf_conn *conntrack) = NULL; LIST_HEAD(nf_conntrack_expect_list); -struct nf_conntrack_protocol **nf_ct_protos[PF_MAX]; -struct nf_conntrack_l3proto *nf_ct_l3protos[PF_MAX]; +struct nf_conntrack_protocol **nf_ct_protos[PF_MAX] __read_mostly; +struct nf_conntrack_l3proto *nf_ct_l3protos[PF_MAX] __read_mostly; static LIST_HEAD(helpers); -unsigned int nf_conntrack_htable_size = 0; -int nf_conntrack_max; -struct list_head *nf_conntrack_hash; -static kmem_cache_t *nf_conntrack_expect_cachep; +unsigned int nf_conntrack_htable_size __read_mostly = 0; +int nf_conntrack_max __read_mostly; +struct list_head *nf_conntrack_hash __read_mostly; +static kmem_cache_t *nf_conntrack_expect_cachep __read_mostly; struct nf_conn nf_conntrack_untracked; -unsigned int nf_ct_log_invalid; +unsigned int nf_ct_log_invalid __read_mostly; static LIST_HEAD(unconfirmed); -static int nf_conntrack_vmalloc; +static int nf_conntrack_vmalloc __read_mostly; static unsigned int nf_conntrack_next_id; static unsigned int nf_conntrack_expect_next_id; @@ -539,15 +538,10 @@ void nf_ct_remove_expectations(struct nf_conn *ct) static void clean_from_lists(struct nf_conn *ct) { - unsigned int ho, hr; - DEBUGP("clean_from_lists(%p)\n", ct); ASSERT_WRITE_LOCK(&nf_conntrack_lock); - - ho = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - hr = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); - LIST_DELETE(&nf_conntrack_hash[ho], &ct->tuplehash[IP_CT_DIR_ORIGINAL]); - LIST_DELETE(&nf_conntrack_hash[hr], &ct->tuplehash[IP_CT_DIR_REPLY]); + list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list); + list_del(&ct->tuplehash[IP_CT_DIR_REPLY].list); /* Destroy all pending expectations */ nf_ct_remove_expectations(ct); @@ -617,16 +611,6 @@ static void death_by_timeout(unsigned long ul_conntrack) nf_ct_put(ct); } -static inline int -conntrack_tuple_cmp(const struct nf_conntrack_tuple_hash *i, - const struct nf_conntrack_tuple *tuple, - const struct nf_conn *ignored_conntrack) -{ - ASSERT_READ_LOCK(&nf_conntrack_lock); - return nf_ct_tuplehash_to_ctrack(i) != ignored_conntrack - && nf_ct_tuple_equal(tuple, &i->tuple); -} - struct nf_conntrack_tuple_hash * __nf_conntrack_find(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack) @@ -636,7 +620,8 @@ __nf_conntrack_find(const struct nf_conntrack_tuple *tuple, ASSERT_READ_LOCK(&nf_conntrack_lock); list_for_each_entry(h, &nf_conntrack_hash[hash], list) { - if (conntrack_tuple_cmp(h, tuple, ignored_conntrack)) { + if (nf_ct_tuplehash_to_ctrack(h) != ignored_conntrack && + nf_ct_tuple_equal(tuple, &h->tuple)) { NF_CT_STAT_INC(found); return h; } @@ -667,10 +652,10 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, unsigned int repl_hash) { ct->id = ++nf_conntrack_next_id; - list_prepend(&nf_conntrack_hash[hash], - &ct->tuplehash[IP_CT_DIR_ORIGINAL].list); - list_prepend(&nf_conntrack_hash[repl_hash], - &ct->tuplehash[IP_CT_DIR_REPLY].list); + list_add(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list, + &nf_conntrack_hash[hash]); + list_add(&ct->tuplehash[IP_CT_DIR_REPLY].list, + &nf_conntrack_hash[repl_hash]); } void nf_conntrack_hash_insert(struct nf_conn *ct) @@ -690,7 +675,9 @@ int __nf_conntrack_confirm(struct sk_buff **pskb) { unsigned int hash, repl_hash; + struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; + struct nf_conn_help *help; enum ip_conntrack_info ctinfo; ct = nf_ct_get(*pskb, &ctinfo); @@ -720,41 +707,41 @@ __nf_conntrack_confirm(struct sk_buff **pskb) /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ - if (!LIST_FIND(&nf_conntrack_hash[hash], - conntrack_tuple_cmp, - struct nf_conntrack_tuple_hash *, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, NULL) - && !LIST_FIND(&nf_conntrack_hash[repl_hash], - 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); + list_for_each_entry(h, &nf_conntrack_hash[hash], list) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &h->tuple)) + goto out; + list_for_each_entry(h, &nf_conntrack_hash[repl_hash], list) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, + &h->tuple)) + goto out; - __nf_conntrack_hash_insert(ct, hash, repl_hash); - /* Timer relative to confirmation time, not original - setting time, otherwise we'd get timer wrap in - weird delay cases. */ - ct->timeout.expires += jiffies; - add_timer(&ct->timeout); - atomic_inc(&ct->ct_general.use); - set_bit(IPS_CONFIRMED_BIT, &ct->status); - NF_CT_STAT_INC(insert); - write_unlock_bh(&nf_conntrack_lock); - help = nfct_help(ct); - if (help && help->helper) - nf_conntrack_event_cache(IPCT_HELPER, *pskb); + /* Remove from unconfirmed list */ + list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list); + + __nf_conntrack_hash_insert(ct, hash, repl_hash); + /* Timer relative to confirmation time, not original + setting time, otherwise we'd get timer wrap in + weird delay cases. */ + ct->timeout.expires += jiffies; + add_timer(&ct->timeout); + atomic_inc(&ct->ct_general.use); + set_bit(IPS_CONFIRMED_BIT, &ct->status); + NF_CT_STAT_INC(insert); + write_unlock_bh(&nf_conntrack_lock); + 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) || - test_bit(IPS_DST_NAT_DONE_BIT, &ct->status)) - nf_conntrack_event_cache(IPCT_NATINFO, *pskb); + if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) || + test_bit(IPS_DST_NAT_DONE_BIT, &ct->status)) + nf_conntrack_event_cache(IPCT_NATINFO, *pskb); #endif - nf_conntrack_event_cache(master_ct(ct) ? - IPCT_RELATED : IPCT_NEW, *pskb); - return NF_ACCEPT; - } + nf_conntrack_event_cache(master_ct(ct) ? + IPCT_RELATED : IPCT_NEW, *pskb); + return NF_ACCEPT; +out: NF_CT_STAT_INC(insert_failed); write_unlock_bh(&nf_conntrack_lock); return NF_DROP; @@ -777,24 +764,21 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, /* There's a small race here where we may free a just-assured connection. Too bad: we're in trouble anyway. */ -static inline int unreplied(const struct nf_conntrack_tuple_hash *i) -{ - return !(test_bit(IPS_ASSURED_BIT, - &nf_ct_tuplehash_to_ctrack(i)->status)); -} - static int early_drop(struct list_head *chain) { /* Traverse backwards: gives us oldest, which is roughly LRU */ struct nf_conntrack_tuple_hash *h; - struct nf_conn *ct = NULL; + struct nf_conn *ct = NULL, *tmp; int dropped = 0; read_lock_bh(&nf_conntrack_lock); - h = LIST_FIND_B(chain, unreplied, struct nf_conntrack_tuple_hash *); - if (h) { - ct = nf_ct_tuplehash_to_ctrack(h); - atomic_inc(&ct->ct_general.use); + list_for_each_entry_reverse(h, chain, list) { + tmp = nf_ct_tuplehash_to_ctrack(h); + if (!test_bit(IPS_ASSURED_BIT, &tmp->status)) { + ct = tmp; + atomic_inc(&ct->ct_general.use); + break; + } } read_unlock_bh(&nf_conntrack_lock); @@ -810,18 +794,16 @@ static int early_drop(struct list_head *chain) return dropped; } -static inline int helper_cmp(const struct nf_conntrack_helper *i, - const struct nf_conntrack_tuple *rtuple) -{ - return nf_ct_tuple_mask_cmp(rtuple, &i->tuple, &i->mask); -} - static struct nf_conntrack_helper * __nf_ct_helper_find(const struct nf_conntrack_tuple *tuple) { - return LIST_FIND(&helpers, helper_cmp, - struct nf_conntrack_helper *, - tuple); + struct nf_conntrack_helper *h; + + list_for_each_entry(h, &helpers, list) { + if (nf_ct_tuple_mask_cmp(tuple, &h->tuple, &h->mask)) + return h; + } + return NULL; } struct nf_conntrack_helper * @@ -866,11 +848,15 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, nf_conntrack_hash_rnd_initted = 1; } + /* We don't want any race condition at early drop stage */ + atomic_inc(&nf_conntrack_count); + if (nf_conntrack_max - && atomic_read(&nf_conntrack_count) >= nf_conntrack_max) { + && atomic_read(&nf_conntrack_count) > nf_conntrack_max) { unsigned int hash = hash_conntrack(orig); /* Try dropping from this hash chain. */ if (!early_drop(&nf_conntrack_hash[hash])) { + atomic_dec(&nf_conntrack_count); if (net_ratelimit()) printk(KERN_WARNING "nf_conntrack: table full, dropping" @@ -921,10 +907,12 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, init_timer(&conntrack->timeout); conntrack->timeout.data = (unsigned long)conntrack; conntrack->timeout.function = death_by_timeout; + read_unlock_bh(&nf_ct_cache_lock); - atomic_inc(&nf_conntrack_count); + return conntrack; out: read_unlock_bh(&nf_ct_cache_lock); + atomic_dec(&nf_conntrack_count); return conntrack; } @@ -1323,7 +1311,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) return ret; } write_lock_bh(&nf_conntrack_lock); - list_prepend(&helpers, me); + list_add(&me->list, &helpers); write_unlock_bh(&nf_conntrack_lock); return 0; @@ -1342,8 +1330,8 @@ __nf_conntrack_helper_find_byname(const char *name) return NULL; } -static inline int unhelp(struct nf_conntrack_tuple_hash *i, - const struct nf_conntrack_helper *me) +static inline void unhelp(struct nf_conntrack_tuple_hash *i, + const struct nf_conntrack_helper *me) { struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); struct nf_conn_help *help = nfct_help(ct); @@ -1352,17 +1340,17 @@ static inline int unhelp(struct nf_conntrack_tuple_hash *i, nf_conntrack_event(IPCT_HELPER, ct); help->helper = NULL; } - return 0; } void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) { unsigned int i; + struct nf_conntrack_tuple_hash *h; struct nf_conntrack_expect *exp, *tmp; /* Need write lock here, to delete helper. */ write_lock_bh(&nf_conntrack_lock); - LIST_DELETE(&helpers, me); + list_del(&me->list); /* Get rid of expectations */ list_for_each_entry_safe(exp, tmp, &nf_conntrack_expect_list, list) { @@ -1374,10 +1362,12 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) } /* Get rid of expecteds, set helpers to NULL. */ - LIST_FIND_W(&unconfirmed, unhelp, struct nf_conntrack_tuple_hash*, me); - for (i = 0; i < nf_conntrack_htable_size; i++) - LIST_FIND_W(&nf_conntrack_hash[i], unhelp, - struct nf_conntrack_tuple_hash *, me); + list_for_each_entry(h, &unconfirmed, list) + unhelp(h, me); + for (i = 0; i < nf_conntrack_htable_size; i++) { + list_for_each_entry(h, &nf_conntrack_hash[i], list) + unhelp(h, me); + } write_unlock_bh(&nf_conntrack_lock); /* Someone could be still looking at the helper in a bh. */ @@ -1510,37 +1500,40 @@ do_iter(const struct nf_conntrack_tuple_hash *i, } /* Bring out ya dead! */ -static struct nf_conntrack_tuple_hash * +static struct nf_conn * get_next_corpse(int (*iter)(struct nf_conn *i, void *data), void *data, unsigned int *bucket) { - struct nf_conntrack_tuple_hash *h = NULL; + struct nf_conntrack_tuple_hash *h; + struct nf_conn *ct; write_lock_bh(&nf_conntrack_lock); for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { - h = LIST_FIND_W(&nf_conntrack_hash[*bucket], do_iter, - struct nf_conntrack_tuple_hash *, iter, data); - if (h) - break; + list_for_each_entry(h, &nf_conntrack_hash[*bucket], list) { + ct = nf_ct_tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; + } } - if (!h) - h = LIST_FIND_W(&unconfirmed, do_iter, - struct nf_conntrack_tuple_hash *, iter, data); - if (h) - atomic_inc(&nf_ct_tuplehash_to_ctrack(h)->ct_general.use); + list_for_each_entry(h, &unconfirmed, list) { + ct = nf_ct_tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; + } + return NULL; +found: + atomic_inc(&nf_ct_tuplehash_to_ctrack(h)->ct_general.use); write_unlock_bh(&nf_conntrack_lock); - - return h; + return ct; } void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), void *data) { - struct nf_conntrack_tuple_hash *h; + struct nf_conn *ct; unsigned int bucket = 0; - while ((h = get_next_corpse(iter, data, &bucket)) != NULL) { - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { /* Time to push up daises... */ if (del_timer(&ct->timeout)) death_by_timeout((unsigned long)ct); diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 960972d225f..0c17a5bd112 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -21,6 +21,7 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/ctype.h> +#include <linux/inet.h> #include <net/checksum.h> #include <net/tcp.h> @@ -111,101 +112,14 @@ static struct ftp_search { }, }; -/* This code is based on inet_pton() in glibc-2.2.4 */ static int get_ipv6_addr(const char *src, size_t dlen, struct in6_addr *dst, u_int8_t term) { - static const char xdigits[] = "0123456789abcdef"; - u_int8_t tmp[16], *tp, *endp, *colonp; - int ch, saw_xdigit; - u_int32_t val; - size_t clen = 0; - - tp = memset(tmp, '\0', sizeof(tmp)); - endp = tp + sizeof(tmp); - colonp = NULL; - - /* Leading :: requires some special handling. */ - if (*src == ':'){ - if (*++src != ':') { - DEBUGP("invalid \":\" at the head of addr\n"); - return 0; - } - clen++; - } - - saw_xdigit = 0; - val = 0; - while ((clen < dlen) && (*src != term)) { - const char *pch; - - ch = tolower(*src++); - clen++; - - pch = strchr(xdigits, ch); - if (pch != NULL) { - val <<= 4; - val |= (pch - xdigits); - if (val > 0xffff) - return 0; - - saw_xdigit = 1; - continue; - } - if (ch != ':') { - DEBUGP("get_ipv6_addr: invalid char. \'%c\'\n", ch); - return 0; - } - - if (!saw_xdigit) { - if (colonp) { - DEBUGP("invalid location of \"::\".\n"); - return 0; - } - colonp = tp; - continue; - } else if (*src == term) { - DEBUGP("trancated IPv6 addr\n"); - return 0; - } - - if (tp + 2 > endp) - return 0; - *tp++ = (u_int8_t) (val >> 8) & 0xff; - *tp++ = (u_int8_t) val & 0xff; - - saw_xdigit = 0; - val = 0; - continue; - } - if (saw_xdigit) { - if (tp + 2 > endp) - return 0; - *tp++ = (u_int8_t) (val >> 8) & 0xff; - *tp++ = (u_int8_t) val & 0xff; - } - if (colonp != NULL) { - /* - * Since some memmove()'s erroneously fail to handle - * overlapping regions, we'll do the shift by hand. - */ - const int n = tp - colonp; - int i; - - if (tp == endp) - return 0; - - for (i = 1; i <= n; i++) { - endp[- i] = colonp[n - i]; - colonp[n - i] = 0; - } - tp = endp; - } - if (tp != endp || (*src != term)) - return 0; - - memcpy(dst->s6_addr, tmp, sizeof(dst->s6_addr)); - return clen; + const char *end; + int ret = in6_pton(src, min_t(size_t, dlen, 0xffff), (u8 *)dst, term, &end); + if (ret > 0) + return (int)(end - src); + return 0; } static int try_number(const char *data, size_t dlen, u_int32_t array[], diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 6527d4e048d..1721f7c78c7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -339,11 +339,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, /* dump everything */ events = ~0UL; group = NFNLGRP_CONNTRACK_NEW; - } else if (events & (IPCT_STATUS | - IPCT_PROTOINFO | - IPCT_HELPER | - IPCT_HELPINFO | - IPCT_NATINFO)) { + } else if (events & (IPCT_STATUS | IPCT_PROTOINFO)) { type = IPCTNL_MSG_CT_NEW; group = NFNLGRP_CONNTRACK_UPDATE; } else @@ -395,6 +391,10 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0) goto nfattr_failure; + if (events & IPCT_MARK + && ctnetlink_dump_mark(skb, ct) < 0) + goto nfattr_failure; + nlh->nlmsg_len = skb->tail - b; nfnetlink_send(skb, 0, group, 0); return NOTIFY_DONE; @@ -455,6 +455,11 @@ restart: cb->args[1] = (unsigned long)ct; goto out; } +#ifdef CONFIG_NF_CT_ACCT + if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == + IPCTNL_MSG_CT_GET_CTRZERO) + memset(&ct->counters, 0, sizeof(ct->counters)); +#endif } if (cb->args[1]) { cb->args[1] = 0; @@ -470,50 +475,6 @@ out: return skb->len; } -#ifdef CONFIG_NF_CT_ACCT -static int -ctnetlink_dump_table_w(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct nf_conn *ct = NULL; - struct nf_conntrack_tuple_hash *h; - struct list_head *i; - u_int32_t *id = (u_int32_t *) &cb->args[1]; - struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh); - u_int8_t l3proto = nfmsg->nfgen_family; - - DEBUGP("entered %s, last bucket=%u id=%u\n", __FUNCTION__, - cb->args[0], *id); - - write_lock_bh(&nf_conntrack_lock); - for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++, *id = 0) { - list_for_each_prev(i, &nf_conntrack_hash[cb->args[0]]) { - h = (struct nf_conntrack_tuple_hash *) i; - if (DIRECTION(h) != IP_CT_DIR_ORIGINAL) - continue; - ct = nf_ct_tuplehash_to_ctrack(h); - if (l3proto && L3PROTO(ct) != l3proto) - continue; - if (ct->id <= *id) - continue; - if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - IPCTNL_MSG_CT_NEW, - 1, ct) < 0) - goto out; - *id = ct->id; - - memset(&ct->counters, 0, sizeof(ct->counters)); - } - } -out: - write_unlock_bh(&nf_conntrack_lock); - - DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id); - - return skb->len; -} -#endif - static inline int ctnetlink_parse_tuple_ip(struct nfattr *attr, struct nf_conntrack_tuple *tuple) { @@ -788,22 +749,14 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_DUMP) { u32 rlen; - if (NFNL_MSG_TYPE(nlh->nlmsg_type) == - IPCTNL_MSG_CT_GET_CTRZERO) { -#ifdef CONFIG_NF_CT_ACCT - if ((*errp = netlink_dump_start(ctnl, skb, nlh, - ctnetlink_dump_table_w, - ctnetlink_done)) != 0) - return -EINVAL; -#else +#ifndef CONFIG_NF_CT_ACCT + if (NFNL_MSG_TYPE(nlh->nlmsg_type) == IPCTNL_MSG_CT_GET_CTRZERO) return -ENOTSUPP; #endif - } else { - if ((*errp = netlink_dump_start(ctnl, skb, nlh, - ctnetlink_dump_table, - ctnetlink_done)) != 0) + if ((*errp = netlink_dump_start(ctnl, skb, nlh, + ctnetlink_dump_table, + ctnetlink_done)) != 0) return -EINVAL; - } rlen = NLMSG_ALIGN(nlh->nlmsg_len); if (rlen > skb->len) @@ -1274,6 +1227,9 @@ static int ctnetlink_expect_event(struct notifier_block *this, } else return NOTIFY_DONE; + if (!nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW)) + return NOTIFY_DONE; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb) return NOTIFY_DONE; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 46bc27e2756..26408bb0955 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -17,7 +17,7 @@ #include <linux/netfilter.h> #include <net/netfilter/nf_conntrack_protocol.h> -unsigned int nf_ct_generic_timeout = 600*HZ; +unsigned int nf_ct_generic_timeout __read_mostly = 600*HZ; static int generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 9bd8a7877fd..af568777372 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -64,13 +64,13 @@ static const char *sctp_conntrack_names[] = { #define HOURS * 60 MINS #define DAYS * 24 HOURS -static unsigned int nf_ct_sctp_timeout_closed = 10 SECS; -static unsigned int nf_ct_sctp_timeout_cookie_wait = 3 SECS; -static unsigned int nf_ct_sctp_timeout_cookie_echoed = 3 SECS; -static unsigned int nf_ct_sctp_timeout_established = 5 DAYS; -static unsigned int nf_ct_sctp_timeout_shutdown_sent = 300 SECS / 1000; -static unsigned int nf_ct_sctp_timeout_shutdown_recd = 300 SECS / 1000; -static unsigned int nf_ct_sctp_timeout_shutdown_ack_sent = 3 SECS; +static unsigned int nf_ct_sctp_timeout_closed __read_mostly = 10 SECS; +static unsigned int nf_ct_sctp_timeout_cookie_wait __read_mostly = 3 SECS; +static unsigned int nf_ct_sctp_timeout_cookie_echoed __read_mostly = 3 SECS; +static unsigned int nf_ct_sctp_timeout_established __read_mostly = 5 DAYS; +static unsigned int nf_ct_sctp_timeout_shutdown_sent __read_mostly = 300 SECS / 1000; +static unsigned int nf_ct_sctp_timeout_shutdown_recd __read_mostly = 300 SECS / 1000; +static unsigned int nf_ct_sctp_timeout_shutdown_ack_sent __read_mostly = 3 SECS; static unsigned int * sctp_timeouts[] = { NULL, /* SCTP_CONNTRACK_NONE */ diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index af8adcba23a..238bbb5b72e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -57,19 +57,19 @@ static DEFINE_RWLOCK(tcp_lock); /* "Be conservative in what you do, be liberal in what you accept from others." If it's non-zero, we mark only out of window RST segments as INVALID. */ -int nf_ct_tcp_be_liberal = 0; +int nf_ct_tcp_be_liberal __read_mostly = 0; /* When connection is picked up from the middle, how many packets are required to pass in each direction when we assume we are in sync - if any side uses window scaling, we lost the game. If it is set to zero, we disable picking up already established connections. */ -int nf_ct_tcp_loose = 3; +int nf_ct_tcp_loose __read_mostly = 3; /* Max number of the retransmitted packets without receiving an (acceptable) ACK from the destination. If this number is reached, a shorter timer will be started. */ -int nf_ct_tcp_max_retrans = 3; +int nf_ct_tcp_max_retrans __read_mostly = 3; /* FIXME: Examine ipfilter's timeouts and conntrack transitions more closely. They're more complex. --RR */ @@ -92,19 +92,19 @@ static const char *tcp_conntrack_names[] = { #define HOURS * 60 MINS #define DAYS * 24 HOURS -unsigned int nf_ct_tcp_timeout_syn_sent = 2 MINS; -unsigned int nf_ct_tcp_timeout_syn_recv = 60 SECS; -unsigned int nf_ct_tcp_timeout_established = 5 DAYS; -unsigned int nf_ct_tcp_timeout_fin_wait = 2 MINS; -unsigned int nf_ct_tcp_timeout_close_wait = 60 SECS; -unsigned int nf_ct_tcp_timeout_last_ack = 30 SECS; -unsigned int nf_ct_tcp_timeout_time_wait = 2 MINS; -unsigned int nf_ct_tcp_timeout_close = 10 SECS; +unsigned int nf_ct_tcp_timeout_syn_sent __read_mostly = 2 MINS; +unsigned int nf_ct_tcp_timeout_syn_recv __read_mostly = 60 SECS; +unsigned int nf_ct_tcp_timeout_established __read_mostly = 5 DAYS; +unsigned int nf_ct_tcp_timeout_fin_wait __read_mostly = 2 MINS; +unsigned int nf_ct_tcp_timeout_close_wait __read_mostly = 60 SECS; +unsigned int nf_ct_tcp_timeout_last_ack __read_mostly = 30 SECS; +unsigned int nf_ct_tcp_timeout_time_wait __read_mostly = 2 MINS; +unsigned int nf_ct_tcp_timeout_close __read_mostly = 10 SECS; /* RFC1122 says the R2 limit should be at least 100 seconds. Linux uses 15 packets as limit, which corresponds to ~13-30min depending on RTO. */ -unsigned int nf_ct_tcp_timeout_max_retrans = 5 MINS; +unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly = 5 MINS; static unsigned int * tcp_timeouts[] = { NULL, /* TCP_CONNTRACK_NONE */ @@ -688,13 +688,15 @@ static int tcp_in_window(struct ip_ct_tcp *state, if (state->last_dir == dir && state->last_seq == seq && state->last_ack == ack - && state->last_end == end) + && state->last_end == end + && state->last_win == win) state->retrans++; else { state->last_dir = dir; state->last_seq = seq; state->last_ack = ack; state->last_end = end; + state->last_win = win; state->retrans = 0; } } @@ -823,8 +825,7 @@ static int tcp_error(struct sk_buff *skb, /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path - * because the semantic of CHECKSUM_HW is different there - * and moreover root might send raw packets. + * because the checksum is assumed to be correct. */ /* FIXME: Source route IP option packets --RR */ if (nf_conntrack_checksum && diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index ae07ebe3ab3..d28981cf9af 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -27,8 +27,8 @@ #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack_protocol.h> -unsigned int nf_ct_udp_timeout = 30*HZ; -unsigned int nf_ct_udp_timeout_stream = 180*HZ; +unsigned int nf_ct_udp_timeout __read_mostly = 30*HZ; +unsigned int nf_ct_udp_timeout_stream __read_mostly = 180*HZ; static int udp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, @@ -131,8 +131,7 @@ static int udp_error(struct sk_buff *skb, unsigned int dataoff, /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path - * because the semantic of CHECKSUM_HW is different there - * and moreover root might send raw packets. + * because the checksum is assumed to be correct. * FIXME: Source route IP option packets --RR */ if (nf_conntrack_checksum && ((pf == PF_INET && hooknum == NF_IP_PRE_ROUTING) || diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4ef83669996..5954f677381 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -37,7 +37,6 @@ #include <net/netfilter/nf_conntrack_protocol.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_helper.h> -#include <linux/netfilter_ipv4/listhelp.h> #if 0 #define DEBUGP printk @@ -428,7 +427,7 @@ static struct file_operations ct_cpu_seq_fops = { /* Sysctl support */ -int nf_conntrack_checksum = 1; +int nf_conntrack_checksum __read_mostly = 1; #ifdef CONFIG_SYSCTL diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 86e392bfe83..a981971ce1d 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -23,7 +23,7 @@ extern unsigned int nf_iterate(struct list_head *head, int hook_thresh); /* nf_queue.c */ -extern int nf_queue(struct sk_buff **skb, +extern int nf_queue(struct sk_buff *skb, struct list_head *elem, int pf, unsigned int hook, struct net_device *indev, diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 662a869593b..4d8936ed581 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -74,13 +74,13 @@ EXPORT_SYMBOL_GPL(nf_unregister_queue_handlers); * Any packet that leaves via this function must come back * through nf_reinject(). */ -int nf_queue(struct sk_buff **skb, - struct list_head *elem, - int pf, unsigned int hook, - struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sk_buff *), - unsigned int queuenum) +static int __nf_queue(struct sk_buff *skb, + struct list_head *elem, + int pf, unsigned int hook, + struct net_device *indev, + struct net_device *outdev, + int (*okfn)(struct sk_buff *), + unsigned int queuenum) { int status; struct nf_info *info; @@ -94,14 +94,14 @@ int nf_queue(struct sk_buff **skb, read_lock(&queue_handler_lock); if (!queue_handler[pf]) { read_unlock(&queue_handler_lock); - kfree_skb(*skb); + kfree_skb(skb); return 1; } afinfo = nf_get_afinfo(pf); if (!afinfo) { read_unlock(&queue_handler_lock); - kfree_skb(*skb); + kfree_skb(skb); return 1; } @@ -109,9 +109,9 @@ int nf_queue(struct sk_buff **skb, if (!info) { if (net_ratelimit()) printk(KERN_ERR "OOM queueing packet %p\n", - *skb); + skb); read_unlock(&queue_handler_lock); - kfree_skb(*skb); + kfree_skb(skb); return 1; } @@ -130,15 +130,15 @@ int nf_queue(struct sk_buff **skb, if (outdev) dev_hold(outdev); #ifdef CONFIG_BRIDGE_NETFILTER - if ((*skb)->nf_bridge) { - physindev = (*skb)->nf_bridge->physindev; + if (skb->nf_bridge) { + physindev = skb->nf_bridge->physindev; if (physindev) dev_hold(physindev); - physoutdev = (*skb)->nf_bridge->physoutdev; + physoutdev = skb->nf_bridge->physoutdev; if (physoutdev) dev_hold(physoutdev); } #endif - afinfo->saveroute(*skb, info); - status = queue_handler[pf]->outfn(*skb, info, queuenum, + afinfo->saveroute(skb, info); + status = queue_handler[pf]->outfn(skb, info, queuenum, queue_handler[pf]->data); read_unlock(&queue_handler_lock); @@ -153,7 +153,7 @@ int nf_queue(struct sk_buff **skb, #endif module_put(info->elem->owner); kfree(info); - kfree_skb(*skb); + kfree_skb(skb); return 1; } @@ -161,6 +161,46 @@ int nf_queue(struct sk_buff **skb, return 1; } +int nf_queue(struct sk_buff *skb, + struct list_head *elem, + int pf, unsigned int hook, + struct net_device *indev, + struct net_device *outdev, + int (*okfn)(struct sk_buff *), + unsigned int queuenum) +{ + struct sk_buff *segs; + + if (!skb_is_gso(skb)) + return __nf_queue(skb, elem, pf, hook, indev, outdev, okfn, + queuenum); + + switch (pf) { + case AF_INET: + skb->protocol = htons(ETH_P_IP); + break; + case AF_INET6: + skb->protocol = htons(ETH_P_IPV6); + break; + } + + segs = skb_gso_segment(skb, 0); + kfree_skb(skb); + if (unlikely(IS_ERR(segs))) + return 1; + + do { + struct sk_buff *nskb = segs->next; + + segs->next = NULL; + if (!__nf_queue(segs, elem, pf, hook, indev, outdev, okfn, + queuenum)) + kfree_skb(segs); + segs = nskb; + } while (segs); + return 1; +} + void nf_reinject(struct sk_buff *skb, struct nf_info *info, unsigned int verdict) { @@ -224,9 +264,9 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info, case NF_STOLEN: break; case NF_QUEUE: - if (!nf_queue(&skb, elem, info->pf, info->hook, - info->indev, info->outdev, info->okfn, - verdict >> NF_VERDICT_BITS)) + if (!__nf_queue(skb, elem, info->pf, info->hook, + info->indev, info->outdev, info->okfn, + verdict >> NF_VERDICT_BITS)) goto next_hook; break; default: diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 49ef41e34c4..8eb2473d83e 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -377,9 +377,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, break; case NFQNL_COPY_PACKET: - if (entskb->ip_summed == CHECKSUM_HW && - (*errp = skb_checksum_help(entskb, - outdev == NULL))) { + if ((entskb->ip_summed == CHECKSUM_PARTIAL || + entskb->ip_summed == CHECKSUM_COMPLETE) && + (*errp = skb_checksum_help(entskb))) { spin_unlock_bh(&queue->lock); return NULL; } @@ -584,7 +584,7 @@ nfqnl_enqueue_packet(struct sk_buff *skb, struct nf_info *info, queue->queue_dropped++; status = -ENOSPC; if (net_ratelimit()) - printk(KERN_WARNING "ip_queue: full at %d entries, " + printk(KERN_WARNING "nf_queue: full at %d entries, " "dropping packets(s). Dropped: %d\n", queue->queue_total, queue->queue_dropped); goto err_out_free_nskb; @@ -635,7 +635,7 @@ nfqnl_mangle(void *data, int data_len, struct nfqnl_queue_entry *e) diff, GFP_ATOMIC); if (newskb == NULL) { - printk(KERN_WARNING "ip_queue: OOM " + printk(KERN_WARNING "nf_queue: OOM " "in mangle, dropping packet\n"); return -ENOMEM; } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 174e8f97009..58522fc65d3 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -81,12 +81,42 @@ xt_unregister_target(struct xt_target *target) int af = target->family; mutex_lock(&xt[af].mutex); - LIST_DELETE(&xt[af].target, target); + list_del(&target->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_target); int +xt_register_targets(struct xt_target *target, unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = xt_register_target(&target[i]); + if (err) + goto err; + } + return err; + +err: + if (i > 0) + xt_unregister_targets(target, i); + return err; +} +EXPORT_SYMBOL(xt_register_targets); + +void +xt_unregister_targets(struct xt_target *target, unsigned int n) +{ + unsigned int i; + + for (i = 0; i < n; i++) + xt_unregister_target(&target[i]); +} +EXPORT_SYMBOL(xt_unregister_targets); + +int xt_register_match(struct xt_match *match) { int ret, af = match->family; @@ -108,11 +138,41 @@ xt_unregister_match(struct xt_match *match) int af = match->family; mutex_lock(&xt[af].mutex); - LIST_DELETE(&xt[af].match, match); + list_del(&match->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_match); +int +xt_register_matches(struct xt_match *match, unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = xt_register_match(&match[i]); + if (err) + goto err; + } + return err; + +err: + if (i > 0) + xt_unregister_matches(match, i); + return err; +} +EXPORT_SYMBOL(xt_register_matches); + +void +xt_unregister_matches(struct xt_match *match, unsigned int n) +{ + unsigned int i; + + for (i = 0; i < n; i++) + xt_unregister_match(&match[i]); +} +EXPORT_SYMBOL(xt_unregister_matches); + /* * These are weird, but module loading must not be done with mutex @@ -273,52 +333,65 @@ int xt_check_match(const struct xt_match *match, unsigned short family, EXPORT_SYMBOL_GPL(xt_check_match); #ifdef CONFIG_COMPAT -int xt_compat_match(void *match, void **dstptr, int *size, int convert) +int xt_compat_match_offset(struct xt_match *match) { - struct xt_match *m; - struct compat_xt_entry_match *pcompat_m; - struct xt_entry_match *pm; - u_int16_t msize; - int off, ret; + u_int16_t csize = match->compatsize ? : match->matchsize; + return XT_ALIGN(match->matchsize) - COMPAT_XT_ALIGN(csize); +} +EXPORT_SYMBOL_GPL(xt_compat_match_offset); - ret = 0; - m = ((struct xt_entry_match *)match)->u.kernel.match; - off = XT_ALIGN(m->matchsize) - COMPAT_XT_ALIGN(m->matchsize); - switch (convert) { - case COMPAT_TO_USER: - pm = (struct xt_entry_match *)match; - msize = pm->u.user.match_size; - if (copy_to_user(*dstptr, pm, msize)) { - ret = -EFAULT; - break; - } - msize -= off; - if (put_user(msize, (u_int16_t *)*dstptr)) - ret = -EFAULT; - *size -= off; - *dstptr += msize; - break; - case COMPAT_FROM_USER: - pcompat_m = (struct compat_xt_entry_match *)match; - pm = (struct xt_entry_match *)*dstptr; - msize = pcompat_m->u.user.match_size; - memcpy(pm, pcompat_m, msize); - msize += off; - pm->u.user.match_size = msize; - *size += off; - *dstptr += msize; - break; - case COMPAT_CALC_SIZE: - *size += off; - break; - default: - ret = -ENOPROTOOPT; - break; +void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, + int *size) +{ + struct xt_match *match = m->u.kernel.match; + struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; + int pad, off = xt_compat_match_offset(match); + u_int16_t msize = cm->u.user.match_size; + + m = *dstptr; + memcpy(m, cm, sizeof(*cm)); + if (match->compat_from_user) + match->compat_from_user(m->data, cm->data); + else + memcpy(m->data, cm->data, msize - sizeof(*cm)); + pad = XT_ALIGN(match->matchsize) - match->matchsize; + if (pad > 0) + memset(m->data + match->matchsize, 0, pad); + + msize += off; + m->u.user.match_size = msize; + + *size += off; + *dstptr += msize; +} +EXPORT_SYMBOL_GPL(xt_compat_match_from_user); + +int xt_compat_match_to_user(struct xt_entry_match *m, void __user **dstptr, + int *size) +{ + struct xt_match *match = m->u.kernel.match; + struct compat_xt_entry_match __user *cm = *dstptr; + int off = xt_compat_match_offset(match); + u_int16_t msize = m->u.user.match_size - off; + + if (copy_to_user(cm, m, sizeof(*cm)) || + put_user(msize, &cm->u.user.match_size)) + return -EFAULT; + + if (match->compat_to_user) { + if (match->compat_to_user((void __user *)cm->data, m->data)) + return -EFAULT; + } else { + if (copy_to_user(cm->data, m->data, msize - sizeof(*cm))) + return -EFAULT; } - return ret; + + *size -= off; + *dstptr += msize; + return 0; } -EXPORT_SYMBOL_GPL(xt_compat_match); -#endif +EXPORT_SYMBOL_GPL(xt_compat_match_to_user); +#endif /* CONFIG_COMPAT */ int xt_check_target(const struct xt_target *target, unsigned short family, unsigned int size, const char *table, unsigned int hook_mask, @@ -350,51 +423,64 @@ int xt_check_target(const struct xt_target *target, unsigned short family, EXPORT_SYMBOL_GPL(xt_check_target); #ifdef CONFIG_COMPAT -int xt_compat_target(void *target, void **dstptr, int *size, int convert) +int xt_compat_target_offset(struct xt_target *target) { - struct xt_target *t; - struct compat_xt_entry_target *pcompat; - struct xt_entry_target *pt; - u_int16_t tsize; - int off, ret; + u_int16_t csize = target->compatsize ? : target->targetsize; + return XT_ALIGN(target->targetsize) - COMPAT_XT_ALIGN(csize); +} +EXPORT_SYMBOL_GPL(xt_compat_target_offset); - ret = 0; - t = ((struct xt_entry_target *)target)->u.kernel.target; - off = XT_ALIGN(t->targetsize) - COMPAT_XT_ALIGN(t->targetsize); - switch (convert) { - case COMPAT_TO_USER: - pt = (struct xt_entry_target *)target; - tsize = pt->u.user.target_size; - if (copy_to_user(*dstptr, pt, tsize)) { - ret = -EFAULT; - break; - } - tsize -= off; - if (put_user(tsize, (u_int16_t *)*dstptr)) - ret = -EFAULT; - *size -= off; - *dstptr += tsize; - break; - case COMPAT_FROM_USER: - pcompat = (struct compat_xt_entry_target *)target; - pt = (struct xt_entry_target *)*dstptr; - tsize = pcompat->u.user.target_size; - memcpy(pt, pcompat, tsize); - tsize += off; - pt->u.user.target_size = tsize; - *size += off; - *dstptr += tsize; - break; - case COMPAT_CALC_SIZE: - *size += off; - break; - default: - ret = -ENOPROTOOPT; - break; +void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, + int *size) +{ + struct xt_target *target = t->u.kernel.target; + struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; + int pad, off = xt_compat_target_offset(target); + u_int16_t tsize = ct->u.user.target_size; + + t = *dstptr; + memcpy(t, ct, sizeof(*ct)); + if (target->compat_from_user) + target->compat_from_user(t->data, ct->data); + else + memcpy(t->data, ct->data, tsize - sizeof(*ct)); + pad = XT_ALIGN(target->targetsize) - target->targetsize; + if (pad > 0) + memset(t->data + target->targetsize, 0, pad); + + tsize += off; + t->u.user.target_size = tsize; + + *size += off; + *dstptr += tsize; +} +EXPORT_SYMBOL_GPL(xt_compat_target_from_user); + +int xt_compat_target_to_user(struct xt_entry_target *t, void __user **dstptr, + int *size) +{ + struct xt_target *target = t->u.kernel.target; + struct compat_xt_entry_target __user *ct = *dstptr; + int off = xt_compat_target_offset(target); + u_int16_t tsize = t->u.user.target_size - off; + + if (copy_to_user(ct, t, sizeof(*ct)) || + put_user(tsize, &ct->u.user.target_size)) + return -EFAULT; + + if (target->compat_to_user) { + if (target->compat_to_user((void __user *)ct->data, t->data)) + return -EFAULT; + } else { + if (copy_to_user(ct->data, t->data, tsize - sizeof(*ct))) + return -EFAULT; } - return ret; + + *size -= off; + *dstptr += tsize; + return 0; } -EXPORT_SYMBOL_GPL(xt_compat_target); +EXPORT_SYMBOL_GPL(xt_compat_target_to_user); #endif struct xt_table_info *xt_alloc_table_info(unsigned int size) @@ -515,15 +601,18 @@ int xt_register_table(struct xt_table *table, { int ret; struct xt_table_info *private; + struct xt_table *t; ret = mutex_lock_interruptible(&xt[table->af].mutex); if (ret != 0) return ret; /* Don't autoload: we'd eat our tail... */ - if (list_named_find(&xt[table->af].tables, table->name)) { - ret = -EEXIST; - goto unlock; + list_for_each_entry(t, &xt[table->af].tables, list) { + if (strcmp(t->name, table->name) == 0) { + ret = -EEXIST; + goto unlock; + } } /* Simplifies replace_table code. */ @@ -538,7 +627,7 @@ int xt_register_table(struct xt_table *table, /* save number of initial entries */ private->initial_entries = private->number; - list_prepend(&xt[table->af].tables, table); + list_add(&table->list, &xt[table->af].tables); ret = 0; unlock: @@ -553,7 +642,7 @@ void *xt_unregister_table(struct xt_table *table) mutex_lock(&xt[table->af].mutex); private = table->private; - LIST_DELETE(&xt[table->af].tables, table); + list_del(&table->list); mutex_unlock(&xt[table->af].mutex); return private; diff --git a/net/netfilter/xt_CLASSIFY.c b/net/netfilter/xt_CLASSIFY.c index e54e5773001..50de965bb10 100644 --- a/net/netfilter/xt_CLASSIFY.c +++ b/net/netfilter/xt_CLASSIFY.c @@ -29,8 +29,7 @@ target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct xt_classify_target_info *clinfo = targinfo; @@ -40,47 +39,41 @@ target(struct sk_buff **pskb, return XT_CONTINUE; } -static struct xt_target classify_reg = { - .name = "CLASSIFY", - .target = target, - .targetsize = sizeof(struct xt_classify_target_info), - .table = "mangle", - .hooks = (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_FORWARD) | - (1 << NF_IP_POST_ROUTING), - .family = AF_INET, - .me = THIS_MODULE, +static struct xt_target xt_classify_target[] = { + { + .family = AF_INET, + .name = "CLASSIFY", + .target = target, + .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, + }, + { + .name = "CLASSIFY", + .family = AF_INET6, + .target = target, + .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, - .targetsize = sizeof(struct xt_classify_target_info), - .table = "mangle", - .hooks = (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_FORWARD) | - (1 << NF_IP_POST_ROUTING), - .family = AF_INET6, - .me = THIS_MODULE, -}; - static int __init xt_classify_init(void) { - int ret; - - ret = xt_register_target(&classify_reg); - if (ret) - return ret; - - ret = xt_register_target(&classify6_reg); - if (ret) - xt_unregister_target(&classify_reg); - - return ret; + return xt_register_targets(xt_classify_target, + ARRAY_SIZE(xt_classify_target)); } static void __exit xt_classify_fini(void) { - xt_unregister_target(&classify_reg); - xt_unregister_target(&classify6_reg); + xt_unregister_targets(xt_classify_target, + ARRAY_SIZE(xt_classify_target)); } module_init(xt_classify_init); diff --git a/net/netfilter/xt_CONNMARK.c b/net/netfilter/xt_CONNMARK.c index 60c375d36f0..c01524f817f 100644 --- a/net/netfilter/xt_CONNMARK.c +++ b/net/netfilter/xt_CONNMARK.c @@ -38,8 +38,7 @@ target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct xt_connmark_target_info *markinfo = targinfo; u_int32_t diff; @@ -49,24 +48,37 @@ target(struct sk_buff **pskb, u_int32_t *ctmark = nf_ct_get_mark(*pskb, &ctinfo); if (ctmark) { - switch(markinfo->mode) { - case XT_CONNMARK_SET: - newmark = (*ctmark & ~markinfo->mask) | markinfo->mark; - if (newmark != *ctmark) - *ctmark = newmark; - break; - case XT_CONNMARK_SAVE: - newmark = (*ctmark & ~markinfo->mask) | ((*pskb)->nfmark & markinfo->mask); - if (*ctmark != newmark) - *ctmark = newmark; - break; - case XT_CONNMARK_RESTORE: - nfmark = (*pskb)->nfmark; - diff = (*ctmark ^ nfmark) & markinfo->mask; - if (diff != 0) - (*pskb)->nfmark = nfmark ^ diff; - break; - } + switch(markinfo->mode) { + case XT_CONNMARK_SET: + newmark = (*ctmark & ~markinfo->mask) | markinfo->mark; + if (newmark != *ctmark) { + *ctmark = newmark; +#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE) + ip_conntrack_event_cache(IPCT_MARK, *pskb); +#else + nf_conntrack_event_cache(IPCT_MARK, *pskb); +#endif + } + break; + case XT_CONNMARK_SAVE: + newmark = (*ctmark & ~markinfo->mask) | + ((*pskb)->nfmark & markinfo->mask); + if (*ctmark != newmark) { + *ctmark = newmark; +#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE) + ip_conntrack_event_cache(IPCT_MARK, *pskb); +#else + nf_conntrack_event_cache(IPCT_MARK, *pskb); +#endif + } + break; + case XT_CONNMARK_RESTORE: + nfmark = (*pskb)->nfmark; + diff = (*ctmark ^ nfmark) & markinfo->mask; + if (diff != 0) + (*pskb)->nfmark = nfmark ^ diff; + break; + } } return XT_CONTINUE; @@ -77,65 +89,91 @@ 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 (matchinfo->mode == XT_CONNMARK_RESTORE) { - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "CONNMARK: restore can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } + if (strcmp(tablename, "mangle") != 0) { + printk(KERN_WARNING "CONNMARK: restore can only be " + "called from \"mangle\" table, not \"%s\"\n", + tablename); + return 0; + } } - if (matchinfo->mark > 0xffffffff || matchinfo->mask > 0xffffffff) { printk(KERN_WARNING "CONNMARK: Only supports 32bit mark\n"); return 0; } - return 1; } -static struct xt_target connmark_reg = { - .name = "CONNMARK", - .target = target, - .targetsize = sizeof(struct xt_connmark_target_info), - .checkentry = checkentry, - .family = AF_INET, - .me = THIS_MODULE +#ifdef CONFIG_COMPAT +struct compat_xt_connmark_target_info { + compat_ulong_t mark, mask; + u_int8_t mode; + u_int8_t __pad1; + u_int16_t __pad2; }; -static struct xt_target connmark6_reg = { - .name = "CONNMARK", - .target = target, - .targetsize = sizeof(struct xt_connmark_target_info), - .checkentry = checkentry, - .family = AF_INET6, - .me = THIS_MODULE +static void compat_from_user(void *dst, void *src) +{ + struct compat_xt_connmark_target_info *cm = src; + struct xt_connmark_target_info m = { + .mark = cm->mark, + .mask = cm->mask, + .mode = cm->mode, + }; + memcpy(dst, &m, sizeof(m)); +} + +static int compat_to_user(void __user *dst, void *src) +{ + struct xt_connmark_target_info *m = src; + struct compat_xt_connmark_target_info cm = { + .mark = m->mark, + .mask = m->mask, + .mode = m->mode, + }; + return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; +} +#endif /* CONFIG_COMPAT */ + +static struct xt_target xt_connmark_target[] = { + { + .name = "CONNMARK", + .family = AF_INET, + .checkentry = checkentry, + .target = target, + .targetsize = sizeof(struct xt_connmark_target_info), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct compat_xt_connmark_target_info), + .compat_from_user = compat_from_user, + .compat_to_user = compat_to_user, +#endif + .me = THIS_MODULE + }, + { + .name = "CONNMARK", + .family = AF_INET6, + .checkentry = checkentry, + .target = target, + .targetsize = sizeof(struct xt_connmark_target_info), + .me = THIS_MODULE + }, }; static int __init xt_connmark_init(void) { - int ret; - need_conntrack(); - - ret = xt_register_target(&connmark_reg); - if (ret) - return ret; - - ret = xt_register_target(&connmark6_reg); - if (ret) - xt_unregister_target(&connmark_reg); - - return ret; + return xt_register_targets(xt_connmark_target, + ARRAY_SIZE(xt_connmark_target)); } static void __exit xt_connmark_fini(void) { - xt_unregister_target(&connmark_reg); - xt_unregister_target(&connmark6_reg); + xt_unregister_targets(xt_connmark_target, + ARRAY_SIZE(xt_connmark_target)); } module_init(xt_connmark_init); diff --git a/net/netfilter/xt_CONNSECMARK.c b/net/netfilter/xt_CONNSECMARK.c index 8c011e02076..46738626667 100644 --- a/net/netfilter/xt_CONNSECMARK.c +++ b/net/netfilter/xt_CONNSECMARK.c @@ -66,7 +66,7 @@ static void secmark_restore(struct sk_buff *skb) static unsigned int 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 void *targinfo) { struct sk_buff *skb = *pskb; const struct xt_connsecmark_target_info *info = targinfo; @@ -89,7 +89,7 @@ static unsigned int target(struct sk_buff **pskb, const struct net_device *in, static int checkentry(const char *tablename, const void *entry, const struct xt_target *target, void *targinfo, - unsigned int targinfosize, unsigned int hook_mask) + unsigned int hook_mask) { struct xt_connsecmark_target_info *info = targinfo; @@ -106,49 +106,38 @@ static int checkentry(const char *tablename, const void *entry, return 1; } -static struct xt_target ipt_connsecmark_reg = { - .name = "CONNSECMARK", - .target = target, - .targetsize = sizeof(struct xt_connsecmark_target_info), - .table = "mangle", - .checkentry = checkentry, - .me = THIS_MODULE, - .family = AF_INET, - .revision = 0, -}; - -static struct xt_target ip6t_connsecmark_reg = { - .name = "CONNSECMARK", - .target = target, - .targetsize = sizeof(struct xt_connsecmark_target_info), - .table = "mangle", - .checkentry = checkentry, - .me = THIS_MODULE, - .family = AF_INET6, - .revision = 0, +static struct xt_target xt_connsecmark_target[] = { + { + .name = "CONNSECMARK", + .family = AF_INET, + .checkentry = checkentry, + .target = target, + .targetsize = sizeof(struct xt_connsecmark_target_info), + .table = "mangle", + .me = THIS_MODULE, + }, + { + .name = "CONNSECMARK", + .family = AF_INET6, + .checkentry = checkentry, + .target = target, + .targetsize = sizeof(struct xt_connsecmark_target_info), + .table = "mangle", + .me = THIS_MODULE, + }, }; static int __init xt_connsecmark_init(void) { - int err; - need_conntrack(); - - err = xt_register_target(&ipt_connsecmark_reg); - if (err) - return err; - - err = xt_register_target(&ip6t_connsecmark_reg); - if (err) - xt_unregister_target(&ipt_connsecmark_reg); - - return err; + return xt_register_targets(xt_connsecmark_target, + ARRAY_SIZE(xt_connsecmark_target)); } static void __exit xt_connsecmark_fini(void) { - xt_unregister_target(&ip6t_connsecmark_reg); - xt_unregister_target(&ipt_connsecmark_reg); + xt_unregister_targets(xt_connsecmark_target, + ARRAY_SIZE(xt_connsecmark_target)); } module_init(xt_connsecmark_init); diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c new file mode 100644 index 00000000000..a7cc75aeb38 --- /dev/null +++ b/net/netfilter/xt_DSCP.c @@ -0,0 +1,118 @@ +/* x_tables module for setting the IPv4/IPv6 DSCP field, Version 1.8 + * + * (C) 2002 by Harald Welte <laforge@netfilter.org> + * based on ipt_FTOS.c (C) 2000 by Matthew G. Marsh <mgm@paktronix.com> + * + * 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. + * + * See RFC2474 for a description of the DSCP field within the IP Header. + * + * xt_DSCP.c,v 1.8 2002/08/06 18:41:57 laforge Exp +*/ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <net/dsfield.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_DSCP.h> + +MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); +MODULE_DESCRIPTION("x_tables DSCP modification module"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_DSCP"); +MODULE_ALIAS("ip6t_DSCP"); + +static unsigned int 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) +{ + const struct xt_DSCP_info *dinfo = targinfo; + u_int8_t dscp = ipv4_get_dsfield((*pskb)->nh.iph) >> XT_DSCP_SHIFT; + + if (dscp != dinfo->dscp) { + if (!skb_make_writable(pskb, sizeof(struct iphdr))) + return NF_DROP; + + ipv4_change_dsfield((*pskb)->nh.iph, (__u8)(~XT_DSCP_MASK), + dinfo->dscp << XT_DSCP_SHIFT); + + } + return XT_CONTINUE; +} + +static unsigned int target6(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) +{ + const struct xt_DSCP_info *dinfo = targinfo; + u_int8_t dscp = ipv6_get_dsfield((*pskb)->nh.ipv6h) >> XT_DSCP_SHIFT; + + if (dscp != dinfo->dscp) { + if (!skb_make_writable(pskb, sizeof(struct ipv6hdr))) + return NF_DROP; + + ipv6_change_dsfield((*pskb)->nh.ipv6h, (__u8)(~XT_DSCP_MASK), + dinfo->dscp << XT_DSCP_SHIFT); + } + return XT_CONTINUE; +} + +static int checkentry(const char *tablename, + const void *e_void, + const struct xt_target *target, + void *targinfo, + unsigned int hook_mask) +{ + const u_int8_t dscp = ((struct xt_DSCP_info *)targinfo)->dscp; + + if ((dscp > XT_DSCP_MAX)) { + printk(KERN_WARNING "DSCP: dscp %x out of range\n", dscp); + return 0; + } + return 1; +} + +static struct xt_target xt_dscp_target[] = { + { + .name = "DSCP", + .family = AF_INET, + .checkentry = checkentry, + .target = target, + .targetsize = sizeof(struct xt_DSCP_info), + .table = "mangle", + .me = THIS_MODULE, + }, + { + .name = "DSCP", + .family = AF_INET6, + .checkentry = checkentry, + .target = target6, + .targetsize = sizeof(struct xt_DSCP_info), + .table = "mangle", + .me = THIS_MODULE, + }, +}; + +static int __init xt_dscp_target_init(void) +{ + return xt_register_targets(xt_dscp_target, ARRAY_SIZE(xt_dscp_target)); +} + +static void __exit xt_dscp_target_fini(void) +{ + xt_unregister_targets(xt_dscp_target, ARRAY_SIZE(xt_dscp_target)); +} + +module_init(xt_dscp_target_init); +module_exit(xt_dscp_target_fini); diff --git a/net/netfilter/xt_MARK.c b/net/netfilter/xt_MARK.c index ee9c34edc76..c6e860a7114 100644 --- a/net/netfilter/xt_MARK.c +++ b/net/netfilter/xt_MARK.c @@ -27,8 +27,7 @@ target_v0(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct xt_mark_target_info *markinfo = targinfo; @@ -44,8 +43,7 @@ target_v1(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct xt_mark_target_info_v1 *markinfo = targinfo; int mark = 0; @@ -76,7 +74,6 @@ 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; @@ -93,7 +90,6 @@ 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; @@ -112,65 +108,81 @@ checkentry_v1(const char *tablename, 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, - .family = AF_INET, - .revision = 0, +#ifdef CONFIG_COMPAT +struct compat_xt_mark_target_info_v1 { + compat_ulong_t mark; + u_int8_t mode; + u_int8_t __pad1; + u_int16_t __pad2; }; -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, - .family = AF_INET, - .revision = 1, -}; +static void compat_from_user_v1(void *dst, void *src) +{ + struct compat_xt_mark_target_info_v1 *cm = src; + struct xt_mark_target_info_v1 m = { + .mark = cm->mark, + .mode = cm->mode, + }; + memcpy(dst, &m, sizeof(m)); +} -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, - .family = AF_INET6, - .revision = 0, +static int compat_to_user_v1(void __user *dst, void *src) +{ + struct xt_mark_target_info_v1 *m = src; + struct compat_xt_mark_target_info_v1 cm = { + .mark = m->mark, + .mode = m->mode, + }; + return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; +} +#endif /* CONFIG_COMPAT */ + +static struct xt_target xt_mark_target[] = { + { + .name = "MARK", + .family = AF_INET, + .revision = 0, + .checkentry = checkentry_v0, + .target = target_v0, + .targetsize = sizeof(struct xt_mark_target_info), + .table = "mangle", + .me = THIS_MODULE, + }, + { + .name = "MARK", + .family = AF_INET, + .revision = 1, + .checkentry = checkentry_v1, + .target = target_v1, + .targetsize = sizeof(struct xt_mark_target_info_v1), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct compat_xt_mark_target_info_v1), + .compat_from_user = compat_from_user_v1, + .compat_to_user = compat_to_user_v1, +#endif + .table = "mangle", + .me = THIS_MODULE, + }, + { + .name = "MARK", + .family = AF_INET6, + .revision = 0, + .checkentry = checkentry_v0, + .target = target_v0, + .targetsize = sizeof(struct xt_mark_target_info), + .table = "mangle", + .me = THIS_MODULE, + }, }; static int __init xt_mark_init(void) { - int err; - - err = xt_register_target(&ipt_mark_reg_v0); - if (err) - return err; - - err = xt_register_target(&ipt_mark_reg_v1); - if (err) - xt_unregister_target(&ipt_mark_reg_v0); - - err = xt_register_target(&ip6t_mark_reg_v0); - if (err) { - xt_unregister_target(&ipt_mark_reg_v0); - xt_unregister_target(&ipt_mark_reg_v1); - } - - return err; + return xt_register_targets(xt_mark_target, ARRAY_SIZE(xt_mark_target)); } static void __exit xt_mark_fini(void) { - xt_unregister_target(&ipt_mark_reg_v0); - xt_unregister_target(&ipt_mark_reg_v1); - xt_unregister_target(&ip6t_mark_reg_v0); + xt_unregister_targets(xt_mark_target, ARRAY_SIZE(xt_mark_target)); } module_init(xt_mark_init); diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 86ccceb61fd..db9b896e57c 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -29,65 +29,46 @@ target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { const struct xt_NFQ_info *tinfo = targinfo; return NF_QUEUE_NR(tinfo->queuenum); } -static struct xt_target ipt_NFQ_reg = { - .name = "NFQUEUE", - .target = target, - .targetsize = sizeof(struct xt_NFQ_info), - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_target ip6t_NFQ_reg = { - .name = "NFQUEUE", - .target = target, - .targetsize = sizeof(struct xt_NFQ_info), - .family = AF_INET6, - .me = THIS_MODULE, -}; - -static struct xt_target arpt_NFQ_reg = { - .name = "NFQUEUE", - .target = target, - .targetsize = sizeof(struct xt_NFQ_info), - .family = NF_ARP, - .me = THIS_MODULE, +static struct xt_target xt_nfqueue_target[] = { + { + .name = "NFQUEUE", + .family = AF_INET, + .target = target, + .targetsize = sizeof(struct xt_NFQ_info), + .me = THIS_MODULE, + }, + { + .name = "NFQUEUE", + .family = AF_INET6, + .target = target, + .targetsize = sizeof(struct xt_NFQ_info), + .me = THIS_MODULE, + }, + { + .name = "NFQUEUE", + .family = NF_ARP, + .target = target, + .targetsize = sizeof(struct xt_NFQ_info), + .me = THIS_MODULE, + }, }; static int __init xt_nfqueue_init(void) { - int ret; - ret = xt_register_target(&ipt_NFQ_reg); - if (ret) - return ret; - ret = xt_register_target(&ip6t_NFQ_reg); - if (ret) - goto out_ip; - ret = xt_register_target(&arpt_NFQ_reg); - if (ret) - goto out_ip6; - - return ret; -out_ip6: - xt_unregister_target(&ip6t_NFQ_reg); -out_ip: - xt_unregister_target(&ipt_NFQ_reg); - - return ret; + return xt_register_targets(xt_nfqueue_target, + ARRAY_SIZE(xt_nfqueue_target)); } static void __exit xt_nfqueue_fini(void) { - xt_unregister_target(&arpt_NFQ_reg); - xt_unregister_target(&ip6t_NFQ_reg); - xt_unregister_target(&ipt_NFQ_reg); + xt_register_targets(xt_nfqueue_target, ARRAY_SIZE(xt_nfqueue_target)); } module_init(xt_nfqueue_init); diff --git a/net/netfilter/xt_NOTRACK.c b/net/netfilter/xt_NOTRACK.c index 98f4b5363ce..6d00dcaed23 100644 --- a/net/netfilter/xt_NOTRACK.c +++ b/net/netfilter/xt_NOTRACK.c @@ -16,8 +16,7 @@ target(struct sk_buff **pskb, const struct net_device *out, unsigned int hooknum, const struct xt_target *target, - const void *targinfo, - void *userinfo) + const void *targinfo) { /* Previously seen (loopback)? Ignore. */ if ((*pskb)->nfct != NULL) @@ -34,43 +33,32 @@ target(struct sk_buff **pskb, return XT_CONTINUE; } -static struct xt_target notrack_reg = { - .name = "NOTRACK", - .target = target, - .targetsize = 0, - .table = "raw", - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_target notrack6_reg = { - .name = "NOTRACK", - .target = target, - .targetsize = 0, - .table = "raw", - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_target xt_notrack_target[] = { + { + .name = "NOTRACK", + .family = AF_INET, + .target = target, + .table = "raw", + .me = THIS_MODULE, + }, + { + .name = "NOTRACK", + .family = AF_INET6, + .target = target, + .table = "raw", + .me = THIS_MODULE, + }, }; static int __init xt_notrack_init(void) { - int ret; - - ret = xt_register_target(¬rack_reg); - if (ret) - return ret; - - ret = xt_register_target(¬rack6_reg); - if (ret) - xt_unregister_target(¬rack_reg); - - return ret; + return xt_register_targets(xt_notrack_target, + ARRAY_SIZE(xt_notrack_target)); } static void __exit xt_notrack_fini(void) { - xt_unregister_target(¬rack6_reg); - xt_unregister_target(¬rack_reg); + xt_unregister_targets(xt_notrack_target, ARRAY_SIZE(xt_notrack_target)); } module_init(xt_notrack_init); diff --git a/net/netfilter/xt_SECMARK.c b/net/netfilter/xt_SECMARK.c index de9537ad9a7..add75219629 100644 --- a/net/netfilter/xt_SECMARK.c +++ b/net/netfilter/xt_SECMARK.c @@ -31,7 +31,7 @@ static u8 mode; static unsigned int 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 void *targinfo) { u32 secmark = 0; const struct xt_secmark_target_info *info = targinfo; @@ -85,7 +85,7 @@ static int checkentry_selinux(struct xt_secmark_target_info *info) static int checkentry(const char *tablename, const void *entry, const struct xt_target *target, void *targinfo, - unsigned int targinfosize, unsigned int hook_mask) + unsigned int hook_mask) { struct xt_secmark_target_info *info = targinfo; @@ -111,47 +111,36 @@ static int checkentry(const char *tablename, const void *entry, return 1; } -static struct xt_target ipt_secmark_reg = { - .name = "SECMARK", - .target = target, - .targetsize = sizeof(struct xt_secmark_target_info), - .table = "mangle", - .checkentry = checkentry, - .me = THIS_MODULE, - .family = AF_INET, - .revision = 0, -}; - -static struct xt_target ip6t_secmark_reg = { - .name = "SECMARK", - .target = target, - .targetsize = sizeof(struct xt_secmark_target_info), - .table = "mangle", - .checkentry = checkentry, - .me = THIS_MODULE, - .family = AF_INET6, - .revision = 0, +static struct xt_target xt_secmark_target[] = { + { + .name = "SECMARK", + .family = AF_INET, + .checkentry = checkentry, + .target = target, + .targetsize = sizeof(struct xt_secmark_target_info), + .table = "mangle", + .me = THIS_MODULE, + }, + { + .name = "SECMARK", + .family = AF_INET6, + .checkentry = checkentry, + .target = target, + .targetsize = sizeof(struct xt_secmark_target_info), + .table = "mangle", + .me = THIS_MODULE, + }, }; static int __init xt_secmark_init(void) { - int err; - - err = xt_register_target(&ipt_secmark_reg); - if (err) - return err; - - err = xt_register_target(&ip6t_secmark_reg); - if (err) - xt_unregister_target(&ipt_secmark_reg); - - return err; + return xt_register_targets(xt_secmark_target, + ARRAY_SIZE(xt_secmark_target)); } static void __exit xt_secmark_fini(void) { - xt_unregister_target(&ip6t_secmark_reg); - xt_unregister_target(&ipt_secmark_reg); + xt_unregister_targets(xt_secmark_target, ARRAY_SIZE(xt_secmark_target)); } module_init(xt_secmark_init); diff --git a/net/netfilter/xt_comment.c b/net/netfilter/xt_comment.c index 197609cb06d..7db492d6522 100644 --- a/net/netfilter/xt_comment.c +++ b/net/netfilter/xt_comment.c @@ -29,41 +29,32 @@ match(const struct sk_buff *skb, return 1; } -static struct xt_match comment_match = { - .name = "comment", - .match = match, - .matchsize = sizeof(struct xt_comment_info), - .family = AF_INET, - .me = THIS_MODULE -}; - -static struct xt_match comment6_match = { - .name = "comment", - .match = match, - .matchsize = sizeof(struct xt_comment_info), - .family = AF_INET6, - .me = THIS_MODULE +static struct xt_match xt_comment_match[] = { + { + .name = "comment", + .family = AF_INET, + .match = match, + .matchsize = sizeof(struct xt_comment_info), + .me = THIS_MODULE + }, + { + .name = "comment", + .family = AF_INET6, + .match = match, + .matchsize = sizeof(struct xt_comment_info), + .me = THIS_MODULE + }, }; static int __init xt_comment_init(void) { - int ret; - - ret = xt_register_match(&comment_match); - if (ret) - return ret; - - ret = xt_register_match(&comment6_match); - if (ret) - xt_unregister_match(&comment_match); - - return ret; + return xt_register_matches(xt_comment_match, + ARRAY_SIZE(xt_comment_match)); } static void __exit xt_comment_fini(void) { - xt_unregister_match(&comment_match); - xt_unregister_match(&comment6_match); + xt_unregister_matches(xt_comment_match, ARRAY_SIZE(xt_comment_match)); } module_init(xt_comment_init); diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c index 1396fe2d07c..dcc497ea818 100644 --- a/net/netfilter/xt_connbytes.c +++ b/net/netfilter/xt_connbytes.c @@ -125,7 +125,6 @@ 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; @@ -143,40 +142,35 @@ static int check(const char *tablename, return 1; } -static struct xt_match connbytes_match = { - .name = "connbytes", - .match = match, - .checkentry = check, - .matchsize = sizeof(struct xt_connbytes_info), - .family = AF_INET, - .me = THIS_MODULE -}; -static struct xt_match connbytes6_match = { - .name = "connbytes", - .match = match, - .checkentry = check, - .matchsize = sizeof(struct xt_connbytes_info), - .family = AF_INET6, - .me = THIS_MODULE +static struct xt_match xt_connbytes_match[] = { + { + .name = "connbytes", + .family = AF_INET, + .checkentry = check, + .match = match, + .matchsize = sizeof(struct xt_connbytes_info), + .me = THIS_MODULE + }, + { + .name = "connbytes", + .family = AF_INET6, + .checkentry = check, + .match = match, + .matchsize = sizeof(struct xt_connbytes_info), + .me = THIS_MODULE + }, }; static int __init xt_connbytes_init(void) { - int ret; - ret = xt_register_match(&connbytes_match); - if (ret) - return ret; - - ret = xt_register_match(&connbytes6_match); - if (ret) - xt_unregister_match(&connbytes_match); - return ret; + return xt_register_matches(xt_connbytes_match, + ARRAY_SIZE(xt_connbytes_match)); } static void __exit xt_connbytes_fini(void) { - xt_unregister_match(&connbytes_match); - xt_unregister_match(&connbytes6_match); + xt_unregister_matches(xt_connbytes_match, + ARRAY_SIZE(xt_connbytes_match)); } module_init(xt_connbytes_init); diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 56324c8aff0..92a5726ef23 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -55,7 +55,6 @@ 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 = matchinfo; @@ -75,53 +74,80 @@ checkentry(const char *tablename, } static void -destroy(const struct xt_match *match, void *matchinfo, unsigned int matchsize) +destroy(const struct xt_match *match, void *matchinfo) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_ct_l3proto_module_put(match->family); #endif } -static struct xt_match connmark_match = { - .name = "connmark", - .match = match, - .matchsize = sizeof(struct xt_connmark_info), - .checkentry = checkentry, - .destroy = destroy, - .family = AF_INET, - .me = THIS_MODULE +#ifdef CONFIG_COMPAT +struct compat_xt_connmark_info { + compat_ulong_t mark, mask; + u_int8_t invert; + u_int8_t __pad1; + u_int16_t __pad2; }; -static struct xt_match connmark6_match = { - .name = "connmark", - .match = match, - .matchsize = sizeof(struct xt_connmark_info), - .checkentry = checkentry, - .destroy = destroy, - .family = AF_INET6, - .me = THIS_MODULE +static void compat_from_user(void *dst, void *src) +{ + struct compat_xt_connmark_info *cm = src; + struct xt_connmark_info m = { + .mark = cm->mark, + .mask = cm->mask, + .invert = cm->invert, + }; + memcpy(dst, &m, sizeof(m)); +} + +static int compat_to_user(void __user *dst, void *src) +{ + struct xt_connmark_info *m = src; + struct compat_xt_connmark_info cm = { + .mark = m->mark, + .mask = m->mask, + .invert = m->invert, + }; + return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; +} +#endif /* CONFIG_COMPAT */ + +static struct xt_match xt_connmark_match[] = { + { + .name = "connmark", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .destroy = destroy, + .matchsize = sizeof(struct xt_connmark_info), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct compat_xt_connmark_info), + .compat_from_user = compat_from_user, + .compat_to_user = compat_to_user, +#endif + .me = THIS_MODULE + }, + { + .name = "connmark", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .destroy = destroy, + .matchsize = sizeof(struct xt_connmark_info), + .me = THIS_MODULE + }, }; static int __init xt_connmark_init(void) { - int ret; - need_conntrack(); - - ret = xt_register_match(&connmark_match); - if (ret) - return ret; - - ret = xt_register_match(&connmark6_match); - if (ret) - xt_unregister_match(&connmark_match); - return ret; + return xt_register_matches(xt_connmark_match, + ARRAY_SIZE(xt_connmark_match)); } static void __exit xt_connmark_fini(void) { - xt_unregister_match(&connmark6_match); - xt_unregister_match(&connmark_match); + xt_register_matches(xt_connmark_match, ARRAY_SIZE(xt_connmark_match)); } module_init(xt_connmark_init); diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 145489a4c3f..0ea501a2fda 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -45,7 +45,7 @@ match(const struct sk_buff *skb, ct = ip_conntrack_get((struct sk_buff *)skb, &ctinfo); -#define FWINV(bool,invflg) ((bool) ^ !!(sinfo->invflags & invflg)) +#define FWINV(bool, invflg) ((bool) ^ !!(sinfo->invflags & invflg)) if (ct == &ip_conntrack_untracked) statebit = XT_CONNTRACK_STATE_UNTRACKED; @@ -54,63 +54,72 @@ match(const struct sk_buff *skb, else statebit = XT_CONNTRACK_STATE_INVALID; - if(sinfo->flags & XT_CONNTRACK_STATE) { + if (sinfo->flags & XT_CONNTRACK_STATE) { if (ct) { - if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip != - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip) + if (test_bit(IPS_SRC_NAT_BIT, &ct->status)) statebit |= XT_CONNTRACK_STATE_SNAT; - - if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip != - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip) + if (test_bit(IPS_DST_NAT_BIT, &ct->status)) statebit |= XT_CONNTRACK_STATE_DNAT; } - - if (FWINV((statebit & sinfo->statemask) == 0, XT_CONNTRACK_STATE)) - return 0; - } - - if(sinfo->flags & XT_CONNTRACK_PROTO) { - if (!ct || FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, XT_CONNTRACK_PROTO)) - return 0; - } - - if(sinfo->flags & XT_CONNTRACK_ORIGSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip&sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, XT_CONNTRACK_ORIGSRC)) + if (FWINV((statebit & sinfo->statemask) == 0, + XT_CONNTRACK_STATE)) return 0; } - if(sinfo->flags & XT_CONNTRACK_ORIGDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip&sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, XT_CONNTRACK_ORIGDST)) + if (ct == NULL) { + if (sinfo->flags & ~XT_CONNTRACK_STATE) return 0; + return 1; } - if(sinfo->flags & XT_CONNTRACK_REPLSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip&sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, XT_CONNTRACK_REPLSRC)) - return 0; - } + if (sinfo->flags & XT_CONNTRACK_PROTO && + FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != + sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, + XT_CONNTRACK_PROTO)) + return 0; + + if (sinfo->flags & XT_CONNTRACK_ORIGSRC && + FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip & + sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != + sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, + XT_CONNTRACK_ORIGSRC)) + return 0; - if(sinfo->flags & XT_CONNTRACK_REPLDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip&sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, XT_CONNTRACK_REPLDST)) - return 0; - } + if (sinfo->flags & XT_CONNTRACK_ORIGDST && + FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip & + sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != + sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, + XT_CONNTRACK_ORIGDST)) + return 0; - if(sinfo->flags & XT_CONNTRACK_STATUS) { - if (!ct || FWINV((ct->status & sinfo->statusmask) == 0, XT_CONNTRACK_STATUS)) - return 0; - } + if (sinfo->flags & XT_CONNTRACK_REPLSRC && + FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip & + sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != + sinfo->tuple[IP_CT_DIR_REPLY].src.ip, + XT_CONNTRACK_REPLSRC)) + return 0; - if(sinfo->flags & XT_CONNTRACK_EXPIRES) { - unsigned long expires; + if (sinfo->flags & XT_CONNTRACK_REPLDST && + FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip & + sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != + sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, + XT_CONNTRACK_REPLDST)) + return 0; - if(!ct) - return 0; + if (sinfo->flags & XT_CONNTRACK_STATUS && + FWINV((ct->status & sinfo->statusmask) == 0, + XT_CONNTRACK_STATUS)) + return 0; - expires = timer_pending(&ct->timeout) ? (ct->timeout.expires - jiffies)/HZ : 0; + if (sinfo->flags & XT_CONNTRACK_EXPIRES) { + unsigned long expires = timer_pending(&ct->timeout) ? + (ct->timeout.expires - jiffies)/HZ : 0; - if (FWINV(!(expires >= sinfo->expires_min && expires <= sinfo->expires_max), XT_CONNTRACK_EXPIRES)) + if (FWINV(!(expires >= sinfo->expires_min && + expires <= sinfo->expires_max), + XT_CONNTRACK_EXPIRES)) return 0; } - return 1; } @@ -141,63 +150,72 @@ match(const struct sk_buff *skb, else statebit = XT_CONNTRACK_STATE_INVALID; - if(sinfo->flags & XT_CONNTRACK_STATE) { + if (sinfo->flags & XT_CONNTRACK_STATE) { if (ct) { - if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip != - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip) + if (test_bit(IPS_SRC_NAT_BIT, &ct->status)) statebit |= XT_CONNTRACK_STATE_SNAT; - - if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip != - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip) + if (test_bit(IPS_DST_NAT_BIT, &ct->status)) statebit |= XT_CONNTRACK_STATE_DNAT; } - - if (FWINV((statebit & sinfo->statemask) == 0, XT_CONNTRACK_STATE)) - return 0; - } - - if(sinfo->flags & XT_CONNTRACK_PROTO) { - if (!ct || FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, XT_CONNTRACK_PROTO)) - return 0; - } - - if(sinfo->flags & XT_CONNTRACK_ORIGSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, XT_CONNTRACK_ORIGSRC)) + if (FWINV((statebit & sinfo->statemask) == 0, + XT_CONNTRACK_STATE)) return 0; } - if(sinfo->flags & XT_CONNTRACK_ORIGDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, XT_CONNTRACK_ORIGDST)) + if (ct == NULL) { + if (sinfo->flags & ~XT_CONNTRACK_STATE) return 0; + return 1; } - if(sinfo->flags & XT_CONNTRACK_REPLSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, XT_CONNTRACK_REPLSRC)) - return 0; - } + if (sinfo->flags & XT_CONNTRACK_PROTO && + FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != + sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, + XT_CONNTRACK_PROTO)) + return 0; + + if (sinfo->flags & XT_CONNTRACK_ORIGSRC && + FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip & + sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != + sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, + XT_CONNTRACK_ORIGSRC)) + return 0; - if(sinfo->flags & XT_CONNTRACK_REPLDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, XT_CONNTRACK_REPLDST)) - return 0; - } + if (sinfo->flags & XT_CONNTRACK_ORIGDST && + FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip & + sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != + sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, + XT_CONNTRACK_ORIGDST)) + return 0; - if(sinfo->flags & XT_CONNTRACK_STATUS) { - if (!ct || FWINV((ct->status & sinfo->statusmask) == 0, XT_CONNTRACK_STATUS)) - return 0; - } + if (sinfo->flags & XT_CONNTRACK_REPLSRC && + FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip & + sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != + sinfo->tuple[IP_CT_DIR_REPLY].src.ip, + XT_CONNTRACK_REPLSRC)) + return 0; - if(sinfo->flags & XT_CONNTRACK_EXPIRES) { - unsigned long expires; + if (sinfo->flags & XT_CONNTRACK_REPLDST && + FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip & + sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != + sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, + XT_CONNTRACK_REPLDST)) + return 0; - if(!ct) - return 0; + if (sinfo->flags & XT_CONNTRACK_STATUS && + FWINV((ct->status & sinfo->statusmask) == 0, + XT_CONNTRACK_STATUS)) + return 0; - expires = timer_pending(&ct->timeout) ? (ct->timeout.expires - jiffies)/HZ : 0; + if(sinfo->flags & XT_CONNTRACK_EXPIRES) { + unsigned long expires = timer_pending(&ct->timeout) ? + (ct->timeout.expires - jiffies)/HZ : 0; - if (FWINV(!(expires >= sinfo->expires_min && expires <= sinfo->expires_max), XT_CONNTRACK_EXPIRES)) + if (FWINV(!(expires >= sinfo->expires_min && + expires <= sinfo->expires_max), + XT_CONNTRACK_EXPIRES)) return 0; } - return 1; } @@ -208,7 +226,6 @@ checkentry(const char *tablename, const void *ip, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) @@ -221,8 +238,7 @@ checkentry(const char *tablename, return 1; } -static void -destroy(const struct xt_match *match, void *matchinfo, unsigned int matchsize) +static void destroy(const struct xt_match *match, void *matchinfo) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_ct_l3proto_module_put(match->family); @@ -241,11 +257,8 @@ static struct xt_match conntrack_match = { static int __init xt_conntrack_init(void) { - int ret; need_conntrack(); - ret = xt_register_match(&conntrack_match); - - return ret; + return xt_register_match(&conntrack_match); } static void __exit xt_conntrack_fini(void) diff --git a/net/netfilter/xt_dccp.c b/net/netfilter/xt_dccp.c index 2e2f825dad4..3e6cf430e51 100644 --- a/net/netfilter/xt_dccp.c +++ b/net/netfilter/xt_dccp.c @@ -131,7 +131,6 @@ checkentry(const char *tablename, const void *inf, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) { const struct xt_dccp_info *info = matchinfo; @@ -141,27 +140,26 @@ checkentry(const char *tablename, && !(info->invflags & ~info->flags); } -static struct xt_match dccp_match = -{ - .name = "dccp", - .match = match, - .matchsize = sizeof(struct xt_dccp_info), - .proto = IPPROTO_DCCP, - .checkentry = checkentry, - .family = AF_INET, - .me = THIS_MODULE, +static struct xt_match xt_dccp_match[] = { + { + .name = "dccp", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_dccp_info), + .proto = IPPROTO_DCCP, + .me = THIS_MODULE, + }, + { + .name = "dccp", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_dccp_info), + .proto = IPPROTO_DCCP, + .me = THIS_MODULE, + }, }; -static struct xt_match dccp6_match = -{ - .name = "dccp", - .match = match, - .matchsize = sizeof(struct xt_dccp_info), - .proto = IPPROTO_DCCP, - .checkentry = checkentry, - .family = AF_INET6, - .me = THIS_MODULE, -}; - static int __init xt_dccp_init(void) { @@ -173,27 +171,19 @@ static int __init xt_dccp_init(void) dccp_optbuf = kmalloc(256 * 4, GFP_KERNEL); if (!dccp_optbuf) return -ENOMEM; - ret = xt_register_match(&dccp_match); + ret = xt_register_matches(xt_dccp_match, ARRAY_SIZE(xt_dccp_match)); if (ret) goto out_kfree; - ret = xt_register_match(&dccp6_match); - if (ret) - goto out_unreg; - return ret; -out_unreg: - xt_unregister_match(&dccp_match); out_kfree: kfree(dccp_optbuf); - return ret; } static void __exit xt_dccp_fini(void) { - xt_unregister_match(&dccp6_match); - xt_unregister_match(&dccp_match); + xt_unregister_matches(xt_dccp_match, ARRAY_SIZE(xt_dccp_match)); kfree(dccp_optbuf); } diff --git a/net/netfilter/xt_dscp.c b/net/netfilter/xt_dscp.c new file mode 100644 index 00000000000..26c7f4ad102 --- /dev/null +++ b/net/netfilter/xt_dscp.c @@ -0,0 +1,103 @@ +/* IP tables module for matching the value of the IPv4/IPv6 DSCP field + * + * xt_dscp.c,v 1.3 2002/08/05 19:00:21 laforge Exp + * + * (C) 2002 by Harald Welte <laforge@netfilter.org> + * + * 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/module.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <net/dsfield.h> + +#include <linux/netfilter/xt_dscp.h> +#include <linux/netfilter/x_tables.h> + +MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); +MODULE_DESCRIPTION("x_tables DSCP matching module"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_dscp"); +MODULE_ALIAS("ip6t_dscp"); + +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_dscp_info *info = matchinfo; + u_int8_t dscp = ipv4_get_dsfield(skb->nh.iph) >> XT_DSCP_SHIFT; + + return (dscp == info->dscp) ^ !!info->invert; +} + +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, + int *hotdrop) +{ + const struct xt_dscp_info *info = matchinfo; + u_int8_t dscp = ipv6_get_dsfield(skb->nh.ipv6h) >> XT_DSCP_SHIFT; + + return (dscp == info->dscp) ^ !!info->invert; +} + +static int checkentry(const char *tablename, + const void *info, + const struct xt_match *match, + void *matchinfo, + unsigned int hook_mask) +{ + const u_int8_t dscp = ((struct xt_dscp_info *)matchinfo)->dscp; + + if (dscp > XT_DSCP_MAX) { + printk(KERN_ERR "xt_dscp: dscp %x out of range\n", dscp); + return 0; + } + + return 1; +} + +static struct xt_match xt_dscp_match[] = { + { + .name = "dscp", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_dscp_info), + .me = THIS_MODULE, + }, + { + .name = "dscp", + .family = AF_INET6, + .checkentry = checkentry, + .match = match6, + .matchsize = sizeof(struct xt_dscp_info), + .me = THIS_MODULE, + }, +}; + +static int __init xt_dscp_match_init(void) +{ + return xt_register_matches(xt_dscp_match, ARRAY_SIZE(xt_dscp_match)); +} + +static void __exit xt_dscp_match_fini(void) +{ + xt_unregister_matches(xt_dscp_match, ARRAY_SIZE(xt_dscp_match)); +} + +module_init(xt_dscp_match_init); +module_exit(xt_dscp_match_fini); diff --git a/net/netfilter/xt_esp.c b/net/netfilter/xt_esp.c index 9dad6281e0c..7c95f149d94 100644 --- a/net/netfilter/xt_esp.c +++ b/net/netfilter/xt_esp.c @@ -79,7 +79,6 @@ checkentry(const char *tablename, const void *ip_void, const struct xt_match *match, void *matchinfo, - unsigned int matchinfosize, unsigned int hook_mask) { const struct xt_esp *espinfo = matchinfo; @@ -92,44 +91,35 @@ checkentry(const char *tablename, return 1; } -static struct xt_match esp_match = { - .name = "esp", - .family = AF_INET, - .proto = IPPROTO_ESP, - .match = &match, - .matchsize = sizeof(struct xt_esp), - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static struct xt_match esp6_match = { - .name = "esp", - .family = AF_INET6, - .proto = IPPROTO_ESP, - .match = &match, - .matchsize = sizeof(struct xt_esp), - .checkentry = &checkentry, - .me = THIS_MODULE, +static struct xt_match xt_esp_match[] = { + { + .name = "esp", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_esp), + .proto = IPPROTO_ESP, + .me = THIS_MODULE, + }, + { + .name = "esp", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_esp), + .proto = IPPROTO_ESP, + .me = THIS_MODULE, + }, }; static int __init xt_esp_init(void) { - int ret; - ret = xt_register_match(&esp_match); - if (ret) - return ret; - - ret = xt_register_match(&esp6_match); - if (ret) - xt_unregister_match(&esp_match); - - return ret; + return xt_register_matches(xt_esp_match, ARRAY_SIZE(xt_esp_match)); } static void __exit xt_esp_cleanup(void) { - xt_unregister_match(&esp_match); - xt_unregister_match(&esp6_match); + xt_unregister_matches(xt_esp_match, ARRAY_SIZE(xt_esp_match)); } module_init(xt_esp_init); diff --git a/net/netfilter/xt_helper.c b/net/netfilter/xt_helper.c index 799c2a43e3b..5d7818b73e3 100644 --- a/net/netfilter/xt_helper.c +++ b/net/netfilter/xt_helper.c @@ -139,7 +139,6 @@ static int check(const char *tablename, const void *inf, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) { struct xt_helper_info *info = matchinfo; @@ -156,52 +155,44 @@ static int check(const char *tablename, } static void -destroy(const struct xt_match *match, void *matchinfo, unsigned int matchsize) +destroy(const struct xt_match *match, void *matchinfo) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_ct_l3proto_module_put(match->family); #endif } -static struct xt_match helper_match = { - .name = "helper", - .match = match, - .matchsize = sizeof(struct xt_helper_info), - .checkentry = check, - .destroy = destroy, - .family = AF_INET, - .me = THIS_MODULE, -}; -static struct xt_match helper6_match = { - .name = "helper", - .match = match, - .matchsize = sizeof(struct xt_helper_info), - .checkentry = check, - .destroy = destroy, - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_helper_match[] = { + { + .name = "helper", + .family = AF_INET, + .checkentry = check, + .match = match, + .destroy = destroy, + .matchsize = sizeof(struct xt_helper_info), + .me = THIS_MODULE, + }, + { + .name = "helper", + .family = AF_INET6, + .checkentry = check, + .match = match, + .destroy = destroy, + .matchsize = sizeof(struct xt_helper_info), + .me = THIS_MODULE, + }, }; static int __init xt_helper_init(void) { - int ret; need_conntrack(); - - ret = xt_register_match(&helper_match); - if (ret < 0) - return ret; - - ret = xt_register_match(&helper6_match); - if (ret < 0) - xt_unregister_match(&helper_match); - - return ret; + return xt_register_matches(xt_helper_match, + ARRAY_SIZE(xt_helper_match)); } static void __exit xt_helper_fini(void) { - xt_unregister_match(&helper_match); - xt_unregister_match(&helper6_match); + xt_unregister_matches(xt_helper_match, ARRAY_SIZE(xt_helper_match)); } module_init(xt_helper_init); diff --git a/net/netfilter/xt_length.c b/net/netfilter/xt_length.c index 109132c9a14..67fd30d9f30 100644 --- a/net/netfilter/xt_length.c +++ b/net/netfilter/xt_length.c @@ -52,39 +52,32 @@ match6(const struct sk_buff *skb, return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } -static struct xt_match length_match = { - .name = "length", - .match = match, - .matchsize = sizeof(struct xt_length_info), - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_match length6_match = { - .name = "length", - .match = match6, - .matchsize = sizeof(struct xt_length_info), - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_length_match[] = { + { + .name = "length", + .family = AF_INET, + .match = match, + .matchsize = sizeof(struct xt_length_info), + .me = THIS_MODULE, + }, + { + .name = "length", + .family = AF_INET6, + .match = match6, + .matchsize = sizeof(struct xt_length_info), + .me = THIS_MODULE, + }, }; static int __init xt_length_init(void) { - int ret; - ret = xt_register_match(&length_match); - if (ret) - return ret; - ret = xt_register_match(&length6_match); - if (ret) - xt_unregister_match(&length_match); - - return ret; + return xt_register_matches(xt_length_match, + ARRAY_SIZE(xt_length_match)); } static void __exit xt_length_fini(void) { - xt_unregister_match(&length_match); - xt_unregister_match(&length6_match); + xt_unregister_matches(xt_length_match, ARRAY_SIZE(xt_length_match)); } module_init(xt_length_init); diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index ce7fdb7e4e0..fda7b7dec27 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -110,7 +110,6 @@ 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; @@ -123,55 +122,95 @@ ipt_limit_checkentry(const char *tablename, return 0; } - /* User avg in seconds * XT_LIMIT_SCALE: convert to jiffies * - 128. */ - r->prev = jiffies; - r->credit = user2credits(r->avg * r->burst); /* Credits full. */ - r->credit_cap = user2credits(r->avg * r->burst); /* Credits full. */ - r->cost = user2credits(r->avg); - /* For SMP, we only want to use one set of counters. */ r->master = r; - + if (r->cost == 0) { + /* User avg in seconds * XT_LIMIT_SCALE: convert to jiffies * + 128. */ + r->prev = jiffies; + r->credit = user2credits(r->avg * r->burst); /* Credits full. */ + r->credit_cap = user2credits(r->avg * r->burst); /* Credits full. */ + r->cost = user2credits(r->avg); + } return 1; } -static struct xt_match ipt_limit_reg = { - .name = "limit", - .match = ipt_limit_match, - .matchsize = sizeof(struct xt_rateinfo), - .checkentry = ipt_limit_checkentry, - .family = AF_INET, - .me = THIS_MODULE, +#ifdef CONFIG_COMPAT +struct compat_xt_rateinfo { + u_int32_t avg; + u_int32_t burst; + + compat_ulong_t prev; + u_int32_t credit; + u_int32_t credit_cap, cost; + + u_int32_t master; }; -static struct xt_match limit6_reg = { - .name = "limit", - .match = ipt_limit_match, - .matchsize = sizeof(struct xt_rateinfo), - .checkentry = ipt_limit_checkentry, - .family = AF_INET6, - .me = THIS_MODULE, + +/* To keep the full "prev" timestamp, the upper 32 bits are stored in the + * master pointer, which does not need to be preserved. */ +static void compat_from_user(void *dst, void *src) +{ + struct compat_xt_rateinfo *cm = src; + struct xt_rateinfo m = { + .avg = cm->avg, + .burst = cm->burst, + .prev = cm->prev | (unsigned long)cm->master << 32, + .credit = cm->credit, + .credit_cap = cm->credit_cap, + .cost = cm->cost, + }; + memcpy(dst, &m, sizeof(m)); +} + +static int compat_to_user(void __user *dst, void *src) +{ + struct xt_rateinfo *m = src; + struct compat_xt_rateinfo cm = { + .avg = m->avg, + .burst = m->burst, + .prev = m->prev, + .credit = m->credit, + .credit_cap = m->credit_cap, + .cost = m->cost, + .master = m->prev >> 32, + }; + return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; +} +#endif /* CONFIG_COMPAT */ + +static struct xt_match xt_limit_match[] = { + { + .name = "limit", + .family = AF_INET, + .checkentry = ipt_limit_checkentry, + .match = ipt_limit_match, + .matchsize = sizeof(struct xt_rateinfo), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct compat_xt_rateinfo), + .compat_from_user = compat_from_user, + .compat_to_user = compat_to_user, +#endif + .me = THIS_MODULE, + }, + { + .name = "limit", + .family = AF_INET6, + .checkentry = ipt_limit_checkentry, + .match = ipt_limit_match, + .matchsize = sizeof(struct xt_rateinfo), + .me = THIS_MODULE, + }, }; static int __init xt_limit_init(void) { - int ret; - - ret = xt_register_match(&ipt_limit_reg); - if (ret) - return ret; - - ret = xt_register_match(&limit6_reg); - if (ret) - xt_unregister_match(&ipt_limit_reg); - - return ret; + return xt_register_matches(xt_limit_match, ARRAY_SIZE(xt_limit_match)); } static void __exit xt_limit_fini(void) { - xt_unregister_match(&ipt_limit_reg); - xt_unregister_match(&limit6_reg); + xt_unregister_matches(xt_limit_match, ARRAY_SIZE(xt_limit_match)); } module_init(xt_limit_init); diff --git a/net/netfilter/xt_mac.c b/net/netfilter/xt_mac.c index 356290ffe38..425fc21e31f 100644 --- a/net/netfilter/xt_mac.c +++ b/net/netfilter/xt_mac.c @@ -43,43 +43,37 @@ match(const struct sk_buff *skb, ^ info->invert)); } -static struct xt_match mac_match = { - .name = "mac", - .match = match, - .matchsize = sizeof(struct xt_mac_info), - .hooks = (1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_IN) | - (1 << NF_IP_FORWARD), - .family = AF_INET, - .me = THIS_MODULE, -}; -static struct xt_match mac6_match = { - .name = "mac", - .match = match, - .matchsize = sizeof(struct xt_mac_info), - .hooks = (1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_IN) | - (1 << NF_IP_FORWARD), - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_mac_match[] = { + { + .name = "mac", + .family = AF_INET, + .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, + }, + { + .name = "mac", + .family = AF_INET6, + .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 int __init xt_mac_init(void) { - int ret; - ret = xt_register_match(&mac_match); - if (ret) - return ret; - - ret = xt_register_match(&mac6_match); - if (ret) - xt_unregister_match(&mac_match); - - return ret; + return xt_register_matches(xt_mac_match, ARRAY_SIZE(xt_mac_match)); } static void __exit xt_mac_fini(void) { - xt_unregister_match(&mac_match); - xt_unregister_match(&mac6_match); + xt_unregister_matches(xt_mac_match, ARRAY_SIZE(xt_mac_match)); } module_init(xt_mac_init); diff --git a/net/netfilter/xt_mark.c b/net/netfilter/xt_mark.c index 876bc579773..934dddfbcd2 100644 --- a/net/netfilter/xt_mark.c +++ b/net/netfilter/xt_mark.c @@ -39,7 +39,6 @@ checkentry(const char *tablename, const void *entry, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) { const struct xt_mark_info *minfo = matchinfo; @@ -51,42 +50,69 @@ checkentry(const char *tablename, return 1; } -static struct xt_match mark_match = { - .name = "mark", - .match = match, - .matchsize = sizeof(struct xt_mark_info), - .checkentry = checkentry, - .family = AF_INET, - .me = THIS_MODULE, +#ifdef CONFIG_COMPAT +struct compat_xt_mark_info { + compat_ulong_t mark, mask; + u_int8_t invert; + u_int8_t __pad1; + u_int16_t __pad2; }; -static struct xt_match mark6_match = { - .name = "mark", - .match = match, - .matchsize = sizeof(struct xt_mark_info), - .checkentry = checkentry, - .family = AF_INET6, - .me = THIS_MODULE, -}; +static void compat_from_user(void *dst, void *src) +{ + struct compat_xt_mark_info *cm = src; + struct xt_mark_info m = { + .mark = cm->mark, + .mask = cm->mask, + .invert = cm->invert, + }; + memcpy(dst, &m, sizeof(m)); +} -static int __init xt_mark_init(void) +static int compat_to_user(void __user *dst, void *src) { - int ret; - ret = xt_register_match(&mark_match); - if (ret) - return ret; + struct xt_mark_info *m = src; + struct compat_xt_mark_info cm = { + .mark = m->mark, + .mask = m->mask, + .invert = m->invert, + }; + return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; +} +#endif /* CONFIG_COMPAT */ - ret = xt_register_match(&mark6_match); - if (ret) - xt_unregister_match(&mark_match); +static struct xt_match xt_mark_match[] = { + { + .name = "mark", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_mark_info), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct compat_xt_mark_info), + .compat_from_user = compat_from_user, + .compat_to_user = compat_to_user, +#endif + .me = THIS_MODULE, + }, + { + .name = "mark", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_mark_info), + .me = THIS_MODULE, + }, +}; - return ret; +static int __init xt_mark_init(void) +{ + return xt_register_matches(xt_mark_match, ARRAY_SIZE(xt_mark_match)); } static void __exit xt_mark_fini(void) { - xt_unregister_match(&mark_match); - xt_unregister_match(&mark6_match); + xt_unregister_matches(xt_mark_match, ARRAY_SIZE(xt_mark_match)); } module_init(xt_mark_init); diff --git a/net/netfilter/xt_multiport.c b/net/netfilter/xt_multiport.c index 1ff0a25396e..d3aefd38093 100644 --- a/net/netfilter/xt_multiport.c +++ b/net/netfilter/xt_multiport.c @@ -176,7 +176,6 @@ 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; @@ -191,7 +190,6 @@ checkentry_v1(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; @@ -206,7 +204,6 @@ checkentry6(const char *tablename, const void *info, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) { const struct ip6t_ip6 *ip = info; @@ -221,7 +218,6 @@ checkentry6_v1(const char *tablename, const void *info, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) { const struct ip6t_ip6 *ip = info; @@ -231,84 +227,55 @@ checkentry6_v1(const char *tablename, multiinfo->count); } -static struct xt_match multiport_match = { - .name = "multiport", - .revision = 0, - .matchsize = sizeof(struct xt_multiport), - .match = &match, - .checkentry = &checkentry, - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_match multiport_match_v1 = { - .name = "multiport", - .revision = 1, - .matchsize = sizeof(struct xt_multiport_v1), - .match = &match_v1, - .checkentry = &checkentry_v1, - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_match multiport6_match = { - .name = "multiport", - .revision = 0, - .matchsize = sizeof(struct xt_multiport), - .match = &match, - .checkentry = &checkentry6, - .family = AF_INET6, - .me = THIS_MODULE, -}; - -static struct xt_match multiport6_match_v1 = { - .name = "multiport", - .revision = 1, - .matchsize = sizeof(struct xt_multiport_v1), - .match = &match_v1, - .checkentry = &checkentry6_v1, - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_multiport_match[] = { + { + .name = "multiport", + .family = AF_INET, + .revision = 0, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_multiport), + .me = THIS_MODULE, + }, + { + .name = "multiport", + .family = AF_INET, + .revision = 1, + .checkentry = checkentry_v1, + .match = match_v1, + .matchsize = sizeof(struct xt_multiport_v1), + .me = THIS_MODULE, + }, + { + .name = "multiport", + .family = AF_INET6, + .revision = 0, + .checkentry = checkentry6, + .match = match, + .matchsize = sizeof(struct xt_multiport), + .me = THIS_MODULE, + }, + { + .name = "multiport", + .family = AF_INET6, + .revision = 1, + .checkentry = checkentry6_v1, + .match = match_v1, + .matchsize = sizeof(struct xt_multiport_v1), + .me = THIS_MODULE, + }, }; static int __init xt_multiport_init(void) { - int ret; - - ret = xt_register_match(&multiport_match); - if (ret) - goto out; - - ret = xt_register_match(&multiport_match_v1); - if (ret) - goto out_unreg_multi_v0; - - ret = xt_register_match(&multiport6_match); - if (ret) - goto out_unreg_multi_v1; - - ret = xt_register_match(&multiport6_match_v1); - if (ret) - goto out_unreg_multi6_v0; - - return ret; - -out_unreg_multi6_v0: - xt_unregister_match(&multiport6_match); -out_unreg_multi_v1: - xt_unregister_match(&multiport_match_v1); -out_unreg_multi_v0: - xt_unregister_match(&multiport_match); -out: - return ret; + return xt_register_matches(xt_multiport_match, + ARRAY_SIZE(xt_multiport_match)); } static void __exit xt_multiport_fini(void) { - xt_unregister_match(&multiport_match); - xt_unregister_match(&multiport_match_v1); - xt_unregister_match(&multiport6_match); - xt_unregister_match(&multiport6_match_v1); + xt_unregister_matches(xt_multiport_match, + ARRAY_SIZE(xt_multiport_match)); } module_init(xt_multiport_init); diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index 63a96546746..fd8f954cded 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -106,7 +106,6 @@ 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; @@ -132,43 +131,34 @@ checkentry(const char *tablename, return 1; } -static struct xt_match physdev_match = { - .name = "physdev", - .match = match, - .matchsize = sizeof(struct xt_physdev_info), - .checkentry = checkentry, - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_match physdev6_match = { - .name = "physdev", - .match = match, - .matchsize = sizeof(struct xt_physdev_info), - .checkentry = checkentry, - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_physdev_match[] = { + { + .name = "physdev", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_physdev_info), + .me = THIS_MODULE, + }, + { + .name = "physdev", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_physdev_info), + .me = THIS_MODULE, + }, }; static int __init xt_physdev_init(void) { - int ret; - - ret = xt_register_match(&physdev_match); - if (ret < 0) - return ret; - - ret = xt_register_match(&physdev6_match); - if (ret < 0) - xt_unregister_match(&physdev_match); - - return ret; + return xt_register_matches(xt_physdev_match, + ARRAY_SIZE(xt_physdev_match)); } static void __exit xt_physdev_fini(void) { - xt_unregister_match(&physdev_match); - xt_unregister_match(&physdev6_match); + xt_unregister_matches(xt_physdev_match, ARRAY_SIZE(xt_physdev_match)); } module_init(xt_physdev_init); diff --git a/net/netfilter/xt_pkttype.c b/net/netfilter/xt_pkttype.c index d2f5320a80b..16e7b080428 100644 --- a/net/netfilter/xt_pkttype.c +++ b/net/netfilter/xt_pkttype.c @@ -43,40 +43,32 @@ static int match(const struct sk_buff *skb, return (type == info->pkttype) ^ info->invert; } -static struct xt_match pkttype_match = { - .name = "pkttype", - .match = match, - .matchsize = sizeof(struct xt_pkttype_info), - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_match pkttype6_match = { - .name = "pkttype", - .match = match, - .matchsize = sizeof(struct xt_pkttype_info), - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_pkttype_match[] = { + { + .name = "pkttype", + .family = AF_INET, + .match = match, + .matchsize = sizeof(struct xt_pkttype_info), + .me = THIS_MODULE, + }, + { + .name = "pkttype", + .family = AF_INET6, + .match = match, + .matchsize = sizeof(struct xt_pkttype_info), + .me = THIS_MODULE, + }, }; static int __init xt_pkttype_init(void) { - int ret; - ret = xt_register_match(&pkttype_match); - if (ret) - return ret; - - ret = xt_register_match(&pkttype6_match); - if (ret) - xt_unregister_match(&pkttype_match); - - return ret; + return xt_register_matches(xt_pkttype_match, + ARRAY_SIZE(xt_pkttype_match)); } static void __exit xt_pkttype_fini(void) { - xt_unregister_match(&pkttype_match); - xt_unregister_match(&pkttype6_match); + xt_unregister_matches(xt_pkttype_match, ARRAY_SIZE(xt_pkttype_match)); } module_init(xt_pkttype_init); diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c index ba1ca03abad..46bde2b1e1e 100644 --- a/net/netfilter/xt_policy.c +++ b/net/netfilter/xt_policy.c @@ -135,8 +135,7 @@ static int 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 matchsize, - unsigned int hook_mask) + void *matchinfo, unsigned int hook_mask) { struct xt_policy_info *info = matchinfo; @@ -165,43 +164,34 @@ static int checkentry(const char *tablename, const void *ip_void, return 1; } -static struct xt_match policy_match = { - .name = "policy", - .family = AF_INET, - .match = match, - .matchsize = sizeof(struct xt_policy_info), - .checkentry = checkentry, - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_match policy6_match = { - .name = "policy", - .family = AF_INET6, - .match = match, - .matchsize = sizeof(struct xt_policy_info), - .checkentry = checkentry, - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_policy_match[] = { + { + .name = "policy", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_policy_info), + .me = THIS_MODULE, + }, + { + .name = "policy", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_policy_info), + .me = THIS_MODULE, + }, }; static int __init init(void) { - int ret; - - ret = xt_register_match(&policy_match); - if (ret) - return ret; - ret = xt_register_match(&policy6_match); - if (ret) - xt_unregister_match(&policy_match); - return ret; + return xt_register_matches(xt_policy_match, + ARRAY_SIZE(xt_policy_match)); } static void __exit fini(void) { - xt_unregister_match(&policy6_match); - xt_unregister_match(&policy_match); + xt_unregister_matches(xt_policy_match, ARRAY_SIZE(xt_policy_match)); } module_init(init); diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c index be8d3c26b56..b75fa2c70e6 100644 --- a/net/netfilter/xt_quota.c +++ b/net/netfilter/xt_quota.c @@ -41,7 +41,7 @@ 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) + unsigned int hook_mask) { struct xt_quota_info *q = (struct xt_quota_info *)matchinfo; @@ -52,46 +52,33 @@ checkentry(const char *tablename, const void *entry, return 1; } -static struct xt_match quota_match = { - .name = "quota", - .family = AF_INET, - .match = match, - .matchsize = sizeof(struct xt_quota_info), - .checkentry = checkentry, - .me = THIS_MODULE -}; - -static struct xt_match quota_match6 = { - .name = "quota", - .family = AF_INET6, - .match = match, - .matchsize = sizeof(struct xt_quota_info), - .checkentry = checkentry, - .me = THIS_MODULE +static struct xt_match xt_quota_match[] = { + { + .name = "quota", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_quota_info), + .me = THIS_MODULE + }, + { + .name = "quota", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_quota_info), + .me = THIS_MODULE + }, }; static int __init xt_quota_init(void) { - int ret; - - ret = xt_register_match("a_match); - if (ret) - goto err1; - ret = xt_register_match("a_match6); - if (ret) - goto err2; - return ret; - -err2: - xt_unregister_match("a_match); -err1: - return ret; + return xt_register_matches(xt_quota_match, ARRAY_SIZE(xt_quota_match)); } static void __exit xt_quota_fini(void) { - xt_unregister_match("a_match6); - xt_unregister_match("a_match); + xt_unregister_matches(xt_quota_match, ARRAY_SIZE(xt_quota_match)); } module_init(xt_quota_init); diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index 843383e01d4..7956acaaa24 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -163,7 +163,6 @@ 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 = matchinfo; @@ -178,44 +177,35 @@ checkentry(const char *tablename, | SCTP_CHUNK_MATCH_ONLY))); } -static struct xt_match sctp_match = { - .name = "sctp", - .match = match, - .matchsize = sizeof(struct xt_sctp_info), - .proto = IPPROTO_SCTP, - .checkentry = checkentry, - .family = AF_INET, - .me = THIS_MODULE -}; - -static struct xt_match sctp6_match = { - .name = "sctp", - .match = match, - .matchsize = sizeof(struct xt_sctp_info), - .proto = IPPROTO_SCTP, - .checkentry = checkentry, - .family = AF_INET6, - .me = THIS_MODULE +static struct xt_match xt_sctp_match[] = { + { + .name = "sctp", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_sctp_info), + .proto = IPPROTO_SCTP, + .me = THIS_MODULE + }, + { + .name = "sctp", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_sctp_info), + .proto = IPPROTO_SCTP, + .me = THIS_MODULE + }, }; static int __init xt_sctp_init(void) { - int ret; - ret = xt_register_match(&sctp_match); - if (ret) - return ret; - - ret = xt_register_match(&sctp6_match); - if (ret) - xt_unregister_match(&sctp_match); - - return ret; + return xt_register_matches(xt_sctp_match, ARRAY_SIZE(xt_sctp_match)); } static void __exit xt_sctp_fini(void) { - xt_unregister_match(&sctp6_match); - xt_unregister_match(&sctp_match); + xt_unregister_matches(xt_sctp_match, ARRAY_SIZE(xt_sctp_match)); } module_init(xt_sctp_init); diff --git a/net/netfilter/xt_state.c b/net/netfilter/xt_state.c index f9e304dc450..d9010b16a1f 100644 --- a/net/netfilter/xt_state.c +++ b/net/netfilter/xt_state.c @@ -48,7 +48,6 @@ static int check(const char *tablename, const void *inf, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) @@ -62,54 +61,43 @@ static int check(const char *tablename, } static void -destroy(const struct xt_match *match, void *matchinfo, unsigned int matchsize) +destroy(const struct xt_match *match, void *matchinfo) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_ct_l3proto_module_put(match->family); #endif } -static struct xt_match state_match = { - .name = "state", - .match = match, - .checkentry = check, - .destroy = destroy, - .matchsize = sizeof(struct xt_state_info), - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_match state6_match = { - .name = "state", - .match = match, - .checkentry = check, - .destroy = destroy, - .matchsize = sizeof(struct xt_state_info), - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_state_match[] = { + { + .name = "state", + .family = AF_INET, + .checkentry = check, + .match = match, + .destroy = destroy, + .matchsize = sizeof(struct xt_state_info), + .me = THIS_MODULE, + }, + { + .name = "state", + .family = AF_INET6, + .checkentry = check, + .match = match, + .destroy = destroy, + .matchsize = sizeof(struct xt_state_info), + .me = THIS_MODULE, + }, }; static int __init xt_state_init(void) { - int ret; - need_conntrack(); - - ret = xt_register_match(&state_match); - if (ret < 0) - return ret; - - ret = xt_register_match(&state6_match); - if (ret < 0) - xt_unregister_match(&state_match); - - return ret; + return xt_register_matches(xt_state_match, ARRAY_SIZE(xt_state_match)); } static void __exit xt_state_fini(void) { - xt_unregister_match(&state_match); - xt_unregister_match(&state6_match); + xt_unregister_matches(xt_state_match, ARRAY_SIZE(xt_state_match)); } module_init(xt_state_init); diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c index de1037f5859..091a9f89f5d 100644 --- a/net/netfilter/xt_statistic.c +++ b/net/netfilter/xt_statistic.c @@ -55,7 +55,7 @@ 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) + unsigned int hook_mask) { struct xt_statistic_info *info = (struct xt_statistic_info *)matchinfo; @@ -66,46 +66,35 @@ checkentry(const char *tablename, const void *entry, return 1; } -static struct xt_match statistic_match = { - .name = "statistic", - .match = match, - .matchsize = sizeof(struct xt_statistic_info), - .checkentry = checkentry, - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_match statistic_match6 = { - .name = "statistic", - .match = match, - .matchsize = sizeof(struct xt_statistic_info), - .checkentry = checkentry, - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_statistic_match[] = { + { + .name = "statistic", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_statistic_info), + .me = THIS_MODULE, + }, + { + .name = "statistic", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .matchsize = sizeof(struct xt_statistic_info), + .me = THIS_MODULE, + }, }; static int __init xt_statistic_init(void) { - int ret; - - ret = xt_register_match(&statistic_match); - if (ret) - goto err1; - - ret = xt_register_match(&statistic_match6); - if (ret) - goto err2; - return ret; -err2: - xt_unregister_match(&statistic_match); -err1: - return ret; + return xt_register_matches(xt_statistic_match, + ARRAY_SIZE(xt_statistic_match)); } static void __exit xt_statistic_fini(void) { - xt_unregister_match(&statistic_match6); - xt_unregister_match(&statistic_match); + xt_unregister_matches(xt_statistic_match, + ARRAY_SIZE(xt_statistic_match)); } module_init(xt_statistic_init); diff --git a/net/netfilter/xt_string.c b/net/netfilter/xt_string.c index 275330fcdaa..4453252400a 100644 --- a/net/netfilter/xt_string.c +++ b/net/netfilter/xt_string.c @@ -46,7 +46,6 @@ 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_string_info *conf = matchinfo; @@ -69,49 +68,40 @@ static int checkentry(const char *tablename, return 1; } -static void destroy(const struct xt_match *match, void *matchinfo, - unsigned int matchsize) +static void destroy(const struct xt_match *match, void *matchinfo) { textsearch_destroy(STRING_TEXT_PRIV(matchinfo)->config); } -static struct xt_match string_match = { - .name = "string", - .match = match, - .matchsize = sizeof(struct xt_string_info), - .checkentry = checkentry, - .destroy = destroy, - .family = AF_INET, - .me = THIS_MODULE -}; -static struct xt_match string6_match = { - .name = "string", - .match = match, - .matchsize = sizeof(struct xt_string_info), - .checkentry = checkentry, - .destroy = destroy, - .family = AF_INET6, - .me = THIS_MODULE +static struct xt_match xt_string_match[] = { + { + .name = "string", + .family = AF_INET, + .checkentry = checkentry, + .match = match, + .destroy = destroy, + .matchsize = sizeof(struct xt_string_info), + .me = THIS_MODULE + }, + { + .name = "string", + .family = AF_INET6, + .checkentry = checkentry, + .match = match, + .destroy = destroy, + .matchsize = sizeof(struct xt_string_info), + .me = THIS_MODULE + }, }; static int __init xt_string_init(void) { - int ret; - - ret = xt_register_match(&string_match); - if (ret) - return ret; - ret = xt_register_match(&string6_match); - if (ret) - xt_unregister_match(&string_match); - - return ret; + return xt_register_matches(xt_string_match, ARRAY_SIZE(xt_string_match)); } static void __exit xt_string_fini(void) { - xt_unregister_match(&string_match); - xt_unregister_match(&string6_match); + xt_unregister_matches(xt_string_match, ARRAY_SIZE(xt_string_match)); } module_init(xt_string_init); diff --git a/net/netfilter/xt_tcpmss.c b/net/netfilter/xt_tcpmss.c index cf7d335cadc..a3682fe2f19 100644 --- a/net/netfilter/xt_tcpmss.c +++ b/net/netfilter/xt_tcpmss.c @@ -18,21 +18,22 @@ #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> -#define TH_SYN 0x02 - MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); MODULE_DESCRIPTION("iptables TCP MSS match module"); MODULE_ALIAS("ipt_tcpmss"); -/* Returns 1 if the mss option is set and matched by the range, 0 otherwise */ -static inline int -mssoption_match(u_int16_t min, u_int16_t max, - const struct sk_buff *skb, - unsigned int protoff, - int invert, - 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 xt_tcpmss_match_info *info = matchinfo; struct tcphdr _tcph, *th; /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ u8 _opt[15 * 4 - sizeof(_tcph)], *op; @@ -64,72 +65,50 @@ mssoption_match(u_int16_t min, u_int16_t max, mssval = (op[i+2] << 8) | op[i+3]; - return (mssval >= min && mssval <= max) ^ invert; + return (mssval >= info->mss_min && + mssval <= info->mss_max) ^ info->invert; } - if (op[i] < 2) i++; - else i += op[i+1]?:1; + if (op[i] < 2) + i++; + else + i += op[i+1] ? : 1; } out: - return invert; + return info->invert; - dropit: +dropit: *hotdrop = 1; return 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_tcpmss_match_info *info = matchinfo; - - return mssoption_match(info->mss_min, info->mss_max, skb, protoff, - info->invert, hotdrop); -} - -static struct xt_match tcpmss_match = { - .name = "tcpmss", - .match = match, - .matchsize = sizeof(struct xt_tcpmss_match_info), - .proto = IPPROTO_TCP, - .family = AF_INET, - .me = THIS_MODULE, -}; - -static struct xt_match tcpmss6_match = { - .name = "tcpmss", - .match = match, - .matchsize = sizeof(struct xt_tcpmss_match_info), - .proto = IPPROTO_TCP, - .family = AF_INET6, - .me = THIS_MODULE, +static struct xt_match xt_tcpmss_match[] = { + { + .name = "tcpmss", + .family = AF_INET, + .match = match, + .matchsize = sizeof(struct xt_tcpmss_match_info), + .proto = IPPROTO_TCP, + .me = THIS_MODULE, + }, + { + .name = "tcpmss", + .family = AF_INET6, + .match = match, + .matchsize = sizeof(struct xt_tcpmss_match_info), + .proto = IPPROTO_TCP, + .me = THIS_MODULE, + }, }; - static int __init xt_tcpmss_init(void) { - int ret; - ret = xt_register_match(&tcpmss_match); - if (ret) - return ret; - - ret = xt_register_match(&tcpmss6_match); - if (ret) - xt_unregister_match(&tcpmss_match); - - return ret; + return xt_register_matches(xt_tcpmss_match, + ARRAY_SIZE(xt_tcpmss_match)); } static void __exit xt_tcpmss_fini(void) { - xt_unregister_match(&tcpmss6_match); - xt_unregister_match(&tcpmss_match); + xt_unregister_matches(xt_tcpmss_match, ARRAY_SIZE(xt_tcpmss_match)); } module_init(xt_tcpmss_init); diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c index a9a63aa6893..e76a68e0bc6 100644 --- a/net/netfilter/xt_tcpudp.c +++ b/net/netfilter/xt_tcpudp.c @@ -141,7 +141,6 @@ tcp_checkentry(const char *tablename, const void *info, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) { const struct xt_tcp *tcpinfo = matchinfo; @@ -190,7 +189,6 @@ udp_checkentry(const char *tablename, const void *info, const struct xt_match *match, void *matchinfo, - unsigned int matchsize, unsigned int hook_mask) { const struct xt_tcp *udpinfo = matchinfo; @@ -199,81 +197,54 @@ udp_checkentry(const char *tablename, return !(udpinfo->invflags & ~XT_UDP_INV_MASK); } -static struct xt_match tcp_matchstruct = { - .name = "tcp", - .match = tcp_match, - .matchsize = sizeof(struct xt_tcp), - .proto = IPPROTO_TCP, - .family = AF_INET, - .checkentry = tcp_checkentry, - .me = THIS_MODULE, -}; - -static struct xt_match tcp6_matchstruct = { - .name = "tcp", - .match = tcp_match, - .matchsize = sizeof(struct xt_tcp), - .proto = IPPROTO_TCP, - .family = AF_INET6, - .checkentry = tcp_checkentry, - .me = THIS_MODULE, -}; - -static struct xt_match udp_matchstruct = { - .name = "udp", - .match = udp_match, - .matchsize = sizeof(struct xt_udp), - .proto = IPPROTO_UDP, - .family = AF_INET, - .checkentry = udp_checkentry, - .me = THIS_MODULE, -}; -static struct xt_match udp6_matchstruct = { - .name = "udp", - .match = udp_match, - .matchsize = sizeof(struct xt_udp), - .proto = IPPROTO_UDP, - .family = AF_INET6, - .checkentry = udp_checkentry, - .me = THIS_MODULE, +static struct xt_match xt_tcpudp_match[] = { + { + .name = "tcp", + .family = AF_INET, + .checkentry = tcp_checkentry, + .match = tcp_match, + .matchsize = sizeof(struct xt_tcp), + .proto = IPPROTO_TCP, + .me = THIS_MODULE, + }, + { + .name = "tcp", + .family = AF_INET6, + .checkentry = tcp_checkentry, + .match = tcp_match, + .matchsize = sizeof(struct xt_tcp), + .proto = IPPROTO_TCP, + .me = THIS_MODULE, + }, + { + .name = "udp", + .family = AF_INET, + .checkentry = udp_checkentry, + .match = udp_match, + .matchsize = sizeof(struct xt_udp), + .proto = IPPROTO_UDP, + .me = THIS_MODULE, + }, + { + .name = "udp", + .family = AF_INET6, + .checkentry = udp_checkentry, + .match = udp_match, + .matchsize = sizeof(struct xt_udp), + .proto = IPPROTO_UDP, + .me = THIS_MODULE, + }, }; static int __init xt_tcpudp_init(void) { - int ret; - ret = xt_register_match(&tcp_matchstruct); - if (ret) - return ret; - - ret = xt_register_match(&tcp6_matchstruct); - if (ret) - goto out_unreg_tcp; - - ret = xt_register_match(&udp_matchstruct); - if (ret) - goto out_unreg_tcp6; - - ret = xt_register_match(&udp6_matchstruct); - if (ret) - goto out_unreg_udp; - - return ret; - -out_unreg_udp: - xt_unregister_match(&udp_matchstruct); -out_unreg_tcp6: - xt_unregister_match(&tcp6_matchstruct); -out_unreg_tcp: - xt_unregister_match(&tcp_matchstruct); - return ret; + return xt_register_matches(xt_tcpudp_match, + ARRAY_SIZE(xt_tcpudp_match)); } static void __exit xt_tcpudp_fini(void) { - xt_unregister_match(&udp6_matchstruct); - xt_unregister_match(&udp_matchstruct); - xt_unregister_match(&tcp6_matchstruct); - xt_unregister_match(&tcp_matchstruct); + xt_unregister_matches(xt_tcpudp_match, ARRAY_SIZE(xt_tcpudp_match)); } module_init(xt_tcpudp_init); diff --git a/net/netlabel/Kconfig b/net/netlabel/Kconfig new file mode 100644 index 00000000000..fe23cb7f1e8 --- /dev/null +++ b/net/netlabel/Kconfig @@ -0,0 +1,14 @@ +# +# NetLabel configuration +# + +config NETLABEL + bool "NetLabel subsystem support" + depends on NET && SECURITY + default n + ---help--- + NetLabel provides support for explicit network packet labeling + protocols such as CIPSO and RIPSO. For more information see + Documentation/netlabel. + + If you are unsure, say N. diff --git a/net/netlabel/Makefile b/net/netlabel/Makefile new file mode 100644 index 00000000000..8af18c0a47d --- /dev/null +++ b/net/netlabel/Makefile @@ -0,0 +1,16 @@ +# +# Makefile for the NetLabel subsystem. +# +# Feb 9, 2006, Paul Moore <paul.moore@hp.com> +# + +# base objects +obj-y := netlabel_user.o netlabel_kapi.o netlabel_domainhash.o + +# management objects +obj-y += netlabel_mgmt.o + +# protocol modules +obj-y += netlabel_unlabeled.o +obj-y += netlabel_cipso_v4.o + diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c new file mode 100644 index 00000000000..a4f40adc447 --- /dev/null +++ b/net/netlabel/netlabel_cipso_v4.c @@ -0,0 +1,542 @@ +/* + * NetLabel CIPSO/IPv4 Support + * + * This file defines the CIPSO/IPv4 functions for the NetLabel system. The + * NetLabel system manages static and dynamic label mappings for network + * protocols such as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <net/netlink.h> +#include <net/genetlink.h> +#include <net/netlabel.h> +#include <net/cipso_ipv4.h> + +#include "netlabel_user.h" +#include "netlabel_cipso_v4.h" + +/* NetLabel Generic NETLINK CIPSOv4 family */ +static struct genl_family netlbl_cipsov4_gnl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = NETLBL_NLTYPE_CIPSOV4_NAME, + .version = NETLBL_PROTO_VERSION, + .maxattr = 0, +}; + + +/* + * Helper Functions + */ + +/** + * netlbl_cipsov4_doi_free - Frees a CIPSO V4 DOI definition + * @entry: the entry's RCU field + * + * Description: + * This function is designed to be used as a callback to the call_rcu() + * function so that the memory allocated to the DOI definition can be released + * safely. + * + */ +static void netlbl_cipsov4_doi_free(struct rcu_head *entry) +{ + struct cipso_v4_doi *ptr; + + ptr = container_of(entry, struct cipso_v4_doi, rcu); + switch (ptr->type) { + case CIPSO_V4_MAP_STD: + kfree(ptr->map.std->lvl.cipso); + kfree(ptr->map.std->lvl.local); + kfree(ptr->map.std->cat.cipso); + kfree(ptr->map.std->cat.local); + break; + } + kfree(ptr); +} + + +/* + * NetLabel Command Handlers + */ + +/** + * netlbl_cipsov4_add_std - Adds a CIPSO V4 DOI definition + * @doi: the DOI value + * @msg: the ADD message data + * @msg_size: the size of the ADD message buffer + * + * Description: + * Create a new CIPSO_V4_MAP_STD DOI definition based on the given ADD message + * and add it to the CIPSO V4 engine. Return zero on success and non-zero on + * error. + * + */ +static int netlbl_cipsov4_add_std(u32 doi, struct nlattr *msg, size_t msg_size) +{ + int ret_val = -EINVAL; + int msg_len = msg_size; + u32 num_tags; + u32 num_lvls; + u32 num_cats; + struct cipso_v4_doi *doi_def = NULL; + u32 iter; + u32 tmp_val_a; + u32 tmp_val_b; + + if (msg_len < NETLBL_LEN_U32) + goto add_std_failure; + num_tags = netlbl_getinc_u32(&msg, &msg_len); + if (num_tags == 0 || num_tags > CIPSO_V4_TAG_MAXCNT) + goto add_std_failure; + + doi_def = kmalloc(sizeof(*doi_def), GFP_KERNEL); + if (doi_def == NULL) { + ret_val = -ENOMEM; + goto add_std_failure; + } + doi_def->map.std = kzalloc(sizeof(*doi_def->map.std), GFP_KERNEL); + if (doi_def->map.std == NULL) { + ret_val = -ENOMEM; + goto add_std_failure; + } + doi_def->type = CIPSO_V4_MAP_STD; + + for (iter = 0; iter < num_tags; iter++) { + if (msg_len < NETLBL_LEN_U8) + goto add_std_failure; + doi_def->tags[iter] = netlbl_getinc_u8(&msg, &msg_len); + switch (doi_def->tags[iter]) { + case CIPSO_V4_TAG_RBITMAP: + break; + default: + goto add_std_failure; + } + } + if (iter < CIPSO_V4_TAG_MAXCNT) + doi_def->tags[iter] = CIPSO_V4_TAG_INVALID; + + if (msg_len < 6 * NETLBL_LEN_U32) + goto add_std_failure; + + num_lvls = netlbl_getinc_u32(&msg, &msg_len); + if (num_lvls == 0) + goto add_std_failure; + doi_def->map.std->lvl.local_size = netlbl_getinc_u32(&msg, &msg_len); + if (doi_def->map.std->lvl.local_size > CIPSO_V4_MAX_LOC_LVLS) + goto add_std_failure; + doi_def->map.std->lvl.local = kcalloc(doi_def->map.std->lvl.local_size, + sizeof(u32), + GFP_KERNEL); + if (doi_def->map.std->lvl.local == NULL) { + ret_val = -ENOMEM; + goto add_std_failure; + } + doi_def->map.std->lvl.cipso_size = netlbl_getinc_u8(&msg, &msg_len); + if (doi_def->map.std->lvl.cipso_size > CIPSO_V4_MAX_REM_LVLS) + goto add_std_failure; + doi_def->map.std->lvl.cipso = kcalloc(doi_def->map.std->lvl.cipso_size, + sizeof(u32), + GFP_KERNEL); + if (doi_def->map.std->lvl.cipso == NULL) { + ret_val = -ENOMEM; + goto add_std_failure; + } + + num_cats = netlbl_getinc_u32(&msg, &msg_len); + doi_def->map.std->cat.local_size = netlbl_getinc_u32(&msg, &msg_len); + if (doi_def->map.std->cat.local_size > CIPSO_V4_MAX_LOC_CATS) + goto add_std_failure; + doi_def->map.std->cat.local = kcalloc(doi_def->map.std->cat.local_size, + sizeof(u32), + GFP_KERNEL); + if (doi_def->map.std->cat.local == NULL) { + ret_val = -ENOMEM; + goto add_std_failure; + } + doi_def->map.std->cat.cipso_size = netlbl_getinc_u16(&msg, &msg_len); + if (doi_def->map.std->cat.cipso_size > CIPSO_V4_MAX_REM_CATS) + goto add_std_failure; + doi_def->map.std->cat.cipso = kcalloc(doi_def->map.std->cat.cipso_size, + sizeof(u32), + GFP_KERNEL); + if (doi_def->map.std->cat.cipso == NULL) { + ret_val = -ENOMEM; + goto add_std_failure; + } + + if (msg_len < + num_lvls * (NETLBL_LEN_U32 + NETLBL_LEN_U8) + + num_cats * (NETLBL_LEN_U32 + NETLBL_LEN_U16)) + goto add_std_failure; + + for (iter = 0; iter < doi_def->map.std->lvl.cipso_size; iter++) + doi_def->map.std->lvl.cipso[iter] = CIPSO_V4_INV_LVL; + for (iter = 0; iter < doi_def->map.std->lvl.local_size; iter++) + doi_def->map.std->lvl.local[iter] = CIPSO_V4_INV_LVL; + for (iter = 0; iter < doi_def->map.std->cat.cipso_size; iter++) + doi_def->map.std->cat.cipso[iter] = CIPSO_V4_INV_CAT; + for (iter = 0; iter < doi_def->map.std->cat.local_size; iter++) + doi_def->map.std->cat.local[iter] = CIPSO_V4_INV_CAT; + + for (iter = 0; iter < num_lvls; iter++) { + tmp_val_a = netlbl_getinc_u32(&msg, &msg_len); + tmp_val_b = netlbl_getinc_u8(&msg, &msg_len); + + if (tmp_val_a >= doi_def->map.std->lvl.local_size || + tmp_val_b >= doi_def->map.std->lvl.cipso_size) + goto add_std_failure; + + doi_def->map.std->lvl.cipso[tmp_val_b] = tmp_val_a; + doi_def->map.std->lvl.local[tmp_val_a] = tmp_val_b; + } + + for (iter = 0; iter < num_cats; iter++) { + tmp_val_a = netlbl_getinc_u32(&msg, &msg_len); + tmp_val_b = netlbl_getinc_u16(&msg, &msg_len); + + if (tmp_val_a >= doi_def->map.std->cat.local_size || + tmp_val_b >= doi_def->map.std->cat.cipso_size) + goto add_std_failure; + + doi_def->map.std->cat.cipso[tmp_val_b] = tmp_val_a; + doi_def->map.std->cat.local[tmp_val_a] = tmp_val_b; + } + + doi_def->doi = doi; + ret_val = cipso_v4_doi_add(doi_def); + if (ret_val != 0) + goto add_std_failure; + return 0; + +add_std_failure: + if (doi_def) + netlbl_cipsov4_doi_free(&doi_def->rcu); + return ret_val; +} + +/** + * netlbl_cipsov4_add_pass - Adds a CIPSO V4 DOI definition + * @doi: the DOI value + * @msg: the ADD message data + * @msg_size: the size of the ADD message buffer + * + * Description: + * Create a new CIPSO_V4_MAP_PASS DOI definition based on the given ADD message + * and add it to the CIPSO V4 engine. Return zero on success and non-zero on + * error. + * + */ +static int netlbl_cipsov4_add_pass(u32 doi, + struct nlattr *msg, + size_t msg_size) +{ + int ret_val = -EINVAL; + int msg_len = msg_size; + u32 num_tags; + struct cipso_v4_doi *doi_def = NULL; + u32 iter; + + if (msg_len < NETLBL_LEN_U32) + goto add_pass_failure; + num_tags = netlbl_getinc_u32(&msg, &msg_len); + if (num_tags == 0 || num_tags > CIPSO_V4_TAG_MAXCNT) + goto add_pass_failure; + + doi_def = kmalloc(sizeof(*doi_def), GFP_KERNEL); + if (doi_def == NULL) { + ret_val = -ENOMEM; + goto add_pass_failure; + } + doi_def->type = CIPSO_V4_MAP_PASS; + + for (iter = 0; iter < num_tags; iter++) { + if (msg_len < NETLBL_LEN_U8) + goto add_pass_failure; + doi_def->tags[iter] = netlbl_getinc_u8(&msg, &msg_len); + switch (doi_def->tags[iter]) { + case CIPSO_V4_TAG_RBITMAP: + break; + default: + goto add_pass_failure; + } + } + if (iter < CIPSO_V4_TAG_MAXCNT) + doi_def->tags[iter] = CIPSO_V4_TAG_INVALID; + + doi_def->doi = doi; + ret_val = cipso_v4_doi_add(doi_def); + if (ret_val != 0) + goto add_pass_failure; + return 0; + +add_pass_failure: + if (doi_def) + netlbl_cipsov4_doi_free(&doi_def->rcu); + return ret_val; +} + +/** + * netlbl_cipsov4_add - Handle an ADD message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Create a new DOI definition based on the given ADD message and add it to the + * CIPSO V4 engine. Returns zero on success, negative values on failure. + * + */ +static int netlbl_cipsov4_add(struct sk_buff *skb, struct genl_info *info) + +{ + int ret_val = -EINVAL; + u32 doi; + u32 map_type; + int msg_len = netlbl_netlink_payload_len(skb); + struct nlattr *msg = netlbl_netlink_payload_data(skb); + + ret_val = netlbl_netlink_cap_check(skb, CAP_NET_ADMIN); + if (ret_val != 0) + goto add_return; + + if (msg_len < 2 * NETLBL_LEN_U32) + goto add_return; + + doi = netlbl_getinc_u32(&msg, &msg_len); + map_type = netlbl_getinc_u32(&msg, &msg_len); + switch (map_type) { + case CIPSO_V4_MAP_STD: + ret_val = netlbl_cipsov4_add_std(doi, msg, msg_len); + break; + case CIPSO_V4_MAP_PASS: + ret_val = netlbl_cipsov4_add_pass(doi, msg, msg_len); + break; + } + +add_return: + netlbl_netlink_send_ack(info, + netlbl_cipsov4_gnl_family.id, + NLBL_CIPSOV4_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_cipsov4_list - Handle a LIST message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated LIST message and respond accordingly. Returns + * zero on success and negative values on error. + * + */ +static int netlbl_cipsov4_list(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -EINVAL; + u32 doi; + struct nlattr *msg = netlbl_netlink_payload_data(skb); + struct sk_buff *ans_skb; + + if (netlbl_netlink_payload_len(skb) != NETLBL_LEN_U32) + goto list_failure; + + doi = nla_get_u32(msg); + ans_skb = cipso_v4_doi_dump(doi, NLMSG_SPACE(GENL_HDRLEN)); + if (ans_skb == NULL) { + ret_val = -ENOMEM; + goto list_failure; + } + netlbl_netlink_hdr_push(ans_skb, + info->snd_pid, + 0, + netlbl_cipsov4_gnl_family.id, + NLBL_CIPSOV4_C_LIST); + + ret_val = netlbl_netlink_snd(ans_skb, info->snd_pid); + if (ret_val != 0) + goto list_failure; + + return 0; + +list_failure: + netlbl_netlink_send_ack(info, + netlbl_cipsov4_gnl_family.id, + NLBL_CIPSOV4_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_cipsov4_listall - Handle a LISTALL message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated LISTALL message and respond accordingly. Returns + * zero on success and negative values on error. + * + */ +static int netlbl_cipsov4_listall(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -EINVAL; + struct sk_buff *ans_skb; + + ans_skb = cipso_v4_doi_dump_all(NLMSG_SPACE(GENL_HDRLEN)); + if (ans_skb == NULL) { + ret_val = -ENOMEM; + goto listall_failure; + } + netlbl_netlink_hdr_push(ans_skb, + info->snd_pid, + 0, + netlbl_cipsov4_gnl_family.id, + NLBL_CIPSOV4_C_LISTALL); + + ret_val = netlbl_netlink_snd(ans_skb, info->snd_pid); + if (ret_val != 0) + goto listall_failure; + + return 0; + +listall_failure: + netlbl_netlink_send_ack(info, + netlbl_cipsov4_gnl_family.id, + NLBL_CIPSOV4_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_cipsov4_remove - Handle a REMOVE message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated REMOVE message and respond accordingly. Returns + * zero on success, negative values on failure. + * + */ +static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val; + u32 doi; + struct nlattr *msg = netlbl_netlink_payload_data(skb); + + ret_val = netlbl_netlink_cap_check(skb, CAP_NET_ADMIN); + if (ret_val != 0) + goto remove_return; + + if (netlbl_netlink_payload_len(skb) != NETLBL_LEN_U32) { + ret_val = -EINVAL; + goto remove_return; + } + + doi = nla_get_u32(msg); + ret_val = cipso_v4_doi_remove(doi, netlbl_cipsov4_doi_free); + +remove_return: + netlbl_netlink_send_ack(info, + netlbl_cipsov4_gnl_family.id, + NLBL_CIPSOV4_C_ACK, + -ret_val); + return ret_val; +} + +/* + * NetLabel Generic NETLINK Command Definitions + */ + +static struct genl_ops netlbl_cipsov4_genl_c_add = { + .cmd = NLBL_CIPSOV4_C_ADD, + .flags = 0, + .doit = netlbl_cipsov4_add, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_cipsov4_genl_c_remove = { + .cmd = NLBL_CIPSOV4_C_REMOVE, + .flags = 0, + .doit = netlbl_cipsov4_remove, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_cipsov4_genl_c_list = { + .cmd = NLBL_CIPSOV4_C_LIST, + .flags = 0, + .doit = netlbl_cipsov4_list, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_cipsov4_genl_c_listall = { + .cmd = NLBL_CIPSOV4_C_LISTALL, + .flags = 0, + .doit = netlbl_cipsov4_listall, + .dumpit = NULL, +}; + +/* + * NetLabel Generic NETLINK Protocol Functions + */ + +/** + * netlbl_cipsov4_genl_init - Register the CIPSOv4 NetLabel component + * + * Description: + * Register the CIPSOv4 packet NetLabel component with the Generic NETLINK + * mechanism. Returns zero on success, negative values on failure. + * + */ +int netlbl_cipsov4_genl_init(void) +{ + int ret_val; + + ret_val = genl_register_family(&netlbl_cipsov4_gnl_family); + if (ret_val != 0) + return ret_val; + + ret_val = genl_register_ops(&netlbl_cipsov4_gnl_family, + &netlbl_cipsov4_genl_c_add); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_cipsov4_gnl_family, + &netlbl_cipsov4_genl_c_remove); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_cipsov4_gnl_family, + &netlbl_cipsov4_genl_c_list); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_cipsov4_gnl_family, + &netlbl_cipsov4_genl_c_listall); + if (ret_val != 0) + return ret_val; + + return 0; +} diff --git a/net/netlabel/netlabel_cipso_v4.h b/net/netlabel/netlabel_cipso_v4.h new file mode 100644 index 00000000000..4c6ff4b9300 --- /dev/null +++ b/net/netlabel/netlabel_cipso_v4.h @@ -0,0 +1,217 @@ +/* + * NetLabel CIPSO/IPv4 Support + * + * This file defines the CIPSO/IPv4 functions for the NetLabel system. The + * NetLabel system manages static and dynamic label mappings for network + * protocols such as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#ifndef _NETLABEL_CIPSO_V4 +#define _NETLABEL_CIPSO_V4 + +#include <net/netlabel.h> + +/* + * The following NetLabel payloads are supported by the CIPSO subsystem, all + * of which are preceeded by the nlmsghdr struct. + * + * o ACK: + * Sent by the kernel in response to an applications message, applications + * should never send this message. + * + * +----------------------+-----------------------+ + * | seq number (32 bits) | return code (32 bits) | + * +----------------------+-----------------------+ + * + * seq number: the sequence number of the original message, taken from the + * nlmsghdr structure + * return code: return value, based on errno values + * + * o ADD: + * Sent by an application to add a new DOI mapping table, after completion + * of the task the kernel should ACK this message. + * + * +---------------+--------------------+---------------------+ + * | DOI (32 bits) | map type (32 bits) | tag count (32 bits) | ... + * +---------------+--------------------+---------------------+ + * + * +-----------------+ + * | tag #X (8 bits) | ... repeated + * +-----------------+ + * + * +-------------- ---- --- -- - + * | mapping data + * +-------------- ---- --- -- - + * + * DOI: the DOI value + * map type: the mapping table type (defined in the cipso_ipv4.h header + * as CIPSO_V4_MAP_*) + * tag count: the number of tags, must be greater than zero + * tag: the CIPSO tag for the DOI, tags listed first are given + * higher priorirty when sending packets + * mapping data: specific to the map type (see below) + * + * CIPSO_V4_MAP_STD + * + * +------------------+-----------------------+----------------------+ + * | levels (32 bits) | max l level (32 bits) | max r level (8 bits) | ... + * +------------------+-----------------------+----------------------+ + * + * +----------------------+---------------------+---------------------+ + * | categories (32 bits) | max l cat (32 bits) | max r cat (16 bits) | ... + * +----------------------+---------------------+---------------------+ + * + * +--------------------------+-------------------------+ + * | local level #X (32 bits) | CIPSO level #X (8 bits) | ... repeated + * +--------------------------+-------------------------+ + * + * +-----------------------------+-----------------------------+ + * | local category #X (32 bits) | CIPSO category #X (16 bits) | ... repeated + * +-----------------------------+-----------------------------+ + * + * levels: the number of level mappings + * max l level: the highest local level + * max r level: the highest remote/CIPSO level + * categories: the number of category mappings + * max l cat: the highest local category + * max r cat: the highest remote/CIPSO category + * local level: the local part of a level mapping + * CIPSO level: the remote/CIPSO part of a level mapping + * local category: the local part of a category mapping + * CIPSO category: the remote/CIPSO part of a category mapping + * + * CIPSO_V4_MAP_PASS + * + * No mapping data is needed for this map type. + * + * o REMOVE: + * Sent by an application to remove a specific DOI mapping table from the + * CIPSO V4 system. The kernel should ACK this message. + * + * +---------------+ + * | DOI (32 bits) | + * +---------------+ + * + * DOI: the DOI value + * + * o LIST: + * Sent by an application to list the details of a DOI definition. The + * kernel should send an ACK on error or a response as indicated below. The + * application generated message format is shown below. + * + * +---------------+ + * | DOI (32 bits) | + * +---------------+ + * + * DOI: the DOI value + * + * The valid response message format depends on the type of the DOI mapping, + * the known formats are shown below. + * + * +--------------------+ + * | map type (32 bits) | ... + * +--------------------+ + * + * map type: the DOI mapping table type (defined in the cipso_ipv4.h + * header as CIPSO_V4_MAP_*) + * + * (map type == CIPSO_V4_MAP_STD) + * + * +----------------+------------------+----------------------+ + * | tags (32 bits) | levels (32 bits) | categories (32 bits) | ... + * +----------------+------------------+----------------------+ + * + * +-----------------+ + * | tag #X (8 bits) | ... repeated + * +-----------------+ + * + * +--------------------------+-------------------------+ + * | local level #X (32 bits) | CIPSO level #X (8 bits) | ... repeated + * +--------------------------+-------------------------+ + * + * +-----------------------------+-----------------------------+ + * | local category #X (32 bits) | CIPSO category #X (16 bits) | ... repeated + * +-----------------------------+-----------------------------+ + * + * tags: the number of CIPSO tag types + * levels: the number of level mappings + * categories: the number of category mappings + * tag: the tag number, tags listed first are given higher + * priority when sending packets + * local level: the local part of a level mapping + * CIPSO level: the remote/CIPSO part of a level mapping + * local category: the local part of a category mapping + * CIPSO category: the remote/CIPSO part of a category mapping + * + * (map type == CIPSO_V4_MAP_PASS) + * + * +----------------+ + * | tags (32 bits) | ... + * +----------------+ + * + * +-----------------+ + * | tag #X (8 bits) | ... repeated + * +-----------------+ + * + * tags: the number of CIPSO tag types + * tag: the tag number, tags listed first are given higher + * priority when sending packets + * + * o LISTALL: + * This message is sent by an application to list the valid DOIs on the + * system. There is no payload and the kernel should respond with an ACK + * or the following message. + * + * +---------------------+------------------+-----------------------+ + * | DOI count (32 bits) | DOI #X (32 bits) | map type #X (32 bits) | + * +---------------------+------------------+-----------------------+ + * + * +-----------------------+ + * | map type #X (32 bits) | ... + * +-----------------------+ + * + * DOI count: the number of DOIs + * DOI: the DOI value + * map type: the DOI mapping table type (defined in the cipso_ipv4.h + * header as CIPSO_V4_MAP_*) + * + */ + +/* NetLabel CIPSOv4 commands */ +enum { + NLBL_CIPSOV4_C_UNSPEC, + NLBL_CIPSOV4_C_ACK, + NLBL_CIPSOV4_C_ADD, + NLBL_CIPSOV4_C_REMOVE, + NLBL_CIPSOV4_C_LIST, + NLBL_CIPSOV4_C_LISTALL, + __NLBL_CIPSOV4_C_MAX, +}; +#define NLBL_CIPSOV4_C_MAX (__NLBL_CIPSOV4_C_MAX - 1) + +/* NetLabel protocol functions */ +int netlbl_cipsov4_genl_init(void); + +#endif diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c new file mode 100644 index 00000000000..0489a137810 --- /dev/null +++ b/net/netlabel/netlabel_domainhash.c @@ -0,0 +1,513 @@ +/* + * NetLabel Domain Hash Table + * + * This file manages the domain hash table that NetLabel uses to determine + * which network labeling protocol to use for a given domain. The NetLabel + * system manages static and dynamic label mappings for network protocols such + * as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/types.h> +#include <linux/rcupdate.h> +#include <linux/list.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <net/netlabel.h> +#include <net/cipso_ipv4.h> +#include <asm/bug.h> + +#include "netlabel_mgmt.h" +#include "netlabel_domainhash.h" + +struct netlbl_domhsh_tbl { + struct list_head *tbl; + u32 size; +}; + +/* Domain hash table */ +/* XXX - updates should be so rare that having one spinlock for the entire + * hash table should be okay */ +static DEFINE_SPINLOCK(netlbl_domhsh_lock); +static struct netlbl_domhsh_tbl *netlbl_domhsh = NULL; + +/* Default domain mapping */ +static DEFINE_SPINLOCK(netlbl_domhsh_def_lock); +static struct netlbl_dom_map *netlbl_domhsh_def = NULL; + +/* + * Domain Hash Table Helper Functions + */ + +/** + * netlbl_domhsh_free_entry - Frees a domain hash table entry + * @entry: the entry's RCU field + * + * Description: + * This function is designed to be used as a callback to the call_rcu() + * function so that the memory allocated to a hash table entry can be released + * safely. + * + */ +static void netlbl_domhsh_free_entry(struct rcu_head *entry) +{ + struct netlbl_dom_map *ptr; + + ptr = container_of(entry, struct netlbl_dom_map, rcu); + kfree(ptr->domain); + kfree(ptr); +} + +/** + * netlbl_domhsh_hash - Hashing function for the domain hash table + * @domain: the domain name to hash + * + * Description: + * This is the hashing function for the domain hash table, it returns the + * correct bucket number for the domain. The caller is responsibile for + * calling the rcu_read_[un]lock() functions. + * + */ +static u32 netlbl_domhsh_hash(const char *key) +{ + u32 iter; + u32 val; + u32 len; + + /* This is taken (with slight modification) from + * security/selinux/ss/symtab.c:symhash() */ + + for (iter = 0, val = 0, len = strlen(key); iter < len; iter++) + val = (val << 4 | (val >> (8 * sizeof(u32) - 4))) ^ key[iter]; + return val & (rcu_dereference(netlbl_domhsh)->size - 1); +} + +/** + * netlbl_domhsh_search - Search for a domain entry + * @domain: the domain + * @def: return default if no match is found + * + * Description: + * Searches the domain hash table and returns a pointer to the hash table + * entry if found, otherwise NULL is returned. If @def is non-zero and a + * match is not found in the domain hash table the default mapping is returned + * if it exists. The caller is responsibile for the rcu hash table locks + * (i.e. the caller much call rcu_read_[un]lock()). + * + */ +static struct netlbl_dom_map *netlbl_domhsh_search(const char *domain, u32 def) +{ + u32 bkt; + struct netlbl_dom_map *iter; + + if (domain != NULL) { + bkt = netlbl_domhsh_hash(domain); + list_for_each_entry_rcu(iter, &netlbl_domhsh->tbl[bkt], list) + if (iter->valid && strcmp(iter->domain, domain) == 0) + return iter; + } + + if (def != 0) { + iter = rcu_dereference(netlbl_domhsh_def); + if (iter != NULL && iter->valid) + return iter; + } + + return NULL; +} + +/* + * Domain Hash Table Functions + */ + +/** + * netlbl_domhsh_init - Init for the domain hash + * @size: the number of bits to use for the hash buckets + * + * Description: + * Initializes the domain hash table, should be called only by + * netlbl_user_init() during initialization. Returns zero on success, non-zero + * values on error. + * + */ +int netlbl_domhsh_init(u32 size) +{ + u32 iter; + struct netlbl_domhsh_tbl *hsh_tbl; + + if (size == 0) + return -EINVAL; + + hsh_tbl = kmalloc(sizeof(*hsh_tbl), GFP_KERNEL); + if (hsh_tbl == NULL) + return -ENOMEM; + hsh_tbl->size = 1 << size; + hsh_tbl->tbl = kcalloc(hsh_tbl->size, + sizeof(struct list_head), + GFP_KERNEL); + if (hsh_tbl->tbl == NULL) { + kfree(hsh_tbl); + return -ENOMEM; + } + for (iter = 0; iter < hsh_tbl->size; iter++) + INIT_LIST_HEAD(&hsh_tbl->tbl[iter]); + + rcu_read_lock(); + spin_lock(&netlbl_domhsh_lock); + rcu_assign_pointer(netlbl_domhsh, hsh_tbl); + spin_unlock(&netlbl_domhsh_lock); + rcu_read_unlock(); + + return 0; +} + +/** + * netlbl_domhsh_add - Adds a entry to the domain hash table + * @entry: the entry to add + * + * Description: + * Adds a new entry to the domain hash table and handles any updates to the + * lower level protocol handler (i.e. CIPSO). Returns zero on success, + * negative on failure. + * + */ +int netlbl_domhsh_add(struct netlbl_dom_map *entry) +{ + int ret_val; + u32 bkt; + + switch (entry->type) { + case NETLBL_NLTYPE_UNLABELED: + ret_val = 0; + break; + case NETLBL_NLTYPE_CIPSOV4: + ret_val = cipso_v4_doi_domhsh_add(entry->type_def.cipsov4, + entry->domain); + break; + default: + return -EINVAL; + } + if (ret_val != 0) + return ret_val; + + entry->valid = 1; + INIT_RCU_HEAD(&entry->rcu); + + ret_val = 0; + rcu_read_lock(); + if (entry->domain != NULL) { + bkt = netlbl_domhsh_hash(entry->domain); + spin_lock(&netlbl_domhsh_lock); + if (netlbl_domhsh_search(entry->domain, 0) == NULL) + list_add_tail_rcu(&entry->list, + &netlbl_domhsh->tbl[bkt]); + else + ret_val = -EEXIST; + spin_unlock(&netlbl_domhsh_lock); + } else if (entry->domain == NULL) { + INIT_LIST_HEAD(&entry->list); + spin_lock(&netlbl_domhsh_def_lock); + if (rcu_dereference(netlbl_domhsh_def) == NULL) + rcu_assign_pointer(netlbl_domhsh_def, entry); + else + ret_val = -EEXIST; + spin_unlock(&netlbl_domhsh_def_lock); + } else + ret_val = -EINVAL; + rcu_read_unlock(); + + if (ret_val != 0) { + switch (entry->type) { + case NETLBL_NLTYPE_CIPSOV4: + if (cipso_v4_doi_domhsh_remove(entry->type_def.cipsov4, + entry->domain) != 0) + BUG(); + break; + } + } + + return ret_val; +} + +/** + * netlbl_domhsh_add_default - Adds the default entry to the domain hash table + * @entry: the entry to add + * + * Description: + * Adds a new default entry to the domain hash table and handles any updates + * to the lower level protocol handler (i.e. CIPSO). Returns zero on success, + * negative on failure. + * + */ +int netlbl_domhsh_add_default(struct netlbl_dom_map *entry) +{ + return netlbl_domhsh_add(entry); +} + +/** + * netlbl_domhsh_remove - Removes an entry from the domain hash table + * @domain: the domain to remove + * + * Description: + * Removes an entry from the domain hash table and handles any updates to the + * lower level protocol handler (i.e. CIPSO). Returns zero on success, + * negative on failure. + * + */ +int netlbl_domhsh_remove(const char *domain) +{ + int ret_val = -ENOENT; + struct netlbl_dom_map *entry; + + rcu_read_lock(); + if (domain != NULL) + entry = netlbl_domhsh_search(domain, 0); + else + entry = netlbl_domhsh_search(domain, 1); + if (entry == NULL) + goto remove_return; + switch (entry->type) { + case NETLBL_NLTYPE_UNLABELED: + break; + case NETLBL_NLTYPE_CIPSOV4: + ret_val = cipso_v4_doi_domhsh_remove(entry->type_def.cipsov4, + entry->domain); + if (ret_val != 0) + goto remove_return; + break; + } + ret_val = 0; + if (entry != rcu_dereference(netlbl_domhsh_def)) { + spin_lock(&netlbl_domhsh_lock); + if (entry->valid) { + entry->valid = 0; + list_del_rcu(&entry->list); + } else + ret_val = -ENOENT; + spin_unlock(&netlbl_domhsh_lock); + } else { + spin_lock(&netlbl_domhsh_def_lock); + if (entry->valid) { + entry->valid = 0; + rcu_assign_pointer(netlbl_domhsh_def, NULL); + } else + ret_val = -ENOENT; + spin_unlock(&netlbl_domhsh_def_lock); + } + if (ret_val == 0) + call_rcu(&entry->rcu, netlbl_domhsh_free_entry); + +remove_return: + rcu_read_unlock(); + return ret_val; +} + +/** + * netlbl_domhsh_remove_default - Removes the default entry from the table + * + * Description: + * Removes/resets the default entry for the domain hash table and handles any + * updates to the lower level protocol handler (i.e. CIPSO). Returns zero on + * success, non-zero on failure. + * + */ +int netlbl_domhsh_remove_default(void) +{ + return netlbl_domhsh_remove(NULL); +} + +/** + * netlbl_domhsh_getentry - Get an entry from the domain hash table + * @domain: the domain name to search for + * + * Description: + * Look through the domain hash table searching for an entry to match @domain, + * return a pointer to a copy of the entry or NULL. The caller is responsibile + * for ensuring that rcu_read_[un]lock() is called. + * + */ +struct netlbl_dom_map *netlbl_domhsh_getentry(const char *domain) +{ + return netlbl_domhsh_search(domain, 1); +} + +/** + * netlbl_domhsh_dump - Dump the domain hash table into a sk_buff + * + * Description: + * Dump the domain hash table into a buffer suitable for returning to an + * application in response to a NetLabel management DOMAIN message. This + * function may fail if another process is growing the hash table at the same + * time. The returned sk_buff has room at the front of the sk_buff for + * @headroom bytes. See netlabel.h for the DOMAIN message format. Returns a + * pointer to a sk_buff on success, NULL on error. + * + */ +struct sk_buff *netlbl_domhsh_dump(size_t headroom) +{ + struct sk_buff *skb = NULL; + ssize_t buf_len; + u32 bkt_iter; + u32 dom_cnt = 0; + struct netlbl_domhsh_tbl *hsh_tbl; + struct netlbl_dom_map *list_iter; + ssize_t tmp_len; + + buf_len = NETLBL_LEN_U32; + rcu_read_lock(); + hsh_tbl = rcu_dereference(netlbl_domhsh); + for (bkt_iter = 0; bkt_iter < hsh_tbl->size; bkt_iter++) + list_for_each_entry_rcu(list_iter, + &hsh_tbl->tbl[bkt_iter], list) { + buf_len += NETLBL_LEN_U32 + + nla_total_size(strlen(list_iter->domain) + 1); + switch (list_iter->type) { + case NETLBL_NLTYPE_UNLABELED: + break; + case NETLBL_NLTYPE_CIPSOV4: + buf_len += 2 * NETLBL_LEN_U32; + break; + } + dom_cnt++; + } + + skb = netlbl_netlink_alloc_skb(headroom, buf_len, GFP_ATOMIC); + if (skb == NULL) + goto dump_failure; + + if (nla_put_u32(skb, NLA_U32, dom_cnt) != 0) + goto dump_failure; + buf_len -= NETLBL_LEN_U32; + hsh_tbl = rcu_dereference(netlbl_domhsh); + for (bkt_iter = 0; bkt_iter < hsh_tbl->size; bkt_iter++) + list_for_each_entry_rcu(list_iter, + &hsh_tbl->tbl[bkt_iter], list) { + tmp_len = nla_total_size(strlen(list_iter->domain) + + 1); + if (buf_len < NETLBL_LEN_U32 + tmp_len) + goto dump_failure; + if (nla_put_string(skb, + NLA_STRING, + list_iter->domain) != 0) + goto dump_failure; + if (nla_put_u32(skb, NLA_U32, list_iter->type) != 0) + goto dump_failure; + buf_len -= NETLBL_LEN_U32 + tmp_len; + switch (list_iter->type) { + case NETLBL_NLTYPE_UNLABELED: + break; + case NETLBL_NLTYPE_CIPSOV4: + if (buf_len < 2 * NETLBL_LEN_U32) + goto dump_failure; + if (nla_put_u32(skb, + NLA_U32, + list_iter->type_def.cipsov4->type) != 0) + goto dump_failure; + if (nla_put_u32(skb, + NLA_U32, + list_iter->type_def.cipsov4->doi) != 0) + goto dump_failure; + buf_len -= 2 * NETLBL_LEN_U32; + break; + } + } + rcu_read_unlock(); + + return skb; + +dump_failure: + rcu_read_unlock(); + kfree_skb(skb); + return NULL; +} + +/** + * netlbl_domhsh_dump_default - Dump the default domain mapping into a sk_buff + * + * Description: + * Dump the default domain mapping into a buffer suitable for returning to an + * application in response to a NetLabel management DEFDOMAIN message. This + * function may fail if another process is changing the default domain mapping + * at the same time. The returned sk_buff has room at the front of the + * skb_buff for @headroom bytes. See netlabel.h for the DEFDOMAIN message + * format. Returns a pointer to a sk_buff on success, NULL on error. + * + */ +struct sk_buff *netlbl_domhsh_dump_default(size_t headroom) +{ + struct sk_buff *skb; + ssize_t buf_len; + struct netlbl_dom_map *entry; + + buf_len = NETLBL_LEN_U32; + rcu_read_lock(); + entry = rcu_dereference(netlbl_domhsh_def); + if (entry != NULL) + switch (entry->type) { + case NETLBL_NLTYPE_UNLABELED: + break; + case NETLBL_NLTYPE_CIPSOV4: + buf_len += 2 * NETLBL_LEN_U32; + break; + } + + skb = netlbl_netlink_alloc_skb(headroom, buf_len, GFP_ATOMIC); + if (skb == NULL) + goto dump_default_failure; + + if (entry != rcu_dereference(netlbl_domhsh_def)) + goto dump_default_failure; + if (entry != NULL) { + if (nla_put_u32(skb, NLA_U32, entry->type) != 0) + goto dump_default_failure; + buf_len -= NETLBL_LEN_U32; + switch (entry->type) { + case NETLBL_NLTYPE_UNLABELED: + break; + case NETLBL_NLTYPE_CIPSOV4: + if (buf_len < 2 * NETLBL_LEN_U32) + goto dump_default_failure; + if (nla_put_u32(skb, + NLA_U32, + entry->type_def.cipsov4->type) != 0) + goto dump_default_failure; + if (nla_put_u32(skb, + NLA_U32, + entry->type_def.cipsov4->doi) != 0) + goto dump_default_failure; + buf_len -= 2 * NETLBL_LEN_U32; + break; + } + } else + nla_put_u32(skb, NLA_U32, NETLBL_NLTYPE_NONE); + rcu_read_unlock(); + + return skb; + +dump_default_failure: + rcu_read_unlock(); + kfree_skb(skb); + return NULL; +} diff --git a/net/netlabel/netlabel_domainhash.h b/net/netlabel/netlabel_domainhash.h new file mode 100644 index 00000000000..99a2287de24 --- /dev/null +++ b/net/netlabel/netlabel_domainhash.h @@ -0,0 +1,67 @@ +/* + * NetLabel Domain Hash Table + * + * This file manages the domain hash table that NetLabel uses to determine + * which network labeling protocol to use for a given domain. The NetLabel + * system manages static and dynamic label mappings for network protocols such + * as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#ifndef _NETLABEL_DOMAINHASH_H +#define _NETLABEL_DOMAINHASH_H + +#include <linux/types.h> +#include <linux/rcupdate.h> +#include <linux/list.h> + +/* Domain hash table size */ +/* XXX - currently this number is an uneducated guess */ +#define NETLBL_DOMHSH_BITSIZE 7 + +/* Domain mapping definition struct */ +struct netlbl_dom_map { + char *domain; + u32 type; + union { + struct cipso_v4_doi *cipsov4; + } type_def; + + u32 valid; + struct list_head list; + struct rcu_head rcu; +}; + +/* init function */ +int netlbl_domhsh_init(u32 size); + +/* Manipulate the domain hash table */ +int netlbl_domhsh_add(struct netlbl_dom_map *entry); +int netlbl_domhsh_add_default(struct netlbl_dom_map *entry); +int netlbl_domhsh_remove_default(void); +struct netlbl_dom_map *netlbl_domhsh_getentry(const char *domain); +struct sk_buff *netlbl_domhsh_dump(size_t headroom); +struct sk_buff *netlbl_domhsh_dump_default(size_t headroom); + +#endif diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c new file mode 100644 index 00000000000..0fd8aaafe23 --- /dev/null +++ b/net/netlabel/netlabel_kapi.c @@ -0,0 +1,231 @@ +/* + * NetLabel Kernel API + * + * This file defines the kernel API for the NetLabel system. The NetLabel + * system manages static and dynamic label mappings for network protocols such + * as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/init.h> +#include <linux/types.h> +#include <net/ip.h> +#include <net/netlabel.h> +#include <net/cipso_ipv4.h> +#include <asm/bug.h> + +#include "netlabel_domainhash.h" +#include "netlabel_unlabeled.h" +#include "netlabel_user.h" + +/* + * LSM Functions + */ + +/** + * netlbl_socket_setattr - Label a socket using the correct protocol + * @sock: the socket to label + * @secattr: the security attributes + * + * Description: + * Attach the correct label to the given socket using the security attributes + * specified in @secattr. This function requires exclusive access to + * @sock->sk, which means it either needs to be in the process of being + * created or locked via lock_sock(sock->sk). Returns zero on success, + * negative values on failure. + * + */ +int netlbl_socket_setattr(const struct socket *sock, + const struct netlbl_lsm_secattr *secattr) +{ + int ret_val = -ENOENT; + struct netlbl_dom_map *dom_entry; + + rcu_read_lock(); + dom_entry = netlbl_domhsh_getentry(secattr->domain); + if (dom_entry == NULL) + goto socket_setattr_return; + switch (dom_entry->type) { + case NETLBL_NLTYPE_CIPSOV4: + ret_val = cipso_v4_socket_setattr(sock, + dom_entry->type_def.cipsov4, + secattr); + break; + case NETLBL_NLTYPE_UNLABELED: + ret_val = 0; + break; + default: + ret_val = -ENOENT; + } + +socket_setattr_return: + rcu_read_unlock(); + return ret_val; +} + +/** + * netlbl_socket_getattr - Determine the security attributes of a socket + * @sock: the socket + * @secattr: the security attributes + * + * Description: + * Examines the given socket to see any NetLabel style labeling has been + * applied to the socket, if so it parses the socket label and returns the + * security attributes in @secattr. Returns zero on success, negative values + * on failure. + * + */ +int netlbl_socket_getattr(const struct socket *sock, + struct netlbl_lsm_secattr *secattr) +{ + int ret_val; + + ret_val = cipso_v4_socket_getattr(sock, secattr); + if (ret_val == 0) + return 0; + + return netlbl_unlabel_getattr(secattr); +} + +/** + * netlbl_skbuff_getattr - Determine the security attributes of a packet + * @skb: the packet + * @secattr: the security attributes + * + * Description: + * Examines the given packet to see if a recognized form of packet labeling + * is present, if so it parses the packet label and returns the security + * attributes in @secattr. Returns zero on success, negative values on + * failure. + * + */ +int netlbl_skbuff_getattr(const struct sk_buff *skb, + struct netlbl_lsm_secattr *secattr) +{ + int ret_val; + + ret_val = cipso_v4_skbuff_getattr(skb, secattr); + if (ret_val == 0) + return 0; + + return netlbl_unlabel_getattr(secattr); +} + +/** + * netlbl_skbuff_err - Handle a LSM error on a sk_buff + * @skb: the packet + * @error: the error code + * + * Description: + * Deal with a LSM problem when handling the packet in @skb, typically this is + * a permission denied problem (-EACCES). The correct action is determined + * according to the packet's labeling protocol. + * + */ +void netlbl_skbuff_err(struct sk_buff *skb, int error) +{ + if (CIPSO_V4_OPTEXIST(skb)) + cipso_v4_error(skb, error, 0); +} + +/** + * netlbl_cache_invalidate - Invalidate all of the NetLabel protocol caches + * + * Description: + * For all of the NetLabel protocols that support some form of label mapping + * cache, invalidate the cache. Returns zero on success, negative values on + * error. + * + */ +void netlbl_cache_invalidate(void) +{ + cipso_v4_cache_invalidate(); +} + +/** + * netlbl_cache_add - Add an entry to a NetLabel protocol cache + * @skb: the packet + * @secattr: the packet's security attributes + * + * Description: + * Add the LSM security attributes for the given packet to the underlying + * NetLabel protocol's label mapping cache. Returns zero on success, negative + * values on error. + * + */ +int netlbl_cache_add(const struct sk_buff *skb, + const struct netlbl_lsm_secattr *secattr) +{ + if (secattr->cache.data == NULL) + return -ENOMSG; + + if (CIPSO_V4_OPTEXIST(skb)) + return cipso_v4_cache_add(skb, secattr); + + return -ENOMSG; +} + +/* + * Setup Functions + */ + +/** + * netlbl_init - Initialize NetLabel + * + * Description: + * Perform the required NetLabel initialization before first use. + * + */ +static int __init netlbl_init(void) +{ + int ret_val; + + printk(KERN_INFO "NetLabel: Initializing\n"); + printk(KERN_INFO "NetLabel: domain hash size = %u\n", + (1 << NETLBL_DOMHSH_BITSIZE)); + printk(KERN_INFO "NetLabel: protocols =" + " UNLABELED" + " CIPSOv4" + "\n"); + + ret_val = netlbl_domhsh_init(NETLBL_DOMHSH_BITSIZE); + if (ret_val != 0) + goto init_failure; + + ret_val = netlbl_netlink_init(); + if (ret_val != 0) + goto init_failure; + + ret_val = netlbl_unlabel_defconf(); + if (ret_val != 0) + goto init_failure; + printk(KERN_INFO "NetLabel: unlabeled traffic allowed by default\n"); + + return 0; + +init_failure: + panic("NetLabel: failed to initialize properly (%d)\n", ret_val); +} + +subsys_initcall(netlbl_init); diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c new file mode 100644 index 00000000000..85bc11a1fc4 --- /dev/null +++ b/net/netlabel/netlabel_mgmt.c @@ -0,0 +1,624 @@ +/* + * NetLabel Management Support + * + * This file defines the management functions for the NetLabel system. The + * NetLabel system manages static and dynamic label mappings for network + * protocols such as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <net/netlink.h> +#include <net/genetlink.h> +#include <net/netlabel.h> +#include <net/cipso_ipv4.h> + +#include "netlabel_domainhash.h" +#include "netlabel_user.h" +#include "netlabel_mgmt.h" + +/* NetLabel Generic NETLINK CIPSOv4 family */ +static struct genl_family netlbl_mgmt_gnl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = NETLBL_NLTYPE_MGMT_NAME, + .version = NETLBL_PROTO_VERSION, + .maxattr = 0, +}; + + +/* + * NetLabel Command Handlers + */ + +/** + * netlbl_mgmt_add - Handle an ADD message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated ADD message and add the domains from the message + * to the hash table. See netlabel.h for a description of the message format. + * Returns zero on success, negative values on failure. + * + */ +static int netlbl_mgmt_add(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -EINVAL; + struct nlattr *msg_ptr = netlbl_netlink_payload_data(skb); + int msg_len = netlbl_netlink_payload_len(skb); + u32 count; + struct netlbl_dom_map *entry = NULL; + u32 iter; + u32 tmp_val; + int tmp_size; + + ret_val = netlbl_netlink_cap_check(skb, CAP_NET_ADMIN); + if (ret_val != 0) + goto add_failure; + + if (msg_len < NETLBL_LEN_U32) + goto add_failure; + count = netlbl_getinc_u32(&msg_ptr, &msg_len); + + for (iter = 0; iter < count && msg_len > 0; iter++, entry = NULL) { + if (msg_len <= 0) { + ret_val = -EINVAL; + goto add_failure; + } + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (entry == NULL) { + ret_val = -ENOMEM; + goto add_failure; + } + tmp_size = nla_len(msg_ptr); + if (tmp_size <= 0 || tmp_size > msg_len) { + ret_val = -EINVAL; + goto add_failure; + } + entry->domain = kmalloc(tmp_size, GFP_KERNEL); + if (entry->domain == NULL) { + ret_val = -ENOMEM; + goto add_failure; + } + nla_strlcpy(entry->domain, msg_ptr, tmp_size); + entry->domain[tmp_size - 1] = '\0'; + msg_ptr = nla_next(msg_ptr, &msg_len); + + if (msg_len < NETLBL_LEN_U32) { + ret_val = -EINVAL; + goto add_failure; + } + tmp_val = netlbl_getinc_u32(&msg_ptr, &msg_len); + entry->type = tmp_val; + switch (tmp_val) { + case NETLBL_NLTYPE_UNLABELED: + ret_val = netlbl_domhsh_add(entry); + break; + case NETLBL_NLTYPE_CIPSOV4: + if (msg_len < NETLBL_LEN_U32) { + ret_val = -EINVAL; + goto add_failure; + } + tmp_val = netlbl_getinc_u32(&msg_ptr, &msg_len); + /* We should be holding a rcu_read_lock() here + * while we hold the result but since the entry + * will always be deleted when the CIPSO DOI + * is deleted we aren't going to keep the lock. */ + rcu_read_lock(); + entry->type_def.cipsov4 = cipso_v4_doi_getdef(tmp_val); + if (entry->type_def.cipsov4 == NULL) { + rcu_read_unlock(); + ret_val = -EINVAL; + goto add_failure; + } + ret_val = netlbl_domhsh_add(entry); + rcu_read_unlock(); + break; + default: + ret_val = -EINVAL; + } + if (ret_val != 0) + goto add_failure; + } + + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + NETLBL_E_OK); + return 0; + +add_failure: + if (entry) + kfree(entry->domain); + kfree(entry); + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_mgmt_remove - Handle a REMOVE message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated REMOVE message and remove the specified domain + * mappings. Returns zero on success, negative values on failure. + * + */ +static int netlbl_mgmt_remove(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -EINVAL; + struct nlattr *msg_ptr = netlbl_netlink_payload_data(skb); + int msg_len = netlbl_netlink_payload_len(skb); + u32 count; + u32 iter; + int tmp_size; + unsigned char *domain; + + ret_val = netlbl_netlink_cap_check(skb, CAP_NET_ADMIN); + if (ret_val != 0) + goto remove_return; + + if (msg_len < NETLBL_LEN_U32) + goto remove_return; + count = netlbl_getinc_u32(&msg_ptr, &msg_len); + + for (iter = 0; iter < count && msg_len > 0; iter++) { + if (msg_len <= 0) { + ret_val = -EINVAL; + goto remove_return; + } + tmp_size = nla_len(msg_ptr); + domain = nla_data(msg_ptr); + if (tmp_size <= 0 || tmp_size > msg_len || + domain[tmp_size - 1] != '\0') { + ret_val = -EINVAL; + goto remove_return; + } + ret_val = netlbl_domhsh_remove(domain); + if (ret_val != 0) + goto remove_return; + msg_ptr = nla_next(msg_ptr, &msg_len); + } + + ret_val = 0; + +remove_return: + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_mgmt_list - Handle a LIST message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated LIST message and dumps the domain hash table in a + * form suitable for use in a kernel generated LIST message. Returns zero on + * success, negative values on failure. + * + */ +static int netlbl_mgmt_list(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -ENOMEM; + struct sk_buff *ans_skb; + + ans_skb = netlbl_domhsh_dump(NLMSG_SPACE(GENL_HDRLEN)); + if (ans_skb == NULL) + goto list_failure; + netlbl_netlink_hdr_push(ans_skb, + info->snd_pid, + 0, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_LIST); + + ret_val = netlbl_netlink_snd(ans_skb, info->snd_pid); + if (ret_val != 0) + goto list_failure; + + return 0; + +list_failure: + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_mgmt_adddef - Handle an ADDDEF message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated ADDDEF message and respond accordingly. Returns + * zero on success, negative values on failure. + * + */ +static int netlbl_mgmt_adddef(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -EINVAL; + struct nlattr *msg_ptr = netlbl_netlink_payload_data(skb); + int msg_len = netlbl_netlink_payload_len(skb); + struct netlbl_dom_map *entry = NULL; + u32 tmp_val; + + ret_val = netlbl_netlink_cap_check(skb, CAP_NET_ADMIN); + if (ret_val != 0) + goto adddef_failure; + + if (msg_len < NETLBL_LEN_U32) + goto adddef_failure; + tmp_val = netlbl_getinc_u32(&msg_ptr, &msg_len); + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (entry == NULL) { + ret_val = -ENOMEM; + goto adddef_failure; + } + + entry->type = tmp_val; + switch (entry->type) { + case NETLBL_NLTYPE_UNLABELED: + ret_val = netlbl_domhsh_add_default(entry); + break; + case NETLBL_NLTYPE_CIPSOV4: + if (msg_len < NETLBL_LEN_U32) { + ret_val = -EINVAL; + goto adddef_failure; + } + tmp_val = netlbl_getinc_u32(&msg_ptr, &msg_len); + /* We should be holding a rcu_read_lock here while we + * hold the result but since the entry will always be + * deleted when the CIPSO DOI is deleted we are going + * to skip the lock. */ + rcu_read_lock(); + entry->type_def.cipsov4 = cipso_v4_doi_getdef(tmp_val); + if (entry->type_def.cipsov4 == NULL) { + rcu_read_unlock(); + ret_val = -EINVAL; + goto adddef_failure; + } + ret_val = netlbl_domhsh_add_default(entry); + rcu_read_unlock(); + break; + default: + ret_val = -EINVAL; + } + if (ret_val != 0) + goto adddef_failure; + + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + NETLBL_E_OK); + return 0; + +adddef_failure: + kfree(entry); + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_mgmt_removedef - Handle a REMOVEDEF message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated REMOVEDEF message and remove the default domain + * mapping. Returns zero on success, negative values on failure. + * + */ +static int netlbl_mgmt_removedef(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val; + + ret_val = netlbl_netlink_cap_check(skb, CAP_NET_ADMIN); + if (ret_val != 0) + goto removedef_return; + + ret_val = netlbl_domhsh_remove_default(); + +removedef_return: + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_mgmt_listdef - Handle a LISTDEF message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated LISTDEF message and dumps the default domain + * mapping in a form suitable for use in a kernel generated LISTDEF message. + * Returns zero on success, negative values on failure. + * + */ +static int netlbl_mgmt_listdef(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -ENOMEM; + struct sk_buff *ans_skb; + + ans_skb = netlbl_domhsh_dump_default(NLMSG_SPACE(GENL_HDRLEN)); + if (ans_skb == NULL) + goto listdef_failure; + netlbl_netlink_hdr_push(ans_skb, + info->snd_pid, + 0, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_LISTDEF); + + ret_val = netlbl_netlink_snd(ans_skb, info->snd_pid); + if (ret_val != 0) + goto listdef_failure; + + return 0; + +listdef_failure: + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_mgmt_modules - Handle a MODULES message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated MODULES message and respond accordingly. + * + */ +static int netlbl_mgmt_modules(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -ENOMEM; + size_t data_size; + u32 mod_count; + struct sk_buff *ans_skb = NULL; + + /* unlabeled + cipsov4 */ + mod_count = 2; + + data_size = GENL_HDRLEN + NETLBL_LEN_U32 + mod_count * NETLBL_LEN_U32; + ans_skb = netlbl_netlink_alloc_skb(0, data_size, GFP_KERNEL); + if (ans_skb == NULL) + goto modules_failure; + + if (netlbl_netlink_hdr_put(ans_skb, + info->snd_pid, + 0, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_MODULES) == NULL) + goto modules_failure; + + ret_val = nla_put_u32(ans_skb, NLA_U32, mod_count); + if (ret_val != 0) + goto modules_failure; + ret_val = nla_put_u32(ans_skb, NLA_U32, NETLBL_NLTYPE_UNLABELED); + if (ret_val != 0) + goto modules_failure; + ret_val = nla_put_u32(ans_skb, NLA_U32, NETLBL_NLTYPE_CIPSOV4); + if (ret_val != 0) + goto modules_failure; + + ret_val = netlbl_netlink_snd(ans_skb, info->snd_pid); + if (ret_val != 0) + goto modules_failure; + + return 0; + +modules_failure: + kfree_skb(ans_skb); + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + -ret_val); + return ret_val; +} + +/** + * netlbl_mgmt_version - Handle a VERSION message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated VERSION message and respond accordingly. Returns + * zero on success, negative values on failure. + * + */ +static int netlbl_mgmt_version(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -ENOMEM; + struct sk_buff *ans_skb = NULL; + + ans_skb = netlbl_netlink_alloc_skb(0, + GENL_HDRLEN + NETLBL_LEN_U32, + GFP_KERNEL); + if (ans_skb == NULL) + goto version_failure; + if (netlbl_netlink_hdr_put(ans_skb, + info->snd_pid, + 0, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_VERSION) == NULL) + goto version_failure; + + ret_val = nla_put_u32(ans_skb, NLA_U32, NETLBL_PROTO_VERSION); + if (ret_val != 0) + goto version_failure; + + ret_val = netlbl_netlink_snd(ans_skb, info->snd_pid); + if (ret_val != 0) + goto version_failure; + + return 0; + +version_failure: + kfree_skb(ans_skb); + netlbl_netlink_send_ack(info, + netlbl_mgmt_gnl_family.id, + NLBL_MGMT_C_ACK, + -ret_val); + return ret_val; +} + + +/* + * NetLabel Generic NETLINK Command Definitions + */ + +static struct genl_ops netlbl_mgmt_genl_c_add = { + .cmd = NLBL_MGMT_C_ADD, + .flags = 0, + .doit = netlbl_mgmt_add, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_mgmt_genl_c_remove = { + .cmd = NLBL_MGMT_C_REMOVE, + .flags = 0, + .doit = netlbl_mgmt_remove, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_mgmt_genl_c_list = { + .cmd = NLBL_MGMT_C_LIST, + .flags = 0, + .doit = netlbl_mgmt_list, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_mgmt_genl_c_adddef = { + .cmd = NLBL_MGMT_C_ADDDEF, + .flags = 0, + .doit = netlbl_mgmt_adddef, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_mgmt_genl_c_removedef = { + .cmd = NLBL_MGMT_C_REMOVEDEF, + .flags = 0, + .doit = netlbl_mgmt_removedef, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_mgmt_genl_c_listdef = { + .cmd = NLBL_MGMT_C_LISTDEF, + .flags = 0, + .doit = netlbl_mgmt_listdef, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_mgmt_genl_c_modules = { + .cmd = NLBL_MGMT_C_MODULES, + .flags = 0, + .doit = netlbl_mgmt_modules, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_mgmt_genl_c_version = { + .cmd = NLBL_MGMT_C_VERSION, + .flags = 0, + .doit = netlbl_mgmt_version, + .dumpit = NULL, +}; + +/* + * NetLabel Generic NETLINK Protocol Functions + */ + +/** + * netlbl_mgmt_genl_init - Register the NetLabel management component + * + * Description: + * Register the NetLabel management component with the Generic NETLINK + * mechanism. Returns zero on success, negative values on failure. + * + */ +int netlbl_mgmt_genl_init(void) +{ + int ret_val; + + ret_val = genl_register_family(&netlbl_mgmt_gnl_family); + if (ret_val != 0) + return ret_val; + + ret_val = genl_register_ops(&netlbl_mgmt_gnl_family, + &netlbl_mgmt_genl_c_add); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_mgmt_gnl_family, + &netlbl_mgmt_genl_c_remove); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_mgmt_gnl_family, + &netlbl_mgmt_genl_c_list); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_mgmt_gnl_family, + &netlbl_mgmt_genl_c_adddef); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_mgmt_gnl_family, + &netlbl_mgmt_genl_c_removedef); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_mgmt_gnl_family, + &netlbl_mgmt_genl_c_listdef); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_mgmt_gnl_family, + &netlbl_mgmt_genl_c_modules); + if (ret_val != 0) + return ret_val; + ret_val = genl_register_ops(&netlbl_mgmt_gnl_family, + &netlbl_mgmt_genl_c_version); + if (ret_val != 0) + return ret_val; + + return 0; +} diff --git a/net/netlabel/netlabel_mgmt.h b/net/netlabel/netlabel_mgmt.h new file mode 100644 index 00000000000..fd6c6acbfa0 --- /dev/null +++ b/net/netlabel/netlabel_mgmt.h @@ -0,0 +1,246 @@ +/* + * NetLabel Management Support + * + * This file defines the management functions for the NetLabel system. The + * NetLabel system manages static and dynamic label mappings for network + * protocols such as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#ifndef _NETLABEL_MGMT_H +#define _NETLABEL_MGMT_H + +#include <net/netlabel.h> + +/* + * The following NetLabel payloads are supported by the management interface, + * all of which are preceeded by the nlmsghdr struct. + * + * o ACK: + * Sent by the kernel in response to an applications message, applications + * should never send this message. + * + * +----------------------+-----------------------+ + * | seq number (32 bits) | return code (32 bits) | + * +----------------------+-----------------------+ + * + * seq number: the sequence number of the original message, taken from the + * nlmsghdr structure + * return code: return value, based on errno values + * + * o ADD: + * Sent by an application to add a domain mapping to the NetLabel system. + * The kernel should respond with an ACK. + * + * +-------------------+ + * | domains (32 bits) | ... + * +-------------------+ + * + * domains: the number of domains in the message + * + * +--------------------------+-------------------------+ + * | domain string (variable) | protocol type (32 bits) | ... + * +--------------------------+-------------------------+ + * + * +-------------- ---- --- -- - + * | mapping data ... repeated + * +-------------- ---- --- -- - + * + * domain string: the domain string, NULL terminated + * protocol type: the protocol type (defined by NETLBL_NLTYPE_*) + * mapping data: specific to the map type (see below) + * + * NETLBL_NLTYPE_UNLABELED + * + * No mapping data for this protocol type. + * + * NETLBL_NLTYPE_CIPSOV4 + * + * +---------------+ + * | doi (32 bits) | + * +---------------+ + * + * doi: the CIPSO DOI value + * + * o REMOVE: + * Sent by an application to remove a domain mapping from the NetLabel + * system. The kernel should ACK this message. + * + * +-------------------+ + * | domains (32 bits) | ... + * +-------------------+ + * + * domains: the number of domains in the message + * + * +--------------------------+ + * | domain string (variable) | ... + * +--------------------------+ + * + * domain string: the domain string, NULL terminated + * + * o LIST: + * This message can be sent either from an application or by the kernel in + * response to an application generated LIST message. When sent by an + * application there is no payload. The kernel should respond to a LIST + * message either with a LIST message on success or an ACK message on + * failure. + * + * +-------------------+ + * | domains (32 bits) | ... + * +-------------------+ + * + * domains: the number of domains in the message + * + * +--------------------------+ + * | domain string (variable) | ... + * +--------------------------+ + * + * +-------------------------+-------------- ---- --- -- - + * | protocol type (32 bits) | mapping data ... repeated + * +-------------------------+-------------- ---- --- -- - + * + * domain string: the domain string, NULL terminated + * protocol type: the protocol type (defined by NETLBL_NLTYPE_*) + * mapping data: specific to the map type (see below) + * + * NETLBL_NLTYPE_UNLABELED + * + * No mapping data for this protocol type. + * + * NETLBL_NLTYPE_CIPSOV4 + * + * +----------------+---------------+ + * | type (32 bits) | doi (32 bits) | + * +----------------+---------------+ + * + * type: the CIPSO mapping table type (defined in the cipso_ipv4.h header + * as CIPSO_V4_MAP_*) + * doi: the CIPSO DOI value + * + * o ADDDEF: + * Sent by an application to set the default domain mapping for the NetLabel + * system. The kernel should respond with an ACK. + * + * +-------------------------+-------------- ---- --- -- - + * | protocol type (32 bits) | mapping data ... repeated + * +-------------------------+-------------- ---- --- -- - + * + * protocol type: the protocol type (defined by NETLBL_NLTYPE_*) + * mapping data: specific to the map type (see below) + * + * NETLBL_NLTYPE_UNLABELED + * + * No mapping data for this protocol type. + * + * NETLBL_NLTYPE_CIPSOV4 + * + * +---------------+ + * | doi (32 bits) | + * +---------------+ + * + * doi: the CIPSO DOI value + * + * o REMOVEDEF: + * Sent by an application to remove the default domain mapping from the + * NetLabel system, there is no payload. The kernel should ACK this message. + * + * o LISTDEF: + * This message can be sent either from an application or by the kernel in + * response to an application generated LISTDEF message. When sent by an + * application there is no payload. The kernel should respond to a + * LISTDEF message either with a LISTDEF message on success or an ACK message + * on failure. + * + * +-------------------------+-------------- ---- --- -- - + * | protocol type (32 bits) | mapping data ... repeated + * +-------------------------+-------------- ---- --- -- - + * + * protocol type: the protocol type (defined by NETLBL_NLTYPE_*) + * mapping data: specific to the map type (see below) + * + * NETLBL_NLTYPE_UNLABELED + * + * No mapping data for this protocol type. + * + * NETLBL_NLTYPE_CIPSOV4 + * + * +----------------+---------------+ + * | type (32 bits) | doi (32 bits) | + * +----------------+---------------+ + * + * type: the CIPSO mapping table type (defined in the cipso_ipv4.h header + * as CIPSO_V4_MAP_*) + * doi: the CIPSO DOI value + * + * o MODULES: + * Sent by an application to request a list of configured NetLabel modules + * in the kernel. When sent by an application there is no payload. + * + * +-------------------+ + * | modules (32 bits) | ... + * +-------------------+ + * + * modules: the number of modules in the message, if this is an application + * generated message and the value is zero then return a list of + * the configured modules + * + * +------------------+ + * | module (32 bits) | ... repeated + * +------------------+ + * + * module: the module number as defined by NETLBL_NLTYPE_* + * + * o VERSION: + * Sent by an application to request the NetLabel version string. When sent + * by an application there is no payload. This message type is also used by + * the kernel to respond to an VERSION request. + * + * +-------------------+ + * | version (32 bits) | + * +-------------------+ + * + * version: the protocol version number + * + */ + +/* NetLabel Management commands */ +enum { + NLBL_MGMT_C_UNSPEC, + NLBL_MGMT_C_ACK, + NLBL_MGMT_C_ADD, + NLBL_MGMT_C_REMOVE, + NLBL_MGMT_C_LIST, + NLBL_MGMT_C_ADDDEF, + NLBL_MGMT_C_REMOVEDEF, + NLBL_MGMT_C_LISTDEF, + NLBL_MGMT_C_MODULES, + NLBL_MGMT_C_VERSION, + __NLBL_MGMT_C_MAX, +}; +#define NLBL_MGMT_C_MAX (__NLBL_MGMT_C_MAX - 1) + +/* NetLabel protocol functions */ +int netlbl_mgmt_genl_init(void); + +#endif diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c new file mode 100644 index 00000000000..785f4960e0d --- /dev/null +++ b/net/netlabel/netlabel_unlabeled.c @@ -0,0 +1,253 @@ +/* + * NetLabel Unlabeled Support + * + * This file defines functions for dealing with unlabeled packets for the + * NetLabel system. The NetLabel system manages static and dynamic label + * mappings for network protocols such as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/types.h> +#include <linux/rcupdate.h> +#include <linux/list.h> +#include <linux/spinlock.h> +#include <linux/socket.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <net/netlabel.h> +#include <asm/bug.h> + +#include "netlabel_user.h" +#include "netlabel_domainhash.h" +#include "netlabel_unlabeled.h" + +/* Accept unlabeled packets flag */ +static atomic_t netlabel_unlabel_accept_flg = ATOMIC_INIT(0); + +/* NetLabel Generic NETLINK CIPSOv4 family */ +static struct genl_family netlbl_unlabel_gnl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = NETLBL_NLTYPE_UNLABELED_NAME, + .version = NETLBL_PROTO_VERSION, + .maxattr = 0, +}; + + +/* + * NetLabel Command Handlers + */ + +/** + * netlbl_unlabel_accept - Handle an ACCEPT message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated ACCEPT message and set the accept flag accordingly. + * Returns zero on success, negative values on failure. + * + */ +static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val; + struct nlattr *data = netlbl_netlink_payload_data(skb); + u32 value; + + ret_val = netlbl_netlink_cap_check(skb, CAP_NET_ADMIN); + if (ret_val != 0) + return ret_val; + + if (netlbl_netlink_payload_len(skb) == NETLBL_LEN_U32) { + value = nla_get_u32(data); + if (value == 1 || value == 0) { + atomic_set(&netlabel_unlabel_accept_flg, value); + netlbl_netlink_send_ack(info, + netlbl_unlabel_gnl_family.id, + NLBL_UNLABEL_C_ACK, + NETLBL_E_OK); + return 0; + } + } + + netlbl_netlink_send_ack(info, + netlbl_unlabel_gnl_family.id, + NLBL_UNLABEL_C_ACK, + EINVAL); + return -EINVAL; +} + +/** + * netlbl_unlabel_list - Handle a LIST message + * @skb: the NETLINK buffer + * @info: the Generic NETLINK info block + * + * Description: + * Process a user generated LIST message and respond with the current status. + * Returns zero on success, negative values on failure. + * + */ +static int netlbl_unlabel_list(struct sk_buff *skb, struct genl_info *info) +{ + int ret_val = -ENOMEM; + struct sk_buff *ans_skb; + + ans_skb = netlbl_netlink_alloc_skb(0, + GENL_HDRLEN + NETLBL_LEN_U32, + GFP_KERNEL); + if (ans_skb == NULL) + goto list_failure; + + if (netlbl_netlink_hdr_put(ans_skb, + info->snd_pid, + 0, + netlbl_unlabel_gnl_family.id, + NLBL_UNLABEL_C_LIST) == NULL) + goto list_failure; + + ret_val = nla_put_u32(ans_skb, + NLA_U32, + atomic_read(&netlabel_unlabel_accept_flg)); + if (ret_val != 0) + goto list_failure; + + ret_val = netlbl_netlink_snd(ans_skb, info->snd_pid); + if (ret_val != 0) + goto list_failure; + + return 0; + +list_failure: + netlbl_netlink_send_ack(info, + netlbl_unlabel_gnl_family.id, + NLBL_UNLABEL_C_ACK, + -ret_val); + return ret_val; +} + + +/* + * NetLabel Generic NETLINK Command Definitions + */ + +static struct genl_ops netlbl_unlabel_genl_c_accept = { + .cmd = NLBL_UNLABEL_C_ACCEPT, + .flags = 0, + .doit = netlbl_unlabel_accept, + .dumpit = NULL, +}; + +static struct genl_ops netlbl_unlabel_genl_c_list = { + .cmd = NLBL_UNLABEL_C_LIST, + .flags = 0, + .doit = netlbl_unlabel_list, + .dumpit = NULL, +}; + + +/* + * NetLabel Generic NETLINK Protocol Functions + */ + +/** + * netlbl_unlabel_genl_init - Register the Unlabeled NetLabel component + * + * Description: + * Register the unlabeled packet NetLabel component with the Generic NETLINK + * mechanism. Returns zero on success, negative values on failure. + * + */ +int netlbl_unlabel_genl_init(void) +{ + int ret_val; + + ret_val = genl_register_family(&netlbl_unlabel_gnl_family); + if (ret_val != 0) + return ret_val; + + ret_val = genl_register_ops(&netlbl_unlabel_gnl_family, + &netlbl_unlabel_genl_c_accept); + if (ret_val != 0) + return ret_val; + + ret_val = genl_register_ops(&netlbl_unlabel_gnl_family, + &netlbl_unlabel_genl_c_list); + if (ret_val != 0) + return ret_val; + + return 0; +} + +/* + * NetLabel KAPI Hooks + */ + +/** + * netlbl_unlabel_getattr - Get the security attributes for an unlabled packet + * @secattr: the security attributes + * + * Description: + * Determine the security attributes, if any, for an unlabled packet and return + * them in @secattr. Returns zero on success and negative values on failure. + * + */ +int netlbl_unlabel_getattr(struct netlbl_lsm_secattr *secattr) +{ + if (atomic_read(&netlabel_unlabel_accept_flg) == 1) { + memset(secattr, 0, sizeof(*secattr)); + return 0; + } + + return -ENOMSG; +} + +/** + * netlbl_unlabel_defconf - Set the default config to allow unlabeled packets + * + * Description: + * Set the default NetLabel configuration to allow incoming unlabeled packets + * and to send unlabeled network traffic by default. + * + */ +int netlbl_unlabel_defconf(void) +{ + int ret_val; + struct netlbl_dom_map *entry; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (entry == NULL) + return -ENOMEM; + entry->type = NETLBL_NLTYPE_UNLABELED; + ret_val = netlbl_domhsh_add_default(entry); + if (ret_val != 0) + return ret_val; + + atomic_set(&netlabel_unlabel_accept_flg, 1); + + return 0; +} diff --git a/net/netlabel/netlabel_unlabeled.h b/net/netlabel/netlabel_unlabeled.h new file mode 100644 index 00000000000..f300e54e14b --- /dev/null +++ b/net/netlabel/netlabel_unlabeled.h @@ -0,0 +1,98 @@ +/* + * NetLabel Unlabeled Support + * + * This file defines functions for dealing with unlabeled packets for the + * NetLabel system. The NetLabel system manages static and dynamic label + * mappings for network protocols such as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#ifndef _NETLABEL_UNLABELED_H +#define _NETLABEL_UNLABELED_H + +#include <net/netlabel.h> + +/* + * The following NetLabel payloads are supported by the Unlabeled subsystem. + * + * o ACK: + * Sent by the kernel in response to an applications message, applications + * should never send this message. + * + * +----------------------+-----------------------+ + * | seq number (32 bits) | return code (32 bits) | + * +----------------------+-----------------------+ + * + * seq number: the sequence number of the original message, taken from the + * nlmsghdr structure + * return code: return value, based on errno values + * + * o ACCEPT + * This message is sent from an application to specify if the kernel should + * allow unlabled packets to pass if they do not match any of the static + * mappings defined in the unlabeled module. + * + * +-----------------+ + * | allow (32 bits) | + * +-----------------+ + * + * allow: if true (1) then allow the packets to pass, if false (0) then + * reject the packets + * + * o LIST + * This message can be sent either from an application or by the kernel in + * response to an application generated LIST message. When sent by an + * application there is no payload. The kernel should respond to a LIST + * message either with a LIST message on success or an ACK message on + * failure. + * + * +-----------------------+ + * | accept flag (32 bits) | + * +-----------------------+ + * + * accept flag: if true (1) then unlabeled packets are allowed to pass, + * if false (0) then unlabeled packets are rejected + * + */ + +/* NetLabel Unlabeled commands */ +enum { + NLBL_UNLABEL_C_UNSPEC, + NLBL_UNLABEL_C_ACK, + NLBL_UNLABEL_C_ACCEPT, + NLBL_UNLABEL_C_LIST, + __NLBL_UNLABEL_C_MAX, +}; +#define NLBL_UNLABEL_C_MAX (__NLBL_UNLABEL_C_MAX - 1) + +/* NetLabel protocol functions */ +int netlbl_unlabel_genl_init(void); + +/* Process Unlabeled incoming network packets */ +int netlbl_unlabel_getattr(struct netlbl_lsm_secattr *secattr); + +/* Set the default configuration to allow Unlabeled packets */ +int netlbl_unlabel_defconf(void); + +#endif diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c new file mode 100644 index 00000000000..73cbe66e42f --- /dev/null +++ b/net/netlabel/netlabel_user.c @@ -0,0 +1,158 @@ +/* + * NetLabel NETLINK Interface + * + * This file defines the NETLINK interface for the NetLabel system. The + * NetLabel system manages static and dynamic label mappings for network + * protocols such as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#include <linux/init.h> +#include <linux/types.h> +#include <linux/list.h> +#include <linux/socket.h> +#include <net/sock.h> +#include <net/netlink.h> +#include <net/genetlink.h> +#include <net/netlabel.h> +#include <asm/bug.h> + +#include "netlabel_mgmt.h" +#include "netlabel_unlabeled.h" +#include "netlabel_cipso_v4.h" +#include "netlabel_user.h" + +/* + * NetLabel NETLINK Setup Functions + */ + +/** + * netlbl_netlink_init - Initialize the NETLINK communication channel + * + * Description: + * Call out to the NetLabel components so they can register their families and + * commands with the Generic NETLINK mechanism. Returns zero on success and + * non-zero on failure. + * + */ +int netlbl_netlink_init(void) +{ + int ret_val; + + ret_val = netlbl_mgmt_genl_init(); + if (ret_val != 0) + return ret_val; + + ret_val = netlbl_cipsov4_genl_init(); + if (ret_val != 0) + return ret_val; + + ret_val = netlbl_unlabel_genl_init(); + if (ret_val != 0) + return ret_val; + + return 0; +} + +/* + * NetLabel Common Protocol Functions + */ + +/** + * netlbl_netlink_send_ack - Send an ACK message + * @info: the generic NETLINK information + * @genl_family: the generic NETLINK family ID value + * @ack_cmd: the generic NETLINK family ACK command value + * @ret_code: return code to use + * + * Description: + * This function sends an ACK message to the sender of the NETLINK message + * specified by @info. + * + */ +void netlbl_netlink_send_ack(const struct genl_info *info, + u32 genl_family, + u8 ack_cmd, + u32 ret_code) +{ + size_t data_size; + struct sk_buff *skb; + + data_size = GENL_HDRLEN + 2 * NETLBL_LEN_U32; + skb = netlbl_netlink_alloc_skb(0, data_size, GFP_KERNEL); + if (skb == NULL) + return; + + if (netlbl_netlink_hdr_put(skb, + info->snd_pid, + 0, + genl_family, + ack_cmd) == NULL) + goto send_ack_failure; + + if (nla_put_u32(skb, NLA_U32, info->snd_seq) != 0) + goto send_ack_failure; + if (nla_put_u32(skb, NLA_U32, ret_code) != 0) + goto send_ack_failure; + + netlbl_netlink_snd(skb, info->snd_pid); + return; + +send_ack_failure: + kfree_skb(skb); +} + +/* + * NETLINK I/O Functions + */ + +/** + * netlbl_netlink_snd - Send a NetLabel message + * @skb: NetLabel message + * @pid: destination PID + * + * Description: + * Sends a unicast NetLabel message over the NETLINK socket. + * + */ +int netlbl_netlink_snd(struct sk_buff *skb, u32 pid) +{ + return genlmsg_unicast(skb, pid); +} + +/** + * netlbl_netlink_snd - Send a NetLabel message + * @skb: NetLabel message + * @pid: sending PID + * @group: multicast group id + * + * Description: + * Sends a multicast NetLabel message over the NETLINK socket to all members + * of @group except @pid. + * + */ +int netlbl_netlink_snd_multicast(struct sk_buff *skb, u32 pid, u32 group) +{ + return genlmsg_multicast(skb, pid, group, GFP_KERNEL); +} diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h new file mode 100644 index 00000000000..385a6c7488c --- /dev/null +++ b/net/netlabel/netlabel_user.h @@ -0,0 +1,215 @@ +/* + * NetLabel NETLINK Interface + * + * This file defines the NETLINK interface for the NetLabel system. The + * NetLabel system manages static and dynamic label mappings for network + * protocols such as CIPSO and RIPSO. + * + * Author: Paul Moore <paul.moore@hp.com> + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * + * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#ifndef _NETLABEL_USER_H +#define _NETLABEL_USER_H + +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/capability.h> +#include <net/netlink.h> +#include <net/genetlink.h> +#include <net/netlabel.h> + +/* NetLabel NETLINK helper functions */ + +/** + * netlbl_netlink_cap_check - Check the NETLINK msg capabilities + * @skb: the NETLINK buffer + * @req_cap: the required capability + * + * Description: + * Check the NETLINK buffer's capabilities against the required capabilities. + * Returns zero on success, negative values on failure. + * + */ +static inline int netlbl_netlink_cap_check(const struct sk_buff *skb, + kernel_cap_t req_cap) +{ + if (cap_raised(NETLINK_CB(skb).eff_cap, req_cap)) + return 0; + return -EPERM; +} + +/** + * netlbl_getinc_u8 - Read a u8 value from a nlattr stream and move on + * @nla: the attribute + * @rem_len: remaining length + * + * Description: + * Return a u8 value pointed to by @nla and advance it to the next attribute. + * + */ +static inline u8 netlbl_getinc_u8(struct nlattr **nla, int *rem_len) +{ + u8 val = nla_get_u8(*nla); + *nla = nla_next(*nla, rem_len); + return val; +} + +/** + * netlbl_getinc_u16 - Read a u16 value from a nlattr stream and move on + * @nla: the attribute + * @rem_len: remaining length + * + * Description: + * Return a u16 value pointed to by @nla and advance it to the next attribute. + * + */ +static inline u16 netlbl_getinc_u16(struct nlattr **nla, int *rem_len) +{ + u16 val = nla_get_u16(*nla); + *nla = nla_next(*nla, rem_len); + return val; +} + +/** + * netlbl_getinc_u32 - Read a u32 value from a nlattr stream and move on + * @nla: the attribute + * @rem_len: remaining length + * + * Description: + * Return a u32 value pointed to by @nla and advance it to the next attribute. + * + */ +static inline u32 netlbl_getinc_u32(struct nlattr **nla, int *rem_len) +{ + u32 val = nla_get_u32(*nla); + *nla = nla_next(*nla, rem_len); + return val; +} + +/** + * netlbl_netlink_hdr_put - Write the NETLINK buffers into a sk_buff + * @skb: the packet + * @pid: the PID of the receipient + * @seq: the sequence number + * @type: the generic NETLINK message family type + * @cmd: command + * + * Description: + * Write both a NETLINK nlmsghdr structure and a Generic NETLINK genlmsghdr + * struct to the packet. Returns a pointer to the start of the payload buffer + * on success or NULL on failure. + * + */ +static inline void *netlbl_netlink_hdr_put(struct sk_buff *skb, + u32 pid, + u32 seq, + int type, + u8 cmd) +{ + return genlmsg_put(skb, + pid, + seq, + type, + 0, + 0, + cmd, + NETLBL_PROTO_VERSION); +} + +/** + * netlbl_netlink_hdr_push - Write the NETLINK buffers into a sk_buff + * @skb: the packet + * @pid: the PID of the receipient + * @seq: the sequence number + * @type: the generic NETLINK message family type + * @cmd: command + * + * Description: + * Write both a NETLINK nlmsghdr structure and a Generic NETLINK genlmsghdr + * struct to the packet. + * + */ +static inline void netlbl_netlink_hdr_push(struct sk_buff *skb, + u32 pid, + u32 seq, + int type, + u8 cmd) + +{ + struct nlmsghdr *nlh; + struct genlmsghdr *hdr; + + nlh = (struct nlmsghdr *)skb_push(skb, NLMSG_SPACE(GENL_HDRLEN)); + nlh->nlmsg_type = type; + nlh->nlmsg_len = skb->len; + nlh->nlmsg_flags = 0; + nlh->nlmsg_pid = pid; + nlh->nlmsg_seq = seq; + + hdr = nlmsg_data(nlh); + hdr->cmd = cmd; + hdr->version = NETLBL_PROTO_VERSION; + hdr->reserved = 0; +} + +/** + * netlbl_netlink_payload_len - Return the length of the payload + * @skb: the NETLINK buffer + * + * Description: + * This function returns the length of the NetLabel payload. + * + */ +static inline u32 netlbl_netlink_payload_len(const struct sk_buff *skb) +{ + return nlmsg_len((struct nlmsghdr *)skb->data) - GENL_HDRLEN; +} + +/** + * netlbl_netlink_payload_data - Returns a pointer to the start of the payload + * @skb: the NETLINK buffer + * + * Description: + * This function returns a pointer to the start of the NetLabel payload. + * + */ +static inline void *netlbl_netlink_payload_data(const struct sk_buff *skb) +{ + return (unsigned char *)nlmsg_data((struct nlmsghdr *)skb->data) + + GENL_HDRLEN; +} + +/* NetLabel common protocol functions */ + +void netlbl_netlink_send_ack(const struct genl_info *info, + u32 genl_family, + u8 ack_cmd, + u32 ret_code); + +/* NetLabel NETLINK I/O functions */ + +int netlbl_netlink_init(void); +int netlbl_netlink_snd(struct sk_buff *skb, u32 pid); +int netlbl_netlink_snd_multicast(struct sk_buff *skb, u32 pid, u32 group); + +#endif diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 8b85036ba8e..d56e0d21f91 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1147,7 +1147,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, if (len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; - skb = alloc_skb(len, GFP_KERNEL); + skb = nlmsg_new(len, GFP_KERNEL); if (skb==NULL) goto out; @@ -1341,19 +1341,18 @@ static int netlink_dump(struct sock *sk) struct netlink_callback *cb; struct sk_buff *skb; struct nlmsghdr *nlh; - int len; + int len, err = -ENOBUFS; skb = sock_rmalloc(sk, NLMSG_GOODSIZE, 0, GFP_KERNEL); if (!skb) - return -ENOBUFS; + goto errout; spin_lock(&nlk->cb_lock); cb = nlk->cb; if (cb == NULL) { - spin_unlock(&nlk->cb_lock); - kfree_skb(skb); - return -EINVAL; + err = -EINVAL; + goto errout_skb; } len = cb->dump(skb, cb); @@ -1365,8 +1364,12 @@ static int netlink_dump(struct sock *sk) return 0; } - nlh = NLMSG_NEW_ANSWER(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI); - memcpy(NLMSG_DATA(nlh), &len, sizeof(len)); + nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI); + if (!nlh) + goto errout_skb; + + memcpy(nlmsg_data(nlh), &len, sizeof(len)); + skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk, skb->len); @@ -1378,8 +1381,11 @@ static int netlink_dump(struct sock *sk) netlink_destroy_callback(cb); return 0; -nlmsg_failure: - return -ENOBUFS; +errout_skb: + spin_unlock(&nlk->cb_lock); + kfree_skb(skb); +errout: + return err; } int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, @@ -1431,11 +1437,11 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) int size; if (err == 0) - size = NLMSG_SPACE(sizeof(struct nlmsgerr)); + size = nlmsg_total_size(sizeof(*errmsg)); else - size = NLMSG_SPACE(4 + NLMSG_ALIGN(nlh->nlmsg_len)); + size = nlmsg_total_size(sizeof(*errmsg) + nlmsg_len(nlh)); - skb = alloc_skb(size, GFP_KERNEL); + skb = nlmsg_new(size, GFP_KERNEL); if (!skb) { struct sock *sk; @@ -1451,16 +1457,15 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) rep = __nlmsg_put(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, NLMSG_ERROR, sizeof(struct nlmsgerr), 0); - errmsg = NLMSG_DATA(rep); + errmsg = nlmsg_data(rep); errmsg->error = err; - memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(struct nlmsghdr)); + memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(*nlh)); netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); } static int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, int *)) { - unsigned int total_len; struct nlmsghdr *nlh; int err; @@ -1470,8 +1475,6 @@ static int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return 0; - total_len = min(NLMSG_ALIGN(nlh->nlmsg_len), skb->len); - if (cb(skb, nlh, &err) < 0) { /* Not an error, but we have to interrupt processing * here. Note: that in this case we do not pull @@ -1483,7 +1486,7 @@ static int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, } else if (nlh->nlmsg_flags & NLM_F_ACK) netlink_ack(skb, nlh, 0); - skb_pull(skb, total_len); + netlink_queue_skip(nlh, skb); } return 0; @@ -1546,6 +1549,38 @@ void netlink_queue_skip(struct nlmsghdr *nlh, struct sk_buff *skb) skb_pull(skb, msglen); } +/** + * nlmsg_notify - send a notification netlink message + * @sk: netlink socket to use + * @skb: notification message + * @pid: destination netlink pid for reports or 0 + * @group: destination multicast group or 0 + * @report: 1 to report back, 0 to disable + * @flags: allocation flags + */ +int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 pid, + unsigned int group, int report, gfp_t flags) +{ + int err = 0; + + if (group) { + int exclude_pid = 0; + + if (report) { + atomic_inc(&skb->users); + exclude_pid = pid; + } + + /* errors reported via destination sk->sk_err */ + nlmsg_multicast(sk, skb, exclude_pid, group, flags); + } + + if (report) + err = nlmsg_unicast(sk, skb, pid); + + return err; +} + #ifdef CONFIG_PROC_FS struct nl_seq_iter { int link; @@ -1727,8 +1762,6 @@ static struct net_proto_family netlink_family_ops = { .owner = THIS_MODULE, /* for consistency 8) */ }; -extern void netlink_skb_parms_too_large(void); - static int __init netlink_proto_init(void) { struct sk_buff *dummy_skb; @@ -1740,8 +1773,7 @@ static int __init netlink_proto_init(void) if (err != 0) goto out; - if (sizeof(struct netlink_skb_parms) > sizeof(dummy_skb->cb)) - netlink_skb_parms_too_large(); + BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof(dummy_skb->cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) @@ -1799,4 +1831,4 @@ EXPORT_SYMBOL(netlink_set_err); EXPORT_SYMBOL(netlink_set_nonroot); EXPORT_SYMBOL(netlink_unicast); EXPORT_SYMBOL(netlink_unregister_notifier); - +EXPORT_SYMBOL(nlmsg_notify); diff --git a/net/netlink/attr.c b/net/netlink/attr.c index dddbd15135a..004139557e0 100644 --- a/net/netlink/attr.c +++ b/net/netlink/attr.c @@ -20,7 +20,6 @@ static u16 nla_attr_minlen[NLA_TYPE_MAX+1] __read_mostly = { [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), - [NLA_STRING] = 1, [NLA_NESTED] = NLA_HDRLEN, }; @@ -28,7 +27,7 @@ static int validate_nla(struct nlattr *nla, int maxtype, struct nla_policy *policy) { struct nla_policy *pt; - int minlen = 0; + int minlen = 0, attrlen = nla_len(nla); if (nla->nla_type <= 0 || nla->nla_type > maxtype) return 0; @@ -37,16 +36,46 @@ static int validate_nla(struct nlattr *nla, int maxtype, BUG_ON(pt->type > NLA_TYPE_MAX); - if (pt->minlen) - minlen = pt->minlen; - else if (pt->type != NLA_UNSPEC) - minlen = nla_attr_minlen[pt->type]; + switch (pt->type) { + case NLA_FLAG: + if (attrlen > 0) + return -ERANGE; + break; - if (pt->type == NLA_FLAG && nla_len(nla) > 0) - return -ERANGE; + case NLA_NUL_STRING: + if (pt->len) + minlen = min_t(int, attrlen, pt->len + 1); + else + minlen = attrlen; - if (nla_len(nla) < minlen) - return -ERANGE; + if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL) + return -EINVAL; + /* fall through */ + + case NLA_STRING: + if (attrlen < 1) + return -ERANGE; + + if (pt->len) { + char *buf = nla_data(nla); + + if (buf[attrlen - 1] == '\0') + attrlen--; + + if (attrlen > pt->len) + return -ERANGE; + } + break; + + default: + if (pt->len) + minlen = pt->len; + else if (pt->type != NLA_UNSPEC) + minlen = nla_attr_minlen[pt->type]; + + if (attrlen < minlen) + return -ERANGE; + } return 0; } @@ -255,6 +284,26 @@ struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) } /** + * __nla_reserve_nohdr - reserve room for attribute without header + * @skb: socket buffer to reserve room on + * @attrlen: length of attribute payload + * + * Reserves room for attribute payload without a header. + * + * The caller is responsible to ensure that the skb provides enough + * tailroom for the payload. + */ +void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) +{ + void *start; + + start = skb_put(skb, NLA_ALIGN(attrlen)); + memset(start, 0, NLA_ALIGN(attrlen)); + + return start; +} + +/** * nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type @@ -275,6 +324,24 @@ struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) } /** + * nla_reserve - reserve room for attribute without header + * @skb: socket buffer to reserve room on + * @len: length of attribute payload + * + * Reserves room for attribute payload without a header. + * + * Returns NULL if the tailroom of the skb is insufficient to store + * the attribute payload. + */ +void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen) +{ + if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) + return NULL; + + return __nla_reserve_nohdr(skb, attrlen); +} + +/** * __nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type @@ -293,6 +360,22 @@ void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, memcpy(nla_data(nla), data, attrlen); } +/** + * __nla_put_nohdr - Add a netlink attribute without header + * @skb: socket buffer to add attribute to + * @attrlen: length of attribute payload + * @data: head of attribute payload + * + * The caller is responsible to ensure that the skb provides enough + * tailroom for the attribute payload. + */ +void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) +{ + void *start; + + start = __nla_reserve_nohdr(skb, attrlen); + memcpy(start, data, attrlen); +} /** * nla_put - Add a netlink attribute to a socket buffer @@ -313,15 +396,36 @@ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) return 0; } +/** + * nla_put_nohdr - Add a netlink attribute without header + * @skb: socket buffer to add attribute to + * @attrlen: length of attribute payload + * @data: head of attribute payload + * + * Returns -1 if the tailroom of the skb is insufficient to store + * the attribute payload. + */ +int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) +{ + if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) + return -1; + + __nla_put_nohdr(skb, attrlen, data); + return 0; +} EXPORT_SYMBOL(nla_validate); EXPORT_SYMBOL(nla_parse); EXPORT_SYMBOL(nla_find); EXPORT_SYMBOL(nla_strlcpy); EXPORT_SYMBOL(__nla_reserve); +EXPORT_SYMBOL(__nla_reserve_nohdr); EXPORT_SYMBOL(nla_reserve); +EXPORT_SYMBOL(nla_reserve_nohdr); EXPORT_SYMBOL(__nla_put); +EXPORT_SYMBOL(__nla_put_nohdr); EXPORT_SYMBOL(nla_put); +EXPORT_SYMBOL(nla_put_nohdr); EXPORT_SYMBOL(nla_memcpy); EXPORT_SYMBOL(nla_memcmp); EXPORT_SYMBOL(nla_strcmp); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index a298f77cc3e..49bc2db7982 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -387,7 +387,10 @@ static void genl_rcv(struct sock *sk, int len) static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { + struct nlattr *nla_ops; + struct genl_ops *ops; void *hdr; + int idx = 1; hdr = genlmsg_put(skb, pid, seq, GENL_ID_CTRL, 0, flags, cmd, family->version); @@ -396,6 +399,37 @@ static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, NLA_PUT_STRING(skb, CTRL_ATTR_FAMILY_NAME, family->name); NLA_PUT_U16(skb, CTRL_ATTR_FAMILY_ID, family->id); + NLA_PUT_U32(skb, CTRL_ATTR_VERSION, family->version); + NLA_PUT_U32(skb, CTRL_ATTR_HDRSIZE, family->hdrsize); + NLA_PUT_U32(skb, CTRL_ATTR_MAXATTR, family->maxattr); + + nla_ops = nla_nest_start(skb, CTRL_ATTR_OPS); + if (nla_ops == NULL) + goto nla_put_failure; + + list_for_each_entry(ops, &family->ops_list, ops_list) { + struct nlattr *nest; + + nest = nla_nest_start(skb, idx++); + if (nest == NULL) + goto nla_put_failure; + + NLA_PUT_U32(skb, CTRL_ATTR_OP_ID, ops->cmd); + NLA_PUT_U32(skb, CTRL_ATTR_OP_FLAGS, ops->flags); + + if (ops->policy) + NLA_PUT_FLAG(skb, CTRL_ATTR_OP_POLICY); + + if (ops->doit) + NLA_PUT_FLAG(skb, CTRL_ATTR_OP_DOIT); + + if (ops->dumpit) + NLA_PUT_FLAG(skb, CTRL_ATTR_OP_DUMPIT); + + nla_nest_end(skb, nest); + } + + nla_nest_end(skb, nla_ops); return genlmsg_end(skb, hdr); @@ -411,6 +445,9 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) int chains_to_skip = cb->args[0]; int fams_to_skip = cb->args[1]; + if (chains_to_skip != 0) + genl_lock(); + for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { if (i < chains_to_skip) continue; @@ -428,6 +465,9 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) } errout: + if (chains_to_skip != 0) + genl_unlock(); + cb->args[0] = i; cb->args[1] = n; @@ -440,7 +480,7 @@ static struct sk_buff *ctrl_build_msg(struct genl_family *family, u32 pid, struct sk_buff *skb; int err; - skb = nlmsg_new(NLMSG_GOODSIZE); + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (skb == NULL) return ERR_PTR(-ENOBUFS); @@ -455,7 +495,8 @@ static struct sk_buff *ctrl_build_msg(struct genl_family *family, u32 pid, static struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] __read_mostly = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, - [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_STRING }, + [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, + .len = GENL_NAMSIZ - 1 }, }; static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) @@ -470,12 +511,9 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[CTRL_ATTR_FAMILY_NAME]) { - char name[GENL_NAMSIZ]; - - if (nla_strlcpy(name, info->attrs[CTRL_ATTR_FAMILY_NAME], - GENL_NAMSIZ) >= GENL_NAMSIZ) - goto errout; + char *name; + name = nla_data(info->attrs[CTRL_ATTR_FAMILY_NAME]); res = genl_family_find_byname(name); } @@ -510,7 +548,7 @@ static int genl_ctrl_event(int event, void *data) if (IS_ERR(msg)) return PTR_ERR(msg); - genlmsg_multicast(msg, 0, GENL_ID_CTRL); + genlmsg_multicast(msg, 0, GENL_ID_CTRL, GFP_KERNEL); break; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4172a523591..f4ccb90e673 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -427,21 +427,24 @@ out_unlock: } #endif -static inline unsigned run_filter(struct sk_buff *skb, struct sock *sk, unsigned res) +static inline int run_filter(struct sk_buff *skb, struct sock *sk, + unsigned *snaplen) { struct sk_filter *filter; + int err = 0; - bh_lock_sock(sk); - filter = sk->sk_filter; - /* - * Our caller already checked that filter != NULL but we need to - * verify that under bh_lock_sock() to be safe - */ - if (likely(filter != NULL)) - res = sk_run_filter(skb, filter->insns, filter->len); - bh_unlock_sock(sk); + rcu_read_lock_bh(); + filter = rcu_dereference(sk->sk_filter); + if (filter != NULL) { + err = sk_run_filter(skb, filter->insns, filter->len); + if (!err) + err = -EPERM; + else if (*snaplen > err) + *snaplen = err; + } + rcu_read_unlock_bh(); - return res; + return err; } /* @@ -491,13 +494,8 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet snaplen = skb->len; - if (sk->sk_filter) { - unsigned res = run_filter(skb, sk, snaplen); - if (res == 0) - goto drop_n_restore; - if (snaplen > res) - snaplen = res; - } + if (run_filter(skb, sk, &snaplen) < 0) + goto drop_n_restore; if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned)sk->sk_rcvbuf) @@ -586,20 +584,15 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb->nh.raw - skb->data); - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; } } snaplen = skb->len; - if (sk->sk_filter) { - unsigned res = run_filter(skb, sk, snaplen); - if (res == 0) - goto drop_n_restore; - if (snaplen > res) - snaplen = res; - } + if (run_filter(skb, sk, &snaplen) < 0) + goto drop_n_restore; if (sk->sk_type == SOCK_DGRAM) { macoff = netoff = TPACKET_ALIGN(TPACKET_HDRLEN) + 16; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index a2587b52e53..835070e9169 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -33,16 +33,230 @@ #include <net/sch_generic.h> #include <net/act_api.h> -#if 0 /* control */ -#define DPRINTK(format, args...) printk(KERN_DEBUG format, ##args) -#else -#define DPRINTK(format, args...) +void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) +{ + unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask); + struct tcf_common **p1p; + + for (p1p = &hinfo->htab[h]; *p1p; p1p = &(*p1p)->tcfc_next) { + if (*p1p == p) { + write_lock_bh(hinfo->lock); + *p1p = p->tcfc_next; + write_unlock_bh(hinfo->lock); +#ifdef CONFIG_NET_ESTIMATOR + gen_kill_estimator(&p->tcfc_bstats, + &p->tcfc_rate_est); #endif -#if 0 /* data */ -#define D2PRINTK(format, args...) printk(KERN_DEBUG format, ##args) -#else -#define D2PRINTK(format, args...) + kfree(p); + return; + } + } + BUG_TRAP(0); +} +EXPORT_SYMBOL(tcf_hash_destroy); + +int tcf_hash_release(struct tcf_common *p, int bind, + struct tcf_hashinfo *hinfo) +{ + int ret = 0; + + if (p) { + if (bind) + p->tcfc_bindcnt--; + + p->tcfc_refcnt--; + if (p->tcfc_bindcnt <= 0 && p->tcfc_refcnt <= 0) { + tcf_hash_destroy(p, hinfo); + ret = 1; + } + } + return ret; +} +EXPORT_SYMBOL(tcf_hash_release); + +static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, + struct tc_action *a, struct tcf_hashinfo *hinfo) +{ + struct tcf_common *p; + int err = 0, index = -1,i = 0, s_i = 0, n_i = 0; + struct rtattr *r ; + + read_lock(hinfo->lock); + + s_i = cb->args[0]; + + for (i = 0; i < (hinfo->hmask + 1); i++) { + p = hinfo->htab[tcf_hash(i, hinfo->hmask)]; + + for (; p; p = p->tcfc_next) { + index++; + if (index < s_i) + continue; + a->priv = p; + a->order = n_i; + r = (struct rtattr*) skb->tail; + RTA_PUT(skb, a->order, 0, NULL); + err = tcf_action_dump_1(skb, a, 0, 0); + if (err < 0) { + index--; + skb_trim(skb, (u8*)r - skb->data); + goto done; + } + r->rta_len = skb->tail - (u8*)r; + n_i++; + if (n_i >= TCA_ACT_MAX_PRIO) + goto done; + } + } +done: + read_unlock(hinfo->lock); + if (n_i) + cb->args[0] += n_i; + return n_i; + +rtattr_failure: + skb_trim(skb, (u8*)r - skb->data); + goto done; +} + +static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, + struct tcf_hashinfo *hinfo) +{ + struct tcf_common *p, *s_p; + struct rtattr *r ; + int i= 0, n_i = 0; + + r = (struct rtattr*) skb->tail; + RTA_PUT(skb, a->order, 0, NULL); + RTA_PUT(skb, TCA_KIND, IFNAMSIZ, a->ops->kind); + for (i = 0; i < (hinfo->hmask + 1); i++) { + p = hinfo->htab[tcf_hash(i, hinfo->hmask)]; + + while (p != NULL) { + s_p = p->tcfc_next; + if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) + module_put(a->ops->owner); + n_i++; + p = s_p; + } + } + RTA_PUT(skb, TCA_FCNT, 4, &n_i); + r->rta_len = skb->tail - (u8*)r; + + return n_i; +rtattr_failure: + skb_trim(skb, (u8*)r - skb->data); + return -EINVAL; +} + +int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, + int type, struct tc_action *a) +{ + struct tcf_hashinfo *hinfo = a->ops->hinfo; + + if (type == RTM_DELACTION) { + return tcf_del_walker(skb, a, hinfo); + } else if (type == RTM_GETACTION) { + return tcf_dump_walker(skb, cb, a, hinfo); + } else { + printk("tcf_generic_walker: unknown action %d\n", type); + return -EINVAL; + } +} +EXPORT_SYMBOL(tcf_generic_walker); + +struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo) +{ + struct tcf_common *p; + + read_lock(hinfo->lock); + for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p; + p = p->tcfc_next) { + if (p->tcfc_index == index) + break; + } + read_unlock(hinfo->lock); + + return p; +} +EXPORT_SYMBOL(tcf_hash_lookup); + +u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo) +{ + u32 val = *idx_gen; + + do { + if (++val == 0) + val = 1; + } while (tcf_hash_lookup(val, hinfo)); + + return (*idx_gen = val); +} +EXPORT_SYMBOL(tcf_hash_new_index); + +int tcf_hash_search(struct tc_action *a, u32 index) +{ + struct tcf_hashinfo *hinfo = a->ops->hinfo; + struct tcf_common *p = tcf_hash_lookup(index, hinfo); + + if (p) { + a->priv = p; + return 1; + } + return 0; +} +EXPORT_SYMBOL(tcf_hash_search); + +struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind, + struct tcf_hashinfo *hinfo) +{ + struct tcf_common *p = NULL; + if (index && (p = tcf_hash_lookup(index, hinfo)) != NULL) { + if (bind) { + p->tcfc_bindcnt++; + p->tcfc_refcnt++; + } + a->priv = p; + } + return p; +} +EXPORT_SYMBOL(tcf_hash_check); + +struct tcf_common *tcf_hash_create(u32 index, struct rtattr *est, struct tc_action *a, int size, int bind, u32 *idx_gen, struct tcf_hashinfo *hinfo) +{ + struct tcf_common *p = kzalloc(size, GFP_KERNEL); + + if (unlikely(!p)) + return p; + p->tcfc_refcnt = 1; + if (bind) + p->tcfc_bindcnt = 1; + + spin_lock_init(&p->tcfc_lock); + p->tcfc_stats_lock = &p->tcfc_lock; + p->tcfc_index = index ? index : tcf_hash_new_index(idx_gen, hinfo); + p->tcfc_tm.install = jiffies; + p->tcfc_tm.lastuse = jiffies; +#ifdef CONFIG_NET_ESTIMATOR + if (est) + gen_new_estimator(&p->tcfc_bstats, &p->tcfc_rate_est, + p->tcfc_stats_lock, est); #endif + a->priv = (void *) p; + return p; +} +EXPORT_SYMBOL(tcf_hash_create); + +void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo) +{ + unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask); + + write_lock_bh(hinfo->lock); + p->tcfc_next = hinfo->htab[h]; + hinfo->htab[h] = p; + write_unlock_bh(hinfo->lock); +} +EXPORT_SYMBOL(tcf_hash_insert); static struct tc_action_ops *act_base = NULL; static DEFINE_RWLOCK(act_mod_lock); @@ -155,9 +369,6 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action *act, if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); - D2PRINTK("(%p)tcf_action_exec: cleared TC_NCLS in %s out %s\n", - skb, skb->input_dev ? skb->input_dev->name : "xxx", - skb->dev->name); ret = TC_ACT_OK; goto exec_done; } @@ -187,8 +398,6 @@ void tcf_action_destroy(struct tc_action *act, int bind) for (a = act; a; a = act) { if (a->ops && a->ops->cleanup) { - DPRINTK("tcf_action_destroy destroying %p next %p\n", - a, a->next); if (a->ops->cleanup(a, bind) == ACT_P_DELETED) module_put(a->ops->owner); act = act->next; @@ -331,7 +540,6 @@ struct tc_action *tcf_action_init_1(struct rtattr *rta, struct rtattr *est, if (*err != ACT_P_CREATED) module_put(a_o->owner); a->ops = a_o; - DPRINTK("tcf_action_init_1: successfull %s\n", act_name); *err = 0; return a; @@ -392,12 +600,12 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (compat_mode) { if (a->type == TCA_OLD_COMPAT) err = gnet_stats_start_copy_compat(skb, 0, - TCA_STATS, TCA_XSTATS, h->stats_lock, &d); + TCA_STATS, TCA_XSTATS, h->tcf_stats_lock, &d); else return 0; } else err = gnet_stats_start_copy(skb, TCA_ACT_STATS, - h->stats_lock, &d); + h->tcf_stats_lock, &d); if (err < 0) goto errout; @@ -406,11 +614,11 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (a->ops->get_stats(skb, a) < 0) goto errout; - if (gnet_stats_copy_basic(&d, &h->bstats) < 0 || + if (gnet_stats_copy_basic(&d, &h->tcf_bstats) < 0 || #ifdef CONFIG_NET_ESTIMATOR - gnet_stats_copy_rate_est(&d, &h->rate_est) < 0 || + gnet_stats_copy_rate_est(&d, &h->tcf_rate_est) < 0 || #endif - gnet_stats_copy_queue(&d, &h->qstats) < 0) + gnet_stats_copy_queue(&d, &h->tcf_qstats) < 0) goto errout; if (gnet_stats_finish_copy(&d) < 0) @@ -459,7 +667,6 @@ static int act_get_notify(u32 pid, struct nlmsghdr *n, struct tc_action *a, int event) { struct sk_buff *skb; - int err = 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) @@ -468,10 +675,8 @@ act_get_notify(u32 pid, struct nlmsghdr *n, struct tc_action *a, int event) kfree_skb(skb); return -EINVAL; } - err = netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT); - if (err > 0) - err = 0; - return err; + + return rtnl_unicast(skb, pid); } static struct tc_action * diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index e75a147ad60..6cff56696a8 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -34,48 +34,43 @@ #include <linux/tc_act/tc_gact.h> #include <net/tc_act/tc_gact.h> -/* use generic hash table */ -#define MY_TAB_SIZE 16 -#define MY_TAB_MASK 15 - -static u32 idx_gen; -static struct tcf_gact *tcf_gact_ht[MY_TAB_SIZE]; +#define GACT_TAB_MASK 15 +static struct tcf_common *tcf_gact_ht[GACT_TAB_MASK + 1]; +static u32 gact_idx_gen; static DEFINE_RWLOCK(gact_lock); -/* ovewrride the defaults */ -#define tcf_st tcf_gact -#define tc_st tc_gact -#define tcf_t_lock gact_lock -#define tcf_ht tcf_gact_ht - -#define CONFIG_NET_ACT_INIT 1 -#include <net/pkt_act.h> +static struct tcf_hashinfo gact_hash_info = { + .htab = tcf_gact_ht, + .hmask = GACT_TAB_MASK, + .lock = &gact_lock, +}; #ifdef CONFIG_GACT_PROB -static int gact_net_rand(struct tcf_gact *p) +static int gact_net_rand(struct tcf_gact *gact) { - if (net_random()%p->pval) - return p->action; - return p->paction; + if (net_random() % gact->tcfg_pval) + return gact->tcf_action; + return gact->tcfg_paction; } -static int gact_determ(struct tcf_gact *p) +static int gact_determ(struct tcf_gact *gact) { - if (p->bstats.packets%p->pval) - return p->action; - return p->paction; + if (gact->tcf_bstats.packets % gact->tcfg_pval) + return gact->tcf_action; + return gact->tcfg_paction; } -typedef int (*g_rand)(struct tcf_gact *p); +typedef int (*g_rand)(struct tcf_gact *gact); static g_rand gact_rand[MAX_RAND]= { NULL, gact_net_rand, gact_determ }; -#endif +#endif /* CONFIG_GACT_PROB */ static int tcf_gact_init(struct rtattr *rta, struct rtattr *est, struct tc_action *a, int ovr, int bind) { struct rtattr *tb[TCA_GACT_MAX]; struct tc_gact *parm; - struct tcf_gact *p; + struct tcf_gact *gact; + struct tcf_common *pc; int ret = 0; if (rta == NULL || rtattr_parse_nested(tb, TCA_GACT_MAX, rta) < 0) @@ -94,105 +89,106 @@ static int tcf_gact_init(struct rtattr *rta, struct rtattr *est, return -EOPNOTSUPP; #endif - p = tcf_hash_check(parm->index, a, ovr, bind); - if (p == NULL) { - p = tcf_hash_create(parm->index, est, a, sizeof(*p), ovr, bind); - if (p == NULL) + pc = tcf_hash_check(parm->index, a, bind, &gact_hash_info); + if (!pc) { + pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), + bind, &gact_idx_gen, &gact_hash_info); + if (unlikely(!pc)) return -ENOMEM; ret = ACT_P_CREATED; } else { if (!ovr) { - tcf_hash_release(p, bind); + tcf_hash_release(pc, bind, &gact_hash_info); return -EEXIST; } } - spin_lock_bh(&p->lock); - p->action = parm->action; + gact = to_gact(pc); + + spin_lock_bh(&gact->tcf_lock); + gact->tcf_action = parm->action; #ifdef CONFIG_GACT_PROB if (tb[TCA_GACT_PROB-1] != NULL) { struct tc_gact_p *p_parm = RTA_DATA(tb[TCA_GACT_PROB-1]); - p->paction = p_parm->paction; - p->pval = p_parm->pval; - p->ptype = p_parm->ptype; + gact->tcfg_paction = p_parm->paction; + gact->tcfg_pval = p_parm->pval; + gact->tcfg_ptype = p_parm->ptype; } #endif - spin_unlock_bh(&p->lock); + spin_unlock_bh(&gact->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(p); + tcf_hash_insert(pc, &gact_hash_info); return ret; } -static int -tcf_gact_cleanup(struct tc_action *a, int bind) +static int tcf_gact_cleanup(struct tc_action *a, int bind) { - struct tcf_gact *p = PRIV(a, gact); + struct tcf_gact *gact = a->priv; - if (p != NULL) - return tcf_hash_release(p, bind); + if (gact) + return tcf_hash_release(&gact->common, bind, &gact_hash_info); return 0; } -static int -tcf_gact(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) +static int tcf_gact(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) { - struct tcf_gact *p = PRIV(a, gact); + struct tcf_gact *gact = a->priv; int action = TC_ACT_SHOT; - spin_lock(&p->lock); + spin_lock(&gact->tcf_lock); #ifdef CONFIG_GACT_PROB - if (p->ptype && gact_rand[p->ptype] != NULL) - action = gact_rand[p->ptype](p); + if (gact->tcfg_ptype && gact_rand[gact->tcfg_ptype] != NULL) + action = gact_rand[gact->tcfg_ptype](gact); else - action = p->action; + action = gact->tcf_action; #else - action = p->action; + action = gact->tcf_action; #endif - p->bstats.bytes += skb->len; - p->bstats.packets++; + gact->tcf_bstats.bytes += skb->len; + gact->tcf_bstats.packets++; if (action == TC_ACT_SHOT) - p->qstats.drops++; - p->tm.lastuse = jiffies; - spin_unlock(&p->lock); + gact->tcf_qstats.drops++; + gact->tcf_tm.lastuse = jiffies; + spin_unlock(&gact->tcf_lock); return action; } -static int -tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb->tail; struct tc_gact opt; - struct tcf_gact *p = PRIV(a, gact); + struct tcf_gact *gact = a->priv; struct tcf_t t; - opt.index = p->index; - opt.refcnt = p->refcnt - ref; - opt.bindcnt = p->bindcnt - bind; - opt.action = p->action; + opt.index = gact->tcf_index; + opt.refcnt = gact->tcf_refcnt - ref; + opt.bindcnt = gact->tcf_bindcnt - bind; + opt.action = gact->tcf_action; RTA_PUT(skb, TCA_GACT_PARMS, sizeof(opt), &opt); #ifdef CONFIG_GACT_PROB - if (p->ptype) { + if (gact->tcfg_ptype) { struct tc_gact_p p_opt; - p_opt.paction = p->paction; - p_opt.pval = p->pval; - p_opt.ptype = p->ptype; + p_opt.paction = gact->tcfg_paction; + p_opt.pval = gact->tcfg_pval; + p_opt.ptype = gact->tcfg_ptype; RTA_PUT(skb, TCA_GACT_PROB, sizeof(p_opt), &p_opt); } #endif - t.install = jiffies_to_clock_t(jiffies - p->tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - p->tm.lastuse); - t.expires = jiffies_to_clock_t(p->tm.expires); + t.install = jiffies_to_clock_t(jiffies - gact->tcf_tm.install); + t.lastuse = jiffies_to_clock_t(jiffies - gact->tcf_tm.lastuse); + t.expires = jiffies_to_clock_t(gact->tcf_tm.expires); RTA_PUT(skb, TCA_GACT_TM, sizeof(t), &t); return skb->len; - rtattr_failure: +rtattr_failure: skb_trim(skb, b - skb->data); return -1; } static struct tc_action_ops act_gact_ops = { .kind = "gact", + .hinfo = &gact_hash_info, .type = TCA_ACT_GACT, .capab = TCA_CAP_NONE, .owner = THIS_MODULE, @@ -208,8 +204,7 @@ MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); MODULE_DESCRIPTION("Generic Classifier actions"); MODULE_LICENSE("GPL"); -static int __init -gact_init_module(void) +static int __init gact_init_module(void) { #ifdef CONFIG_GACT_PROB printk("GACT probability on\n"); @@ -219,8 +214,7 @@ gact_init_module(void) return tcf_register_action(&act_gact_ops); } -static void __exit -gact_cleanup_module(void) +static void __exit gact_cleanup_module(void) { tcf_unregister_action(&act_gact_ops); } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index d799e01248c..d8c9310da6e 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -38,25 +38,19 @@ #include <linux/netfilter_ipv4/ip_tables.h> -/* use generic hash table */ -#define MY_TAB_SIZE 16 -#define MY_TAB_MASK 15 -static u32 idx_gen; -static struct tcf_ipt *tcf_ipt_ht[MY_TAB_SIZE]; -/* ipt hash table lock */ +#define IPT_TAB_MASK 15 +static struct tcf_common *tcf_ipt_ht[IPT_TAB_MASK + 1]; +static u32 ipt_idx_gen; static DEFINE_RWLOCK(ipt_lock); -/* ovewrride the defaults */ -#define tcf_st tcf_ipt -#define tcf_t_lock ipt_lock -#define tcf_ht tcf_ipt_ht - -#define CONFIG_NET_ACT_INIT -#include <net/pkt_act.h> +static struct tcf_hashinfo ipt_hash_info = { + .htab = tcf_ipt_ht, + .hmask = IPT_TAB_MASK, + .lock = &ipt_lock, +}; -static int -ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook) +static int ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook) { struct ipt_target *target; int ret = 0; @@ -65,7 +59,6 @@ ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook) if (!target) return -ENOENT; - DPRINTK("ipt_init_target: found %s\n", target->name); t->u.kernel.target = target; ret = xt_check_target(target, AF_INET, t->u.target_size - sizeof(*t), @@ -76,10 +69,7 @@ ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook) if (t->u.kernel.target->checkentry && !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", - t->u.kernel.target->name); module_put(t->u.kernel.target->me); ret = -EINVAL; } @@ -87,40 +77,37 @@ ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook) return ret; } -static void -ipt_destroy_target(struct ipt_entry_target *t) +static void ipt_destroy_target(struct ipt_entry_target *t) { if (t->u.kernel.target->destroy) - t->u.kernel.target->destroy(t->u.kernel.target, t->data, - t->u.target_size - sizeof(*t)); + t->u.kernel.target->destroy(t->u.kernel.target, t->data); module_put(t->u.kernel.target->me); } -static int -tcf_ipt_release(struct tcf_ipt *p, int bind) +static int tcf_ipt_release(struct tcf_ipt *ipt, int bind) { int ret = 0; - if (p) { + if (ipt) { if (bind) - p->bindcnt--; - p->refcnt--; - if (p->bindcnt <= 0 && p->refcnt <= 0) { - ipt_destroy_target(p->t); - kfree(p->tname); - kfree(p->t); - tcf_hash_destroy(p); + ipt->tcf_bindcnt--; + ipt->tcf_refcnt--; + if (ipt->tcf_bindcnt <= 0 && ipt->tcf_refcnt <= 0) { + ipt_destroy_target(ipt->tcfi_t); + kfree(ipt->tcfi_tname); + kfree(ipt->tcfi_t); + tcf_hash_destroy(&ipt->common, &ipt_hash_info); ret = ACT_P_DELETED; } } return ret; } -static int -tcf_ipt_init(struct rtattr *rta, struct rtattr *est, struct tc_action *a, - int ovr, int bind) +static int tcf_ipt_init(struct rtattr *rta, struct rtattr *est, + struct tc_action *a, int ovr, int bind) { struct rtattr *tb[TCA_IPT_MAX]; - struct tcf_ipt *p; + struct tcf_ipt *ipt; + struct tcf_common *pc; struct ipt_entry_target *td, *t; char *tname; int ret = 0, err; @@ -144,49 +131,51 @@ tcf_ipt_init(struct rtattr *rta, struct rtattr *est, struct tc_action *a, RTA_PAYLOAD(tb[TCA_IPT_INDEX-1]) >= sizeof(u32)) index = *(u32 *)RTA_DATA(tb[TCA_IPT_INDEX-1]); - p = tcf_hash_check(index, a, ovr, bind); - if (p == NULL) { - p = tcf_hash_create(index, est, a, sizeof(*p), ovr, bind); - if (p == NULL) + pc = tcf_hash_check(index, a, bind, &ipt_hash_info); + if (!pc) { + pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind, + &ipt_idx_gen, &ipt_hash_info); + if (unlikely(!pc)) return -ENOMEM; ret = ACT_P_CREATED; } else { if (!ovr) { - tcf_ipt_release(p, bind); + tcf_ipt_release(to_ipt(pc), bind); return -EEXIST; } } + ipt = to_ipt(pc); hook = *(u32 *)RTA_DATA(tb[TCA_IPT_HOOK-1]); err = -ENOMEM; tname = kmalloc(IFNAMSIZ, GFP_KERNEL); - if (tname == NULL) + if (unlikely(!tname)) goto err1; if (tb[TCA_IPT_TABLE - 1] == NULL || rtattr_strlcpy(tname, tb[TCA_IPT_TABLE-1], IFNAMSIZ) >= IFNAMSIZ) strcpy(tname, "mangle"); t = kmalloc(td->u.target_size, GFP_KERNEL); - if (t == NULL) + if (unlikely(!t)) goto err2; memcpy(t, td, td->u.target_size); if ((err = ipt_init_target(t, tname, hook)) < 0) goto err3; - spin_lock_bh(&p->lock); + spin_lock_bh(&ipt->tcf_lock); if (ret != ACT_P_CREATED) { - ipt_destroy_target(p->t); - kfree(p->tname); - kfree(p->t); + ipt_destroy_target(ipt->tcfi_t); + kfree(ipt->tcfi_tname); + kfree(ipt->tcfi_t); } - p->tname = tname; - p->t = t; - p->hook = hook; - spin_unlock_bh(&p->lock); + ipt->tcfi_tname = tname; + ipt->tcfi_t = t; + ipt->tcfi_hook = hook; + spin_unlock_bh(&ipt->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(p); + tcf_hash_insert(pc, &ipt_hash_info); return ret; err3: @@ -194,33 +183,32 @@ err3: err2: kfree(tname); err1: - kfree(p); + kfree(pc); return err; } -static int -tcf_ipt_cleanup(struct tc_action *a, int bind) +static int tcf_ipt_cleanup(struct tc_action *a, int bind) { - struct tcf_ipt *p = PRIV(a, ipt); - return tcf_ipt_release(p, bind); + struct tcf_ipt *ipt = a->priv; + return tcf_ipt_release(ipt, bind); } -static int -tcf_ipt(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) +static int tcf_ipt(struct sk_buff *skb, struct tc_action *a, + struct tcf_result *res) { int ret = 0, result = 0; - struct tcf_ipt *p = PRIV(a, ipt); + struct tcf_ipt *ipt = a->priv; if (skb_cloned(skb)) { if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) return TC_ACT_UNSPEC; } - spin_lock(&p->lock); + spin_lock(&ipt->tcf_lock); - p->tm.lastuse = jiffies; - p->bstats.bytes += skb->len; - p->bstats.packets++; + ipt->tcf_tm.lastuse = jiffies; + ipt->tcf_bstats.bytes += skb->len; + ipt->tcf_bstats.packets++; /* yes, we have to worry about both in and out dev worry later - danger - this API seems to have changed @@ -229,16 +217,17 @@ 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->u.kernel.target, p->t->data, - NULL); + ret = ipt->tcfi_t->u.kernel.target->target(&skb, skb->dev, NULL, + ipt->tcfi_hook, + ipt->tcfi_t->u.kernel.target, + ipt->tcfi_t->data); switch (ret) { case NF_ACCEPT: result = TC_ACT_OK; break; case NF_DROP: result = TC_ACT_SHOT; - p->qstats.drops++; + ipt->tcf_qstats.drops++; break; case IPT_CONTINUE: result = TC_ACT_PIPE; @@ -249,53 +238,46 @@ tcf_ipt(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) result = TC_POLICE_OK; break; } - spin_unlock(&p->lock); + spin_unlock(&ipt->tcf_lock); return result; } -static int -tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { + unsigned char *b = skb->tail; + struct tcf_ipt *ipt = a->priv; struct ipt_entry_target *t; struct tcf_t tm; struct tc_cnt c; - unsigned char *b = skb->tail; - struct tcf_ipt *p = PRIV(a, ipt); /* for simple targets kernel size == user size ** user name = target name ** for foolproof you need to not assume this */ - t = kmalloc(p->t->u.user.target_size, GFP_ATOMIC); - if (t == NULL) + t = kmalloc(ipt->tcfi_t->u.user.target_size, GFP_ATOMIC); + if (unlikely(!t)) goto rtattr_failure; - c.bindcnt = p->bindcnt - bind; - c.refcnt = p->refcnt - ref; - memcpy(t, p->t, p->t->u.user.target_size); - strcpy(t->u.user.name, p->t->u.kernel.target->name); - - DPRINTK("\ttcf_ipt_dump tablename %s length %d\n", p->tname, - strlen(p->tname)); - DPRINTK("\tdump target name %s size %d size user %d " - "data[0] %x data[1] %x\n", p->t->u.kernel.target->name, - p->t->u.target_size, p->t->u.user.target_size, - p->t->data[0], p->t->data[1]); - RTA_PUT(skb, TCA_IPT_TARG, p->t->u.user.target_size, t); - RTA_PUT(skb, TCA_IPT_INDEX, 4, &p->index); - RTA_PUT(skb, TCA_IPT_HOOK, 4, &p->hook); + c.bindcnt = ipt->tcf_bindcnt - bind; + c.refcnt = ipt->tcf_refcnt - ref; + memcpy(t, ipt->tcfi_t, ipt->tcfi_t->u.user.target_size); + strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name); + + RTA_PUT(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t); + RTA_PUT(skb, TCA_IPT_INDEX, 4, &ipt->tcf_index); + RTA_PUT(skb, TCA_IPT_HOOK, 4, &ipt->tcfi_hook); RTA_PUT(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c); - RTA_PUT(skb, TCA_IPT_TABLE, IFNAMSIZ, p->tname); - tm.install = jiffies_to_clock_t(jiffies - p->tm.install); - tm.lastuse = jiffies_to_clock_t(jiffies - p->tm.lastuse); - tm.expires = jiffies_to_clock_t(p->tm.expires); + RTA_PUT(skb, TCA_IPT_TABLE, IFNAMSIZ, ipt->tcfi_tname); + tm.install = jiffies_to_clock_t(jiffies - ipt->tcf_tm.install); + tm.lastuse = jiffies_to_clock_t(jiffies - ipt->tcf_tm.lastuse); + tm.expires = jiffies_to_clock_t(ipt->tcf_tm.expires); RTA_PUT(skb, TCA_IPT_TM, sizeof (tm), &tm); kfree(t); return skb->len; - rtattr_failure: +rtattr_failure: skb_trim(skb, b - skb->data); kfree(t); return -1; @@ -303,6 +285,7 @@ tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) static struct tc_action_ops act_ipt_ops = { .kind = "ipt", + .hinfo = &ipt_hash_info, .type = TCA_ACT_IPT, .capab = TCA_CAP_NONE, .owner = THIS_MODULE, @@ -318,14 +301,12 @@ MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); MODULE_DESCRIPTION("Iptables target actions"); MODULE_LICENSE("GPL"); -static int __init -ipt_init_module(void) +static int __init ipt_init_module(void) { return tcf_register_action(&act_ipt_ops); } -static void __exit -ipt_cleanup_module(void) +static void __exit ipt_cleanup_module(void) { tcf_unregister_action(&act_ipt_ops); } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index fc562047ecc..483897271f1 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -39,46 +39,39 @@ #include <linux/etherdevice.h> #include <linux/if_arp.h> - -/* use generic hash table */ -#define MY_TAB_SIZE 8 -#define MY_TAB_MASK (MY_TAB_SIZE - 1) -static u32 idx_gen; -static struct tcf_mirred *tcf_mirred_ht[MY_TAB_SIZE]; +#define MIRRED_TAB_MASK 7 +static struct tcf_common *tcf_mirred_ht[MIRRED_TAB_MASK + 1]; +static u32 mirred_idx_gen; static DEFINE_RWLOCK(mirred_lock); -/* ovewrride the defaults */ -#define tcf_st tcf_mirred -#define tc_st tc_mirred -#define tcf_t_lock mirred_lock -#define tcf_ht tcf_mirred_ht - -#define CONFIG_NET_ACT_INIT 1 -#include <net/pkt_act.h> +static struct tcf_hashinfo mirred_hash_info = { + .htab = tcf_mirred_ht, + .hmask = MIRRED_TAB_MASK, + .lock = &mirred_lock, +}; -static inline int -tcf_mirred_release(struct tcf_mirred *p, int bind) +static inline int tcf_mirred_release(struct tcf_mirred *m, int bind) { - if (p) { + if (m) { if (bind) - p->bindcnt--; - p->refcnt--; - if(!p->bindcnt && p->refcnt <= 0) { - dev_put(p->dev); - tcf_hash_destroy(p); + m->tcf_bindcnt--; + m->tcf_refcnt--; + if(!m->tcf_bindcnt && m->tcf_refcnt <= 0) { + dev_put(m->tcfm_dev); + tcf_hash_destroy(&m->common, &mirred_hash_info); return 1; } } return 0; } -static int -tcf_mirred_init(struct rtattr *rta, struct rtattr *est, struct tc_action *a, - int ovr, int bind) +static int tcf_mirred_init(struct rtattr *rta, struct rtattr *est, + struct tc_action *a, int ovr, int bind) { struct rtattr *tb[TCA_MIRRED_MAX]; struct tc_mirred *parm; - struct tcf_mirred *p; + struct tcf_mirred *m; + struct tcf_common *pc; struct net_device *dev = NULL; int ret = 0; int ok_push = 0; @@ -110,64 +103,62 @@ tcf_mirred_init(struct rtattr *rta, struct rtattr *est, struct tc_action *a, } } - p = tcf_hash_check(parm->index, a, ovr, bind); - if (p == NULL) { + pc = tcf_hash_check(parm->index, a, bind, &mirred_hash_info); + if (!pc) { if (!parm->ifindex) return -EINVAL; - p = tcf_hash_create(parm->index, est, a, sizeof(*p), ovr, bind); - if (p == NULL) + pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind, + &mirred_idx_gen, &mirred_hash_info); + if (unlikely(!pc)) return -ENOMEM; ret = ACT_P_CREATED; } else { if (!ovr) { - tcf_mirred_release(p, bind); + tcf_mirred_release(to_mirred(pc), bind); return -EEXIST; } } + m = to_mirred(pc); - spin_lock_bh(&p->lock); - p->action = parm->action; - p->eaction = parm->eaction; + spin_lock_bh(&m->tcf_lock); + m->tcf_action = parm->action; + m->tcfm_eaction = parm->eaction; if (parm->ifindex) { - p->ifindex = parm->ifindex; + m->tcfm_ifindex = parm->ifindex; if (ret != ACT_P_CREATED) - dev_put(p->dev); - p->dev = dev; + dev_put(m->tcfm_dev); + m->tcfm_dev = dev; dev_hold(dev); - p->ok_push = ok_push; + m->tcfm_ok_push = ok_push; } - spin_unlock_bh(&p->lock); + spin_unlock_bh(&m->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(p); + tcf_hash_insert(pc, &mirred_hash_info); - DPRINTK("tcf_mirred_init index %d action %d eaction %d device %s " - "ifindex %d\n", parm->index, parm->action, parm->eaction, - dev->name, parm->ifindex); return ret; } -static int -tcf_mirred_cleanup(struct tc_action *a, int bind) +static int tcf_mirred_cleanup(struct tc_action *a, int bind) { - struct tcf_mirred *p = PRIV(a, mirred); + struct tcf_mirred *m = a->priv; - if (p != NULL) - return tcf_mirred_release(p, bind); + if (m) + return tcf_mirred_release(m, bind); return 0; } -static int -tcf_mirred(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) +static int tcf_mirred(struct sk_buff *skb, struct tc_action *a, + struct tcf_result *res) { - struct tcf_mirred *p = PRIV(a, mirred); + struct tcf_mirred *m = a->priv; struct net_device *dev; struct sk_buff *skb2 = NULL; u32 at = G_TC_AT(skb->tc_verd); - spin_lock(&p->lock); + spin_lock(&m->tcf_lock); - dev = p->dev; - p->tm.lastuse = jiffies; + dev = m->tcfm_dev; + m->tcf_tm.lastuse = jiffies; if (!(dev->flags&IFF_UP) ) { if (net_ratelimit()) @@ -176,10 +167,10 @@ tcf_mirred(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) bad_mirred: if (skb2 != NULL) kfree_skb(skb2); - p->qstats.overlimits++; - p->bstats.bytes += skb->len; - p->bstats.packets++; - spin_unlock(&p->lock); + m->tcf_qstats.overlimits++; + m->tcf_bstats.bytes += skb->len; + m->tcf_bstats.packets++; + spin_unlock(&m->tcf_lock); /* should we be asking for packet to be dropped? * may make sense for redirect case only */ @@ -189,59 +180,59 @@ bad_mirred: skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2 == NULL) goto bad_mirred; - if (p->eaction != TCA_EGRESS_MIRROR && p->eaction != TCA_EGRESS_REDIR) { + if (m->tcfm_eaction != TCA_EGRESS_MIRROR && + m->tcfm_eaction != TCA_EGRESS_REDIR) { if (net_ratelimit()) - printk("tcf_mirred unknown action %d\n", p->eaction); + printk("tcf_mirred unknown action %d\n", + m->tcfm_eaction); goto bad_mirred; } - p->bstats.bytes += skb2->len; - p->bstats.packets++; + m->tcf_bstats.bytes += skb2->len; + m->tcf_bstats.packets++; if (!(at & AT_EGRESS)) - if (p->ok_push) + if (m->tcfm_ok_push) skb_push(skb2, skb2->dev->hard_header_len); /* mirror is always swallowed */ - if (p->eaction != TCA_EGRESS_MIRROR) + if (m->tcfm_eaction != TCA_EGRESS_MIRROR) skb2->tc_verd = SET_TC_FROM(skb2->tc_verd, at); skb2->dev = dev; skb2->input_dev = skb->dev; dev_queue_xmit(skb2); - spin_unlock(&p->lock); - return p->action; + spin_unlock(&m->tcf_lock); + return m->tcf_action; } -static int -tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb->tail; + struct tcf_mirred *m = a->priv; struct tc_mirred opt; - struct tcf_mirred *p = PRIV(a, mirred); struct tcf_t t; - opt.index = p->index; - opt.action = p->action; - opt.refcnt = p->refcnt - ref; - opt.bindcnt = p->bindcnt - bind; - opt.eaction = p->eaction; - opt.ifindex = p->ifindex; - DPRINTK("tcf_mirred_dump index %d action %d eaction %d ifindex %d\n", - p->index, p->action, p->eaction, p->ifindex); + opt.index = m->tcf_index; + opt.action = m->tcf_action; + opt.refcnt = m->tcf_refcnt - ref; + opt.bindcnt = m->tcf_bindcnt - bind; + opt.eaction = m->tcfm_eaction; + opt.ifindex = m->tcfm_ifindex; RTA_PUT(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt); - t.install = jiffies_to_clock_t(jiffies - p->tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - p->tm.lastuse); - t.expires = jiffies_to_clock_t(p->tm.expires); + t.install = jiffies_to_clock_t(jiffies - m->tcf_tm.install); + t.lastuse = jiffies_to_clock_t(jiffies - m->tcf_tm.lastuse); + t.expires = jiffies_to_clock_t(m->tcf_tm.expires); RTA_PUT(skb, TCA_MIRRED_TM, sizeof(t), &t); return skb->len; - rtattr_failure: +rtattr_failure: skb_trim(skb, b - skb->data); return -1; } static struct tc_action_ops act_mirred_ops = { .kind = "mirred", + .hinfo = &mirred_hash_info, .type = TCA_ACT_MIRRED, .capab = TCA_CAP_NONE, .owner = THIS_MODULE, @@ -257,15 +248,13 @@ MODULE_AUTHOR("Jamal Hadi Salim(2002)"); MODULE_DESCRIPTION("Device Mirror/redirect actions"); MODULE_LICENSE("GPL"); -static int __init -mirred_init_module(void) +static int __init mirred_init_module(void) { printk("Mirror/redirect action on\n"); return tcf_register_action(&act_mirred_ops); } -static void __exit -mirred_cleanup_module(void) +static void __exit mirred_cleanup_module(void) { tcf_unregister_action(&act_mirred_ops); } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index f257475e0e0..8ac65c219b9 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -33,32 +33,25 @@ #include <linux/tc_act/tc_pedit.h> #include <net/tc_act/tc_pedit.h> - -#define PEDIT_DEB 1 - -/* use generic hash table */ -#define MY_TAB_SIZE 16 -#define MY_TAB_MASK 15 -static u32 idx_gen; -static struct tcf_pedit *tcf_pedit_ht[MY_TAB_SIZE]; +#define PEDIT_TAB_MASK 15 +static struct tcf_common *tcf_pedit_ht[PEDIT_TAB_MASK + 1]; +static u32 pedit_idx_gen; static DEFINE_RWLOCK(pedit_lock); -#define tcf_st tcf_pedit -#define tc_st tc_pedit -#define tcf_t_lock pedit_lock -#define tcf_ht tcf_pedit_ht - -#define CONFIG_NET_ACT_INIT 1 -#include <net/pkt_act.h> +static struct tcf_hashinfo pedit_hash_info = { + .htab = tcf_pedit_ht, + .hmask = PEDIT_TAB_MASK, + .lock = &pedit_lock, +}; -static int -tcf_pedit_init(struct rtattr *rta, struct rtattr *est, struct tc_action *a, - int ovr, int bind) +static int tcf_pedit_init(struct rtattr *rta, struct rtattr *est, + struct tc_action *a, int ovr, int bind) { struct rtattr *tb[TCA_PEDIT_MAX]; struct tc_pedit *parm; int ret = 0; struct tcf_pedit *p; + struct tcf_common *pc; struct tc_pedit_key *keys = NULL; int ksize; @@ -73,54 +66,56 @@ tcf_pedit_init(struct rtattr *rta, struct rtattr *est, struct tc_action *a, if (RTA_PAYLOAD(tb[TCA_PEDIT_PARMS-1]) < sizeof(*parm) + ksize) return -EINVAL; - p = tcf_hash_check(parm->index, a, ovr, bind); - if (p == NULL) { + pc = tcf_hash_check(parm->index, a, bind, &pedit_hash_info); + if (!pc) { if (!parm->nkeys) return -EINVAL; - p = tcf_hash_create(parm->index, est, a, sizeof(*p), ovr, bind); - if (p == NULL) + pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, + &pedit_idx_gen, &pedit_hash_info); + if (unlikely(!pc)) return -ENOMEM; + p = to_pedit(pc); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { - kfree(p); + kfree(pc); return -ENOMEM; } ret = ACT_P_CREATED; } else { + p = to_pedit(pc); if (!ovr) { - tcf_hash_release(p, bind); + tcf_hash_release(pc, bind, &pedit_hash_info); return -EEXIST; } - if (p->nkeys && p->nkeys != parm->nkeys) { + if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) { keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) return -ENOMEM; } } - spin_lock_bh(&p->lock); - p->flags = parm->flags; - p->action = parm->action; + spin_lock_bh(&p->tcf_lock); + p->tcfp_flags = parm->flags; + p->tcf_action = parm->action; if (keys) { - kfree(p->keys); - p->keys = keys; - p->nkeys = parm->nkeys; + kfree(p->tcfp_keys); + p->tcfp_keys = keys; + p->tcfp_nkeys = parm->nkeys; } - memcpy(p->keys, parm->keys, ksize); - spin_unlock_bh(&p->lock); + memcpy(p->tcfp_keys, parm->keys, ksize); + spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(p); + tcf_hash_insert(pc, &pedit_hash_info); return ret; } -static int -tcf_pedit_cleanup(struct tc_action *a, int bind) +static int tcf_pedit_cleanup(struct tc_action *a, int bind) { - struct tcf_pedit *p = PRIV(a, pedit); + struct tcf_pedit *p = a->priv; - if (p != NULL) { - struct tc_pedit_key *keys = p->keys; - if (tcf_hash_release(p, bind)) { + if (p) { + struct tc_pedit_key *keys = p->tcfp_keys; + if (tcf_hash_release(&p->common, bind, &pedit_hash_info)) { kfree(keys); return 1; } @@ -128,30 +123,30 @@ tcf_pedit_cleanup(struct tc_action *a, int bind) return 0; } -static int -tcf_pedit(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) +static int tcf_pedit(struct sk_buff *skb, struct tc_action *a, + struct tcf_result *res) { - struct tcf_pedit *p = PRIV(a, pedit); + struct tcf_pedit *p = a->priv; int i, munged = 0; u8 *pptr; if (!(skb->tc_verd & TC_OK2MUNGE)) { /* should we set skb->cloned? */ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { - return p->action; + return p->tcf_action; } } pptr = skb->nh.raw; - spin_lock(&p->lock); + spin_lock(&p->tcf_lock); - p->tm.lastuse = jiffies; + p->tcf_tm.lastuse = jiffies; - if (p->nkeys > 0) { - struct tc_pedit_key *tkey = p->keys; + if (p->tcfp_nkeys > 0) { + struct tc_pedit_key *tkey = p->tcfp_keys; - for (i = p->nkeys; i > 0; i--, tkey++) { + for (i = p->tcfp_nkeys; i > 0; i--, tkey++) { u32 *ptr; int offset = tkey->off; @@ -169,7 +164,8 @@ tcf_pedit(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) printk("offset must be on 32 bit boundaries\n"); goto bad; } - if (skb->len < 0 || (offset > 0 && offset > skb->len)) { + if (skb->len < 0 || + (offset > 0 && offset > skb->len)) { printk("offset %d cant exceed pkt length %d\n", offset, skb->len); goto bad; @@ -185,63 +181,47 @@ tcf_pedit(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) skb->tc_verd = SET_TC_MUNGED(skb->tc_verd); goto done; } else { - printk("pedit BUG: index %d\n",p->index); + printk("pedit BUG: index %d\n", p->tcf_index); } bad: - p->qstats.overlimits++; + p->tcf_qstats.overlimits++; done: - p->bstats.bytes += skb->len; - p->bstats.packets++; - spin_unlock(&p->lock); - return p->action; + p->tcf_bstats.bytes += skb->len; + p->tcf_bstats.packets++; + spin_unlock(&p->tcf_lock); + return p->tcf_action; } -static int -tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,int bind, int ref) +static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) { unsigned char *b = skb->tail; + struct tcf_pedit *p = a->priv; struct tc_pedit *opt; - struct tcf_pedit *p = PRIV(a, pedit); struct tcf_t t; int s; - s = sizeof(*opt) + p->nkeys * sizeof(struct tc_pedit_key); + s = sizeof(*opt) + p->tcfp_nkeys * sizeof(struct tc_pedit_key); /* netlink spinlocks held above us - must use ATOMIC */ opt = kzalloc(s, GFP_ATOMIC); - if (opt == NULL) + if (unlikely(!opt)) return -ENOBUFS; - memcpy(opt->keys, p->keys, p->nkeys * sizeof(struct tc_pedit_key)); - opt->index = p->index; - opt->nkeys = p->nkeys; - opt->flags = p->flags; - opt->action = p->action; - opt->refcnt = p->refcnt - ref; - opt->bindcnt = p->bindcnt - bind; - - -#ifdef PEDIT_DEB - { - /* Debug - get rid of later */ - int i; - struct tc_pedit_key *key = opt->keys; - - for (i=0; i<opt->nkeys; i++, key++) { - printk( "\n key #%d",i); - printk( " at %d: val %08x mask %08x", - (unsigned int)key->off, - (unsigned int)key->val, - (unsigned int)key->mask); - } - } -#endif + memcpy(opt->keys, p->tcfp_keys, + p->tcfp_nkeys * sizeof(struct tc_pedit_key)); + opt->index = p->tcf_index; + opt->nkeys = p->tcfp_nkeys; + opt->flags = p->tcfp_flags; + opt->action = p->tcf_action; + opt->refcnt = p->tcf_refcnt - ref; + opt->bindcnt = p->tcf_bindcnt - bind; RTA_PUT(skb, TCA_PEDIT_PARMS, s, opt); - t.install = jiffies_to_clock_t(jiffies - p->tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - p->tm.lastuse); - t.expires = jiffies_to_clock_t(p->tm.expires); + t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install); + t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse); + t.expires = jiffies_to_clock_t(p->tcf_tm.expires); RTA_PUT(skb, TCA_PEDIT_TM, sizeof(t), &t); kfree(opt); return skb->len; @@ -252,9 +232,9 @@ rtattr_failure: return -1; } -static -struct tc_action_ops act_pedit_ops = { +static struct tc_action_ops act_pedit_ops = { .kind = "pedit", + .hinfo = &pedit_hash_info, .type = TCA_ACT_PEDIT, .capab = TCA_CAP_NONE, .owner = THIS_MODULE, @@ -270,14 +250,12 @@ MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); MODULE_DESCRIPTION("Generic Packet Editor actions"); MODULE_LICENSE("GPL"); -static int __init -pedit_init_module(void) +static int __init pedit_init_module(void) { return tcf_register_action(&act_pedit_ops); } -static void __exit -pedit_cleanup_module(void) +static void __exit pedit_cleanup_module(void) { tcf_unregister_action(&act_pedit_ops); } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index da905d7b4b4..fed47b65883 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -32,43 +32,27 @@ #include <net/sock.h> #include <net/act_api.h> -#define L2T(p,L) ((p)->R_tab->data[(L)>>(p)->R_tab->rate.cell_log]) -#define L2T_P(p,L) ((p)->P_tab->data[(L)>>(p)->P_tab->rate.cell_log]) -#define PRIV(a) ((struct tcf_police *) (a)->priv) - -/* use generic hash table */ -#define MY_TAB_SIZE 16 -#define MY_TAB_MASK 15 -static u32 idx_gen; -static struct tcf_police *tcf_police_ht[MY_TAB_SIZE]; -/* Policer hash table lock */ -static DEFINE_RWLOCK(police_lock); - -/* Each policer is serialized by its individual spinlock */ +#define L2T(p,L) ((p)->tcfp_R_tab->data[(L)>>(p)->tcfp_R_tab->rate.cell_log]) +#define L2T_P(p,L) ((p)->tcfp_P_tab->data[(L)>>(p)->tcfp_P_tab->rate.cell_log]) -static __inline__ unsigned tcf_police_hash(u32 index) -{ - return index&0xF; -} +#define POL_TAB_MASK 15 +static struct tcf_common *tcf_police_ht[POL_TAB_MASK + 1]; +static u32 police_idx_gen; +static DEFINE_RWLOCK(police_lock); -static __inline__ struct tcf_police * tcf_police_lookup(u32 index) -{ - struct tcf_police *p; +static struct tcf_hashinfo police_hash_info = { + .htab = tcf_police_ht, + .hmask = POL_TAB_MASK, + .lock = &police_lock, +}; - read_lock(&police_lock); - for (p = tcf_police_ht[tcf_police_hash(index)]; p; p = p->next) { - if (p->index == index) - break; - } - read_unlock(&police_lock); - return p; -} +/* Each policer is serialized by its individual spinlock */ #ifdef CONFIG_NET_CLS_ACT static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *cb, int type, struct tc_action *a) { - struct tcf_police *p; + struct tcf_common *p; int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; struct rtattr *r; @@ -76,10 +60,10 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c s_i = cb->args[0]; - for (i = 0; i < MY_TAB_SIZE; i++) { - p = tcf_police_ht[tcf_police_hash(i)]; + for (i = 0; i < (POL_TAB_MASK + 1); i++) { + p = tcf_police_ht[tcf_hash(i, POL_TAB_MASK)]; - for (; p; p = p->next) { + for (; p; p = p->tcfc_next) { index++; if (index < s_i) continue; @@ -110,48 +94,26 @@ rtattr_failure: skb_trim(skb, (u8*)r - skb->data); goto done; } - -static inline int -tcf_act_police_hash_search(struct tc_action *a, u32 index) -{ - struct tcf_police *p = tcf_police_lookup(index); - - if (p != NULL) { - a->priv = p; - return 1; - } else { - return 0; - } -} #endif -static inline u32 tcf_police_new_index(void) -{ - do { - if (++idx_gen == 0) - idx_gen = 1; - } while (tcf_police_lookup(idx_gen)); - - return idx_gen; -} - void tcf_police_destroy(struct tcf_police *p) { - unsigned h = tcf_police_hash(p->index); - struct tcf_police **p1p; + unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK); + struct tcf_common **p1p; - for (p1p = &tcf_police_ht[h]; *p1p; p1p = &(*p1p)->next) { - if (*p1p == p) { + for (p1p = &tcf_police_ht[h]; *p1p; p1p = &(*p1p)->tcfc_next) { + if (*p1p == &p->common) { write_lock_bh(&police_lock); - *p1p = p->next; + *p1p = p->tcf_next; write_unlock_bh(&police_lock); #ifdef CONFIG_NET_ESTIMATOR - gen_kill_estimator(&p->bstats, &p->rate_est); + gen_kill_estimator(&p->tcf_bstats, + &p->tcf_rate_est); #endif - if (p->R_tab) - qdisc_put_rtab(p->R_tab); - if (p->P_tab) - qdisc_put_rtab(p->P_tab); + if (p->tcfp_R_tab) + qdisc_put_rtab(p->tcfp_R_tab); + if (p->tcfp_P_tab) + qdisc_put_rtab(p->tcfp_P_tab); kfree(p); return; } @@ -167,7 +129,7 @@ static int tcf_act_police_locate(struct rtattr *rta, struct rtattr *est, int ret = 0, err; struct rtattr *tb[TCA_POLICE_MAX]; struct tc_police *parm; - struct tcf_police *p; + struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; if (rta == NULL || rtattr_parse_nested(tb, TCA_POLICE_MAX, rta) < 0) @@ -185,27 +147,32 @@ static int tcf_act_police_locate(struct rtattr *rta, struct rtattr *est, RTA_PAYLOAD(tb[TCA_POLICE_RESULT-1]) != sizeof(u32)) return -EINVAL; - if (parm->index && (p = tcf_police_lookup(parm->index)) != NULL) { - a->priv = p; - if (bind) { - p->bindcnt += 1; - p->refcnt += 1; + if (parm->index) { + struct tcf_common *pc; + + pc = tcf_hash_lookup(parm->index, &police_hash_info); + if (pc != NULL) { + a->priv = pc; + police = to_police(pc); + if (bind) { + police->tcf_bindcnt += 1; + police->tcf_refcnt += 1; + } + if (ovr) + goto override; + return ret; } - if (ovr) - goto override; - return ret; } - p = kzalloc(sizeof(*p), GFP_KERNEL); - if (p == NULL) + police = kzalloc(sizeof(*police), GFP_KERNEL); + if (police == NULL) return -ENOMEM; - ret = ACT_P_CREATED; - p->refcnt = 1; - spin_lock_init(&p->lock); - p->stats_lock = &p->lock; + police->tcf_refcnt = 1; + spin_lock_init(&police->tcf_lock); + police->tcf_stats_lock = &police->tcf_lock; if (bind) - p->bindcnt = 1; + police->tcf_bindcnt = 1; override: if (parm->rate.rate) { err = -ENOMEM; @@ -215,67 +182,71 @@ override: if (parm->peakrate.rate) { P_tab = qdisc_get_rtab(&parm->peakrate, tb[TCA_POLICE_PEAKRATE-1]); - if (p->P_tab == NULL) { + if (P_tab == NULL) { qdisc_put_rtab(R_tab); goto failure; } } } /* No failure allowed after this point */ - spin_lock_bh(&p->lock); + spin_lock_bh(&police->tcf_lock); if (R_tab != NULL) { - qdisc_put_rtab(p->R_tab); - p->R_tab = R_tab; + qdisc_put_rtab(police->tcfp_R_tab); + police->tcfp_R_tab = R_tab; } if (P_tab != NULL) { - qdisc_put_rtab(p->P_tab); - p->P_tab = P_tab; + qdisc_put_rtab(police->tcfp_P_tab); + police->tcfp_P_tab = P_tab; } if (tb[TCA_POLICE_RESULT-1]) - p->result = *(u32*)RTA_DATA(tb[TCA_POLICE_RESULT-1]); - p->toks = p->burst = parm->burst; - p->mtu = parm->mtu; - if (p->mtu == 0) { - p->mtu = ~0; - if (p->R_tab) - p->mtu = 255<<p->R_tab->rate.cell_log; + police->tcfp_result = *(u32*)RTA_DATA(tb[TCA_POLICE_RESULT-1]); + police->tcfp_toks = police->tcfp_burst = parm->burst; + police->tcfp_mtu = parm->mtu; + if (police->tcfp_mtu == 0) { + police->tcfp_mtu = ~0; + if (police->tcfp_R_tab) + police->tcfp_mtu = 255<<police->tcfp_R_tab->rate.cell_log; } - if (p->P_tab) - p->ptoks = L2T_P(p, p->mtu); - p->action = parm->action; + if (police->tcfp_P_tab) + police->tcfp_ptoks = L2T_P(police, police->tcfp_mtu); + police->tcf_action = parm->action; #ifdef CONFIG_NET_ESTIMATOR if (tb[TCA_POLICE_AVRATE-1]) - p->ewma_rate = *(u32*)RTA_DATA(tb[TCA_POLICE_AVRATE-1]); + police->tcfp_ewma_rate = + *(u32*)RTA_DATA(tb[TCA_POLICE_AVRATE-1]); if (est) - gen_replace_estimator(&p->bstats, &p->rate_est, p->stats_lock, est); + gen_replace_estimator(&police->tcf_bstats, + &police->tcf_rate_est, + police->tcf_stats_lock, est); #endif - spin_unlock_bh(&p->lock); + spin_unlock_bh(&police->tcf_lock); if (ret != ACT_P_CREATED) return ret; - PSCHED_GET_TIME(p->t_c); - p->index = parm->index ? : tcf_police_new_index(); - h = tcf_police_hash(p->index); + PSCHED_GET_TIME(police->tcfp_t_c); + police->tcf_index = parm->index ? parm->index : + tcf_hash_new_index(&police_idx_gen, &police_hash_info); + h = tcf_hash(police->tcf_index, POL_TAB_MASK); write_lock_bh(&police_lock); - p->next = tcf_police_ht[h]; - tcf_police_ht[h] = p; + police->tcf_next = tcf_police_ht[h]; + tcf_police_ht[h] = &police->common; write_unlock_bh(&police_lock); - a->priv = p; + a->priv = police; return ret; failure: if (ret == ACT_P_CREATED) - kfree(p); + kfree(police); return err; } static int tcf_act_police_cleanup(struct tc_action *a, int bind) { - struct tcf_police *p = PRIV(a); + struct tcf_police *p = a->priv; if (p != NULL) return tcf_police_release(p, bind); @@ -285,86 +256,87 @@ static int tcf_act_police_cleanup(struct tc_action *a, int bind) static int tcf_act_police(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) { + struct tcf_police *police = a->priv; psched_time_t now; - struct tcf_police *p = PRIV(a); long toks; long ptoks = 0; - spin_lock(&p->lock); + spin_lock(&police->tcf_lock); - p->bstats.bytes += skb->len; - p->bstats.packets++; + police->tcf_bstats.bytes += skb->len; + police->tcf_bstats.packets++; #ifdef CONFIG_NET_ESTIMATOR - if (p->ewma_rate && p->rate_est.bps >= p->ewma_rate) { - p->qstats.overlimits++; - spin_unlock(&p->lock); - return p->action; + if (police->tcfp_ewma_rate && + police->tcf_rate_est.bps >= police->tcfp_ewma_rate) { + police->tcf_qstats.overlimits++; + spin_unlock(&police->tcf_lock); + return police->tcf_action; } #endif - if (skb->len <= p->mtu) { - if (p->R_tab == NULL) { - spin_unlock(&p->lock); - return p->result; + if (skb->len <= police->tcfp_mtu) { + if (police->tcfp_R_tab == NULL) { + spin_unlock(&police->tcf_lock); + return police->tcfp_result; } PSCHED_GET_TIME(now); - toks = PSCHED_TDIFF_SAFE(now, p->t_c, p->burst); - - if (p->P_tab) { - ptoks = toks + p->ptoks; - if (ptoks > (long)L2T_P(p, p->mtu)) - ptoks = (long)L2T_P(p, p->mtu); - ptoks -= L2T_P(p, skb->len); + toks = PSCHED_TDIFF_SAFE(now, police->tcfp_t_c, + police->tcfp_burst); + if (police->tcfp_P_tab) { + ptoks = toks + police->tcfp_ptoks; + if (ptoks > (long)L2T_P(police, police->tcfp_mtu)) + ptoks = (long)L2T_P(police, police->tcfp_mtu); + ptoks -= L2T_P(police, skb->len); } - toks += p->toks; - if (toks > (long)p->burst) - toks = p->burst; - toks -= L2T(p, skb->len); - + toks += police->tcfp_toks; + if (toks > (long)police->tcfp_burst) + toks = police->tcfp_burst; + toks -= L2T(police, skb->len); if ((toks|ptoks) >= 0) { - p->t_c = now; - p->toks = toks; - p->ptoks = ptoks; - spin_unlock(&p->lock); - return p->result; + police->tcfp_t_c = now; + police->tcfp_toks = toks; + police->tcfp_ptoks = ptoks; + spin_unlock(&police->tcf_lock); + return police->tcfp_result; } } - p->qstats.overlimits++; - spin_unlock(&p->lock); - return p->action; + police->tcf_qstats.overlimits++; + spin_unlock(&police->tcf_lock); + return police->tcf_action; } static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb->tail; + struct tcf_police *police = a->priv; struct tc_police opt; - struct tcf_police *p = PRIV(a); - - opt.index = p->index; - opt.action = p->action; - opt.mtu = p->mtu; - opt.burst = p->burst; - opt.refcnt = p->refcnt - ref; - opt.bindcnt = p->bindcnt - bind; - if (p->R_tab) - opt.rate = p->R_tab->rate; + + opt.index = police->tcf_index; + opt.action = police->tcf_action; + opt.mtu = police->tcfp_mtu; + opt.burst = police->tcfp_burst; + opt.refcnt = police->tcf_refcnt - ref; + opt.bindcnt = police->tcf_bindcnt - bind; + if (police->tcfp_R_tab) + opt.rate = police->tcfp_R_tab->rate; else memset(&opt.rate, 0, sizeof(opt.rate)); - if (p->P_tab) - opt.peakrate = p->P_tab->rate; + if (police->tcfp_P_tab) + opt.peakrate = police->tcfp_P_tab->rate; else memset(&opt.peakrate, 0, sizeof(opt.peakrate)); RTA_PUT(skb, TCA_POLICE_TBF, sizeof(opt), &opt); - if (p->result) - RTA_PUT(skb, TCA_POLICE_RESULT, sizeof(int), &p->result); + if (police->tcfp_result) + RTA_PUT(skb, TCA_POLICE_RESULT, sizeof(int), + &police->tcfp_result); #ifdef CONFIG_NET_ESTIMATOR - if (p->ewma_rate) - RTA_PUT(skb, TCA_POLICE_AVRATE, 4, &p->ewma_rate); + if (police->tcfp_ewma_rate) + RTA_PUT(skb, TCA_POLICE_AVRATE, 4, &police->tcfp_ewma_rate); #endif return skb->len; @@ -379,13 +351,14 @@ MODULE_LICENSE("GPL"); static struct tc_action_ops act_police_ops = { .kind = "police", + .hinfo = &police_hash_info, .type = TCA_ID_POLICE, .capab = TCA_CAP_NONE, .owner = THIS_MODULE, .act = tcf_act_police, .dump = tcf_act_police_dump, .cleanup = tcf_act_police_cleanup, - .lookup = tcf_act_police_hash_search, + .lookup = tcf_hash_search, .init = tcf_act_police_locate, .walk = tcf_act_police_walker }; @@ -407,10 +380,39 @@ module_exit(police_cleanup_module); #else /* CONFIG_NET_CLS_ACT */ -struct tcf_police * tcf_police_locate(struct rtattr *rta, struct rtattr *est) +static struct tcf_common *tcf_police_lookup(u32 index) { - unsigned h; - struct tcf_police *p; + struct tcf_hashinfo *hinfo = &police_hash_info; + struct tcf_common *p; + + read_lock(hinfo->lock); + for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p; + p = p->tcfc_next) { + if (p->tcfc_index == index) + break; + } + read_unlock(hinfo->lock); + + return p; +} + +static u32 tcf_police_new_index(void) +{ + u32 *idx_gen = &police_idx_gen; + u32 val = *idx_gen; + + do { + if (++val == 0) + val = 1; + } while (tcf_police_lookup(val)); + + return (*idx_gen = val); +} + +struct tcf_police *tcf_police_locate(struct rtattr *rta, struct rtattr *est) +{ + unsigned int h; + struct tcf_police *police; struct rtattr *tb[TCA_POLICE_MAX]; struct tc_police *parm; @@ -423,149 +425,158 @@ struct tcf_police * tcf_police_locate(struct rtattr *rta, struct rtattr *est) parm = RTA_DATA(tb[TCA_POLICE_TBF-1]); - if (parm->index && (p = tcf_police_lookup(parm->index)) != NULL) { - p->refcnt++; - return p; - } + if (parm->index) { + struct tcf_common *pc; - p = kzalloc(sizeof(*p), GFP_KERNEL); - if (p == NULL) + pc = tcf_police_lookup(parm->index); + if (pc) { + police = to_police(pc); + police->tcf_refcnt++; + return police; + } + } + police = kzalloc(sizeof(*police), GFP_KERNEL); + if (unlikely(!police)) return NULL; - p->refcnt = 1; - spin_lock_init(&p->lock); - p->stats_lock = &p->lock; + police->tcf_refcnt = 1; + spin_lock_init(&police->tcf_lock); + police->tcf_stats_lock = &police->tcf_lock; if (parm->rate.rate) { - p->R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE-1]); - if (p->R_tab == NULL) + police->tcfp_R_tab = + qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE-1]); + if (police->tcfp_R_tab == NULL) goto failure; if (parm->peakrate.rate) { - p->P_tab = qdisc_get_rtab(&parm->peakrate, - tb[TCA_POLICE_PEAKRATE-1]); - if (p->P_tab == NULL) + police->tcfp_P_tab = + qdisc_get_rtab(&parm->peakrate, + tb[TCA_POLICE_PEAKRATE-1]); + if (police->tcfp_P_tab == NULL) goto failure; } } if (tb[TCA_POLICE_RESULT-1]) { if (RTA_PAYLOAD(tb[TCA_POLICE_RESULT-1]) != sizeof(u32)) goto failure; - p->result = *(u32*)RTA_DATA(tb[TCA_POLICE_RESULT-1]); + police->tcfp_result = *(u32*)RTA_DATA(tb[TCA_POLICE_RESULT-1]); } #ifdef CONFIG_NET_ESTIMATOR if (tb[TCA_POLICE_AVRATE-1]) { if (RTA_PAYLOAD(tb[TCA_POLICE_AVRATE-1]) != sizeof(u32)) goto failure; - p->ewma_rate = *(u32*)RTA_DATA(tb[TCA_POLICE_AVRATE-1]); + police->tcfp_ewma_rate = + *(u32*)RTA_DATA(tb[TCA_POLICE_AVRATE-1]); } #endif - p->toks = p->burst = parm->burst; - p->mtu = parm->mtu; - if (p->mtu == 0) { - p->mtu = ~0; - if (p->R_tab) - p->mtu = 255<<p->R_tab->rate.cell_log; + police->tcfp_toks = police->tcfp_burst = parm->burst; + police->tcfp_mtu = parm->mtu; + if (police->tcfp_mtu == 0) { + police->tcfp_mtu = ~0; + if (police->tcfp_R_tab) + police->tcfp_mtu = 255<<police->tcfp_R_tab->rate.cell_log; } - if (p->P_tab) - p->ptoks = L2T_P(p, p->mtu); - PSCHED_GET_TIME(p->t_c); - p->index = parm->index ? : tcf_police_new_index(); - p->action = parm->action; + if (police->tcfp_P_tab) + police->tcfp_ptoks = L2T_P(police, police->tcfp_mtu); + PSCHED_GET_TIME(police->tcfp_t_c); + police->tcf_index = parm->index ? parm->index : + tcf_police_new_index(); + police->tcf_action = parm->action; #ifdef CONFIG_NET_ESTIMATOR if (est) - gen_new_estimator(&p->bstats, &p->rate_est, p->stats_lock, est); + gen_new_estimator(&police->tcf_bstats, &police->tcf_rate_est, + police->tcf_stats_lock, est); #endif - h = tcf_police_hash(p->index); + h = tcf_hash(police->tcf_index, POL_TAB_MASK); write_lock_bh(&police_lock); - p->next = tcf_police_ht[h]; - tcf_police_ht[h] = p; + police->tcf_next = tcf_police_ht[h]; + tcf_police_ht[h] = &police->common; write_unlock_bh(&police_lock); - return p; + return police; failure: - if (p->R_tab) - qdisc_put_rtab(p->R_tab); - kfree(p); + if (police->tcfp_R_tab) + qdisc_put_rtab(police->tcfp_R_tab); + kfree(police); return NULL; } -int tcf_police(struct sk_buff *skb, struct tcf_police *p) +int tcf_police(struct sk_buff *skb, struct tcf_police *police) { psched_time_t now; long toks; long ptoks = 0; - spin_lock(&p->lock); + spin_lock(&police->tcf_lock); - p->bstats.bytes += skb->len; - p->bstats.packets++; + police->tcf_bstats.bytes += skb->len; + police->tcf_bstats.packets++; #ifdef CONFIG_NET_ESTIMATOR - if (p->ewma_rate && p->rate_est.bps >= p->ewma_rate) { - p->qstats.overlimits++; - spin_unlock(&p->lock); - return p->action; + if (police->tcfp_ewma_rate && + police->tcf_rate_est.bps >= police->tcfp_ewma_rate) { + police->tcf_qstats.overlimits++; + spin_unlock(&police->tcf_lock); + return police->tcf_action; } #endif - - if (skb->len <= p->mtu) { - if (p->R_tab == NULL) { - spin_unlock(&p->lock); - return p->result; + if (skb->len <= police->tcfp_mtu) { + if (police->tcfp_R_tab == NULL) { + spin_unlock(&police->tcf_lock); + return police->tcfp_result; } PSCHED_GET_TIME(now); - - toks = PSCHED_TDIFF_SAFE(now, p->t_c, p->burst); - - if (p->P_tab) { - ptoks = toks + p->ptoks; - if (ptoks > (long)L2T_P(p, p->mtu)) - ptoks = (long)L2T_P(p, p->mtu); - ptoks -= L2T_P(p, skb->len); + toks = PSCHED_TDIFF_SAFE(now, police->tcfp_t_c, + police->tcfp_burst); + if (police->tcfp_P_tab) { + ptoks = toks + police->tcfp_ptoks; + if (ptoks > (long)L2T_P(police, police->tcfp_mtu)) + ptoks = (long)L2T_P(police, police->tcfp_mtu); + ptoks -= L2T_P(police, skb->len); } - toks += p->toks; - if (toks > (long)p->burst) - toks = p->burst; - toks -= L2T(p, skb->len); - + toks += police->tcfp_toks; + if (toks > (long)police->tcfp_burst) + toks = police->tcfp_burst; + toks -= L2T(police, skb->len); if ((toks|ptoks) >= 0) { - p->t_c = now; - p->toks = toks; - p->ptoks = ptoks; - spin_unlock(&p->lock); - return p->result; + police->tcfp_t_c = now; + police->tcfp_toks = toks; + police->tcfp_ptoks = ptoks; + spin_unlock(&police->tcf_lock); + return police->tcfp_result; } } - p->qstats.overlimits++; - spin_unlock(&p->lock); - return p->action; + police->tcf_qstats.overlimits++; + spin_unlock(&police->tcf_lock); + return police->tcf_action; } EXPORT_SYMBOL(tcf_police); -int tcf_police_dump(struct sk_buff *skb, struct tcf_police *p) +int tcf_police_dump(struct sk_buff *skb, struct tcf_police *police) { - unsigned char *b = skb->tail; + unsigned char *b = skb->tail; struct tc_police opt; - opt.index = p->index; - opt.action = p->action; - opt.mtu = p->mtu; - opt.burst = p->burst; - if (p->R_tab) - opt.rate = p->R_tab->rate; + opt.index = police->tcf_index; + opt.action = police->tcf_action; + opt.mtu = police->tcfp_mtu; + opt.burst = police->tcfp_burst; + if (police->tcfp_R_tab) + opt.rate = police->tcfp_R_tab->rate; else memset(&opt.rate, 0, sizeof(opt.rate)); - if (p->P_tab) - opt.peakrate = p->P_tab->rate; + if (police->tcfp_P_tab) + opt.peakrate = police->tcfp_P_tab->rate; else memset(&opt.peakrate, 0, sizeof(opt.peakrate)); RTA_PUT(skb, TCA_POLICE_TBF, sizeof(opt), &opt); - if (p->result) - RTA_PUT(skb, TCA_POLICE_RESULT, sizeof(int), &p->result); + if (police->tcfp_result) + RTA_PUT(skb, TCA_POLICE_RESULT, sizeof(int), + &police->tcfp_result); #ifdef CONFIG_NET_ESTIMATOR - if (p->ewma_rate) - RTA_PUT(skb, TCA_POLICE_AVRATE, 4, &p->ewma_rate); + if (police->tcfp_ewma_rate) + RTA_PUT(skb, TCA_POLICE_AVRATE, 4, &police->tcfp_ewma_rate); #endif return skb->len; @@ -574,19 +585,20 @@ rtattr_failure: return -1; } -int tcf_police_dump_stats(struct sk_buff *skb, struct tcf_police *p) +int tcf_police_dump_stats(struct sk_buff *skb, struct tcf_police *police) { struct gnet_dump d; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, - TCA_XSTATS, p->stats_lock, &d) < 0) + TCA_XSTATS, police->tcf_stats_lock, + &d) < 0) goto errout; - if (gnet_stats_copy_basic(&d, &p->bstats) < 0 || + if (gnet_stats_copy_basic(&d, &police->tcf_bstats) < 0 || #ifdef CONFIG_NET_ESTIMATOR - gnet_stats_copy_rate_est(&d, &p->rate_est) < 0 || + gnet_stats_copy_rate_est(&d, &police->tcf_rate_est) < 0 || #endif - gnet_stats_copy_queue(&d, &p->qstats) < 0) + gnet_stats_copy_queue(&d, &police->tcf_qstats) < 0) goto errout; if (gnet_stats_finish_copy(&d) < 0) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 17105c82537..901571a6770 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -20,54 +20,175 @@ #define TCA_ACT_SIMP 22 -/* XXX: Hide all these common elements under some macro - * probably -*/ #include <linux/tc_act/tc_defact.h> #include <net/tc_act/tc_defact.h> -/* use generic hash table with 8 buckets */ -#define MY_TAB_SIZE 8 -#define MY_TAB_MASK (MY_TAB_SIZE - 1) -static u32 idx_gen; -static struct tcf_defact *tcf_simp_ht[MY_TAB_SIZE]; +#define SIMP_TAB_MASK 7 +static struct tcf_common *tcf_simp_ht[SIMP_TAB_MASK + 1]; +static u32 simp_idx_gen; static DEFINE_RWLOCK(simp_lock); -/* override the defaults */ -#define tcf_st tcf_defact -#define tc_st tc_defact -#define tcf_t_lock simp_lock -#define tcf_ht tcf_simp_ht - -#define CONFIG_NET_ACT_INIT 1 -#include <net/pkt_act.h> -#include <net/act_generic.h> +static struct tcf_hashinfo simp_hash_info = { + .htab = tcf_simp_ht, + .hmask = SIMP_TAB_MASK, + .lock = &simp_lock, +}; static int tcf_simp(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) { - struct tcf_defact *p = PRIV(a, defact); + struct tcf_defact *d = a->priv; - spin_lock(&p->lock); - p->tm.lastuse = jiffies; - p->bstats.bytes += skb->len; - p->bstats.packets++; + spin_lock(&d->tcf_lock); + d->tcf_tm.lastuse = jiffies; + d->tcf_bstats.bytes += skb->len; + d->tcf_bstats.packets++; /* print policy string followed by _ then packet count * Example if this was the 3rd packet and the string was "hello" * then it would look like "hello_3" (without quotes) **/ - printk("simple: %s_%d\n", (char *)p->defdata, p->bstats.packets); - spin_unlock(&p->lock); - return p->action; + printk("simple: %s_%d\n", + (char *)d->tcfd_defdata, d->tcf_bstats.packets); + spin_unlock(&d->tcf_lock); + return d->tcf_action; +} + +static int tcf_simp_release(struct tcf_defact *d, int bind) +{ + int ret = 0; + if (d) { + if (bind) + d->tcf_bindcnt--; + d->tcf_refcnt--; + if (d->tcf_bindcnt <= 0 && d->tcf_refcnt <= 0) { + kfree(d->tcfd_defdata); + tcf_hash_destroy(&d->common, &simp_hash_info); + ret = 1; + } + } + return ret; +} + +static int alloc_defdata(struct tcf_defact *d, u32 datalen, void *defdata) +{ + d->tcfd_defdata = kmalloc(datalen, GFP_KERNEL); + if (unlikely(!d->tcfd_defdata)) + return -ENOMEM; + d->tcfd_datalen = datalen; + memcpy(d->tcfd_defdata, defdata, datalen); + return 0; +} + +static int realloc_defdata(struct tcf_defact *d, u32 datalen, void *defdata) +{ + kfree(d->tcfd_defdata); + return alloc_defdata(d, datalen, defdata); +} + +static int tcf_simp_init(struct rtattr *rta, struct rtattr *est, + struct tc_action *a, int ovr, int bind) +{ + struct rtattr *tb[TCA_DEF_MAX]; + struct tc_defact *parm; + struct tcf_defact *d; + struct tcf_common *pc; + void *defdata; + u32 datalen = 0; + int ret = 0; + + if (rta == NULL || rtattr_parse_nested(tb, TCA_DEF_MAX, rta) < 0) + return -EINVAL; + + if (tb[TCA_DEF_PARMS - 1] == NULL || + RTA_PAYLOAD(tb[TCA_DEF_PARMS - 1]) < sizeof(*parm)) + return -EINVAL; + + parm = RTA_DATA(tb[TCA_DEF_PARMS - 1]); + defdata = RTA_DATA(tb[TCA_DEF_DATA - 1]); + if (defdata == NULL) + return -EINVAL; + + datalen = RTA_PAYLOAD(tb[TCA_DEF_DATA - 1]); + if (datalen <= 0) + return -EINVAL; + + pc = tcf_hash_check(parm->index, a, bind, &simp_hash_info); + if (!pc) { + pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, + &simp_idx_gen, &simp_hash_info); + if (unlikely(!pc)) + return -ENOMEM; + + d = to_defact(pc); + ret = alloc_defdata(d, datalen, defdata); + if (ret < 0) { + kfree(pc); + return ret; + } + ret = ACT_P_CREATED; + } else { + d = to_defact(pc); + if (!ovr) { + tcf_simp_release(d, bind); + return -EEXIST; + } + realloc_defdata(d, datalen, defdata); + } + + spin_lock_bh(&d->tcf_lock); + d->tcf_action = parm->action; + spin_unlock_bh(&d->tcf_lock); + + if (ret == ACT_P_CREATED) + tcf_hash_insert(pc, &simp_hash_info); + return ret; +} + +static inline int tcf_simp_cleanup(struct tc_action *a, int bind) +{ + struct tcf_defact *d = a->priv; + + if (d) + return tcf_simp_release(d, bind); + return 0; +} + +static inline int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *b = skb->tail; + struct tcf_defact *d = a->priv; + struct tc_defact opt; + struct tcf_t t; + + opt.index = d->tcf_index; + opt.refcnt = d->tcf_refcnt - ref; + opt.bindcnt = d->tcf_bindcnt - bind; + opt.action = d->tcf_action; + RTA_PUT(skb, TCA_DEF_PARMS, sizeof(opt), &opt); + RTA_PUT(skb, TCA_DEF_DATA, d->tcfd_datalen, d->tcfd_defdata); + t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install); + t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse); + t.expires = jiffies_to_clock_t(d->tcf_tm.expires); + RTA_PUT(skb, TCA_DEF_TM, sizeof(t), &t); + return skb->len; + +rtattr_failure: + skb_trim(skb, b - skb->data); + return -1; } static struct tc_action_ops act_simp_ops = { - .kind = "simple", - .type = TCA_ACT_SIMP, - .capab = TCA_CAP_NONE, - .owner = THIS_MODULE, - .act = tcf_simp, - tca_use_default_ops + .kind = "simple", + .hinfo = &simp_hash_info, + .type = TCA_ACT_SIMP, + .capab = TCA_CAP_NONE, + .owner = THIS_MODULE, + .act = tcf_simp, + .dump = tcf_simp_dump, + .cleanup = tcf_simp_cleanup, + .init = tcf_simp_init, + .walk = tcf_generic_walker, }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index e6973d9b686..e54acc6bccc 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -50,6 +50,7 @@ struct fw_head { struct fw_filter *ht[HTSIZE]; + u32 mask; }; struct fw_filter @@ -101,7 +102,7 @@ static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, struct fw_filter *f; int r; #ifdef CONFIG_NETFILTER - u32 id = skb->nfmark; + u32 id = skb->nfmark & head->mask; #else u32 id = 0; #endif @@ -209,7 +210,9 @@ static int fw_change_attrs(struct tcf_proto *tp, struct fw_filter *f, struct rtattr **tb, struct rtattr **tca, unsigned long base) { + struct fw_head *head = (struct fw_head *)tp->root; struct tcf_exts e; + u32 mask; int err; err = tcf_exts_validate(tp, tb, tca[TCA_RATE-1], &e, &fw_ext_map); @@ -232,6 +235,15 @@ fw_change_attrs(struct tcf_proto *tp, struct fw_filter *f, } #endif /* CONFIG_NET_CLS_IND */ + if (tb[TCA_FW_MASK-1]) { + if (RTA_PAYLOAD(tb[TCA_FW_MASK-1]) != sizeof(u32)) + goto errout; + mask = *(u32*)RTA_DATA(tb[TCA_FW_MASK-1]); + if (mask != head->mask) + goto errout; + } else if (head->mask != 0xFFFFFFFF) + goto errout; + tcf_exts_change(tp, &f->exts, &e); return 0; @@ -267,9 +279,17 @@ static int fw_change(struct tcf_proto *tp, unsigned long base, return -EINVAL; if (head == NULL) { + u32 mask = 0xFFFFFFFF; + if (tb[TCA_FW_MASK-1]) { + if (RTA_PAYLOAD(tb[TCA_FW_MASK-1]) != sizeof(u32)) + return -EINVAL; + mask = *(u32*)RTA_DATA(tb[TCA_FW_MASK-1]); + } + head = kzalloc(sizeof(struct fw_head), GFP_KERNEL); if (head == NULL) return -ENOBUFS; + head->mask = mask; tcf_tree_lock(tp); tp->root = head; @@ -330,6 +350,7 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int fw_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f = (struct fw_filter*)fh; unsigned char *b = skb->tail; struct rtattr *rta; @@ -351,6 +372,8 @@ static int fw_dump(struct tcf_proto *tp, unsigned long fh, if (strlen(f->indev)) RTA_PUT(skb, TCA_FW_INDEV, IFNAMSIZ, f->indev); #endif /* CONFIG_NET_CLS_IND */ + if (head->mask != 0xFFFFFFFF) + RTA_PUT(skb, TCA_FW_MASK, 4, &head->mask); if (tcf_exts_dump(skb, &f->exts, &fw_ext_map) < 0) goto rtattr_failure; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 880a3394a51..bb3ddd4784b 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1,4 +1,4 @@ -/* vim: ts=8 sw=8 +/* * net/sched/sch_htb.c Hierarchical token bucket, feed tree version * * This program is free software; you can redistribute it and/or @@ -68,218 +68,165 @@ one less than their parent. */ -#define HTB_HSIZE 16 /* classid hash size */ -#define HTB_EWMAC 2 /* rate average over HTB_EWMAC*HTB_HSIZE sec */ -#undef HTB_DEBUG /* compile debugging support (activated by tc tool) */ -#define HTB_RATECM 1 /* whether to use rate computer */ -#define HTB_HYSTERESIS 1/* whether to use mode hysteresis for speedup */ -#define HTB_QLOCK(S) spin_lock_bh(&(S)->dev->queue_lock) -#define HTB_QUNLOCK(S) spin_unlock_bh(&(S)->dev->queue_lock) -#define HTB_VER 0x30011 /* major must be matched with number suplied by TC as version */ +#define HTB_HSIZE 16 /* classid hash size */ +#define HTB_EWMAC 2 /* rate average over HTB_EWMAC*HTB_HSIZE sec */ +#define HTB_RATECM 1 /* whether to use rate computer */ +#define HTB_HYSTERESIS 1 /* whether to use mode hysteresis for speedup */ +#define HTB_VER 0x30011 /* major must be matched with number suplied by TC as version */ #if HTB_VER >> 16 != TC_HTB_PROTOVER #error "Mismatched sch_htb.c and pkt_sch.h" #endif -/* debugging support; S is subsystem, these are defined: - 0 - netlink messages - 1 - enqueue - 2 - drop & requeue - 3 - dequeue main - 4 - dequeue one prio DRR part - 5 - dequeue class accounting - 6 - class overlimit status computation - 7 - hint tree - 8 - event queue - 10 - rate estimator - 11 - classifier - 12 - fast dequeue cache - - L is level; 0 = none, 1 = basic info, 2 = detailed, 3 = full - q->debug uint32 contains 16 2-bit fields one for subsystem starting - from LSB - */ -#ifdef HTB_DEBUG -#define HTB_DBG_COND(S,L) (((q->debug>>(2*S))&3) >= L) -#define HTB_DBG(S,L,FMT,ARG...) if (HTB_DBG_COND(S,L)) \ - printk(KERN_DEBUG FMT,##ARG) -#define HTB_CHCL(cl) BUG_TRAP((cl)->magic == HTB_CMAGIC) -#define HTB_PASSQ q, -#define HTB_ARGQ struct htb_sched *q, -#define static -#undef __inline__ -#define __inline__ -#undef inline -#define inline -#define HTB_CMAGIC 0xFEFAFEF1 -#define htb_safe_rb_erase(N,R) do { BUG_TRAP((N)->rb_color != -1); \ - if ((N)->rb_color == -1) break; \ - rb_erase(N,R); \ - (N)->rb_color = -1; } while (0) -#else -#define HTB_DBG_COND(S,L) (0) -#define HTB_DBG(S,L,FMT,ARG...) -#define HTB_PASSQ -#define HTB_ARGQ -#define HTB_CHCL(cl) -#define htb_safe_rb_erase(N,R) rb_erase(N,R) -#endif - - /* used internaly to keep status of single class */ enum htb_cmode { - HTB_CANT_SEND, /* class can't send and can't borrow */ - HTB_MAY_BORROW, /* class can't send but may borrow */ - HTB_CAN_SEND /* class can send */ + HTB_CANT_SEND, /* class can't send and can't borrow */ + HTB_MAY_BORROW, /* class can't send but may borrow */ + HTB_CAN_SEND /* class can send */ }; /* interior & leaf nodes; props specific to leaves are marked L: */ -struct htb_class -{ -#ifdef HTB_DEBUG - unsigned magic; -#endif - /* general class parameters */ - u32 classid; - struct gnet_stats_basic bstats; - struct gnet_stats_queue qstats; - struct gnet_stats_rate_est rate_est; - struct tc_htb_xstats xstats;/* our special stats */ - int refcnt; /* usage count of this class */ +struct htb_class { + /* general class parameters */ + u32 classid; + struct gnet_stats_basic bstats; + struct gnet_stats_queue qstats; + struct gnet_stats_rate_est rate_est; + struct tc_htb_xstats xstats; /* our special stats */ + int refcnt; /* usage count of this class */ #ifdef HTB_RATECM - /* rate measurement counters */ - unsigned long rate_bytes,sum_bytes; - unsigned long rate_packets,sum_packets; + /* rate measurement counters */ + unsigned long rate_bytes, sum_bytes; + unsigned long rate_packets, sum_packets; #endif - /* topology */ - int level; /* our level (see above) */ - struct htb_class *parent; /* parent class */ - struct list_head hlist; /* classid hash list item */ - struct list_head sibling; /* sibling list item */ - struct list_head children; /* children list */ - - union { - struct htb_class_leaf { - struct Qdisc *q; - int prio; - int aprio; - int quantum; - int deficit[TC_HTB_MAXDEPTH]; - struct list_head drop_list; - } leaf; - struct htb_class_inner { - struct rb_root feed[TC_HTB_NUMPRIO]; /* feed trees */ - struct rb_node *ptr[TC_HTB_NUMPRIO]; /* current class ptr */ - /* When class changes from state 1->2 and disconnects from - parent's feed then we lost ptr value and start from the - first child again. Here we store classid of the - last valid ptr (used when ptr is NULL). */ - u32 last_ptr_id[TC_HTB_NUMPRIO]; - } inner; - } un; - struct rb_node node[TC_HTB_NUMPRIO]; /* node for self or feed tree */ - struct rb_node pq_node; /* node for event queue */ - unsigned long pq_key; /* the same type as jiffies global */ - - int prio_activity; /* for which prios are we active */ - enum htb_cmode cmode; /* current mode of the class */ - - /* class attached filters */ - struct tcf_proto *filter_list; - int filter_cnt; - - int warned; /* only one warning about non work conserving .. */ - - /* token bucket parameters */ - struct qdisc_rate_table *rate; /* rate table of the class itself */ - struct qdisc_rate_table *ceil; /* ceiling rate (limits borrows too) */ - long buffer,cbuffer; /* token bucket depth/rate */ - psched_tdiff_t mbuffer; /* max wait time */ - long tokens,ctokens; /* current number of tokens */ - psched_time_t t_c; /* checkpoint time */ + /* topology */ + int level; /* our level (see above) */ + struct htb_class *parent; /* parent class */ + struct hlist_node hlist; /* classid hash list item */ + struct list_head sibling; /* sibling list item */ + struct list_head children; /* children list */ + + union { + struct htb_class_leaf { + struct Qdisc *q; + int prio; + int aprio; + int quantum; + int deficit[TC_HTB_MAXDEPTH]; + struct list_head drop_list; + } leaf; + struct htb_class_inner { + struct rb_root feed[TC_HTB_NUMPRIO]; /* feed trees */ + struct rb_node *ptr[TC_HTB_NUMPRIO]; /* current class ptr */ + /* When class changes from state 1->2 and disconnects from + parent's feed then we lost ptr value and start from the + first child again. Here we store classid of the + last valid ptr (used when ptr is NULL). */ + u32 last_ptr_id[TC_HTB_NUMPRIO]; + } inner; + } un; + struct rb_node node[TC_HTB_NUMPRIO]; /* node for self or feed tree */ + struct rb_node pq_node; /* node for event queue */ + unsigned long pq_key; /* the same type as jiffies global */ + + int prio_activity; /* for which prios are we active */ + enum htb_cmode cmode; /* current mode of the class */ + + /* class attached filters */ + struct tcf_proto *filter_list; + int filter_cnt; + + int warned; /* only one warning about non work conserving .. */ + + /* token bucket parameters */ + struct qdisc_rate_table *rate; /* rate table of the class itself */ + struct qdisc_rate_table *ceil; /* ceiling rate (limits borrows too) */ + long buffer, cbuffer; /* token bucket depth/rate */ + psched_tdiff_t mbuffer; /* max wait time */ + long tokens, ctokens; /* current number of tokens */ + psched_time_t t_c; /* checkpoint time */ }; /* TODO: maybe compute rate when size is too large .. or drop ? */ -static __inline__ long L2T(struct htb_class *cl,struct qdisc_rate_table *rate, - int size) -{ - int slot = size >> rate->rate.cell_log; - if (slot > 255) { - cl->xstats.giants++; - slot = 255; - } - return rate->data[slot]; +static inline long L2T(struct htb_class *cl, struct qdisc_rate_table *rate, + int size) +{ + int slot = size >> rate->rate.cell_log; + if (slot > 255) { + cl->xstats.giants++; + slot = 255; + } + return rate->data[slot]; } -struct htb_sched -{ - struct list_head root; /* root classes list */ - struct list_head hash[HTB_HSIZE]; /* hashed by classid */ - struct list_head drops[TC_HTB_NUMPRIO]; /* active leaves (for drops) */ - - /* self list - roots of self generating tree */ - struct rb_root row[TC_HTB_MAXDEPTH][TC_HTB_NUMPRIO]; - int row_mask[TC_HTB_MAXDEPTH]; - struct rb_node *ptr[TC_HTB_MAXDEPTH][TC_HTB_NUMPRIO]; - u32 last_ptr_id[TC_HTB_MAXDEPTH][TC_HTB_NUMPRIO]; - - /* self wait list - roots of wait PQs per row */ - struct rb_root wait_pq[TC_HTB_MAXDEPTH]; - - /* time of nearest event per level (row) */ - unsigned long near_ev_cache[TC_HTB_MAXDEPTH]; - - /* cached value of jiffies in dequeue */ - unsigned long jiffies; - - /* whether we hit non-work conserving class during this dequeue; we use */ - int nwc_hit; /* this to disable mindelay complaint in dequeue */ - - int defcls; /* class where unclassified flows go to */ - u32 debug; /* subsystem debug levels */ - - /* filters for qdisc itself */ - struct tcf_proto *filter_list; - int filter_cnt; - - int rate2quantum; /* quant = rate / rate2quantum */ - psched_time_t now; /* cached dequeue time */ - struct timer_list timer; /* send delay timer */ +struct htb_sched { + struct list_head root; /* root classes list */ + struct hlist_head hash[HTB_HSIZE]; /* hashed by classid */ + struct list_head drops[TC_HTB_NUMPRIO];/* active leaves (for drops) */ + + /* self list - roots of self generating tree */ + struct rb_root row[TC_HTB_MAXDEPTH][TC_HTB_NUMPRIO]; + int row_mask[TC_HTB_MAXDEPTH]; + struct rb_node *ptr[TC_HTB_MAXDEPTH][TC_HTB_NUMPRIO]; + u32 last_ptr_id[TC_HTB_MAXDEPTH][TC_HTB_NUMPRIO]; + + /* self wait list - roots of wait PQs per row */ + struct rb_root wait_pq[TC_HTB_MAXDEPTH]; + + /* time of nearest event per level (row) */ + unsigned long near_ev_cache[TC_HTB_MAXDEPTH]; + + /* cached value of jiffies in dequeue */ + unsigned long jiffies; + + /* whether we hit non-work conserving class during this dequeue; we use */ + int nwc_hit; /* this to disable mindelay complaint in dequeue */ + + int defcls; /* class where unclassified flows go to */ + + /* filters for qdisc itself */ + struct tcf_proto *filter_list; + int filter_cnt; + + int rate2quantum; /* quant = rate / rate2quantum */ + psched_time_t now; /* cached dequeue time */ + struct timer_list timer; /* send delay timer */ #ifdef HTB_RATECM - struct timer_list rttim; /* rate computer timer */ - int recmp_bucket; /* which hash bucket to recompute next */ + struct timer_list rttim; /* rate computer timer */ + int recmp_bucket; /* which hash bucket to recompute next */ #endif - - /* non shaped skbs; let them go directly thru */ - struct sk_buff_head direct_queue; - int direct_qlen; /* max qlen of above */ - long direct_pkts; + /* non shaped skbs; let them go directly thru */ + struct sk_buff_head direct_queue; + int direct_qlen; /* max qlen of above */ + + long direct_pkts; }; /* compute hash of size HTB_HSIZE for given handle */ -static __inline__ int htb_hash(u32 h) +static inline int htb_hash(u32 h) { #if HTB_HSIZE != 16 - #error "Declare new hash for your HTB_HSIZE" +#error "Declare new hash for your HTB_HSIZE" #endif - h ^= h>>8; /* stolen from cbq_hash */ - h ^= h>>4; - return h & 0xf; + h ^= h >> 8; /* stolen from cbq_hash */ + h ^= h >> 4; + return h & 0xf; } /* find class in global hash table using given handle */ -static __inline__ struct htb_class *htb_find(u32 handle, struct Qdisc *sch) +static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) { struct htb_sched *q = qdisc_priv(sch); - struct list_head *p; - if (TC_H_MAJ(handle) != sch->handle) + struct hlist_node *p; + struct htb_class *cl; + + if (TC_H_MAJ(handle) != sch->handle) return NULL; - - list_for_each (p,q->hash+htb_hash(handle)) { - struct htb_class *cl = list_entry(p,struct htb_class,hlist); + + hlist_for_each_entry(cl, p, q->hash + htb_hash(handle), hlist) { if (cl->classid == handle) return cl; } @@ -304,7 +251,8 @@ static inline u32 htb_classid(struct htb_class *cl) return (cl && cl != HTB_DIRECT) ? cl->classid : TC_H_UNSPEC; } -static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) +static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl; @@ -316,8 +264,8 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, in note that nfmark can be used too by attaching filter fw with no rules in it */ if (skb->priority == sch->handle) - return HTB_DIRECT; /* X:0 (direct flow) selected */ - if ((cl = htb_find(skb->priority,sch)) != NULL && cl->level == 0) + return HTB_DIRECT; /* X:0 (direct flow) selected */ + if ((cl = htb_find(skb->priority, sch)) != NULL && cl->level == 0) return cl; *qerr = NET_XMIT_BYPASS; @@ -326,7 +274,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, in #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: - case TC_ACT_STOLEN: + case TC_ACT_STOLEN: *qerr = NET_XMIT_SUCCESS; case TC_ACT_SHOT: return NULL; @@ -335,97 +283,44 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, in if (result == TC_POLICE_SHOT) return HTB_DIRECT; #endif - if ((cl = (void*)res.class) == NULL) { + if ((cl = (void *)res.class) == NULL) { if (res.classid == sch->handle) - return HTB_DIRECT; /* X:0 (direct flow) */ - if ((cl = htb_find(res.classid,sch)) == NULL) - break; /* filter selected invalid classid */ + return HTB_DIRECT; /* X:0 (direct flow) */ + if ((cl = htb_find(res.classid, sch)) == NULL) + break; /* filter selected invalid classid */ } if (!cl->level) - return cl; /* we hit leaf; return it */ + return cl; /* we hit leaf; return it */ /* we have got inner class; apply inner filter chain */ tcf = cl->filter_list; } /* classification failed; try to use default class */ - cl = htb_find(TC_H_MAKE(TC_H_MAJ(sch->handle),q->defcls),sch); + cl = htb_find(TC_H_MAKE(TC_H_MAJ(sch->handle), q->defcls), sch); if (!cl || cl->level) - return HTB_DIRECT; /* bad default .. this is safe bet */ + return HTB_DIRECT; /* bad default .. this is safe bet */ return cl; } -#ifdef HTB_DEBUG -static void htb_next_rb_node(struct rb_node **n); -#define HTB_DUMTREE(root,memb) if(root) { \ - struct rb_node *n = (root)->rb_node; \ - while (n->rb_left) n = n->rb_left; \ - while (n) { \ - struct htb_class *cl = rb_entry(n, struct htb_class, memb); \ - printk(" %x",cl->classid); htb_next_rb_node (&n); \ - } } - -static void htb_debug_dump (struct htb_sched *q) -{ - int i,p; - printk(KERN_DEBUG "htb*g j=%lu lj=%lu\n",jiffies,q->jiffies); - /* rows */ - for (i=TC_HTB_MAXDEPTH-1;i>=0;i--) { - printk(KERN_DEBUG "htb*r%d m=%x",i,q->row_mask[i]); - for (p=0;p<TC_HTB_NUMPRIO;p++) { - if (!q->row[i][p].rb_node) continue; - printk(" p%d:",p); - HTB_DUMTREE(q->row[i]+p,node[p]); - } - printk("\n"); - } - /* classes */ - for (i = 0; i < HTB_HSIZE; i++) { - struct list_head *l; - list_for_each (l,q->hash+i) { - struct htb_class *cl = list_entry(l,struct htb_class,hlist); - long diff = PSCHED_TDIFF_SAFE(q->now, cl->t_c, (u32)cl->mbuffer); - printk(KERN_DEBUG "htb*c%x m=%d t=%ld c=%ld pq=%lu df=%ld ql=%d " - "pa=%x f:", - cl->classid,cl->cmode,cl->tokens,cl->ctokens, - cl->pq_node.rb_color==-1?0:cl->pq_key,diff, - cl->level?0:cl->un.leaf.q->q.qlen,cl->prio_activity); - if (cl->level) - for (p=0;p<TC_HTB_NUMPRIO;p++) { - if (!cl->un.inner.feed[p].rb_node) continue; - printk(" p%d a=%x:",p,cl->un.inner.ptr[p]?rb_entry(cl->un.inner.ptr[p], struct htb_class,node[p])->classid:0); - HTB_DUMTREE(cl->un.inner.feed+p,node[p]); - } - printk("\n"); - } - } -} -#endif /** * htb_add_to_id_tree - adds class to the round robin list * * Routine adds class to the list (actually tree) sorted by classid. * Make sure that class is not already on such list for given prio. */ -static void htb_add_to_id_tree (HTB_ARGQ struct rb_root *root, - struct htb_class *cl,int prio) +static void htb_add_to_id_tree(struct rb_root *root, + struct htb_class *cl, int prio) { struct rb_node **p = &root->rb_node, *parent = NULL; - HTB_DBG(7,3,"htb_add_id_tree cl=%X prio=%d\n",cl->classid,prio); -#ifdef HTB_DEBUG - if (cl->node[prio].rb_color != -1) { BUG_TRAP(0); return; } - HTB_CHCL(cl); - if (*p) { - struct htb_class *x = rb_entry(*p,struct htb_class,node[prio]); - HTB_CHCL(x); - } -#endif + while (*p) { - struct htb_class *c; parent = *p; + struct htb_class *c; + parent = *p; c = rb_entry(parent, struct htb_class, node[prio]); - HTB_CHCL(c); + if (cl->classid > c->classid) p = &parent->rb_right; - else + else p = &parent->rb_left; } rb_link_node(&cl->node[prio], parent, p); @@ -439,17 +334,11 @@ static void htb_add_to_id_tree (HTB_ARGQ struct rb_root *root, * change its mode in cl->pq_key microseconds. Make sure that class is not * already in the queue. */ -static void htb_add_to_wait_tree (struct htb_sched *q, - struct htb_class *cl,long delay,int debug_hint) +static void htb_add_to_wait_tree(struct htb_sched *q, + struct htb_class *cl, long delay) { struct rb_node **p = &q->wait_pq[cl->level].rb_node, *parent = NULL; - HTB_DBG(7,3,"htb_add_wt cl=%X key=%lu\n",cl->classid,cl->pq_key); -#ifdef HTB_DEBUG - if (cl->pq_node.rb_color != -1) { BUG_TRAP(0); return; } - HTB_CHCL(cl); - if ((delay <= 0 || delay > cl->mbuffer) && net_ratelimit()) - printk(KERN_ERR "HTB: suspicious delay in wait_tree d=%ld cl=%X h=%d\n",delay,cl->classid,debug_hint); -#endif + cl->pq_key = q->jiffies + PSCHED_US2JIFFIE(delay); if (cl->pq_key == q->jiffies) cl->pq_key++; @@ -457,13 +346,14 @@ static void htb_add_to_wait_tree (struct htb_sched *q, /* update the nearest event cache */ if (time_after(q->near_ev_cache[cl->level], cl->pq_key)) q->near_ev_cache[cl->level] = cl->pq_key; - + while (*p) { - struct htb_class *c; parent = *p; + struct htb_class *c; + parent = *p; c = rb_entry(parent, struct htb_class, pq_node); if (time_after_eq(cl->pq_key, c->pq_key)) p = &parent->rb_right; - else + else p = &parent->rb_left; } rb_link_node(&cl->pq_node, parent, p); @@ -476,7 +366,7 @@ static void htb_add_to_wait_tree (struct htb_sched *q, * When we are past last key we return NULL. * Average complexity is 2 steps per call. */ -static void htb_next_rb_node(struct rb_node **n) +static inline void htb_next_rb_node(struct rb_node **n) { *n = rb_next(*n); } @@ -487,42 +377,51 @@ static void htb_next_rb_node(struct rb_node **n) * The class is added to row at priorities marked in mask. * It does nothing if mask == 0. */ -static inline void htb_add_class_to_row(struct htb_sched *q, - struct htb_class *cl,int mask) +static inline void htb_add_class_to_row(struct htb_sched *q, + struct htb_class *cl, int mask) { - HTB_DBG(7,2,"htb_addrow cl=%X mask=%X rmask=%X\n", - cl->classid,mask,q->row_mask[cl->level]); - HTB_CHCL(cl); q->row_mask[cl->level] |= mask; while (mask) { int prio = ffz(~mask); mask &= ~(1 << prio); - htb_add_to_id_tree(HTB_PASSQ q->row[cl->level]+prio,cl,prio); + htb_add_to_id_tree(q->row[cl->level] + prio, cl, prio); + } +} + +/* If this triggers, it is a bug in this code, but it need not be fatal */ +static void htb_safe_rb_erase(struct rb_node *rb, struct rb_root *root) +{ + if (RB_EMPTY_NODE(rb)) { + WARN_ON(1); + } else { + rb_erase(rb, root); + RB_CLEAR_NODE(rb); } } + /** * htb_remove_class_from_row - removes class from its row * * The class is removed from row at priorities marked in mask. * It does nothing if mask == 0. */ -static __inline__ void htb_remove_class_from_row(struct htb_sched *q, - struct htb_class *cl,int mask) +static inline void htb_remove_class_from_row(struct htb_sched *q, + struct htb_class *cl, int mask) { int m = 0; - HTB_CHCL(cl); + while (mask) { int prio = ffz(~mask); + mask &= ~(1 << prio); - if (q->ptr[cl->level][prio] == cl->node+prio) - htb_next_rb_node(q->ptr[cl->level]+prio); - htb_safe_rb_erase(cl->node + prio,q->row[cl->level]+prio); - if (!q->row[cl->level][prio].rb_node) + if (q->ptr[cl->level][prio] == cl->node + prio) + htb_next_rb_node(q->ptr[cl->level] + prio); + + htb_safe_rb_erase(cl->node + prio, q->row[cl->level] + prio); + if (!q->row[cl->level][prio].rb_node) m |= 1 << prio; } - HTB_DBG(7,2,"htb_delrow cl=%X mask=%X rmask=%X maskdel=%X\n", - cl->classid,mask,q->row_mask[cl->level],m); q->row_mask[cl->level] &= ~m; } @@ -533,34 +432,31 @@ static __inline__ void htb_remove_class_from_row(struct htb_sched *q, * for priorities it is participating on. cl->cmode must be new * (activated) mode. It does nothing if cl->prio_activity == 0. */ -static void htb_activate_prios(struct htb_sched *q,struct htb_class *cl) +static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) { struct htb_class *p = cl->parent; - long m,mask = cl->prio_activity; - HTB_DBG(7,2,"htb_act_prios cl=%X mask=%lX cmode=%d\n",cl->classid,mask,cl->cmode); - HTB_CHCL(cl); + long m, mask = cl->prio_activity; while (cl->cmode == HTB_MAY_BORROW && p && mask) { - HTB_CHCL(p); - m = mask; while (m) { + m = mask; + while (m) { int prio = ffz(~m); m &= ~(1 << prio); - + if (p->un.inner.feed[prio].rb_node) /* parent already has its feed in use so that reset bit in mask as parent is already ok */ mask &= ~(1 << prio); - - htb_add_to_id_tree(HTB_PASSQ p->un.inner.feed+prio,cl,prio); + + htb_add_to_id_tree(p->un.inner.feed + prio, cl, prio); } - HTB_DBG(7,3,"htb_act_pr_aft p=%X pact=%X mask=%lX pmode=%d\n", - p->classid,p->prio_activity,mask,p->cmode); p->prio_activity |= mask; - cl = p; p = cl->parent; - HTB_CHCL(cl); + cl = p; + p = cl->parent; + } if (cl->cmode == HTB_CAN_SEND && mask) - htb_add_class_to_row(q,cl,mask); + htb_add_class_to_row(q, cl, mask); } /** @@ -573,39 +469,52 @@ static void htb_activate_prios(struct htb_sched *q,struct htb_class *cl) static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) { struct htb_class *p = cl->parent; - long m,mask = cl->prio_activity; - HTB_DBG(7,2,"htb_deact_prios cl=%X mask=%lX cmode=%d\n",cl->classid,mask,cl->cmode); - HTB_CHCL(cl); + long m, mask = cl->prio_activity; while (cl->cmode == HTB_MAY_BORROW && p && mask) { - m = mask; mask = 0; + m = mask; + mask = 0; while (m) { int prio = ffz(~m); m &= ~(1 << prio); - - if (p->un.inner.ptr[prio] == cl->node+prio) { + + if (p->un.inner.ptr[prio] == cl->node + prio) { /* we are removing child which is pointed to from parent feed - forget the pointer but remember classid */ p->un.inner.last_ptr_id[prio] = cl->classid; p->un.inner.ptr[prio] = NULL; } - - htb_safe_rb_erase(cl->node + prio,p->un.inner.feed + prio); - - if (!p->un.inner.feed[prio].rb_node) + + htb_safe_rb_erase(cl->node + prio, p->un.inner.feed + prio); + + if (!p->un.inner.feed[prio].rb_node) mask |= 1 << prio; } - HTB_DBG(7,3,"htb_deact_pr_aft p=%X pact=%X mask=%lX pmode=%d\n", - p->classid,p->prio_activity,mask,p->cmode); + p->prio_activity &= ~mask; - cl = p; p = cl->parent; - HTB_CHCL(cl); + cl = p; + p = cl->parent; + } - if (cl->cmode == HTB_CAN_SEND && mask) - htb_remove_class_from_row(q,cl,mask); + if (cl->cmode == HTB_CAN_SEND && mask) + htb_remove_class_from_row(q, cl, mask); } +#if HTB_HYSTERESIS +static inline long htb_lowater(const struct htb_class *cl) +{ + return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0; +} +static inline long htb_hiwater(const struct htb_class *cl) +{ + return cl->cmode == HTB_CAN_SEND ? -cl->buffer : 0; +} +#else +#define htb_lowater(cl) (0) +#define htb_hiwater(cl) (0) +#endif + /** * htb_class_mode - computes and returns current class mode * @@ -617,28 +526,21 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) * 0 .. -cl->{c,}buffer range. It is meant to limit number of * mode transitions per time unit. The speed gain is about 1/6. */ -static __inline__ enum htb_cmode -htb_class_mode(struct htb_class *cl,long *diff) +static inline enum htb_cmode +htb_class_mode(struct htb_class *cl, long *diff) { - long toks; + long toks; - if ((toks = (cl->ctokens + *diff)) < ( -#if HTB_HYSTERESIS - cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : -#endif - 0)) { - *diff = -toks; - return HTB_CANT_SEND; - } - if ((toks = (cl->tokens + *diff)) >= ( -#if HTB_HYSTERESIS - cl->cmode == HTB_CAN_SEND ? -cl->buffer : -#endif - 0)) - return HTB_CAN_SEND; + if ((toks = (cl->ctokens + *diff)) < htb_lowater(cl)) { + *diff = -toks; + return HTB_CANT_SEND; + } + + if ((toks = (cl->tokens + *diff)) >= htb_hiwater(cl)) + return HTB_CAN_SEND; - *diff = -toks; - return HTB_MAY_BORROW; + *diff = -toks; + return HTB_MAY_BORROW; } /** @@ -650,24 +552,21 @@ htb_class_mode(struct htb_class *cl,long *diff) * be different from old one and cl->pq_key has to be valid if changing * to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree). */ -static void +static void htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, long *diff) -{ - enum htb_cmode new_mode = htb_class_mode(cl,diff); - - HTB_CHCL(cl); - HTB_DBG(7,1,"htb_chging_clmode %d->%d cl=%X\n",cl->cmode,new_mode,cl->classid); +{ + enum htb_cmode new_mode = htb_class_mode(cl, diff); if (new_mode == cl->cmode) - return; - - if (cl->prio_activity) { /* not necessary: speed optimization */ - if (cl->cmode != HTB_CANT_SEND) - htb_deactivate_prios(q,cl); + return; + + if (cl->prio_activity) { /* not necessary: speed optimization */ + if (cl->cmode != HTB_CANT_SEND) + htb_deactivate_prios(q, cl); cl->cmode = new_mode; - if (new_mode != HTB_CANT_SEND) - htb_activate_prios(q,cl); - } else + if (new_mode != HTB_CANT_SEND) + htb_activate_prios(q, cl); + } else cl->cmode = new_mode; } @@ -678,14 +577,15 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, long *diff) * for the prio. It can be called on already active leaf safely. * It also adds leaf into droplist. */ -static __inline__ void htb_activate(struct htb_sched *q,struct htb_class *cl) +static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { BUG_TRAP(!cl->level && cl->un.leaf.q && cl->un.leaf.q->q.qlen); - HTB_CHCL(cl); + if (!cl->prio_activity) { cl->prio_activity = 1 << (cl->un.leaf.aprio = cl->un.leaf.prio); - htb_activate_prios(q,cl); - list_add_tail(&cl->un.leaf.drop_list,q->drops+cl->un.leaf.aprio); + htb_activate_prios(q, cl); + list_add_tail(&cl->un.leaf.drop_list, + q->drops + cl->un.leaf.aprio); } } @@ -695,120 +595,120 @@ static __inline__ void htb_activate(struct htb_sched *q,struct htb_class *cl) * Make sure that leaf is active. In the other words it can't be called * with non-active leaf. It also removes class from the drop list. */ -static __inline__ void -htb_deactivate(struct htb_sched *q,struct htb_class *cl) +static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) { BUG_TRAP(cl->prio_activity); - HTB_CHCL(cl); - htb_deactivate_prios(q,cl); + + htb_deactivate_prios(q, cl); cl->prio_activity = 0; list_del_init(&cl->un.leaf.drop_list); } static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) { - int ret; - struct htb_sched *q = qdisc_priv(sch); - struct htb_class *cl = htb_classify(skb,sch,&ret); - - if (cl == HTB_DIRECT) { - /* enqueue to helper queue */ - if (q->direct_queue.qlen < q->direct_qlen) { - __skb_queue_tail(&q->direct_queue, skb); - q->direct_pkts++; - } else { - kfree_skb(skb); - sch->qstats.drops++; - return NET_XMIT_DROP; - } + int ret; + struct htb_sched *q = qdisc_priv(sch); + struct htb_class *cl = htb_classify(skb, sch, &ret); + + if (cl == HTB_DIRECT) { + /* enqueue to helper queue */ + if (q->direct_queue.qlen < q->direct_qlen) { + __skb_queue_tail(&q->direct_queue, skb); + q->direct_pkts++; + } else { + kfree_skb(skb); + sch->qstats.drops++; + return NET_XMIT_DROP; + } #ifdef CONFIG_NET_CLS_ACT - } else if (!cl) { - if (ret == NET_XMIT_BYPASS) - sch->qstats.drops++; - kfree_skb (skb); - return ret; + } else if (!cl) { + if (ret == NET_XMIT_BYPASS) + sch->qstats.drops++; + kfree_skb(skb); + return ret; #endif - } else if (cl->un.leaf.q->enqueue(skb, cl->un.leaf.q) != NET_XMIT_SUCCESS) { - sch->qstats.drops++; - cl->qstats.drops++; - return NET_XMIT_DROP; - } else { - cl->bstats.packets++; cl->bstats.bytes += skb->len; - htb_activate (q,cl); - } - - sch->q.qlen++; - sch->bstats.packets++; sch->bstats.bytes += skb->len; - HTB_DBG(1,1,"htb_enq_ok cl=%X skb=%p\n",(cl && cl != HTB_DIRECT)?cl->classid:0,skb); - return NET_XMIT_SUCCESS; + } else if (cl->un.leaf.q->enqueue(skb, cl->un.leaf.q) != + NET_XMIT_SUCCESS) { + sch->qstats.drops++; + cl->qstats.drops++; + return NET_XMIT_DROP; + } else { + cl->bstats.packets++; + cl->bstats.bytes += skb->len; + htb_activate(q, cl); + } + + sch->q.qlen++; + sch->bstats.packets++; + sch->bstats.bytes += skb->len; + return NET_XMIT_SUCCESS; } /* TODO: requeuing packet charges it to policers again !! */ static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch) { - struct htb_sched *q = qdisc_priv(sch); - int ret = NET_XMIT_SUCCESS; - struct htb_class *cl = htb_classify(skb,sch, &ret); - struct sk_buff *tskb; - - if (cl == HTB_DIRECT || !cl) { - /* enqueue to helper queue */ - if (q->direct_queue.qlen < q->direct_qlen && cl) { - __skb_queue_head(&q->direct_queue, skb); - } else { - __skb_queue_head(&q->direct_queue, skb); - tskb = __skb_dequeue_tail(&q->direct_queue); - kfree_skb (tskb); - sch->qstats.drops++; - return NET_XMIT_CN; - } - } else if (cl->un.leaf.q->ops->requeue(skb, cl->un.leaf.q) != NET_XMIT_SUCCESS) { - sch->qstats.drops++; - cl->qstats.drops++; - return NET_XMIT_DROP; - } else - htb_activate (q,cl); - - sch->q.qlen++; - sch->qstats.requeues++; - HTB_DBG(1,1,"htb_req_ok cl=%X skb=%p\n",(cl && cl != HTB_DIRECT)?cl->classid:0,skb); - return NET_XMIT_SUCCESS; + struct htb_sched *q = qdisc_priv(sch); + int ret = NET_XMIT_SUCCESS; + struct htb_class *cl = htb_classify(skb, sch, &ret); + struct sk_buff *tskb; + + if (cl == HTB_DIRECT || !cl) { + /* enqueue to helper queue */ + if (q->direct_queue.qlen < q->direct_qlen && cl) { + __skb_queue_head(&q->direct_queue, skb); + } else { + __skb_queue_head(&q->direct_queue, skb); + tskb = __skb_dequeue_tail(&q->direct_queue); + kfree_skb(tskb); + sch->qstats.drops++; + return NET_XMIT_CN; + } + } else if (cl->un.leaf.q->ops->requeue(skb, cl->un.leaf.q) != + NET_XMIT_SUCCESS) { + sch->qstats.drops++; + cl->qstats.drops++; + return NET_XMIT_DROP; + } else + htb_activate(q, cl); + + sch->q.qlen++; + sch->qstats.requeues++; + return NET_XMIT_SUCCESS; } static void htb_timer(unsigned long arg) { - struct Qdisc *sch = (struct Qdisc*)arg; - sch->flags &= ~TCQ_F_THROTTLED; - wmb(); - netif_schedule(sch->dev); + struct Qdisc *sch = (struct Qdisc *)arg; + sch->flags &= ~TCQ_F_THROTTLED; + wmb(); + netif_schedule(sch->dev); } #ifdef HTB_RATECM #define RT_GEN(D,R) R+=D-(R/HTB_EWMAC);D=0 static void htb_rate_timer(unsigned long arg) { - struct Qdisc *sch = (struct Qdisc*)arg; + struct Qdisc *sch = (struct Qdisc *)arg; struct htb_sched *q = qdisc_priv(sch); - struct list_head *p; + struct hlist_node *p; + struct htb_class *cl; + /* lock queue so that we can muck with it */ - HTB_QLOCK(sch); - HTB_DBG(10,1,"htb_rttmr j=%ld\n",jiffies); + spin_lock_bh(&sch->dev->queue_lock); q->rttim.expires = jiffies + HZ; add_timer(&q->rttim); /* scan and recompute one bucket at time */ - if (++q->recmp_bucket >= HTB_HSIZE) + if (++q->recmp_bucket >= HTB_HSIZE) q->recmp_bucket = 0; - list_for_each (p,q->hash+q->recmp_bucket) { - struct htb_class *cl = list_entry(p,struct htb_class,hlist); - HTB_DBG(10,2,"htb_rttmr_cl cl=%X sbyte=%lu spkt=%lu\n", - cl->classid,cl->sum_bytes,cl->sum_packets); - RT_GEN (cl->sum_bytes,cl->rate_bytes); - RT_GEN (cl->sum_packets,cl->rate_packets); + + hlist_for_each_entry(cl,p, q->hash + q->recmp_bucket, hlist) { + RT_GEN(cl->sum_bytes, cl->rate_bytes); + RT_GEN(cl->sum_packets, cl->rate_packets); } - HTB_QUNLOCK(sch); + spin_unlock_bh(&sch->dev->queue_lock); } #endif @@ -823,12 +723,11 @@ static void htb_rate_timer(unsigned long arg) * CAN_SEND) because we can use more precise clock that event queue here. * In such case we remove class from event queue first. */ -static void htb_charge_class(struct htb_sched *q,struct htb_class *cl, - int level,int bytes) -{ - long toks,diff; +static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, + int level, int bytes) +{ + long toks, diff; enum htb_cmode old_mode; - HTB_DBG(5,1,"htb_chrg_cl cl=%X lev=%d len=%d\n",cl->classid,level,bytes); #define HTB_ACCNT(T,B,R) toks = diff + cl->T; \ if (toks > cl->B) toks = cl->B; \ @@ -837,47 +736,31 @@ static void htb_charge_class(struct htb_sched *q,struct htb_class *cl, cl->T = toks while (cl) { - HTB_CHCL(cl); - diff = PSCHED_TDIFF_SAFE(q->now, cl->t_c, (u32)cl->mbuffer); -#ifdef HTB_DEBUG - if (diff > cl->mbuffer || diff < 0 || PSCHED_TLESS(q->now, cl->t_c)) { - if (net_ratelimit()) - printk(KERN_ERR "HTB: bad diff in charge, cl=%X diff=%lX now=%Lu then=%Lu j=%lu\n", - cl->classid, diff, -#ifdef CONFIG_NET_SCH_CLK_GETTIMEOFDAY - q->now.tv_sec * 1000000ULL + q->now.tv_usec, - cl->t_c.tv_sec * 1000000ULL + cl->t_c.tv_usec, -#else - (unsigned long long) q->now, - (unsigned long long) cl->t_c, -#endif - q->jiffies); - diff = 1000; - } -#endif + diff = PSCHED_TDIFF_SAFE(q->now, cl->t_c, (u32) cl->mbuffer); if (cl->level >= level) { - if (cl->level == level) cl->xstats.lends++; - HTB_ACCNT (tokens,buffer,rate); + if (cl->level == level) + cl->xstats.lends++; + HTB_ACCNT(tokens, buffer, rate); } else { cl->xstats.borrows++; - cl->tokens += diff; /* we moved t_c; update tokens */ + cl->tokens += diff; /* we moved t_c; update tokens */ } - HTB_ACCNT (ctokens,cbuffer,ceil); + HTB_ACCNT(ctokens, cbuffer, ceil); cl->t_c = q->now; - HTB_DBG(5,2,"htb_chrg_clp cl=%X diff=%ld tok=%ld ctok=%ld\n",cl->classid,diff,cl->tokens,cl->ctokens); - old_mode = cl->cmode; diff = 0; - htb_change_class_mode(q,cl,&diff); + old_mode = cl->cmode; + diff = 0; + htb_change_class_mode(q, cl, &diff); if (old_mode != cl->cmode) { if (old_mode != HTB_CAN_SEND) - htb_safe_rb_erase(&cl->pq_node,q->wait_pq+cl->level); + htb_safe_rb_erase(&cl->pq_node, q->wait_pq + cl->level); if (cl->cmode != HTB_CAN_SEND) - htb_add_to_wait_tree (q,cl,diff,1); + htb_add_to_wait_tree(q, cl, diff); } - #ifdef HTB_RATECM /* update rate counters */ - cl->sum_bytes += bytes; cl->sum_packets++; + cl->sum_bytes += bytes; + cl->sum_packets++; #endif /* update byte stats except for leaves which are already updated */ @@ -896,60 +779,46 @@ static void htb_charge_class(struct htb_sched *q,struct htb_class *cl, * next pending event (0 for no event in pq). * Note: Aplied are events whose have cl->pq_key <= jiffies. */ -static long htb_do_events(struct htb_sched *q,int level) +static long htb_do_events(struct htb_sched *q, int level) { int i; - HTB_DBG(8,1,"htb_do_events l=%d root=%p rmask=%X\n", - level,q->wait_pq[level].rb_node,q->row_mask[level]); + for (i = 0; i < 500; i++) { struct htb_class *cl; long diff; struct rb_node *p = q->wait_pq[level].rb_node; - if (!p) return 0; - while (p->rb_left) p = p->rb_left; + if (!p) + return 0; + while (p->rb_left) + p = p->rb_left; cl = rb_entry(p, struct htb_class, pq_node); if (time_after(cl->pq_key, q->jiffies)) { - HTB_DBG(8,3,"htb_do_ev_ret delay=%ld\n",cl->pq_key - q->jiffies); return cl->pq_key - q->jiffies; } - htb_safe_rb_erase(p,q->wait_pq+level); - diff = PSCHED_TDIFF_SAFE(q->now, cl->t_c, (u32)cl->mbuffer); -#ifdef HTB_DEBUG - if (diff > cl->mbuffer || diff < 0 || PSCHED_TLESS(q->now, cl->t_c)) { - if (net_ratelimit()) - printk(KERN_ERR "HTB: bad diff in events, cl=%X diff=%lX now=%Lu then=%Lu j=%lu\n", - cl->classid, diff, -#ifdef CONFIG_NET_SCH_CLK_GETTIMEOFDAY - q->now.tv_sec * 1000000ULL + q->now.tv_usec, - cl->t_c.tv_sec * 1000000ULL + cl->t_c.tv_usec, -#else - (unsigned long long) q->now, - (unsigned long long) cl->t_c, -#endif - q->jiffies); - diff = 1000; - } -#endif - htb_change_class_mode(q,cl,&diff); + htb_safe_rb_erase(p, q->wait_pq + level); + diff = PSCHED_TDIFF_SAFE(q->now, cl->t_c, (u32) cl->mbuffer); + htb_change_class_mode(q, cl, &diff); if (cl->cmode != HTB_CAN_SEND) - htb_add_to_wait_tree (q,cl,diff,2); + htb_add_to_wait_tree(q, cl, diff); } if (net_ratelimit()) printk(KERN_WARNING "htb: too many events !\n"); - return HZ/10; + return HZ / 10; } /* Returns class->node+prio from id-tree where classe's id is >= id. NULL is no such one exists. */ -static struct rb_node * -htb_id_find_next_upper(int prio,struct rb_node *n,u32 id) +static struct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n, + u32 id) { struct rb_node *r = NULL; while (n) { - struct htb_class *cl = rb_entry(n,struct htb_class,node[prio]); - if (id == cl->classid) return n; - + struct htb_class *cl = + rb_entry(n, struct htb_class, node[prio]); + if (id == cl->classid) + return n; + if (id > cl->classid) { n = n->rb_right; } else { @@ -965,49 +834,49 @@ htb_id_find_next_upper(int prio,struct rb_node *n,u32 id) * * Find leaf where current feed pointers points to. */ -static struct htb_class * -htb_lookup_leaf(HTB_ARGQ struct rb_root *tree,int prio,struct rb_node **pptr,u32 *pid) +static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, + struct rb_node **pptr, u32 * pid) { int i; struct { struct rb_node *root; struct rb_node **pptr; u32 *pid; - } stk[TC_HTB_MAXDEPTH],*sp = stk; - + } stk[TC_HTB_MAXDEPTH], *sp = stk; + BUG_TRAP(tree->rb_node); sp->root = tree->rb_node; sp->pptr = pptr; sp->pid = pid; for (i = 0; i < 65535; i++) { - HTB_DBG(4,2,"htb_lleaf ptr=%p pid=%X\n",*sp->pptr,*sp->pid); - - if (!*sp->pptr && *sp->pid) { + if (!*sp->pptr && *sp->pid) { /* ptr was invalidated but id is valid - try to recover the original or next ptr */ - *sp->pptr = htb_id_find_next_upper(prio,sp->root,*sp->pid); + *sp->pptr = + htb_id_find_next_upper(prio, sp->root, *sp->pid); } - *sp->pid = 0; /* ptr is valid now so that remove this hint as it - can become out of date quickly */ - if (!*sp->pptr) { /* we are at right end; rewind & go up */ + *sp->pid = 0; /* ptr is valid now so that remove this hint as it + can become out of date quickly */ + if (!*sp->pptr) { /* we are at right end; rewind & go up */ *sp->pptr = sp->root; - while ((*sp->pptr)->rb_left) + while ((*sp->pptr)->rb_left) *sp->pptr = (*sp->pptr)->rb_left; if (sp > stk) { sp--; - BUG_TRAP(*sp->pptr); if(!*sp->pptr) return NULL; - htb_next_rb_node (sp->pptr); + BUG_TRAP(*sp->pptr); + if (!*sp->pptr) + return NULL; + htb_next_rb_node(sp->pptr); } } else { struct htb_class *cl; - cl = rb_entry(*sp->pptr,struct htb_class,node[prio]); - HTB_CHCL(cl); - if (!cl->level) + cl = rb_entry(*sp->pptr, struct htb_class, node[prio]); + if (!cl->level) return cl; (++sp)->root = cl->un.inner.feed[prio].rb_node; - sp->pptr = cl->un.inner.ptr+prio; - sp->pid = cl->un.inner.last_ptr_id+prio; + sp->pptr = cl->un.inner.ptr + prio; + sp->pid = cl->un.inner.last_ptr_id + prio; } } BUG_TRAP(0); @@ -1016,21 +885,21 @@ htb_lookup_leaf(HTB_ARGQ struct rb_root *tree,int prio,struct rb_node **pptr,u32 /* dequeues packet at given priority and level; call only if you are sure that there is active class at prio/level */ -static struct sk_buff * -htb_dequeue_tree(struct htb_sched *q,int prio,int level) +static struct sk_buff *htb_dequeue_tree(struct htb_sched *q, int prio, + int level) { struct sk_buff *skb = NULL; - struct htb_class *cl,*start; + struct htb_class *cl, *start; /* look initial class up in the row */ - start = cl = htb_lookup_leaf (HTB_PASSQ q->row[level]+prio,prio, - q->ptr[level]+prio,q->last_ptr_id[level]+prio); - + start = cl = htb_lookup_leaf(q->row[level] + prio, prio, + q->ptr[level] + prio, + q->last_ptr_id[level] + prio); + do { next: - BUG_TRAP(cl); - if (!cl) return NULL; - HTB_DBG(4,1,"htb_deq_tr prio=%d lev=%d cl=%X defic=%d\n", - prio,level,cl->classid,cl->un.leaf.deficit[level]); + BUG_TRAP(cl); + if (!cl) + return NULL; /* class can be empty - it is unlikely but can be true if leaf qdisc drops packets in enqueue routine or if someone used @@ -1038,64 +907,69 @@ next: simply deactivate and skip such class */ if (unlikely(cl->un.leaf.q->q.qlen == 0)) { struct htb_class *next; - htb_deactivate(q,cl); + htb_deactivate(q, cl); /* row/level might become empty */ if ((q->row_mask[level] & (1 << prio)) == 0) - return NULL; - - next = htb_lookup_leaf (HTB_PASSQ q->row[level]+prio, - prio,q->ptr[level]+prio,q->last_ptr_id[level]+prio); + return NULL; + + next = htb_lookup_leaf(q->row[level] + prio, + prio, q->ptr[level] + prio, + q->last_ptr_id[level] + prio); - if (cl == start) /* fix start if we just deleted it */ + if (cl == start) /* fix start if we just deleted it */ start = next; cl = next; goto next; } - - if (likely((skb = cl->un.leaf.q->dequeue(cl->un.leaf.q)) != NULL)) + + skb = cl->un.leaf.q->dequeue(cl->un.leaf.q); + if (likely(skb != NULL)) break; if (!cl->warned) { - printk(KERN_WARNING "htb: class %X isn't work conserving ?!\n",cl->classid); + printk(KERN_WARNING + "htb: class %X isn't work conserving ?!\n", + cl->classid); cl->warned = 1; } q->nwc_hit++; - htb_next_rb_node((level?cl->parent->un.inner.ptr:q->ptr[0])+prio); - cl = htb_lookup_leaf (HTB_PASSQ q->row[level]+prio,prio,q->ptr[level]+prio, - q->last_ptr_id[level]+prio); + htb_next_rb_node((level ? cl->parent->un.inner.ptr : q-> + ptr[0]) + prio); + cl = htb_lookup_leaf(q->row[level] + prio, prio, + q->ptr[level] + prio, + q->last_ptr_id[level] + prio); } while (cl != start); if (likely(skb != NULL)) { if ((cl->un.leaf.deficit[level] -= skb->len) < 0) { - HTB_DBG(4,2,"htb_next_cl oldptr=%p quant_add=%d\n", - level?cl->parent->un.inner.ptr[prio]:q->ptr[0][prio],cl->un.leaf.quantum); cl->un.leaf.deficit[level] += cl->un.leaf.quantum; - htb_next_rb_node((level?cl->parent->un.inner.ptr:q->ptr[0])+prio); + htb_next_rb_node((level ? cl->parent->un.inner.ptr : q-> + ptr[0]) + prio); } /* this used to be after charge_class but this constelation gives us slightly better performance */ if (!cl->un.leaf.q->q.qlen) - htb_deactivate (q,cl); - htb_charge_class (q,cl,level,skb->len); + htb_deactivate(q, cl); + htb_charge_class(q, cl, level, skb->len); } return skb; } -static void htb_delay_by(struct Qdisc *sch,long delay) +static void htb_delay_by(struct Qdisc *sch, long delay) { struct htb_sched *q = qdisc_priv(sch); - if (delay <= 0) delay = 1; - if (unlikely(delay > 5*HZ)) { + if (delay <= 0) + delay = 1; + if (unlikely(delay > 5 * HZ)) { if (net_ratelimit()) printk(KERN_INFO "HTB delay %ld > 5sec\n", delay); - delay = 5*HZ; + delay = 5 * HZ; } /* why don't use jiffies here ? because expires can be in past */ mod_timer(&q->timer, q->jiffies + delay); sch->flags |= TCQ_F_THROTTLED; sch->qstats.overlimits++; - HTB_DBG(3,1,"htb_deq t_delay=%ld\n",delay); } static struct sk_buff *htb_dequeue(struct Qdisc *sch) @@ -1104,22 +978,19 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) struct htb_sched *q = qdisc_priv(sch); int level; long min_delay; -#ifdef HTB_DEBUG - int evs_used = 0; -#endif q->jiffies = jiffies; - HTB_DBG(3,1,"htb_deq dircnt=%d qlen=%d\n",skb_queue_len(&q->direct_queue), - sch->q.qlen); /* try to dequeue direct packets as high prio (!) to minimize cpu work */ - if ((skb = __skb_dequeue(&q->direct_queue)) != NULL) { + skb = __skb_dequeue(&q->direct_queue); + if (skb != NULL) { sch->flags &= ~TCQ_F_THROTTLED; sch->q.qlen--; return skb; } - if (!sch->q.qlen) goto fin; + if (!sch->q.qlen) + goto fin; PSCHED_GET_TIME(q->now); min_delay = LONG_MAX; @@ -1129,21 +1000,19 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) int m; long delay; if (time_after_eq(q->jiffies, q->near_ev_cache[level])) { - delay = htb_do_events(q,level); - q->near_ev_cache[level] = q->jiffies + (delay ? delay : HZ); -#ifdef HTB_DEBUG - evs_used++; -#endif + delay = htb_do_events(q, level); + q->near_ev_cache[level] = + q->jiffies + (delay ? delay : HZ); } else - delay = q->near_ev_cache[level] - q->jiffies; - - if (delay && min_delay > delay) + delay = q->near_ev_cache[level] - q->jiffies; + + if (delay && min_delay > delay) min_delay = delay; m = ~q->row_mask[level]; while (m != (int)(-1)) { - int prio = ffz (m); + int prio = ffz(m); m |= 1 << prio; - skb = htb_dequeue_tree(q,prio,level); + skb = htb_dequeue_tree(q, prio, level); if (likely(skb != NULL)) { sch->q.qlen--; sch->flags &= ~TCQ_F_THROTTLED; @@ -1151,40 +1020,28 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) } } } -#ifdef HTB_DEBUG - if (!q->nwc_hit && min_delay >= 10*HZ && net_ratelimit()) { - if (min_delay == LONG_MAX) { - printk(KERN_ERR "HTB: dequeue bug (%d,%lu,%lu), report it please !\n", - evs_used,q->jiffies,jiffies); - htb_debug_dump(q); - } else - printk(KERN_WARNING "HTB: mindelay=%ld, some class has " - "too small rate\n",min_delay); - } -#endif - htb_delay_by (sch,min_delay > 5*HZ ? 5*HZ : min_delay); + htb_delay_by(sch, min_delay > 5 * HZ ? 5 * HZ : min_delay); fin: - HTB_DBG(3,1,"htb_deq_end %s j=%lu skb=%p\n",sch->dev->name,q->jiffies,skb); return skb; } /* try to drop from each class (by prio) until one succeed */ -static unsigned int htb_drop(struct Qdisc* sch) +static unsigned int htb_drop(struct Qdisc *sch) { struct htb_sched *q = qdisc_priv(sch); int prio; for (prio = TC_HTB_NUMPRIO - 1; prio >= 0; prio--) { struct list_head *p; - list_for_each (p,q->drops+prio) { + list_for_each(p, q->drops + prio) { struct htb_class *cl = list_entry(p, struct htb_class, un.leaf.drop_list); unsigned int len; - if (cl->un.leaf.q->ops->drop && - (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) { + if (cl->un.leaf.q->ops->drop && + (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) { sch->q.qlen--; if (!cl->un.leaf.q->q.qlen) - htb_deactivate (q,cl); + htb_deactivate(q, cl); return len; } } @@ -1194,29 +1051,25 @@ static unsigned int htb_drop(struct Qdisc* sch) /* reset all classes */ /* always caled under BH & queue lock */ -static void htb_reset(struct Qdisc* sch) +static void htb_reset(struct Qdisc *sch) { struct htb_sched *q = qdisc_priv(sch); int i; - HTB_DBG(0,1,"htb_reset sch=%p, handle=%X\n",sch,sch->handle); for (i = 0; i < HTB_HSIZE; i++) { - struct list_head *p; - list_for_each (p,q->hash+i) { - struct htb_class *cl = list_entry(p,struct htb_class,hlist); + struct hlist_node *p; + struct htb_class *cl; + + hlist_for_each_entry(cl, p, q->hash + i, hlist) { if (cl->level) - memset(&cl->un.inner,0,sizeof(cl->un.inner)); + memset(&cl->un.inner, 0, sizeof(cl->un.inner)); else { - if (cl->un.leaf.q) + if (cl->un.leaf.q) qdisc_reset(cl->un.leaf.q); INIT_LIST_HEAD(&cl->un.leaf.drop_list); } cl->prio_activity = 0; cl->cmode = HTB_CAN_SEND; -#ifdef HTB_DEBUG - cl->pq_node.rb_color = -1; - memset(cl->node,255,sizeof(cl->node)); -#endif } } @@ -1224,12 +1077,12 @@ static void htb_reset(struct Qdisc* sch) del_timer(&q->timer); __skb_queue_purge(&q->direct_queue); sch->q.qlen = 0; - memset(q->row,0,sizeof(q->row)); - memset(q->row_mask,0,sizeof(q->row_mask)); - memset(q->wait_pq,0,sizeof(q->wait_pq)); - memset(q->ptr,0,sizeof(q->ptr)); + memset(q->row, 0, sizeof(q->row)); + memset(q->row_mask, 0, sizeof(q->row_mask)); + memset(q->wait_pq, 0, sizeof(q->wait_pq)); + memset(q->ptr, 0, sizeof(q->ptr)); for (i = 0; i < TC_HTB_NUMPRIO; i++) - INIT_LIST_HEAD(q->drops+i); + INIT_LIST_HEAD(q->drops + i); } static int htb_init(struct Qdisc *sch, struct rtattr *opt) @@ -1238,36 +1091,31 @@ static int htb_init(struct Qdisc *sch, struct rtattr *opt) struct rtattr *tb[TCA_HTB_INIT]; struct tc_htb_glob *gopt; int i; -#ifdef HTB_DEBUG - printk(KERN_INFO "HTB init, kernel part version %d.%d\n", - HTB_VER >> 16,HTB_VER & 0xffff); -#endif if (!opt || rtattr_parse_nested(tb, TCA_HTB_INIT, opt) || - tb[TCA_HTB_INIT-1] == NULL || - RTA_PAYLOAD(tb[TCA_HTB_INIT-1]) < sizeof(*gopt)) { + tb[TCA_HTB_INIT - 1] == NULL || + RTA_PAYLOAD(tb[TCA_HTB_INIT - 1]) < sizeof(*gopt)) { printk(KERN_ERR "HTB: hey probably you have bad tc tool ?\n"); return -EINVAL; } - gopt = RTA_DATA(tb[TCA_HTB_INIT-1]); + gopt = RTA_DATA(tb[TCA_HTB_INIT - 1]); if (gopt->version != HTB_VER >> 16) { - printk(KERN_ERR "HTB: need tc/htb version %d (minor is %d), you have %d\n", - HTB_VER >> 16,HTB_VER & 0xffff,gopt->version); + printk(KERN_ERR + "HTB: need tc/htb version %d (minor is %d), you have %d\n", + HTB_VER >> 16, HTB_VER & 0xffff, gopt->version); return -EINVAL; } - q->debug = gopt->debug; - HTB_DBG(0,1,"htb_init sch=%p handle=%X r2q=%d\n",sch,sch->handle,gopt->rate2quantum); INIT_LIST_HEAD(&q->root); for (i = 0; i < HTB_HSIZE; i++) - INIT_LIST_HEAD(q->hash+i); + INIT_HLIST_HEAD(q->hash + i); for (i = 0; i < TC_HTB_NUMPRIO; i++) - INIT_LIST_HEAD(q->drops+i); + INIT_LIST_HEAD(q->drops + i); init_timer(&q->timer); skb_queue_head_init(&q->direct_queue); q->direct_qlen = sch->dev->tx_queue_len; - if (q->direct_qlen < 2) /* some devices have zero tx_queue_len */ + if (q->direct_qlen < 2) /* some devices have zero tx_queue_len */ q->direct_qlen = 2; q->timer.function = htb_timer; q->timer.data = (unsigned long)sch; @@ -1289,80 +1137,72 @@ static int htb_init(struct Qdisc *sch, struct rtattr *opt) static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) { struct htb_sched *q = qdisc_priv(sch); - unsigned char *b = skb->tail; + unsigned char *b = skb->tail; struct rtattr *rta; struct tc_htb_glob gopt; - HTB_DBG(0,1,"htb_dump sch=%p, handle=%X\n",sch,sch->handle); - HTB_QLOCK(sch); + spin_lock_bh(&sch->dev->queue_lock); gopt.direct_pkts = q->direct_pkts; -#ifdef HTB_DEBUG - if (HTB_DBG_COND(0,2)) - htb_debug_dump(q); -#endif gopt.version = HTB_VER; gopt.rate2quantum = q->rate2quantum; gopt.defcls = q->defcls; - gopt.debug = q->debug; - rta = (struct rtattr*)b; + gopt.debug = 0; + rta = (struct rtattr *)b; RTA_PUT(skb, TCA_OPTIONS, 0, NULL); RTA_PUT(skb, TCA_HTB_INIT, sizeof(gopt), &gopt); rta->rta_len = skb->tail - b; - HTB_QUNLOCK(sch); + spin_unlock_bh(&sch->dev->queue_lock); return skb->len; rtattr_failure: - HTB_QUNLOCK(sch); + spin_unlock_bh(&sch->dev->queue_lock); skb_trim(skb, skb->tail - skb->data); return -1; } static int htb_dump_class(struct Qdisc *sch, unsigned long arg, - struct sk_buff *skb, struct tcmsg *tcm) + struct sk_buff *skb, struct tcmsg *tcm) { -#ifdef HTB_DEBUG - struct htb_sched *q = qdisc_priv(sch); -#endif - struct htb_class *cl = (struct htb_class*)arg; - unsigned char *b = skb->tail; + struct htb_class *cl = (struct htb_class *)arg; + unsigned char *b = skb->tail; struct rtattr *rta; struct tc_htb_opt opt; - HTB_DBG(0,1,"htb_dump_class handle=%X clid=%X\n",sch->handle,cl->classid); - - HTB_QLOCK(sch); + spin_lock_bh(&sch->dev->queue_lock); tcm->tcm_parent = cl->parent ? cl->parent->classid : TC_H_ROOT; tcm->tcm_handle = cl->classid; if (!cl->level && cl->un.leaf.q) tcm->tcm_info = cl->un.leaf.q->handle; - rta = (struct rtattr*)b; + rta = (struct rtattr *)b; RTA_PUT(skb, TCA_OPTIONS, 0, NULL); - memset (&opt,0,sizeof(opt)); + memset(&opt, 0, sizeof(opt)); - opt.rate = cl->rate->rate; opt.buffer = cl->buffer; - opt.ceil = cl->ceil->rate; opt.cbuffer = cl->cbuffer; - opt.quantum = cl->un.leaf.quantum; opt.prio = cl->un.leaf.prio; - opt.level = cl->level; + opt.rate = cl->rate->rate; + opt.buffer = cl->buffer; + opt.ceil = cl->ceil->rate; + opt.cbuffer = cl->cbuffer; + opt.quantum = cl->un.leaf.quantum; + opt.prio = cl->un.leaf.prio; + opt.level = cl->level; RTA_PUT(skb, TCA_HTB_PARMS, sizeof(opt), &opt); rta->rta_len = skb->tail - b; - HTB_QUNLOCK(sch); + spin_unlock_bh(&sch->dev->queue_lock); return skb->len; rtattr_failure: - HTB_QUNLOCK(sch); + spin_unlock_bh(&sch->dev->queue_lock); skb_trim(skb, b - skb->data); return -1; } static int -htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) +htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { - struct htb_class *cl = (struct htb_class*)arg; + struct htb_class *cl = (struct htb_class *)arg; #ifdef HTB_RATECM - cl->rate_est.bps = cl->rate_bytes/(HTB_EWMAC*HTB_HSIZE); - cl->rate_est.pps = cl->rate_packets/(HTB_EWMAC*HTB_HSIZE); + cl->rate_est.bps = cl->rate_bytes / (HTB_EWMAC * HTB_HSIZE); + cl->rate_est.pps = cl->rate_packets / (HTB_EWMAC * HTB_HSIZE); #endif if (!cl->level && cl->un.leaf.q) @@ -1379,21 +1219,22 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, } static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old) + struct Qdisc **old) { - struct htb_class *cl = (struct htb_class*)arg; + struct htb_class *cl = (struct htb_class *)arg; if (cl && !cl->level) { - if (new == NULL && (new = qdisc_create_dflt(sch->dev, - &pfifo_qdisc_ops)) == NULL) - return -ENOBUFS; + if (new == NULL && (new = qdisc_create_dflt(sch->dev, + &pfifo_qdisc_ops)) + == NULL) + return -ENOBUFS; sch_tree_lock(sch); if ((*old = xchg(&cl->un.leaf.q, new)) != NULL) { if (cl->prio_activity) - htb_deactivate (qdisc_priv(sch),cl); + htb_deactivate(qdisc_priv(sch), cl); /* TODO: is it correct ? Why CBQ doesn't do it ? */ - sch->q.qlen -= (*old)->q.qlen; + sch->q.qlen -= (*old)->q.qlen; qdisc_reset(*old); } sch_tree_unlock(sch); @@ -1402,20 +1243,16 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, return -ENOENT; } -static struct Qdisc * htb_leaf(struct Qdisc *sch, unsigned long arg) +static struct Qdisc *htb_leaf(struct Qdisc *sch, unsigned long arg) { - struct htb_class *cl = (struct htb_class*)arg; + struct htb_class *cl = (struct htb_class *)arg; return (cl && !cl->level) ? cl->un.leaf.q : NULL; } static unsigned long htb_get(struct Qdisc *sch, u32 classid) { -#ifdef HTB_DEBUG - struct htb_sched *q = qdisc_priv(sch); -#endif - struct htb_class *cl = htb_find(classid,sch); - HTB_DBG(0,1,"htb_get clid=%X q=%p cl=%p ref=%d\n",classid,q,cl,cl?cl->refcnt:0); - if (cl) + struct htb_class *cl = htb_find(classid, sch); + if (cl) cl->refcnt++; return (unsigned long)cl; } @@ -1430,10 +1267,9 @@ static void htb_destroy_filters(struct tcf_proto **fl) } } -static void htb_destroy_class(struct Qdisc* sch,struct htb_class *cl) +static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { struct htb_sched *q = qdisc_priv(sch); - HTB_DBG(0,1,"htb_destrycls clid=%X ref=%d\n", cl?cl->classid:0,cl?cl->refcnt:0); if (!cl->level) { BUG_TRAP(cl->un.leaf.q); sch->q.qlen -= cl->un.leaf.q->q.qlen; @@ -1441,45 +1277,45 @@ static void htb_destroy_class(struct Qdisc* sch,struct htb_class *cl) } qdisc_put_rtab(cl->rate); qdisc_put_rtab(cl->ceil); - - htb_destroy_filters (&cl->filter_list); - - while (!list_empty(&cl->children)) - htb_destroy_class (sch,list_entry(cl->children.next, - struct htb_class,sibling)); + + htb_destroy_filters(&cl->filter_list); + + while (!list_empty(&cl->children)) + htb_destroy_class(sch, list_entry(cl->children.next, + struct htb_class, sibling)); /* note: this delete may happen twice (see htb_delete) */ - list_del(&cl->hlist); + if (!hlist_unhashed(&cl->hlist)) + hlist_del(&cl->hlist); list_del(&cl->sibling); - + if (cl->prio_activity) - htb_deactivate (q,cl); - + htb_deactivate(q, cl); + if (cl->cmode != HTB_CAN_SEND) - htb_safe_rb_erase(&cl->pq_node,q->wait_pq+cl->level); - + htb_safe_rb_erase(&cl->pq_node, q->wait_pq + cl->level); + kfree(cl); } /* always caled under BH & queue lock */ -static void htb_destroy(struct Qdisc* sch) +static void htb_destroy(struct Qdisc *sch) { struct htb_sched *q = qdisc_priv(sch); - HTB_DBG(0,1,"htb_destroy q=%p\n",q); - del_timer_sync (&q->timer); + del_timer_sync(&q->timer); #ifdef HTB_RATECM - del_timer_sync (&q->rttim); + del_timer_sync(&q->rttim); #endif /* This line used to be after htb_destroy_class call below and surprisingly it worked in 2.4. But it must precede it because filter need its target class alive to be able to call unbind_filter on it (without Oops). */ htb_destroy_filters(&q->filter_list); - - while (!list_empty(&q->root)) - htb_destroy_class (sch,list_entry(q->root.next, - struct htb_class,sibling)); + + while (!list_empty(&q->root)) + htb_destroy_class(sch, list_entry(q->root.next, + struct htb_class, sibling)); __skb_queue_purge(&q->direct_queue); } @@ -1487,24 +1323,25 @@ static void htb_destroy(struct Qdisc* sch) static int htb_delete(struct Qdisc *sch, unsigned long arg) { struct htb_sched *q = qdisc_priv(sch); - struct htb_class *cl = (struct htb_class*)arg; - HTB_DBG(0,1,"htb_delete q=%p cl=%X ref=%d\n",q,cl?cl->classid:0,cl?cl->refcnt:0); + struct htb_class *cl = (struct htb_class *)arg; // TODO: why don't allow to delete subtree ? references ? does // tc subsys quarantee us that in htb_destroy it holds no class // refs so that we can remove children safely there ? if (!list_empty(&cl->children) || cl->filter_cnt) return -EBUSY; - + sch_tree_lock(sch); - + /* delete from hash and active; remainder in destroy_class */ - list_del_init(&cl->hlist); + if (!hlist_unhashed(&cl->hlist)) + hlist_del(&cl->hlist); + if (cl->prio_activity) - htb_deactivate (q,cl); + htb_deactivate(q, cl); if (--cl->refcnt == 0) - htb_destroy_class(sch,cl); + htb_destroy_class(sch, cl); sch_tree_unlock(sch); return 0; @@ -1512,45 +1349,46 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) static void htb_put(struct Qdisc *sch, unsigned long arg) { -#ifdef HTB_DEBUG - struct htb_sched *q = qdisc_priv(sch); -#endif - struct htb_class *cl = (struct htb_class*)arg; - HTB_DBG(0,1,"htb_put q=%p cl=%X ref=%d\n",q,cl?cl->classid:0,cl?cl->refcnt:0); + struct htb_class *cl = (struct htb_class *)arg; if (--cl->refcnt == 0) - htb_destroy_class(sch,cl); + htb_destroy_class(sch, cl); } -static int htb_change_class(struct Qdisc *sch, u32 classid, - u32 parentid, struct rtattr **tca, unsigned long *arg) +static int htb_change_class(struct Qdisc *sch, u32 classid, + u32 parentid, struct rtattr **tca, + unsigned long *arg) { int err = -EINVAL; struct htb_sched *q = qdisc_priv(sch); - struct htb_class *cl = (struct htb_class*)*arg,*parent; - struct rtattr *opt = tca[TCA_OPTIONS-1]; + struct htb_class *cl = (struct htb_class *)*arg, *parent; + struct rtattr *opt = tca[TCA_OPTIONS - 1]; struct qdisc_rate_table *rtab = NULL, *ctab = NULL; struct rtattr *tb[TCA_HTB_RTAB]; struct tc_htb_opt *hopt; /* extract all subattrs from opt attr */ if (!opt || rtattr_parse_nested(tb, TCA_HTB_RTAB, opt) || - tb[TCA_HTB_PARMS-1] == NULL || - RTA_PAYLOAD(tb[TCA_HTB_PARMS-1]) < sizeof(*hopt)) + tb[TCA_HTB_PARMS - 1] == NULL || + RTA_PAYLOAD(tb[TCA_HTB_PARMS - 1]) < sizeof(*hopt)) goto failure; - - parent = parentid == TC_H_ROOT ? NULL : htb_find (parentid,sch); - hopt = RTA_DATA(tb[TCA_HTB_PARMS-1]); - HTB_DBG(0,1,"htb_chg cl=%p(%X), clid=%X, parid=%X, opt/prio=%d, rate=%u, buff=%d, quant=%d\n", cl,cl?cl->classid:0,classid,parentid,(int)hopt->prio,hopt->rate.rate,hopt->buffer,hopt->quantum); - rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB-1]); - ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB-1]); - if (!rtab || !ctab) goto failure; + parent = parentid == TC_H_ROOT ? NULL : htb_find(parentid, sch); + + hopt = RTA_DATA(tb[TCA_HTB_PARMS - 1]); + + rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB - 1]); + ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB - 1]); + if (!rtab || !ctab) + goto failure; - if (!cl) { /* new class */ + if (!cl) { /* new class */ struct Qdisc *new_q; + int prio; + /* check for valid classid */ - if (!classid || TC_H_MAJ(classid^sch->handle) || htb_find(classid,sch)) + if (!classid || TC_H_MAJ(classid ^ sch->handle) + || htb_find(classid, sch)) goto failure; /* check maximal depth */ @@ -1561,15 +1399,16 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, err = -ENOBUFS; if ((cl = kzalloc(sizeof(*cl), GFP_KERNEL)) == NULL) goto failure; - + cl->refcnt = 1; INIT_LIST_HEAD(&cl->sibling); - INIT_LIST_HEAD(&cl->hlist); + INIT_HLIST_NODE(&cl->hlist); INIT_LIST_HEAD(&cl->children); INIT_LIST_HEAD(&cl->un.leaf.drop_list); -#ifdef HTB_DEBUG - cl->magic = HTB_CMAGIC; -#endif + RB_CLEAR_NODE(&cl->pq_node); + + for (prio = 0; prio < TC_HTB_NUMPRIO; prio++) + RB_CLEAR_NODE(&cl->node[prio]); /* create leaf qdisc early because it uses kmalloc(GFP_KERNEL) so that can't be used inside of sch_tree_lock @@ -1579,53 +1418,53 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (parent && !parent->level) { /* turn parent into inner node */ sch->q.qlen -= parent->un.leaf.q->q.qlen; - qdisc_destroy (parent->un.leaf.q); - if (parent->prio_activity) - htb_deactivate (q,parent); + qdisc_destroy(parent->un.leaf.q); + if (parent->prio_activity) + htb_deactivate(q, parent); /* remove from evt list because of level change */ if (parent->cmode != HTB_CAN_SEND) { - htb_safe_rb_erase(&parent->pq_node,q->wait_pq /*+0*/); + htb_safe_rb_erase(&parent->pq_node, q->wait_pq); parent->cmode = HTB_CAN_SEND; } parent->level = (parent->parent ? parent->parent->level - : TC_HTB_MAXDEPTH) - 1; - memset (&parent->un.inner,0,sizeof(parent->un.inner)); + : TC_HTB_MAXDEPTH) - 1; + memset(&parent->un.inner, 0, sizeof(parent->un.inner)); } /* leaf (we) needs elementary qdisc */ cl->un.leaf.q = new_q ? new_q : &noop_qdisc; - cl->classid = classid; cl->parent = parent; + cl->classid = classid; + cl->parent = parent; /* set class to be in HTB_CAN_SEND state */ cl->tokens = hopt->buffer; cl->ctokens = hopt->cbuffer; - cl->mbuffer = PSCHED_JIFFIE2US(HZ*60); /* 1min */ + cl->mbuffer = PSCHED_JIFFIE2US(HZ * 60); /* 1min */ PSCHED_GET_TIME(cl->t_c); cl->cmode = HTB_CAN_SEND; /* attach to the hash list and parent's family */ - list_add_tail(&cl->hlist, q->hash+htb_hash(classid)); - list_add_tail(&cl->sibling, parent ? &parent->children : &q->root); -#ifdef HTB_DEBUG - { - int i; - for (i = 0; i < TC_HTB_NUMPRIO; i++) cl->node[i].rb_color = -1; - cl->pq_node.rb_color = -1; - } -#endif - } else sch_tree_lock(sch); + hlist_add_head(&cl->hlist, q->hash + htb_hash(classid)); + list_add_tail(&cl->sibling, + parent ? &parent->children : &q->root); + } else + sch_tree_lock(sch); /* it used to be a nasty bug here, we have to check that node - is really leaf before changing cl->un.leaf ! */ + is really leaf before changing cl->un.leaf ! */ if (!cl->level) { cl->un.leaf.quantum = rtab->rate.rate / q->rate2quantum; if (!hopt->quantum && cl->un.leaf.quantum < 1000) { - printk(KERN_WARNING "HTB: quantum of class %X is small. Consider r2q change.\n", cl->classid); + printk(KERN_WARNING + "HTB: quantum of class %X is small. Consider r2q change.\n", + cl->classid); cl->un.leaf.quantum = 1000; } if (!hopt->quantum && cl->un.leaf.quantum > 200000) { - printk(KERN_WARNING "HTB: quantum of class %X is big. Consider r2q change.\n", cl->classid); + printk(KERN_WARNING + "HTB: quantum of class %X is big. Consider r2q change.\n", + cl->classid); cl->un.leaf.quantum = 200000; } if (hopt->quantum) @@ -1636,16 +1475,22 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->buffer = hopt->buffer; cl->cbuffer = hopt->cbuffer; - if (cl->rate) qdisc_put_rtab(cl->rate); cl->rate = rtab; - if (cl->ceil) qdisc_put_rtab(cl->ceil); cl->ceil = ctab; + if (cl->rate) + qdisc_put_rtab(cl->rate); + cl->rate = rtab; + if (cl->ceil) + qdisc_put_rtab(cl->ceil); + cl->ceil = ctab; sch_tree_unlock(sch); *arg = (unsigned long)cl; return 0; failure: - if (rtab) qdisc_put_rtab(rtab); - if (ctab) qdisc_put_rtab(ctab); + if (rtab) + qdisc_put_rtab(rtab); + if (ctab) + qdisc_put_rtab(ctab); return err; } @@ -1654,28 +1499,28 @@ static struct tcf_proto **htb_find_tcf(struct Qdisc *sch, unsigned long arg) struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; struct tcf_proto **fl = cl ? &cl->filter_list : &q->filter_list; - HTB_DBG(0,2,"htb_tcf q=%p clid=%X fref=%d fl=%p\n",q,cl?cl->classid:0,cl?cl->filter_cnt:q->filter_cnt,*fl); + return fl; } static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent, - u32 classid) + u32 classid) { struct htb_sched *q = qdisc_priv(sch); - struct htb_class *cl = htb_find (classid,sch); - HTB_DBG(0,2,"htb_bind q=%p clid=%X cl=%p fref=%d\n",q,classid,cl,cl?cl->filter_cnt:q->filter_cnt); + struct htb_class *cl = htb_find(classid, sch); + /*if (cl && !cl->level) return 0; - The line above used to be there to prevent attaching filters to - leaves. But at least tc_index filter uses this just to get class - for other reasons so that we have to allow for it. - ---- - 19.6.2002 As Werner explained it is ok - bind filter is just - another way to "lock" the class - unlike "get" this lock can - be broken by class during destroy IIUC. + The line above used to be there to prevent attaching filters to + leaves. But at least tc_index filter uses this just to get class + for other reasons so that we have to allow for it. + ---- + 19.6.2002 As Werner explained it is ok - bind filter is just + another way to "lock" the class - unlike "get" this lock can + be broken by class during destroy IIUC. */ - if (cl) - cl->filter_cnt++; - else + if (cl) + cl->filter_cnt++; + else q->filter_cnt++; return (unsigned long)cl; } @@ -1684,10 +1529,10 @@ static void htb_unbind_filter(struct Qdisc *sch, unsigned long arg) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; - HTB_DBG(0,2,"htb_unbind q=%p cl=%p fref=%d\n",q,cl,cl?cl->filter_cnt:q->filter_cnt); - if (cl) - cl->filter_cnt--; - else + + if (cl) + cl->filter_cnt--; + else q->filter_cnt--; } @@ -1700,9 +1545,10 @@ static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg) return; for (i = 0; i < HTB_HSIZE; i++) { - struct list_head *p; - list_for_each (p,q->hash+i) { - struct htb_class *cl = list_entry(p,struct htb_class,hlist); + struct hlist_node *p; + struct htb_class *cl; + + hlist_for_each_entry(cl, p, q->hash + i, hlist) { if (arg->count < arg->skip) { arg->count++; continue; @@ -1750,12 +1596,13 @@ static struct Qdisc_ops htb_qdisc_ops = { static int __init htb_module_init(void) { - return register_qdisc(&htb_qdisc_ops); + return register_qdisc(&htb_qdisc_ops); } -static void __exit htb_module_exit(void) +static void __exit htb_module_exit(void) { - unregister_qdisc(&htb_qdisc_ops); + unregister_qdisc(&htb_qdisc_ops); } + module_init(htb_module_init) module_exit(htb_module_exit) MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a08ec4c7c55..45939bafbdf 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -192,8 +192,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) */ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) { if (!(skb = skb_unshare(skb, GFP_ATOMIC)) - || (skb->ip_summed == CHECKSUM_HW - && skb_checksum_help(skb, 0))) { + || (skb->ip_summed == CHECKSUM_PARTIAL + && skb_checksum_help(skb))) { sch->qstats.drops++; return NET_XMIT_DROP; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 42b66e74bbb..03f65de75d8 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -228,7 +228,7 @@ int sctp_rcv(struct sk_buff *skb) goto discard_release; nf_reset(skb); - if (sk_filter(sk, skb, 1)) + if (sk_filter(sk, skb)) goto discard_release; /* Create an SCTP packet structure. */ @@ -255,10 +255,13 @@ int sctp_rcv(struct sk_buff *skb) */ sctp_bh_lock_sock(sk); - if (sock_owned_by_user(sk)) + if (sock_owned_by_user(sk)) { + SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_BACKLOG); sctp_add_backlog(sk, skb); - else + } else { + SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_SOFTIRQ); sctp_inq_push(&chunk->rcvr->inqueue, chunk); + } sctp_bh_unlock_sock(sk); @@ -271,6 +274,7 @@ int sctp_rcv(struct sk_buff *skb) return 0; discard_it: + SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_DISCARDS); kfree_skb(skb); return 0; diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index cf0c767d43a..cf6deed7e84 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -87,7 +87,7 @@ void sctp_inq_free(struct sctp_inq *queue) /* Put a new packet in an SCTP inqueue. * We assume that packet->sctp_hdr is set and in host byte order. */ -void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *packet) +void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) { /* Directly call the packet handling routine. */ @@ -96,7 +96,7 @@ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *packet) * Eventually, we should clean up inqueue to not rely * on the BH related data structures. */ - list_add_tail(&packet->list, &q->in_chunk_list); + list_add_tail(&chunk->list, &q->in_chunk_list); q->immediate.func(q->immediate.data); } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 99c0cefc04e..249e5033c1a 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -78,7 +78,6 @@ #include <asm/uaccess.h> -extern int sctp_inetaddr_event(struct notifier_block *, unsigned long, void *); static struct notifier_block sctp_inet6addr_notifier = { .notifier_call = sctp_inetaddr_event, }; @@ -322,9 +321,9 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, struct inet6_ifaddr *ifp; struct sctp_sockaddr_entry *addr; - read_lock(&addrconf_lock); + rcu_read_lock(); if ((in6_dev = __in6_dev_get(dev)) == NULL) { - read_unlock(&addrconf_lock); + rcu_read_unlock(); return; } @@ -343,7 +342,7 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, } read_unlock(&in6_dev->lock); - read_unlock(&addrconf_lock); + rcu_read_unlock(); } /* Initialize a sockaddr_storage from in incoming skb. */ diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 30b710c54e6..37074a39ecb 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -467,6 +467,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, switch(reason) { case SCTP_RTXR_T3_RTX: + SCTP_INC_STATS(SCTP_MIB_T3_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_T3_RTX); /* Update the retran path if the T3-rtx timer has expired for * the current retran path. @@ -475,12 +476,15 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, sctp_assoc_update_retran_path(transport->asoc); break; case SCTP_RTXR_FAST_RTX: + SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); fast_retransmit = 1; break; case SCTP_RTXR_PMTUD: - default: + SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS); break; + default: + BUG(); } sctp_retransmit_mark(q, transport, fast_retransmit); diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 5b3b0e0ae7e..a356d8d310a 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -57,6 +57,21 @@ static struct snmp_mib sctp_snmp_list[] = { SNMP_MIB_ITEM("SctpReasmUsrMsgs", SCTP_MIB_REASMUSRMSGS), SNMP_MIB_ITEM("SctpOutSCTPPacks", SCTP_MIB_OUTSCTPPACKS), SNMP_MIB_ITEM("SctpInSCTPPacks", SCTP_MIB_INSCTPPACKS), + SNMP_MIB_ITEM("SctpT1InitExpireds", SCTP_MIB_T1_INIT_EXPIREDS), + SNMP_MIB_ITEM("SctpT1CookieExpireds", SCTP_MIB_T1_COOKIE_EXPIREDS), + SNMP_MIB_ITEM("SctpT2ShutdownExpireds", SCTP_MIB_T2_SHUTDOWN_EXPIREDS), + SNMP_MIB_ITEM("SctpT3RtxExpireds", SCTP_MIB_T3_RTX_EXPIREDS), + SNMP_MIB_ITEM("SctpT4RtoExpireds", SCTP_MIB_T4_RTO_EXPIREDS), + SNMP_MIB_ITEM("SctpT5ShutdownGuardExpireds", SCTP_MIB_T5_SHUTDOWN_GUARD_EXPIREDS), + SNMP_MIB_ITEM("SctpDelaySackExpireds", SCTP_MIB_DELAY_SACK_EXPIREDS), + SNMP_MIB_ITEM("SctpAutocloseExpireds", SCTP_MIB_AUTOCLOSE_EXPIREDS), + SNMP_MIB_ITEM("SctpT3Retransmits", SCTP_MIB_T3_RETRANSMITS), + SNMP_MIB_ITEM("SctpPmtudRetransmits", SCTP_MIB_PMTUD_RETRANSMITS), + SNMP_MIB_ITEM("SctpFastRetransmits", SCTP_MIB_FAST_RETRANSMITS), + SNMP_MIB_ITEM("SctpInPktSoftirq", SCTP_MIB_IN_PKT_SOFTIRQ), + SNMP_MIB_ITEM("SctpInPktBacklog", SCTP_MIB_IN_PKT_BACKLOG), + SNMP_MIB_ITEM("SctpInPktDiscards", SCTP_MIB_IN_PKT_DISCARDS), + SNMP_MIB_ITEM("SctpInDataChunkDiscards", SCTP_MIB_IN_DATA_CHUNK_DISCARDS), SNMP_MIB_SENTINEL }; @@ -328,8 +343,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) "%8p %8p %-3d %-3d %-2d %-4d %4d %8d %8d %7d %5lu %-5d %5d ", assoc, sk, sctp_sk(sk)->type, sk->sk_state, assoc->state, hash, assoc->assoc_id, - (sk->sk_rcvbuf - assoc->rwnd), assoc->sndbuf_used, + (sk->sk_rcvbuf - assoc->rwnd), sock_i_uid(sk), sock_i_ino(sk), epb->bind_addr.port, assoc->peer.port); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 1ab03a27a76..fac7674438a 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -61,7 +61,7 @@ #include <net/inet_ecn.h> /* Global data structures. */ -struct sctp_globals sctp_globals; +struct sctp_globals sctp_globals __read_mostly; struct proc_dir_entry *proc_net_sctp; DEFINE_SNMP_STAT(struct sctp_mib, sctp_statistics) __read_mostly; @@ -82,13 +82,6 @@ static struct sctp_af *sctp_af_v6_specific; kmem_cache_t *sctp_chunk_cachep __read_mostly; kmem_cache_t *sctp_bucket_cachep __read_mostly; -extern int sctp_snmp_proc_init(void); -extern int sctp_snmp_proc_exit(void); -extern int sctp_eps_proc_init(void); -extern int sctp_eps_proc_exit(void); -extern int sctp_assocs_proc_init(void); -extern int sctp_assocs_proc_exit(void); - /* Return the address of the control sock. */ struct sock *sctp_get_ctl_sock(void) { @@ -1049,7 +1042,7 @@ SCTP_STATIC __init int sctp_init(void) sctp_rto_beta = SCTP_RTO_BETA; /* Valid.Cookie.Life - 60 seconds */ - sctp_valid_cookie_life = 60 * HZ; + sctp_valid_cookie_life = SCTP_DEFAULT_COOKIE_LIFE; /* Whether Cookie Preservative is enabled(1) or not(0) */ sctp_cookie_preserve_enable = 1; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 5b5ae795832..1c42fe983a5 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -187,10 +187,9 @@ sctp_disposition_t sctp_sf_do_4_C(const struct sctp_endpoint *ep, */ ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_SHUTDOWN_COMP, 0, 0, 0, GFP_ATOMIC); - if (!ev) - goto nomem; - - sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); + if (ev) + sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, + SCTP_ULPEVENT(ev)); /* Upon reception of the SHUTDOWN COMPLETE chunk the endpoint * will verify that it is in SHUTDOWN-ACK-SENT state, if it is @@ -215,9 +214,6 @@ sctp_disposition_t sctp_sf_do_4_C(const struct sctp_endpoint *ep, sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); return SCTP_DISPOSITION_DELETE_TCB; - -nomem: - return SCTP_DISPOSITION_NOMEM; } /* @@ -347,8 +343,6 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, GFP_ATOMIC)) goto nomem_init; - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); - /* B) "Z" shall respond immediately with an INIT ACK chunk. */ /* If there are errors need to be reported for unknown parameters, @@ -360,11 +354,11 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, sizeof(sctp_chunkhdr_t); if (sctp_assoc_set_bind_addr_from_ep(new_asoc, GFP_ATOMIC) < 0) - goto nomem_ack; + goto nomem_init; repl = sctp_make_init_ack(new_asoc, chunk, GFP_ATOMIC, len); if (!repl) - goto nomem_ack; + goto nomem_init; /* If there are errors need to be reported for unknown parameters, * include them in the outgoing INIT ACK as "Unrecognized parameter" @@ -388,6 +382,8 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, sctp_chunk_free(err_chunk); } + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); /* @@ -400,12 +396,11 @@ sctp_disposition_t sctp_sf_do_5_1B_init(const struct sctp_endpoint *ep, return SCTP_DISPOSITION_DELETE_TCB; -nomem_ack: - if (err_chunk) - sctp_chunk_free(err_chunk); nomem_init: sctp_association_free(new_asoc); nomem: + if (err_chunk) + sctp_chunk_free(err_chunk); return SCTP_DISPOSITION_NOMEM; } @@ -600,7 +595,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep, struct sctp_association *new_asoc; sctp_init_chunk_t *peer_init; struct sctp_chunk *repl; - struct sctp_ulpevent *ev; + struct sctp_ulpevent *ev, *ai_ev = NULL; int error = 0; struct sctp_chunk *err_chk_p; @@ -659,20 +654,10 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep, }; } - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, - SCTP_STATE(SCTP_STATE_ESTABLISHED)); - SCTP_INC_STATS(SCTP_MIB_CURRESTAB); - SCTP_INC_STATS(SCTP_MIB_PASSIVEESTABS); - sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL()); - if (new_asoc->autoclose) - sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, - SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); - - sctp_add_cmd_sf(commands, SCTP_CMD_TRANSMIT, SCTP_NULL()); - - /* Re-build the bind address for the association is done in + /* Delay state machine commands until later. + * + * Re-build the bind address for the association is done in * the sctp_unpack_cookie() already. */ /* This is a brand-new association, so these are not yet side @@ -687,9 +672,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep, repl = sctp_make_cookie_ack(new_asoc, chunk); if (!repl) - goto nomem_repl; - - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + goto nomem_init; /* RFC 2960 5.1 Normal Establishment of an Association * @@ -704,28 +687,53 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(const struct sctp_endpoint *ep, if (!ev) goto nomem_ev; - sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); - /* Sockets API Draft Section 5.3.1.6 * When a peer sends a Adaption Layer Indication parameter , SCTP * delivers this notification to inform the application that of the * peers requested adaption layer. */ if (new_asoc->peer.adaption_ind) { - ev = sctp_ulpevent_make_adaption_indication(new_asoc, + ai_ev = sctp_ulpevent_make_adaption_indication(new_asoc, GFP_ATOMIC); - if (!ev) - goto nomem_ev; + if (!ai_ev) + goto nomem_aiev; + } + + /* Add all the state machine commands now since we've created + * everything. This way we don't introduce memory corruptions + * during side-effect processing and correclty count established + * associations. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, + SCTP_STATE(SCTP_STATE_ESTABLISHED)); + SCTP_INC_STATS(SCTP_MIB_CURRESTAB); + SCTP_INC_STATS(SCTP_MIB_PASSIVEESTABS); + sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL()); + + if (new_asoc->autoclose) + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, + SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); + sctp_add_cmd_sf(commands, SCTP_CMD_TRANSMIT, SCTP_NULL()); + + /* This will send the COOKIE ACK */ + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); + + /* Queue the ASSOC_CHANGE event */ + sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); + + /* Send up the Adaptation Layer Indication event */ + if (ai_ev) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, - SCTP_ULPEVENT(ev)); - } + SCTP_ULPEVENT(ai_ev)); return SCTP_DISPOSITION_CONSUME; +nomem_aiev: + sctp_ulpevent_free(ev); nomem_ev: sctp_chunk_free(repl); -nomem_repl: nomem_init: sctp_association_free(new_asoc); nomem: @@ -1360,10 +1368,8 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( if (!sctp_process_init(new_asoc, chunk->chunk_hdr->type, sctp_source(chunk), (sctp_init_chunk_t *)chunk->chunk_hdr, - GFP_ATOMIC)) { - retval = SCTP_DISPOSITION_NOMEM; - goto nomem_init; - } + GFP_ATOMIC)) + goto nomem; /* Make sure no new addresses are being added during the * restart. Do not do this check for COOKIE-WAIT state, @@ -1374,7 +1380,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) { retval = SCTP_DISPOSITION_CONSUME; - goto cleanup_asoc; + goto nomem_retval; } } @@ -1430,17 +1436,17 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); retval = SCTP_DISPOSITION_CONSUME; + return retval; + +nomem: + retval = SCTP_DISPOSITION_NOMEM; +nomem_retval: + if (new_asoc) + sctp_association_free(new_asoc); cleanup: if (err_chunk) sctp_chunk_free(err_chunk); return retval; -nomem: - retval = SCTP_DISPOSITION_NOMEM; - goto cleanup; -nomem_init: -cleanup_asoc: - sctp_association_free(new_asoc); - goto cleanup; } /* @@ -1611,15 +1617,10 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep, */ sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_OUTQUEUE, SCTP_NULL()); - /* Update the content of current association. */ - sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); - repl = sctp_make_cookie_ack(new_asoc, chunk); if (!repl) goto nomem; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); - /* Report association restart to upper layer. */ ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_RESTART, 0, new_asoc->c.sinit_num_ostreams, @@ -1628,6 +1629,9 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep, if (!ev) goto nomem_ev; + /* Update the content of current association. */ + sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); return SCTP_DISPOSITION_CONSUME; @@ -1751,7 +1755,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_d(const struct sctp_endpoint *ep, sctp_cmd_seq_t *commands, struct sctp_association *new_asoc) { - struct sctp_ulpevent *ev = NULL; + struct sctp_ulpevent *ev = NULL, *ai_ev = NULL; struct sctp_chunk *repl; /* Clarification from Implementor's Guide: @@ -1778,29 +1782,25 @@ static sctp_disposition_t sctp_sf_do_dupcook_d(const struct sctp_endpoint *ep, * SCTP user upon reception of a valid COOKIE * ECHO chunk. */ - ev = sctp_ulpevent_make_assoc_change(new_asoc, 0, + ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_UP, 0, - new_asoc->c.sinit_num_ostreams, - new_asoc->c.sinit_max_instreams, + asoc->c.sinit_num_ostreams, + asoc->c.sinit_max_instreams, GFP_ATOMIC); if (!ev) goto nomem; - sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, - SCTP_ULPEVENT(ev)); /* Sockets API Draft Section 5.3.1.6 * When a peer sends a Adaption Layer Indication parameter, * SCTP delivers this notification to inform the application * that of the peers requested adaption layer. */ - if (new_asoc->peer.adaption_ind) { - ev = sctp_ulpevent_make_adaption_indication(new_asoc, + if (asoc->peer.adaption_ind) { + ai_ev = sctp_ulpevent_make_adaption_indication(asoc, GFP_ATOMIC); - if (!ev) + if (!ai_ev) goto nomem; - sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, - SCTP_ULPEVENT(ev)); } } sctp_add_cmd_sf(commands, SCTP_CMD_TRANSMIT, SCTP_NULL()); @@ -1809,12 +1809,21 @@ static sctp_disposition_t sctp_sf_do_dupcook_d(const struct sctp_endpoint *ep, if (!repl) goto nomem; + if (ev) + sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, + SCTP_ULPEVENT(ev)); + if (ai_ev) + sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, + SCTP_ULPEVENT(ai_ev)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); sctp_add_cmd_sf(commands, SCTP_CMD_TRANSMIT, SCTP_NULL()); return SCTP_DISPOSITION_CONSUME; nomem: + if (ai_ev) + sctp_ulpevent_free(ai_ev); if (ev) sctp_ulpevent_free(ev); return SCTP_DISPOSITION_NOMEM; @@ -2663,9 +2672,11 @@ sctp_disposition_t sctp_sf_eat_data_6_2(const struct sctp_endpoint *ep, break; case SCTP_IERROR_HIGH_TSN: case SCTP_IERROR_BAD_STREAM: + SCTP_INC_STATS(SCTP_MIB_IN_DATA_CHUNK_DISCARDS); goto discard_noforce; case SCTP_IERROR_DUP_TSN: case SCTP_IERROR_IGNORE_TSN: + SCTP_INC_STATS(SCTP_MIB_IN_DATA_CHUNK_DISCARDS); goto discard_force; case SCTP_IERROR_NO_DATA: goto consume; @@ -3017,7 +3028,6 @@ sctp_disposition_t sctp_sf_do_9_2_final(const struct sctp_endpoint *ep, if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) return sctp_sf_violation_chunklen(ep, asoc, type, arg, commands); - /* 10.2 H) SHUTDOWN COMPLETE notification * * When SCTP completes the shutdown procedures (section 9.2) this @@ -3028,6 +3038,14 @@ sctp_disposition_t sctp_sf_do_9_2_final(const struct sctp_endpoint *ep, if (!ev) goto nomem; + /* ...send a SHUTDOWN COMPLETE chunk to its peer, */ + reply = sctp_make_shutdown_complete(asoc, chunk); + if (!reply) + goto nomem_chunk; + + /* Do all the commands now (after allocation), so that we + * have consistent state if memory allocation failes + */ sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); /* Upon the receipt of the SHUTDOWN ACK, the SHUTDOWN sender shall @@ -3039,11 +3057,6 @@ sctp_disposition_t sctp_sf_do_9_2_final(const struct sctp_endpoint *ep, sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); - /* ...send a SHUTDOWN COMPLETE chunk to its peer, */ - reply = sctp_make_shutdown_complete(asoc, chunk); - if (!reply) - goto nomem; - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); SCTP_INC_STATS(SCTP_MIB_SHUTDOWNS); @@ -3054,6 +3067,8 @@ sctp_disposition_t sctp_sf_do_9_2_final(const struct sctp_endpoint *ep, sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); return SCTP_DISPOSITION_DELETE_TCB; +nomem_chunk: + sctp_ulpevent_free(ev); nomem: return SCTP_DISPOSITION_NOMEM; } @@ -3652,6 +3667,7 @@ sctp_disposition_t sctp_sf_pdiscard(const struct sctp_endpoint *ep, void *arg, sctp_cmd_seq_t *commands) { + SCTP_INC_STATS(SCTP_MIB_IN_PKT_DISCARDS); sctp_add_cmd_sf(commands, SCTP_CMD_DISCARD_PACKET, SCTP_NULL()); return SCTP_DISPOSITION_CONSUME; @@ -4548,6 +4564,8 @@ sctp_disposition_t sctp_sf_do_6_3_3_rtx(const struct sctp_endpoint *ep, { struct sctp_transport *transport = arg; + SCTP_INC_STATS(SCTP_MIB_T3_RTX_EXPIREDS); + if (asoc->overall_error_count >= asoc->max_retrans) { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); @@ -4616,6 +4634,7 @@ sctp_disposition_t sctp_sf_do_6_2_sack(const struct sctp_endpoint *ep, void *arg, sctp_cmd_seq_t *commands) { + SCTP_INC_STATS(SCTP_MIB_DELAY_SACK_EXPIREDS); sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_FORCE()); return SCTP_DISPOSITION_CONSUME; } @@ -4650,6 +4669,7 @@ sctp_disposition_t sctp_sf_t1_init_timer_expire(const struct sctp_endpoint *ep, int attempts = asoc->init_err_counter + 1; SCTP_DEBUG_PRINTK("Timer T1 expired (INIT).\n"); + SCTP_INC_STATS(SCTP_MIB_T1_INIT_EXPIREDS); if (attempts <= asoc->max_init_attempts) { bp = (struct sctp_bind_addr *) &asoc->base.bind_addr; @@ -4709,6 +4729,7 @@ sctp_disposition_t sctp_sf_t1_cookie_timer_expire(const struct sctp_endpoint *ep int attempts = asoc->init_err_counter + 1; SCTP_DEBUG_PRINTK("Timer T1 expired (COOKIE-ECHO).\n"); + SCTP_INC_STATS(SCTP_MIB_T1_COOKIE_EXPIREDS); if (attempts <= asoc->max_init_attempts) { repl = sctp_make_cookie_echo(asoc, NULL); @@ -4753,6 +4774,8 @@ sctp_disposition_t sctp_sf_t2_timer_expire(const struct sctp_endpoint *ep, struct sctp_chunk *reply = NULL; SCTP_DEBUG_PRINTK("Timer T2 expired.\n"); + SCTP_INC_STATS(SCTP_MIB_T2_SHUTDOWN_EXPIREDS); + if (asoc->overall_error_count >= asoc->max_retrans) { sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ETIMEDOUT)); @@ -4814,6 +4837,8 @@ sctp_disposition_t sctp_sf_t4_timer_expire( struct sctp_chunk *chunk = asoc->addip_last_asconf; struct sctp_transport *transport = chunk->transport; + SCTP_INC_STATS(SCTP_MIB_T4_RTO_EXPIREDS); + /* ADDIP 4.1 B1) Increment the error counters and perform path failure * detection on the appropriate destination address as defined in * RFC2960 [5] section 8.1 and 8.2. @@ -4880,6 +4905,7 @@ sctp_disposition_t sctp_sf_t5_timer_expire(const struct sctp_endpoint *ep, struct sctp_chunk *reply = NULL; SCTP_DEBUG_PRINTK("Timer T5 expired.\n"); + SCTP_INC_STATS(SCTP_MIB_T5_SHUTDOWN_GUARD_EXPIREDS); reply = sctp_make_abort(asoc, NULL, 0); if (!reply) @@ -4910,6 +4936,8 @@ sctp_disposition_t sctp_sf_autoclose_timer_expire( { int disposition; + SCTP_INC_STATS(SCTP_MIB_AUTOCLOSE_EXPIREDS); + /* From 9.2 Shutdown of an Association * Upon receipt of the SHUTDOWN primitive from its upper * layer, the endpoint enters SHUTDOWN-PENDING state and diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 85caf796388..79c3e072cf2 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2081,13 +2081,13 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, * SPP_SACKDELAY_ENABLE, setting both will have undefined * results. */ -int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, - struct sctp_transport *trans, - struct sctp_association *asoc, - struct sctp_sock *sp, - int hb_change, - int pmtud_change, - int sackdelay_change) +static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, + struct sctp_transport *trans, + struct sctp_association *asoc, + struct sctp_sock *sp, + int hb_change, + int pmtud_change, + int sackdelay_change) { int error; @@ -2970,7 +2970,7 @@ SCTP_STATIC struct sock *sctp_accept(struct sock *sk, int flags, int *err) goto out; } - timeo = sock_rcvtimeo(sk, sk->sk_socket->file->f_flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); error = sctp_wait_for_accept(sk, timeo); if (error) @@ -3045,14 +3045,14 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) sp->initmsg.sinit_num_ostreams = sctp_max_outstreams; sp->initmsg.sinit_max_instreams = sctp_max_instreams; sp->initmsg.sinit_max_attempts = sctp_max_retrans_init; - sp->initmsg.sinit_max_init_timeo = jiffies_to_msecs(sctp_rto_max); + sp->initmsg.sinit_max_init_timeo = sctp_rto_max; /* Initialize default RTO related parameters. These parameters can * be modified for with the SCTP_RTOINFO socket option. */ - sp->rtoinfo.srto_initial = jiffies_to_msecs(sctp_rto_initial); - sp->rtoinfo.srto_max = jiffies_to_msecs(sctp_rto_max); - sp->rtoinfo.srto_min = jiffies_to_msecs(sctp_rto_min); + sp->rtoinfo.srto_initial = sctp_rto_initial; + sp->rtoinfo.srto_max = sctp_rto_max; + sp->rtoinfo.srto_min = sctp_rto_min; /* Initialize default association related parameters. These parameters * can be modified with the SCTP_ASSOCINFO socket option. @@ -3061,8 +3061,7 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) sp->assocparams.sasoc_number_peer_destinations = 0; sp->assocparams.sasoc_peer_rwnd = 0; sp->assocparams.sasoc_local_rwnd = 0; - sp->assocparams.sasoc_cookie_life = - jiffies_to_msecs(sctp_valid_cookie_life); + sp->assocparams.sasoc_cookie_life = sctp_valid_cookie_life; /* Initialize default event subscriptions. By default, all the * options are off. @@ -3072,10 +3071,10 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) /* Default Peer Address Parameters. These defaults can * be modified via SCTP_PEER_ADDR_PARAMS */ - sp->hbinterval = jiffies_to_msecs(sctp_hb_interval); + sp->hbinterval = sctp_hb_interval; sp->pathmaxrxt = sctp_max_retrans_path; sp->pathmtu = 0; // allow default discovery - sp->sackdelay = jiffies_to_msecs(sctp_sack_timeout); + sp->sackdelay = sctp_sack_timeout; sp->param_flags = SPP_HB_ENABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; @@ -5619,6 +5618,8 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, /* Copy the bind_addr list from the original endpoint to the new * endpoint so that we can handle restarts properly */ + if (PF_INET6 == assoc->base.sk->sk_family) + flags = SCTP_ADDR6_ALLOWED; if (assoc->peer.ipv4_address) flags |= SCTP_ADDR4_PEERSUPP; if (assoc->peer.ipv6_address) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index dc6f3ff3235..633cd178654 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -45,9 +45,10 @@ #include <net/sctp/sctp.h> #include <linux/sysctl.h> -static ctl_handler sctp_sysctl_jiffies_ms; -static long rto_timer_min = 1; -static long rto_timer_max = 86400000; /* One day */ +static int zero = 0; +static int one = 1; +static int timer_max = 86400000; /* ms in one day */ +static int int_max = INT_MAX; static long sack_timer_min = 1; static long sack_timer_max = 500; @@ -56,45 +57,45 @@ static ctl_table sctp_table[] = { .ctl_name = NET_SCTP_RTO_INITIAL, .procname = "rto_initial", .data = &sctp_rto_initial, - .maxlen = sizeof(long), + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, - .strategy = &sctp_sysctl_jiffies_ms, - .extra1 = &rto_timer_min, - .extra2 = &rto_timer_max + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &timer_max }, { .ctl_name = NET_SCTP_RTO_MIN, .procname = "rto_min", .data = &sctp_rto_min, - .maxlen = sizeof(long), + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, - .strategy = &sctp_sysctl_jiffies_ms, - .extra1 = &rto_timer_min, - .extra2 = &rto_timer_max + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &timer_max }, { .ctl_name = NET_SCTP_RTO_MAX, .procname = "rto_max", .data = &sctp_rto_max, - .maxlen = sizeof(long), + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, - .strategy = &sctp_sysctl_jiffies_ms, - .extra1 = &rto_timer_min, - .extra2 = &rto_timer_max + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &timer_max }, { .ctl_name = NET_SCTP_VALID_COOKIE_LIFE, .procname = "valid_cookie_life", .data = &sctp_valid_cookie_life, - .maxlen = sizeof(long), + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, - .strategy = &sctp_sysctl_jiffies_ms, - .extra1 = &rto_timer_min, - .extra2 = &rto_timer_max + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &timer_max }, { .ctl_name = NET_SCTP_MAX_BURST, @@ -102,7 +103,10 @@ static ctl_table sctp_table[] = { .data = &sctp_max_burst, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &int_max }, { .ctl_name = NET_SCTP_ASSOCIATION_MAX_RETRANS, @@ -110,7 +114,10 @@ static ctl_table sctp_table[] = { .data = &sctp_max_retrans_association, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &int_max }, { .ctl_name = NET_SCTP_SNDBUF_POLICY, @@ -118,7 +125,8 @@ static ctl_table sctp_table[] = { .data = &sctp_sndbuf_policy, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec }, { .ctl_name = NET_SCTP_RCVBUF_POLICY, @@ -126,7 +134,8 @@ static ctl_table sctp_table[] = { .data = &sctp_rcvbuf_policy, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec }, { .ctl_name = NET_SCTP_PATH_MAX_RETRANS, @@ -134,7 +143,10 @@ static ctl_table sctp_table[] = { .data = &sctp_max_retrans_path, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &int_max }, { .ctl_name = NET_SCTP_MAX_INIT_RETRANSMITS, @@ -142,18 +154,21 @@ static ctl_table sctp_table[] = { .data = &sctp_max_retrans_init, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &int_max }, { .ctl_name = NET_SCTP_HB_INTERVAL, .procname = "hb_interval", .data = &sctp_hb_interval, - .maxlen = sizeof(long), + .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, - .strategy = &sctp_sysctl_jiffies_ms, - .extra1 = &rto_timer_min, - .extra2 = &rto_timer_max + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &timer_max }, { .ctl_name = NET_SCTP_PRESERVE_ENABLE, @@ -161,23 +176,26 @@ static ctl_table sctp_table[] = { .data = &sctp_cookie_preserve_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec }, { .ctl_name = NET_SCTP_RTO_ALPHA, .procname = "rto_alpha_exp_divisor", .data = &sctp_rto_alpha, .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec + .mode = 0444, + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec }, { .ctl_name = NET_SCTP_RTO_BETA, .procname = "rto_beta_exp_divisor", .data = &sctp_rto_beta, .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec + .mode = 0444, + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec }, { .ctl_name = NET_SCTP_ADDIP_ENABLE, @@ -185,7 +203,8 @@ static ctl_table sctp_table[] = { .data = &sctp_addip_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec }, { .ctl_name = NET_SCTP_PRSCTP_ENABLE, @@ -193,7 +212,8 @@ static ctl_table sctp_table[] = { .data = &sctp_prsctp_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec, + .strategy = &sysctl_intvec }, { .ctl_name = NET_SCTP_SACK_TIMEOUT, @@ -201,8 +221,8 @@ static ctl_table sctp_table[] = { .data = &sctp_sack_timeout, .maxlen = sizeof(long), .mode = 0644, - .proc_handler = &proc_doulongvec_ms_jiffies_minmax, - .strategy = &sctp_sysctl_jiffies_ms, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, .extra1 = &sack_timer_min, .extra2 = &sack_timer_max, }, @@ -242,37 +262,3 @@ void sctp_sysctl_unregister(void) { unregister_sysctl_table(sctp_sysctl_header); } - -/* Strategy function to convert jiffies to milliseconds. */ -static int sctp_sysctl_jiffies_ms(ctl_table *table, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, void **context) { - - if (oldval) { - size_t olen; - - if (oldlenp) { - if (get_user(olen, oldlenp)) - return -EFAULT; - - if (olen != sizeof (int)) - return -EINVAL; - } - if (put_user((*(int *)(table->data) * 1000) / HZ, - (int __user *)oldval) || - (oldlenp && put_user(sizeof (int), oldlenp))) - return -EFAULT; - } - if (newval && newlen) { - int new; - - if (newlen != sizeof (int)) - return -EINVAL; - - if (get_user(new, (int __user *)newval)) - return -EFAULT; - - *(int *)(table->data) = (new * HZ) / 1000; - } - return 1; -} diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 2763aa93de1..3e5936a5f67 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -75,7 +75,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, * parameter 'RTO.Initial'. */ peer->rtt = 0; - peer->rto = sctp_rto_initial; + peer->rto = msecs_to_jiffies(sctp_rto_initial); peer->rttvar = 0; peer->srtt = 0; peer->rto_pending = 0; diff --git a/net/socket.c b/net/socket.c index 6d261bf206f..1bc4167e0da 100644 --- a/net/socket.c +++ b/net/socket.c @@ -42,7 +42,7 @@ * Andi Kleen : Some small cleanups, optimizations, * and fixed a copy_from_user() bug. * Tigran Aivazian : sys_send(args) calls sys_sendto(args, NULL, 0) - * Tigran Aivazian : Made listen(2) backlog sanity checks + * Tigran Aivazian : Made listen(2) backlog sanity checks * protocol-independent * * @@ -53,17 +53,17 @@ * * * This module is effectively the top level interface to the BSD socket - * paradigm. + * paradigm. * * Based upon Swansea University Computer Society NET3.039 */ #include <linux/mm.h> -#include <linux/smp_lock.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/net.h> #include <linux/interrupt.h> +#include <linux/rcupdate.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -96,25 +96,24 @@ static int sock_no_open(struct inode *irrelevant, struct file *dontcare); static ssize_t sock_aio_read(struct kiocb *iocb, char __user *buf, - size_t size, loff_t pos); + size_t size, loff_t pos); static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *buf, - size_t size, loff_t pos); -static int sock_mmap(struct file *file, struct vm_area_struct * vma); + size_t size, loff_t pos); +static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); static unsigned int sock_poll(struct file *file, struct poll_table_struct *wait); -static long sock_ioctl(struct file *file, - unsigned int cmd, unsigned long arg); +static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT static long compat_sock_ioctl(struct file *file, - unsigned int cmd, unsigned long arg); + unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); static ssize_t sock_readv(struct file *file, const struct iovec *vector, unsigned long count, loff_t *ppos); static ssize_t sock_writev(struct file *file, const struct iovec *vector, - unsigned long count, loff_t *ppos); + unsigned long count, loff_t *ppos); static ssize_t sock_sendpage(struct file *file, struct page *page, int offset, size_t size, loff_t *ppos, int more); @@ -147,52 +146,8 @@ static struct file_operations socket_file_ops = { * The protocol list. Each protocol is registered in here. */ -static struct net_proto_family *net_families[NPROTO]; - -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) -static atomic_t net_family_lockct = ATOMIC_INIT(0); static DEFINE_SPINLOCK(net_family_lock); - -/* The strategy is: modifications net_family vector are short, do not - sleep and veeery rare, but read access should be free of any exclusive - locks. - */ - -static void net_family_write_lock(void) -{ - spin_lock(&net_family_lock); - while (atomic_read(&net_family_lockct) != 0) { - spin_unlock(&net_family_lock); - - yield(); - - spin_lock(&net_family_lock); - } -} - -static __inline__ void net_family_write_unlock(void) -{ - spin_unlock(&net_family_lock); -} - -static __inline__ void net_family_read_lock(void) -{ - atomic_inc(&net_family_lockct); - spin_unlock_wait(&net_family_lock); -} - -static __inline__ void net_family_read_unlock(void) -{ - atomic_dec(&net_family_lockct); -} - -#else -#define net_family_write_lock() do { } while(0) -#define net_family_write_unlock() do { } while(0) -#define net_family_read_lock() do { } while(0) -#define net_family_read_unlock() do { } while(0) -#endif - +static const struct net_proto_family *net_families[NPROTO] __read_mostly; /* * Statistics counters of the socket lists @@ -201,19 +156,20 @@ static __inline__ void net_family_read_unlock(void) static DEFINE_PER_CPU(int, sockets_in_use) = 0; /* - * Support routines. Move socket addresses back and forth across the kernel/user - * divide and look after the messy bits. + * Support routines. + * Move socket addresses back and forth across the kernel/user + * divide and look after the messy bits. */ -#define MAX_SOCK_ADDR 128 /* 108 for Unix domain - +#define MAX_SOCK_ADDR 128 /* 108 for Unix domain - 16 for IP, 16 for IPX, 24 for IPv6, - about 80 for AX.25 + about 80 for AX.25 must be at least one bigger than the AF_UNIX size (see net/unix/af_unix.c - :unix_mkname()). + :unix_mkname()). */ - + /** * move_addr_to_kernel - copy a socket address into kernel space * @uaddr: Address in user space @@ -227,11 +183,11 @@ static DEFINE_PER_CPU(int, sockets_in_use) = 0; int move_addr_to_kernel(void __user *uaddr, int ulen, void *kaddr) { - if(ulen<0||ulen>MAX_SOCK_ADDR) + if (ulen < 0 || ulen > MAX_SOCK_ADDR) return -EINVAL; - if(ulen==0) + if (ulen == 0) return 0; - if(copy_from_user(kaddr,uaddr,ulen)) + if (copy_from_user(kaddr, uaddr, ulen)) return -EFAULT; return audit_sockaddr(ulen, kaddr); } @@ -252,51 +208,52 @@ int move_addr_to_kernel(void __user *uaddr, int ulen, void *kaddr) * length of the data is written over the length limit the user * specified. Zero is returned for a success. */ - -int move_addr_to_user(void *kaddr, int klen, void __user *uaddr, int __user *ulen) + +int move_addr_to_user(void *kaddr, int klen, void __user *uaddr, + int __user *ulen) { int err; int len; - if((err=get_user(len, ulen))) + err = get_user(len, ulen); + if (err) return err; - if(len>klen) - len=klen; - if(len<0 || len> MAX_SOCK_ADDR) + if (len > klen) + len = klen; + if (len < 0 || len > MAX_SOCK_ADDR) return -EINVAL; - if(len) - { + if (len) { if (audit_sockaddr(klen, kaddr)) return -ENOMEM; - if(copy_to_user(uaddr,kaddr,len)) + if (copy_to_user(uaddr, kaddr, len)) return -EFAULT; } /* - * "fromlen shall refer to the value before truncation.." - * 1003.1g + * "fromlen shall refer to the value before truncation.." + * 1003.1g */ return __put_user(klen, ulen); } #define SOCKFS_MAGIC 0x534F434B -static kmem_cache_t * sock_inode_cachep __read_mostly; +static kmem_cache_t *sock_inode_cachep __read_mostly; static struct inode *sock_alloc_inode(struct super_block *sb) { struct socket_alloc *ei; - ei = (struct socket_alloc *)kmem_cache_alloc(sock_inode_cachep, SLAB_KERNEL); + + ei = kmem_cache_alloc(sock_inode_cachep, SLAB_KERNEL); if (!ei) return NULL; init_waitqueue_head(&ei->socket.wait); - + ei->socket.fasync_list = NULL; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; ei->socket.ops = NULL; ei->socket.sk = NULL; ei->socket.file = NULL; - ei->socket.flags = 0; return &ei->vfs_inode; } @@ -307,22 +264,25 @@ static void sock_destroy_inode(struct inode *inode) container_of(inode, struct socket_alloc, vfs_inode)); } -static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags) +static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags) { - struct socket_alloc *ei = (struct socket_alloc *) foo; + struct socket_alloc *ei = (struct socket_alloc *)foo; - if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == - SLAB_CTOR_CONSTRUCTOR) + if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) + == SLAB_CTOR_CONSTRUCTOR) inode_init_once(&ei->vfs_inode); } - + static int init_inodecache(void) { sock_inode_cachep = kmem_cache_create("sock_inode_cache", - sizeof(struct socket_alloc), - 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), - init_once, NULL); + sizeof(struct socket_alloc), + 0, + (SLAB_HWCACHE_ALIGN | + SLAB_RECLAIM_ACCOUNT | + SLAB_MEM_SPREAD), + init_once, + NULL); if (sock_inode_cachep == NULL) return -ENOMEM; return 0; @@ -335,7 +295,8 @@ static struct super_operations sockfs_ops = { }; static int sockfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) + int flags, const char *dev_name, void *data, + struct vfsmount *mnt) { return get_sb_pseudo(fs_type, "socket:", &sockfs_ops, SOCKFS_MAGIC, mnt); @@ -348,12 +309,13 @@ static struct file_system_type sock_fs_type = { .get_sb = sockfs_get_sb, .kill_sb = kill_anon_super, }; + static int sockfs_delete_dentry(struct dentry *dentry) { return 1; } static struct dentry_operations sockfs_dentry_operations = { - .d_delete = sockfs_delete_dentry, + .d_delete = sockfs_delete_dentry, }; /* @@ -477,10 +439,12 @@ struct socket *sockfd_lookup(int fd, int *err) struct file *file; struct socket *sock; - if (!(file = fget(fd))) { + file = fget(fd); + if (!file) { *err = -EBADF; return NULL; } + sock = sock_from_file(file, err); if (!sock) fput(file); @@ -505,7 +469,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) /** * sock_alloc - allocate a socket - * + * * Allocate a new inode and socket object. The two are bound together * and initialised. The socket is then returned. If we are out of inodes * NULL is returned. @@ -513,8 +477,8 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) static struct socket *sock_alloc(void) { - struct inode * inode; - struct socket * sock; + struct inode *inode; + struct socket *sock; inode = new_inode(sock_mnt->mnt_sb); if (!inode) @@ -522,7 +486,7 @@ static struct socket *sock_alloc(void) sock = SOCKET_I(inode); - inode->i_mode = S_IFSOCK|S_IRWXUGO; + inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; @@ -536,7 +500,7 @@ static struct socket *sock_alloc(void) * a back door. Remember to keep it shut otherwise you'll let the * creepy crawlies in. */ - + static int sock_no_open(struct inode *irrelevant, struct file *dontcare) { return -ENXIO; @@ -553,9 +517,9 @@ const struct file_operations bad_sock_fops = { * * The socket is released from the protocol stack if it has a release * callback, and the inode is then released if the socket is bound to - * an inode not a file. + * an inode not a file. */ - + void sock_release(struct socket *sock) { if (sock->ops) { @@ -575,10 +539,10 @@ void sock_release(struct socket *sock) iput(SOCK_INODE(sock)); return; } - sock->file=NULL; + sock->file = NULL; } -static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, +static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size) { struct sock_iocb *si = kiocb_to_siocb(iocb); @@ -621,14 +585,14 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, * the following is safe, since for compiler definitions of kvec and * iovec are identical, yielding the same in-core layout and alignment */ - msg->msg_iov = (struct iovec *)vec, + msg->msg_iov = (struct iovec *)vec; msg->msg_iovlen = num; result = sock_sendmsg(sock, msg, size); set_fs(oldfs); return result; } -static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, +static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { int err; @@ -647,14 +611,14 @@ static inline int __sock_recvmsg(struct kiocb *iocb, struct socket *sock, return sock->ops->recvmsg(iocb, sock, msg, size, flags); } -int sock_recvmsg(struct socket *sock, struct msghdr *msg, +int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct kiocb iocb; struct sock_iocb siocb; int ret; - init_sync_kiocb(&iocb, NULL); + init_sync_kiocb(&iocb, NULL); iocb.private = &siocb; ret = __sock_recvmsg(&iocb, sock, msg, size, flags); if (-EIOCBQUEUED == ret) @@ -662,9 +626,8 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, return ret; } -int kernel_recvmsg(struct socket *sock, struct msghdr *msg, - struct kvec *vec, size_t num, - size_t size, int flags) +int kernel_recvmsg(struct socket *sock, struct msghdr *msg, + struct kvec *vec, size_t num, size_t size, int flags) { mm_segment_t oldfs = get_fs(); int result; @@ -674,8 +637,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, * the following is safe, since for compiler definitions of kvec and * iovec are identical, yielding the same in-core layout and alignment */ - msg->msg_iov = (struct iovec *)vec, - msg->msg_iovlen = num; + msg->msg_iov = (struct iovec *)vec, msg->msg_iovlen = num; result = sock_recvmsg(sock, msg, size, flags); set_fs(oldfs); return result; @@ -702,7 +664,8 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, } static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, - char __user *ubuf, size_t size, struct sock_iocb *siocb) + char __user *ubuf, size_t size, + struct sock_iocb *siocb) { if (!is_sync_kiocb(iocb)) { siocb = kmalloc(sizeof(*siocb), GFP_KERNEL); @@ -720,20 +683,21 @@ static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb, } static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, unsigned long nr_segs) + struct file *file, struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; int i; - for (i = 0 ; i < nr_segs ; i++) - size += iov[i].iov_len; + for (i = 0; i < nr_segs; i++) + size += iov[i].iov_len; msg->msg_name = NULL; msg->msg_namelen = 0; msg->msg_control = NULL; msg->msg_controllen = 0; - msg->msg_iov = (struct iovec *) iov; + msg->msg_iov = (struct iovec *)iov; msg->msg_iovlen = nr_segs; msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; @@ -748,7 +712,7 @@ static ssize_t sock_readv(struct file *file, const struct iovec *iov, struct msghdr msg; int ret; - init_sync_kiocb(&iocb, NULL); + init_sync_kiocb(&iocb, NULL); iocb.private = &siocb; ret = do_sock_read(&msg, &iocb, file, (struct iovec *)iov, nr_segs); @@ -758,7 +722,7 @@ static ssize_t sock_readv(struct file *file, const struct iovec *iov, } static ssize_t sock_aio_read(struct kiocb *iocb, char __user *ubuf, - size_t count, loff_t pos) + size_t count, loff_t pos) { struct sock_iocb siocb, *x; @@ -771,24 +735,25 @@ static ssize_t sock_aio_read(struct kiocb *iocb, char __user *ubuf, if (!x) return -ENOMEM; return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + &x->async_iov, 1); } static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, - struct file *file, struct iovec *iov, unsigned long nr_segs) + struct file *file, struct iovec *iov, + unsigned long nr_segs) { struct socket *sock = file->private_data; size_t size = 0; int i; - for (i = 0 ; i < nr_segs ; i++) - size += iov[i].iov_len; + for (i = 0; i < nr_segs; i++) + size += iov[i].iov_len; msg->msg_name = NULL; msg->msg_namelen = 0; msg->msg_control = NULL; msg->msg_controllen = 0; - msg->msg_iov = (struct iovec *) iov; + msg->msg_iov = (struct iovec *)iov; msg->msg_iovlen = nr_segs; msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; if (sock->type == SOCK_SEQPACKET) @@ -815,7 +780,7 @@ static ssize_t sock_writev(struct file *file, const struct iovec *iov, } static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *ubuf, - size_t count, loff_t pos) + size_t count, loff_t pos) { struct sock_iocb siocb, *x; @@ -829,46 +794,48 @@ static ssize_t sock_aio_write(struct kiocb *iocb, const char __user *ubuf, return -ENOMEM; return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, - &x->async_iov, 1); + &x->async_iov, 1); } - /* * Atomic setting of ioctl hooks to avoid race * with module unload. */ static DEFINE_MUTEX(br_ioctl_mutex); -static int (*br_ioctl_hook)(unsigned int cmd, void __user *arg) = NULL; +static int (*br_ioctl_hook) (unsigned int cmd, void __user *arg) = NULL; -void brioctl_set(int (*hook)(unsigned int, void __user *)) +void brioctl_set(int (*hook) (unsigned int, void __user *)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; mutex_unlock(&br_ioctl_mutex); } + EXPORT_SYMBOL(brioctl_set); static DEFINE_MUTEX(vlan_ioctl_mutex); -static int (*vlan_ioctl_hook)(void __user *arg); +static int (*vlan_ioctl_hook) (void __user *arg); -void vlan_ioctl_set(int (*hook)(void __user *)) +void vlan_ioctl_set(int (*hook) (void __user *)) { mutex_lock(&vlan_ioctl_mutex); vlan_ioctl_hook = hook; mutex_unlock(&vlan_ioctl_mutex); } + EXPORT_SYMBOL(vlan_ioctl_set); static DEFINE_MUTEX(dlci_ioctl_mutex); -static int (*dlci_ioctl_hook)(unsigned int, void __user *); +static int (*dlci_ioctl_hook) (unsigned int, void __user *); -void dlci_ioctl_set(int (*hook)(unsigned int, void __user *)) +void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) { mutex_lock(&dlci_ioctl_mutex); dlci_ioctl_hook = hook; mutex_unlock(&dlci_ioctl_mutex); } + EXPORT_SYMBOL(dlci_ioctl_set); /* @@ -890,8 +857,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { err = dev_ioctl(cmd, argp); } else -#endif /* CONFIG_WIRELESS_EXT */ - switch (cmd) { +#endif /* CONFIG_WIRELESS_EXT */ + switch (cmd) { case FIOSETOWN: case SIOCSPGRP: err = -EFAULT; @@ -901,7 +868,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) break; case FIOGETOWN: case SIOCGPGRP: - err = put_user(sock->file->f_owner.pid, (int __user *)argp); + err = put_user(sock->file->f_owner.pid, + (int __user *)argp); break; case SIOCGIFBR: case SIOCSIFBR: @@ -912,7 +880,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) request_module("bridge"); mutex_lock(&br_ioctl_mutex); - if (br_ioctl_hook) + if (br_ioctl_hook) err = br_ioctl_hook(cmd, argp); mutex_unlock(&br_ioctl_mutex); break; @@ -929,7 +897,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) break; case SIOCGIFDIVERT: case SIOCSIFDIVERT: - /* Convert this to call through a hook */ + /* Convert this to call through a hook */ err = divert_ioctl(cmd, argp); break; case SIOCADDDLCI: @@ -954,7 +922,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) if (err == -ENOIOCTLCMD) err = dev_ioctl(cmd, argp); break; - } + } return err; } @@ -962,7 +930,7 @@ int sock_create_lite(int family, int type, int protocol, struct socket **res) { int err; struct socket *sock = NULL; - + err = security_socket_create(family, type, protocol, 1); if (err) goto out; @@ -973,26 +941,33 @@ int sock_create_lite(int family, int type, int protocol, struct socket **res) goto out; } - security_socket_post_create(sock, family, type, protocol, 1); sock->type = type; + err = security_socket_post_create(sock, family, type, protocol, 1); + if (err) + goto out_release; + out: *res = sock; return err; +out_release: + sock_release(sock); + sock = NULL; + goto out; } /* No kernel lock held - perfect */ -static unsigned int sock_poll(struct file *file, poll_table * wait) +static unsigned int sock_poll(struct file *file, poll_table *wait) { struct socket *sock; /* - * We can't return errors to poll, so it's either yes or no. + * We can't return errors to poll, so it's either yes or no. */ sock = file->private_data; return sock->ops->poll(file, sock, wait); } -static int sock_mmap(struct file * file, struct vm_area_struct * vma) +static int sock_mmap(struct file *file, struct vm_area_struct *vma) { struct socket *sock = file->private_data; @@ -1002,12 +977,11 @@ static int sock_mmap(struct file * file, struct vm_area_struct * vma) static int sock_close(struct inode *inode, struct file *filp) { /* - * It was possible the inode is NULL we were - * closing an unfinished socket. + * It was possible the inode is NULL we were + * closing an unfinished socket. */ - if (!inode) - { + if (!inode) { printk(KERN_DEBUG "sock_close: NULL inode\n"); return 0; } @@ -1033,57 +1007,52 @@ static int sock_close(struct inode *inode, struct file *filp) static int sock_fasync(int fd, struct file *filp, int on) { - struct fasync_struct *fa, *fna=NULL, **prev; + struct fasync_struct *fa, *fna = NULL, **prev; struct socket *sock; struct sock *sk; - if (on) - { + if (on) { fna = kmalloc(sizeof(struct fasync_struct), GFP_KERNEL); - if(fna==NULL) + if (fna == NULL) return -ENOMEM; } sock = filp->private_data; - if ((sk=sock->sk) == NULL) { + sk = sock->sk; + if (sk == NULL) { kfree(fna); return -EINVAL; } lock_sock(sk); - prev=&(sock->fasync_list); + prev = &(sock->fasync_list); - for (fa=*prev; fa!=NULL; prev=&fa->fa_next,fa=*prev) - if (fa->fa_file==filp) + for (fa = *prev; fa != NULL; prev = &fa->fa_next, fa = *prev) + if (fa->fa_file == filp) break; - if(on) - { - if(fa!=NULL) - { + if (on) { + if (fa != NULL) { write_lock_bh(&sk->sk_callback_lock); - fa->fa_fd=fd; + fa->fa_fd = fd; write_unlock_bh(&sk->sk_callback_lock); kfree(fna); goto out; } - fna->fa_file=filp; - fna->fa_fd=fd; - fna->magic=FASYNC_MAGIC; - fna->fa_next=sock->fasync_list; + fna->fa_file = filp; + fna->fa_fd = fd; + fna->magic = FASYNC_MAGIC; + fna->fa_next = sock->fasync_list; write_lock_bh(&sk->sk_callback_lock); - sock->fasync_list=fna; + sock->fasync_list = fna; write_unlock_bh(&sk->sk_callback_lock); - } - else - { - if (fa!=NULL) - { + } else { + if (fa != NULL) { write_lock_bh(&sk->sk_callback_lock); - *prev=fa->fa_next; + *prev = fa->fa_next; write_unlock_bh(&sk->sk_callback_lock); kfree(fa); } @@ -1100,10 +1069,9 @@ int sock_wake_async(struct socket *sock, int how, int band) { if (!sock || !sock->fasync_list) return -1; - switch (how) - { + switch (how) { case 1: - + if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags)) break; goto call_kill; @@ -1112,7 +1080,7 @@ int sock_wake_async(struct socket *sock, int how, int band) break; /* fall through */ case 0: - call_kill: +call_kill: __kill_fasync(sock->fasync_list, SIGIO, band); break; case 3: @@ -1121,13 +1089,15 @@ int sock_wake_async(struct socket *sock, int how, int band) return 0; } -static int __sock_create(int family, int type, int protocol, struct socket **res, int kern) +static int __sock_create(int family, int type, int protocol, + struct socket **res, int kern) { int err; struct socket *sock; + const struct net_proto_family *pf; /* - * Check protocol is in range + * Check protocol is in range */ if (family < 0 || family >= NPROTO) return -EAFNOSUPPORT; @@ -1140,10 +1110,11 @@ static int __sock_create(int family, int type, int protocol, struct socket **res deadlock in module load. */ if (family == PF_INET && type == SOCK_PACKET) { - static int warned; + static int warned; if (!warned) { warned = 1; - printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n", current->comm); + printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n", + current->comm); } family = PF_PACKET; } @@ -1151,79 +1122,84 @@ static int __sock_create(int family, int type, int protocol, struct socket **res err = security_socket_create(family, type, protocol, kern); if (err) return err; - + + /* + * Allocate the socket and allow the family to set things up. if + * the protocol is 0, the family is instructed to select an appropriate + * default. + */ + sock = sock_alloc(); + if (!sock) { + if (net_ratelimit()) + printk(KERN_WARNING "socket: no more sockets\n"); + return -ENFILE; /* Not exactly a match, but its the + closest posix thing */ + } + + sock->type = type; + #if defined(CONFIG_KMOD) - /* Attempt to load a protocol module if the find failed. - * - * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user + /* Attempt to load a protocol module if the find failed. + * + * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user * requested real, full-featured networking support upon configuration. * Otherwise module support will break! */ - if (net_families[family]==NULL) - { - request_module("net-pf-%d",family); - } + if (net_families[family] == NULL) + request_module("net-pf-%d", family); #endif - net_family_read_lock(); - if (net_families[family] == NULL) { - err = -EAFNOSUPPORT; - goto out; - } - -/* - * Allocate the socket and allow the family to set things up. if - * the protocol is 0, the family is instructed to select an appropriate - * default. - */ - - if (!(sock = sock_alloc())) { - if (net_ratelimit()) - printk(KERN_WARNING "socket: no more sockets\n"); - err = -ENFILE; /* Not exactly a match, but its the - closest posix thing */ - goto out; - } - - sock->type = type; + rcu_read_lock(); + pf = rcu_dereference(net_families[family]); + err = -EAFNOSUPPORT; + if (!pf) + goto out_release; /* * We will call the ->create function, that possibly is in a loadable * module, so we have to bump that loadable module refcnt first. */ - err = -EAFNOSUPPORT; - if (!try_module_get(net_families[family]->owner)) + if (!try_module_get(pf->owner)) goto out_release; - if ((err = net_families[family]->create(sock, protocol)) < 0) { - sock->ops = NULL; + /* Now protected by module ref count */ + rcu_read_unlock(); + + err = pf->create(sock, protocol); + if (err < 0) goto out_module_put; - } /* * Now to bump the refcnt of the [loadable] module that owns this * socket at sock_release time we decrement its refcnt. */ - if (!try_module_get(sock->ops->owner)) { - sock->ops = NULL; - goto out_module_put; - } + if (!try_module_get(sock->ops->owner)) + goto out_module_busy; + /* * Now that we're done with the ->create function, the [loadable] * module can have its refcnt decremented */ - module_put(net_families[family]->owner); + module_put(pf->owner); + err = security_socket_post_create(sock, family, type, protocol, kern); + if (err) + goto out_release; *res = sock; - security_socket_post_create(sock, family, type, protocol, kern); -out: - net_family_read_unlock(); - return err; + return 0; + +out_module_busy: + err = -EAFNOSUPPORT; out_module_put: - module_put(net_families[family]->owner); -out_release: + sock->ops = NULL; + module_put(pf->owner); +out_sock_release: sock_release(sock); - goto out; + return err; + +out_release: + rcu_read_unlock(); + goto out_sock_release; } int sock_create(int family, int type, int protocol, struct socket **res) @@ -1262,7 +1238,8 @@ out_release: * Create a pair of connected sockets. */ -asmlinkage long sys_socketpair(int family, int type, int protocol, int __user *usockvec) +asmlinkage long sys_socketpair(int family, int type, int protocol, + int __user *usockvec) { struct socket *sock1, *sock2; int fd1, fd2, err; @@ -1281,7 +1258,7 @@ asmlinkage long sys_socketpair(int family, int type, int protocol, int __user *u goto out_release_1; err = sock1->ops->socketpair(sock1, sock2); - if (err < 0) + if (err < 0) goto out_release_both; fd1 = fd2 = -1; @@ -1300,7 +1277,7 @@ asmlinkage long sys_socketpair(int family, int type, int protocol, int __user *u * Not kernel problem. */ - err = put_user(fd1, &usockvec[0]); + err = put_user(fd1, &usockvec[0]); if (!err) err = put_user(fd2, &usockvec[1]); if (!err) @@ -1311,19 +1288,18 @@ asmlinkage long sys_socketpair(int family, int type, int protocol, int __user *u return err; out_close_1: - sock_release(sock2); + sock_release(sock2); sys_close(fd1); return err; out_release_both: - sock_release(sock2); + sock_release(sock2); out_release_1: - sock_release(sock1); + sock_release(sock1); out: return err; } - /* * Bind a name to a socket. Nothing much to do here since it's * the protocol's responsibility to handle the local address. @@ -1338,35 +1314,39 @@ asmlinkage long sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) char address[MAX_SOCK_ADDR]; int err, fput_needed; - 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); + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if(sock) { + err = move_addr_to_kernel(umyaddr, addrlen, address); + if (err >= 0) { + err = security_socket_bind(sock, + (struct sockaddr *)address, + addrlen); if (!err) err = sock->ops->bind(sock, - (struct sockaddr *)address, addrlen); + (struct sockaddr *) + address, addrlen); } fput_light(sock->file, fput_needed); - } + } return err; } - /* * Perform a listen. Basically, we allow the protocol to do anything * necessary for a listen, and if that works, we mark the socket as * ready for listening. */ -int sysctl_somaxconn = SOMAXCONN; +int sysctl_somaxconn __read_mostly = SOMAXCONN; asmlinkage long sys_listen(int fd, int backlog) { struct socket *sock; int err, fput_needed; - - if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) { - if ((unsigned) backlog > sysctl_somaxconn) + + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (sock) { + if ((unsigned)backlog > sysctl_somaxconn) backlog = sysctl_somaxconn; err = security_socket_listen(sock, backlog); @@ -1378,7 +1358,6 @@ asmlinkage long sys_listen(int fd, int backlog) return err; } - /* * For accept, we attempt to create a new socket, set up the link * with the client, wake up the client, then return the new @@ -1391,7 +1370,8 @@ asmlinkage long sys_listen(int fd, int backlog) * clean when we restucture accept also. */ -asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen) +asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen) { struct socket *sock, *newsock; struct file *newfile; @@ -1403,7 +1383,7 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, int _ goto out; err = -ENFILE; - if (!(newsock = sock_alloc())) + if (!(newsock = sock_alloc())) goto out_put; newsock->type = sock->type; @@ -1435,11 +1415,13 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr, int _ goto out_fd; if (upeer_sockaddr) { - if(newsock->ops->getname(newsock, (struct sockaddr *)address, &len, 2)<0) { + if (newsock->ops->getname(newsock, (struct sockaddr *)address, + &len, 2) < 0) { err = -ECONNABORTED; goto out_fd; } - err = move_addr_to_user(address, len, upeer_sockaddr, upeer_addrlen); + err = move_addr_to_user(address, len, upeer_sockaddr, + upeer_addrlen); if (err < 0) goto out_fd; } @@ -1461,7 +1443,6 @@ out_fd: goto out_put; } - /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. @@ -1474,7 +1455,8 @@ out_fd: * include the -EINPROGRESS status for such sockets. */ -asmlinkage long sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) +asmlinkage long sys_connect(int fd, struct sockaddr __user *uservaddr, + int addrlen) { struct socket *sock; char address[MAX_SOCK_ADDR]; @@ -1487,11 +1469,12 @@ asmlinkage long sys_connect(int fd, struct sockaddr __user *uservaddr, int addrl if (err < 0) goto out_put; - err = security_socket_connect(sock, (struct sockaddr *)address, addrlen); + err = + security_socket_connect(sock, (struct sockaddr *)address, addrlen); if (err) goto out_put; - err = sock->ops->connect(sock, (struct sockaddr *) address, addrlen, + err = sock->ops->connect(sock, (struct sockaddr *)address, addrlen, sock->file->f_flags); out_put: fput_light(sock->file, fput_needed); @@ -1504,12 +1487,13 @@ out: * name to user space. */ -asmlinkage long sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) +asmlinkage long sys_getsockname(int fd, struct sockaddr __user *usockaddr, + int __user *usockaddr_len) { struct socket *sock; char address[MAX_SOCK_ADDR]; int len, err, fput_needed; - + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -1534,22 +1518,27 @@ out: * name to user space. */ -asmlinkage long sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) +asmlinkage long sys_getpeername(int fd, struct sockaddr __user *usockaddr, + int __user *usockaddr_len) { struct socket *sock; char address[MAX_SOCK_ADDR]; int len, err, fput_needed; - if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) { + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (sock != NULL) { err = security_socket_getpeername(sock); if (err) { fput_light(sock->file, fput_needed); return err; } - err = sock->ops->getname(sock, (struct sockaddr *)address, &len, 1); + err = + sock->ops->getname(sock, (struct sockaddr *)address, &len, + 1); if (!err) - err=move_addr_to_user(address,len, usockaddr, usockaddr_len); + err = move_addr_to_user(address, len, usockaddr, + usockaddr_len); fput_light(sock->file, fput_needed); } return err; @@ -1561,8 +1550,9 @@ asmlinkage long sys_getpeername(int fd, struct sockaddr __user *usockaddr, int _ * the protocol. */ -asmlinkage long sys_sendto(int fd, void __user * buff, size_t len, unsigned flags, - struct sockaddr __user *addr, int addr_len) +asmlinkage long sys_sendto(int fd, void __user *buff, size_t len, + unsigned flags, struct sockaddr __user *addr, + int addr_len) { struct socket *sock; char address[MAX_SOCK_ADDR]; @@ -1579,54 +1569,55 @@ asmlinkage long sys_sendto(int fd, void __user * buff, size_t len, unsigned flag sock = sock_from_file(sock_file, &err); if (!sock) goto out_put; - iov.iov_base=buff; - iov.iov_len=len; - msg.msg_name=NULL; - msg.msg_iov=&iov; - msg.msg_iovlen=1; - msg.msg_control=NULL; - msg.msg_controllen=0; - msg.msg_namelen=0; + iov.iov_base = buff; + iov.iov_len = len; + msg.msg_name = NULL; + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_namelen = 0; if (addr) { err = move_addr_to_kernel(addr, addr_len, address); if (err < 0) goto out_put; - msg.msg_name=address; - msg.msg_namelen=addr_len; + msg.msg_name = address; + msg.msg_namelen = addr_len; } if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; err = sock_sendmsg(sock, &msg, len); -out_put: +out_put: fput_light(sock_file, fput_needed); return err; } /* - * Send a datagram down a socket. + * Send a datagram down a socket. */ -asmlinkage long sys_send(int fd, void __user * buff, size_t len, unsigned flags) +asmlinkage long sys_send(int fd, void __user *buff, size_t len, unsigned flags) { return sys_sendto(fd, buff, len, flags, NULL, 0); } /* - * Receive a frame from the socket and optionally record the address of the + * Receive a frame from the socket and optionally record the address of the * sender. We verify the buffers are writable and if needed move the * sender address from kernel to user space. */ -asmlinkage long sys_recvfrom(int fd, void __user * ubuf, size_t size, unsigned flags, - struct sockaddr __user *addr, int __user *addr_len) +asmlinkage long sys_recvfrom(int fd, void __user *ubuf, size_t size, + unsigned flags, struct sockaddr __user *addr, + int __user *addr_len) { struct socket *sock; struct iovec iov; struct msghdr msg; char address[MAX_SOCK_ADDR]; - int err,err2; + int err, err2; struct file *sock_file; int fput_needed; @@ -1638,23 +1629,22 @@ asmlinkage long sys_recvfrom(int fd, void __user * ubuf, size_t size, unsigned f if (!sock) goto out; - msg.msg_control=NULL; - msg.msg_controllen=0; - msg.msg_iovlen=1; - msg.msg_iov=&iov; - iov.iov_len=size; - iov.iov_base=ubuf; - msg.msg_name=address; - msg.msg_namelen=MAX_SOCK_ADDR; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_iovlen = 1; + msg.msg_iov = &iov; + iov.iov_len = size; + iov.iov_base = ubuf; + msg.msg_name = address; + msg.msg_namelen = MAX_SOCK_ADDR; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; - err=sock_recvmsg(sock, &msg, size, flags); + err = sock_recvmsg(sock, &msg, size, flags); - if(err >= 0 && addr != NULL) - { - err2=move_addr_to_user(address, msg.msg_namelen, addr, addr_len); - if(err2<0) - err=err2; + if (err >= 0 && addr != NULL) { + err2 = move_addr_to_user(address, msg.msg_namelen, addr, addr_len); + if (err2 < 0) + err = err2; } out: fput_light(sock_file, fput_needed); @@ -1662,10 +1652,11 @@ out: } /* - * Receive a datagram from a socket. + * Receive a datagram from a socket. */ -asmlinkage long sys_recv(int fd, void __user * ubuf, size_t size, unsigned flags) +asmlinkage long sys_recv(int fd, void __user *ubuf, size_t size, + unsigned flags) { return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } @@ -1675,24 +1666,29 @@ asmlinkage long sys_recv(int fd, void __user * ubuf, size_t size, unsigned flags * to pass the user mode parameter for the protocols to sort out. */ -asmlinkage long sys_setsockopt(int fd, int level, int optname, char __user *optval, int optlen) +asmlinkage long sys_setsockopt(int fd, int level, int optname, + char __user *optval, int optlen) { int err, fput_needed; struct socket *sock; if (optlen < 0) return -EINVAL; - - if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) - { - err = security_socket_setsockopt(sock,level,optname); + + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (sock != NULL) { + err = security_socket_setsockopt(sock, level, optname); if (err) goto out_put; if (level == SOL_SOCKET) - err=sock_setsockopt(sock,level,optname,optval,optlen); + err = + sock_setsockopt(sock, level, optname, optval, + optlen); else - err=sock->ops->setsockopt(sock, level, optname, optval, optlen); + err = + sock->ops->setsockopt(sock, level, optname, optval, + optlen); out_put: fput_light(sock->file, fput_needed); } @@ -1704,27 +1700,32 @@ out_put: * to pass a user mode parameter for the protocols to sort out. */ -asmlinkage long sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) +asmlinkage long sys_getsockopt(int fd, int level, int optname, + char __user *optval, int __user *optlen) { int err, fput_needed; struct socket *sock; - if ((sock = sockfd_lookup_light(fd, &err, &fput_needed)) != NULL) { + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (sock != 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); + err = + sock_getsockopt(sock, level, optname, optval, + optlen); else - err=sock->ops->getsockopt(sock, level, optname, optval, optlen); + err = + sock->ops->getsockopt(sock, level, optname, optval, + optlen); out_put: fput_light(sock->file, fput_needed); } return err; } - /* * Shutdown a socket. */ @@ -1734,8 +1735,8 @@ asmlinkage long sys_shutdown(int fd, int how) int err, fput_needed; struct socket *sock; - if ((sock = sockfd_lookup_light(fd, &err, &fput_needed))!=NULL) - { + sock = sockfd_lookup_light(fd, &err, &fput_needed); + if (sock != NULL) { err = security_socket_shutdown(sock, how); if (!err) err = sock->ops->shutdown(sock, how); @@ -1744,41 +1745,42 @@ asmlinkage long sys_shutdown(int fd, int how) return err; } -/* A couple of helpful macros for getting the address of the 32/64 bit +/* A couple of helpful macros for getting the address of the 32/64 bit * fields which are the same type (int / unsigned) on our platforms. */ #define COMPAT_MSG(msg, member) ((MSG_CMSG_COMPAT & flags) ? &msg##_compat->member : &msg->member) #define COMPAT_NAMELEN(msg) COMPAT_MSG(msg, msg_namelen) #define COMPAT_FLAGS(msg) COMPAT_MSG(msg, msg_flags) - /* * BSD sendmsg interface */ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) { - struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; + struct compat_msghdr __user *msg_compat = + (struct compat_msghdr __user *)msg; struct socket *sock; char address[MAX_SOCK_ADDR]; struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; unsigned char ctl[sizeof(struct cmsghdr) + 20] - __attribute__ ((aligned (sizeof(__kernel_size_t)))); - /* 20 is size of ipv6_pktinfo */ + __attribute__ ((aligned(sizeof(__kernel_size_t)))); + /* 20 is size of ipv6_pktinfo */ 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) { if (get_compat_msghdr(&msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr))) + } + else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr))) return -EFAULT; sock = sockfd_lookup_light(fd, &err, &fput_needed); - if (!sock) + if (!sock) goto out; /* do not move before msg_sys is valid */ @@ -1786,7 +1788,7 @@ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) if (msg_sys.msg_iovlen > UIO_MAXIOV) goto out_put; - /* Check whether to allocate the iovec area*/ + /* Check whether to allocate the iovec area */ err = -ENOMEM; iov_size = msg_sys.msg_iovlen * sizeof(struct iovec); if (msg_sys.msg_iovlen > UIO_FASTIOV) { @@ -1800,7 +1802,7 @@ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) err = verify_compat_iovec(&msg_sys, iov, address, VERIFY_READ); } else err = verify_iovec(&msg_sys, iov, address, VERIFY_READ); - if (err < 0) + if (err < 0) goto out_freeiov; total_len = err; @@ -1808,18 +1810,19 @@ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) if (msg_sys.msg_controllen > INT_MAX) goto out_freeiov; - ctl_len = msg_sys.msg_controllen; + ctl_len = msg_sys.msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { - err = cmsghdr_from_user_compat_to_kern(&msg_sys, sock->sk, ctl, sizeof(ctl)); + err = + cmsghdr_from_user_compat_to_kern(&msg_sys, sock->sk, ctl, + sizeof(ctl)); if (err) goto out_freeiov; ctl_buf = msg_sys.msg_control; ctl_len = msg_sys.msg_controllen; } else if (ctl_len) { - if (ctl_len > sizeof(ctl)) - { + if (ctl_len > sizeof(ctl)) { ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL); - if (ctl_buf == NULL) + if (ctl_buf == NULL) goto out_freeiov; } err = -EFAULT; @@ -1828,7 +1831,8 @@ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) * Afterwards, it will be a kernel pointer. Thus the compiler-assisted * checking falls down on this. */ - if (copy_from_user(ctl_buf, (void __user *) msg_sys.msg_control, ctl_len)) + if (copy_from_user(ctl_buf, (void __user *)msg_sys.msg_control, + ctl_len)) goto out_freectl; msg_sys.msg_control = ctl_buf; } @@ -1839,14 +1843,14 @@ asmlinkage long sys_sendmsg(int fd, struct msghdr __user *msg, unsigned flags) err = sock_sendmsg(sock, &msg_sys, total_len); out_freectl: - if (ctl_buf != ctl) + if (ctl_buf != ctl) sock_kfree_s(sock->sk, ctl_buf, ctl_len); out_freeiov: if (iov != iovstack) sock_kfree_s(sock->sk, iov, iov_size); out_put: fput_light(sock->file, fput_needed); -out: +out: return err; } @@ -1854,12 +1858,14 @@ out: * BSD recvmsg interface */ -asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flags) +asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, + unsigned int flags) { - struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; + struct compat_msghdr __user *msg_compat = + (struct compat_msghdr __user *)msg; struct socket *sock; struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov=iovstack; + struct iovec *iov = iovstack; struct msghdr msg_sys; unsigned long cmsg_ptr; int err, iov_size, total_len, len; @@ -1871,13 +1877,13 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flag /* user mode address pointers */ struct sockaddr __user *uaddr; int __user *uaddr_len; - + if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(&msg_sys, msg_compat)) return -EFAULT; - } else - if (copy_from_user(&msg_sys,msg,sizeof(struct msghdr))) - return -EFAULT; + } + else if (copy_from_user(&msg_sys, msg, sizeof(struct msghdr))) + return -EFAULT; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) @@ -1886,8 +1892,8 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flag err = -EMSGSIZE; if (msg_sys.msg_iovlen > UIO_MAXIOV) goto out_put; - - /* Check whether to allocate the iovec area*/ + + /* Check whether to allocate the iovec area */ err = -ENOMEM; iov_size = msg_sys.msg_iovlen * sizeof(struct iovec); if (msg_sys.msg_iovlen > UIO_FASTIOV) { @@ -1897,11 +1903,11 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flag } /* - * Save the user-mode address (verify_iovec will change the - * kernel msghdr to use the kernel address space) + * Save the user-mode address (verify_iovec will change the + * kernel msghdr to use the kernel address space) */ - - uaddr = (void __user *) msg_sys.msg_name; + + uaddr = (void __user *)msg_sys.msg_name; uaddr_len = COMPAT_NAMELEN(msg); if (MSG_CMSG_COMPAT & flags) { err = verify_compat_iovec(&msg_sys, iov, addr, VERIFY_WRITE); @@ -1909,13 +1915,13 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flag err = verify_iovec(&msg_sys, iov, addr, VERIFY_WRITE); if (err < 0) goto out_freeiov; - total_len=err; + total_len = err; cmsg_ptr = (unsigned long)msg_sys.msg_control; msg_sys.msg_flags = 0; if (MSG_CMSG_COMPAT & flags) msg_sys.msg_flags = MSG_CMSG_COMPAT; - + if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg_sys, total_len, flags); @@ -1924,7 +1930,8 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flag len = err; if (uaddr != NULL) { - err = move_addr_to_user(addr, msg_sys.msg_namelen, uaddr, uaddr_len); + err = move_addr_to_user(addr, msg_sys.msg_namelen, uaddr, + uaddr_len); if (err < 0) goto out_freeiov; } @@ -1933,10 +1940,10 @@ asmlinkage long sys_recvmsg(int fd, struct msghdr __user *msg, unsigned int flag if (err) goto out_freeiov; if (MSG_CMSG_COMPAT & flags) - err = __put_user((unsigned long)msg_sys.msg_control-cmsg_ptr, + err = __put_user((unsigned long)msg_sys.msg_control - cmsg_ptr, &msg_compat->msg_controllen); else - err = __put_user((unsigned long)msg_sys.msg_control-cmsg_ptr, + err = __put_user((unsigned long)msg_sys.msg_control - cmsg_ptr, &msg->msg_controllen); if (err) goto out_freeiov; @@ -1955,163 +1962,187 @@ out: /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) -static unsigned char nargs[18]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), - AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), - AL(6),AL(2),AL(5),AL(5),AL(3),AL(3)}; +static const unsigned char nargs[18]={ + AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), + AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), + AL(6),AL(2),AL(5),AL(5),AL(3),AL(3) +}; + #undef AL /* - * System call vectors. + * System call vectors. * * Argument checking cleaned up. Saved 20% in size. * This function doesn't need to set the kernel lock because - * it is set by the callees. + * it is set by the callees. */ asmlinkage long sys_socketcall(int call, unsigned long __user *args) { unsigned long a[6]; - unsigned long a0,a1; + unsigned long a0, a1; int err; - if(call<1||call>SYS_RECVMSG) + if (call < 1 || call > SYS_RECVMSG) return -EINVAL; /* copy_from_user should be SMP safe. */ if (copy_from_user(a, args, nargs[call])) return -EFAULT; - err = audit_socketcall(nargs[call]/sizeof(unsigned long), a); + err = audit_socketcall(nargs[call] / sizeof(unsigned long), a); if (err) return err; - a0=a[0]; - a1=a[1]; - - switch(call) - { - case SYS_SOCKET: - err = sys_socket(a0,a1,a[2]); - break; - case SYS_BIND: - err = sys_bind(a0,(struct sockaddr __user *)a1, a[2]); - break; - case SYS_CONNECT: - err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]); - break; - case SYS_LISTEN: - err = sys_listen(a0,a1); - break; - case SYS_ACCEPT: - err = sys_accept(a0,(struct sockaddr __user *)a1, (int __user *)a[2]); - break; - case SYS_GETSOCKNAME: - err = sys_getsockname(a0,(struct sockaddr __user *)a1, (int __user *)a[2]); - break; - case SYS_GETPEERNAME: - err = sys_getpeername(a0, (struct sockaddr __user *)a1, (int __user *)a[2]); - break; - case SYS_SOCKETPAIR: - err = sys_socketpair(a0,a1, a[2], (int __user *)a[3]); - break; - case SYS_SEND: - err = sys_send(a0, (void __user *)a1, a[2], a[3]); - break; - case SYS_SENDTO: - err = sys_sendto(a0,(void __user *)a1, a[2], a[3], - (struct sockaddr __user *)a[4], a[5]); - break; - case SYS_RECV: - err = sys_recv(a0, (void __user *)a1, a[2], a[3]); - break; - case SYS_RECVFROM: - err = sys_recvfrom(a0, (void __user *)a1, a[2], a[3], - (struct sockaddr __user *)a[4], (int __user *)a[5]); - break; - case SYS_SHUTDOWN: - err = sys_shutdown(a0,a1); - break; - case SYS_SETSOCKOPT: - err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]); - break; - case SYS_GETSOCKOPT: - err = sys_getsockopt(a0, a1, a[2], (char __user *)a[3], (int __user *)a[4]); - break; - case SYS_SENDMSG: - err = sys_sendmsg(a0, (struct msghdr __user *) a1, a[2]); - break; - case SYS_RECVMSG: - err = sys_recvmsg(a0, (struct msghdr __user *) a1, a[2]); - break; - default: - err = -EINVAL; - break; + a0 = a[0]; + a1 = a[1]; + + switch (call) { + case SYS_SOCKET: + err = sys_socket(a0, a1, a[2]); + break; + case SYS_BIND: + err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]); + break; + case SYS_CONNECT: + err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]); + break; + case SYS_LISTEN: + err = sys_listen(a0, a1); + break; + case SYS_ACCEPT: + err = + sys_accept(a0, (struct sockaddr __user *)a1, + (int __user *)a[2]); + break; + case SYS_GETSOCKNAME: + err = + sys_getsockname(a0, (struct sockaddr __user *)a1, + (int __user *)a[2]); + break; + case SYS_GETPEERNAME: + err = + sys_getpeername(a0, (struct sockaddr __user *)a1, + (int __user *)a[2]); + break; + case SYS_SOCKETPAIR: + err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]); + break; + case SYS_SEND: + err = sys_send(a0, (void __user *)a1, a[2], a[3]); + break; + case SYS_SENDTO: + err = sys_sendto(a0, (void __user *)a1, a[2], a[3], + (struct sockaddr __user *)a[4], a[5]); + break; + case SYS_RECV: + err = sys_recv(a0, (void __user *)a1, a[2], a[3]); + break; + case SYS_RECVFROM: + err = sys_recvfrom(a0, (void __user *)a1, a[2], a[3], + (struct sockaddr __user *)a[4], + (int __user *)a[5]); + break; + case SYS_SHUTDOWN: + err = sys_shutdown(a0, a1); + break; + case SYS_SETSOCKOPT: + err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]); + break; + case SYS_GETSOCKOPT: + err = + sys_getsockopt(a0, a1, a[2], (char __user *)a[3], + (int __user *)a[4]); + break; + case SYS_SENDMSG: + err = sys_sendmsg(a0, (struct msghdr __user *)a1, a[2]); + break; + case SYS_RECVMSG: + err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]); + break; + default: + err = -EINVAL; + break; } return err; } -#endif /* __ARCH_WANT_SYS_SOCKETCALL */ +#endif /* __ARCH_WANT_SYS_SOCKETCALL */ -/* +/** + * sock_register - add a socket protocol handler + * @ops: description of protocol + * * This function is called by a protocol handler that wants to * advertise its address family, and have it linked into the - * SOCKET module. + * socket interface. The value ops->family coresponds to the + * socket system call protocol family. */ - -int sock_register(struct net_proto_family *ops) +int sock_register(const struct net_proto_family *ops) { int err; if (ops->family >= NPROTO) { - printk(KERN_CRIT "protocol %d >= NPROTO(%d)\n", ops->family, NPROTO); + printk(KERN_CRIT "protocol %d >= NPROTO(%d)\n", ops->family, + NPROTO); return -ENOBUFS; } - net_family_write_lock(); - err = -EEXIST; - if (net_families[ops->family] == NULL) { - net_families[ops->family]=ops; + + spin_lock(&net_family_lock); + if (net_families[ops->family]) + err = -EEXIST; + else { + net_families[ops->family] = ops; err = 0; } - net_family_write_unlock(); - printk(KERN_INFO "NET: Registered protocol family %d\n", - ops->family); + spin_unlock(&net_family_lock); + + printk(KERN_INFO "NET: Registered protocol family %d\n", ops->family); return err; } -/* +/** + * sock_unregister - remove a protocol handler + * @family: protocol family to remove + * * This function is called by a protocol handler that wants to * remove its address family, and have it unlinked from the - * SOCKET module. + * new socket creation. + * + * If protocol handler is a module, then it can use module reference + * counts to protect against new references. If protocol handler is not + * a module then it needs to provide its own protection in + * the ops->create routine. */ - -int sock_unregister(int family) +void sock_unregister(int family) { - if (family < 0 || family >= NPROTO) - return -1; + BUG_ON(family < 0 || family >= NPROTO); - net_family_write_lock(); - net_families[family]=NULL; - net_family_write_unlock(); - printk(KERN_INFO "NET: Unregistered protocol family %d\n", - family); - return 0; + spin_lock(&net_family_lock); + net_families[family] = NULL; + spin_unlock(&net_family_lock); + + synchronize_rcu(); + + printk(KERN_INFO "NET: Unregistered protocol family %d\n", family); } static int __init sock_init(void) { /* - * Initialize sock SLAB cache. + * Initialize sock SLAB cache. */ - + sk_init(); /* - * Initialize skbuff SLAB cache + * Initialize skbuff SLAB cache */ skb_init(); /* - * Initialize the protocols module. + * Initialize the protocols module. */ init_inodecache(); @@ -2137,7 +2168,7 @@ void socket_seq_show(struct seq_file *seq) int counter = 0; for_each_possible_cpu(cpu) - counter += per_cpu(sockets_in_use, cpu); + counter += per_cpu(sockets_in_use, cpu); /* It can be negative, by the way. 8) */ if (counter < 0) @@ -2145,11 +2176,11 @@ void socket_seq_show(struct seq_file *seq) seq_printf(seq, "sockets: used %d\n", counter); } -#endif /* CONFIG_PROC_FS */ +#endif /* CONFIG_PROC_FS */ #ifdef CONFIG_COMPAT static long compat_sock_ioctl(struct file *file, unsigned cmd, - unsigned long arg) + unsigned long arg) { struct socket *sock = file->private_data; int ret = -ENOIOCTLCMD; @@ -2161,6 +2192,109 @@ static long compat_sock_ioctl(struct file *file, unsigned cmd, } #endif +int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) +{ + return sock->ops->bind(sock, addr, addrlen); +} + +int kernel_listen(struct socket *sock, int backlog) +{ + return sock->ops->listen(sock, backlog); +} + +int kernel_accept(struct socket *sock, struct socket **newsock, int flags) +{ + struct sock *sk = sock->sk; + int err; + + err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, + newsock); + if (err < 0) + goto done; + + err = sock->ops->accept(sock, *newsock, flags); + if (err < 0) { + sock_release(*newsock); + goto done; + } + + (*newsock)->ops = sock->ops; + +done: + return err; +} + +int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, + int flags) +{ + return sock->ops->connect(sock, addr, addrlen, flags); +} + +int kernel_getsockname(struct socket *sock, struct sockaddr *addr, + int *addrlen) +{ + return sock->ops->getname(sock, addr, addrlen, 0); +} + +int kernel_getpeername(struct socket *sock, struct sockaddr *addr, + int *addrlen) +{ + return sock->ops->getname(sock, addr, addrlen, 1); +} + +int kernel_getsockopt(struct socket *sock, int level, int optname, + char *optval, int *optlen) +{ + mm_segment_t oldfs = get_fs(); + int err; + + set_fs(KERNEL_DS); + if (level == SOL_SOCKET) + err = sock_getsockopt(sock, level, optname, optval, optlen); + else + err = sock->ops->getsockopt(sock, level, optname, optval, + optlen); + set_fs(oldfs); + return err; +} + +int kernel_setsockopt(struct socket *sock, int level, int optname, + char *optval, int optlen) +{ + mm_segment_t oldfs = get_fs(); + int err; + + set_fs(KERNEL_DS); + if (level == SOL_SOCKET) + err = sock_setsockopt(sock, level, optname, optval, optlen); + else + err = sock->ops->setsockopt(sock, level, optname, optval, + optlen); + set_fs(oldfs); + return err; +} + +int kernel_sendpage(struct socket *sock, struct page *page, int offset, + size_t size, int flags) +{ + if (sock->ops->sendpage) + return sock->ops->sendpage(sock, page, offset, size, flags); + + return sock_no_sendpage(sock, page, offset, size, flags); +} + +int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg) +{ + mm_segment_t oldfs = get_fs(); + int err; + + set_fs(KERNEL_DS); + err = sock->ops->ioctl(sock, cmd, arg); + set_fs(oldfs); + + return err; +} + /* ABI emulation layers need these two */ EXPORT_SYMBOL(move_addr_to_kernel); EXPORT_SYMBOL(move_addr_to_user); @@ -2177,3 +2311,13 @@ EXPORT_SYMBOL(sock_wake_async); EXPORT_SYMBOL(sockfd_lookup); EXPORT_SYMBOL(kernel_sendmsg); EXPORT_SYMBOL(kernel_recvmsg); +EXPORT_SYMBOL(kernel_bind); +EXPORT_SYMBOL(kernel_listen); +EXPORT_SYMBOL(kernel_accept); +EXPORT_SYMBOL(kernel_connect); +EXPORT_SYMBOL(kernel_getsockname); +EXPORT_SYMBOL(kernel_getpeername); +EXPORT_SYMBOL(kernel_getsockopt); +EXPORT_SYMBOL(kernel_setsockopt); +EXPORT_SYMBOL(kernel_sendpage); +EXPORT_SYMBOL(kernel_sock_ioctl); diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index eb330d4f66d..6f17527b9e6 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -168,7 +168,7 @@ int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb) return -1; if ((unsigned short)csum_fold(desc.csum)) return -1; - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); return 0; no_checksum: diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index d9a95732df4..953aff89bca 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -388,7 +388,7 @@ svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr) /* send head */ if (slen == xdr->head[0].iov_len) flags = 0; - len = sock->ops->sendpage(sock, rqstp->rq_respages[0], 0, xdr->head[0].iov_len, flags); + len = kernel_sendpage(sock, rqstp->rq_respages[0], 0, xdr->head[0].iov_len, flags); if (len != xdr->head[0].iov_len) goto out; slen -= xdr->head[0].iov_len; @@ -400,7 +400,7 @@ svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr) while (pglen > 0) { if (slen == size) flags = 0; - result = sock->ops->sendpage(sock, *ppage, base, size, flags); + result = kernel_sendpage(sock, *ppage, base, size, flags); if (result > 0) len += result; if (result != size) @@ -413,7 +413,7 @@ svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr) } /* send tail */ if (xdr->tail[0].iov_len) { - result = sock->ops->sendpage(sock, rqstp->rq_respages[rqstp->rq_restailpage], + result = kernel_sendpage(sock, rqstp->rq_respages[rqstp->rq_restailpage], ((unsigned long)xdr->tail[0].iov_base)& (PAGE_SIZE-1), xdr->tail[0].iov_len, 0); @@ -434,13 +434,10 @@ out: static int svc_recv_available(struct svc_sock *svsk) { - mm_segment_t oldfs; struct socket *sock = svsk->sk_sock; int avail, err; - oldfs = get_fs(); set_fs(KERNEL_DS); - err = sock->ops->ioctl(sock, TIOCINQ, (unsigned long) &avail); - set_fs(oldfs); + err = kernel_sock_ioctl(sock, TIOCINQ, (unsigned long) &avail); return (err >= 0)? avail : err; } @@ -472,7 +469,7 @@ svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, int buflen) * at accept time. FIXME */ alen = sizeof(rqstp->rq_addr); - sock->ops->getname(sock, (struct sockaddr *)&rqstp->rq_addr, &alen, 1); + kernel_getpeername(sock, (struct sockaddr *)&rqstp->rq_addr, &alen); dprintk("svc: socket %p recvfrom(%p, %Zu) = %d\n", rqstp->rq_sock, iov[0].iov_base, iov[0].iov_len, len); @@ -758,7 +755,6 @@ svc_tcp_accept(struct svc_sock *svsk) struct svc_serv *serv = svsk->sk_server; struct socket *sock = svsk->sk_sock; struct socket *newsock; - const struct proto_ops *ops; struct svc_sock *newsvsk; int err, slen; @@ -766,29 +762,23 @@ svc_tcp_accept(struct svc_sock *svsk) if (!sock) return; - err = sock_create_lite(PF_INET, SOCK_STREAM, IPPROTO_TCP, &newsock); - if (err) { + clear_bit(SK_CONN, &svsk->sk_flags); + err = kernel_accept(sock, &newsock, O_NONBLOCK); + if (err < 0) { if (err == -ENOMEM) printk(KERN_WARNING "%s: no more sockets!\n", serv->sv_name); - return; - } - - dprintk("svc: tcp_accept %p allocated\n", newsock); - newsock->ops = ops = sock->ops; - - clear_bit(SK_CONN, &svsk->sk_flags); - if ((err = ops->accept(sock, newsock, O_NONBLOCK)) < 0) { - if (err != -EAGAIN && net_ratelimit()) + else if (err != -EAGAIN && net_ratelimit()) printk(KERN_WARNING "%s: accept failed (err %d)!\n", serv->sv_name, -err); - goto failed; /* aborted connection or whatever */ + return; } + set_bit(SK_CONN, &svsk->sk_flags); svc_sock_enqueue(svsk); slen = sizeof(sin); - err = ops->getname(newsock, (struct sockaddr *) &sin, &slen, 1); + err = kernel_getpeername(newsock, (struct sockaddr *) &sin, &slen); if (err < 0) { if (net_ratelimit()) printk(KERN_WARNING "%s: peername failed (err %d)!\n", @@ -1406,14 +1396,14 @@ svc_create_socket(struct svc_serv *serv, int protocol, struct sockaddr_in *sin) if (sin != NULL) { if (type == SOCK_STREAM) sock->sk->sk_reuse = 1; /* allow address reuse */ - error = sock->ops->bind(sock, (struct sockaddr *) sin, + error = kernel_bind(sock, (struct sockaddr *) sin, sizeof(*sin)); if (error < 0) goto bummer; } if (protocol == IPPROTO_TCP) { - if ((error = sock->ops->listen(sock, 64)) < 0) + if ((error = kernel_listen(sock, 64)) < 0) goto bummer; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 441bd53f5ec..897bdd98231 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -174,7 +174,6 @@ static inline int xs_sendpages(struct socket *sock, struct sockaddr *addr, int a struct page **ppage = xdr->pages; unsigned int len, pglen = xdr->page_len; int err, ret = 0; - ssize_t (*sendpage)(struct socket *, struct page *, int, size_t, int); if (unlikely(!sock)) return -ENOTCONN; @@ -207,7 +206,6 @@ static inline int xs_sendpages(struct socket *sock, struct sockaddr *addr, int a base &= ~PAGE_CACHE_MASK; } - sendpage = sock->ops->sendpage ? : sock_no_sendpage; do { int flags = XS_SENDMSG_FLAGS; @@ -220,10 +218,7 @@ static inline int xs_sendpages(struct socket *sock, struct sockaddr *addr, int a if (pglen != len || xdr->tail[0].iov_len != 0) flags |= MSG_MORE; - /* Hmm... We might be dealing with highmem pages */ - if (PageHighMem(*ppage)) - sendpage = sock_no_sendpage; - err = sendpage(sock, *ppage, base, len, flags); + err = kernel_sendpage(sock, *ppage, base, len, flags); if (ret == 0) ret = err; else if (err > 0) @@ -986,7 +981,7 @@ static int xs_bindresvport(struct rpc_xprt *xprt, struct socket *sock) do { myaddr.sin_port = htons(port); - err = sock->ops->bind(sock, (struct sockaddr *) &myaddr, + err = kernel_bind(sock, (struct sockaddr *) &myaddr, sizeof(myaddr)); if (err == 0) { xprt->port = port; @@ -1081,7 +1076,7 @@ static void xs_tcp_reuse_connection(struct rpc_xprt *xprt) */ memset(&any, 0, sizeof(any)); any.sa_family = AF_UNSPEC; - result = sock->ops->connect(sock, &any, sizeof(any), 0); + result = kernel_connect(sock, &any, sizeof(any), 0); if (result) dprintk("RPC: AF_UNSPEC connect return code %d\n", result); @@ -1151,7 +1146,7 @@ static void xs_tcp_connect_worker(void *args) /* Tell the socket layer to start connecting... */ xprt->stat.connect_count++; xprt->stat.connect_start = jiffies; - status = sock->ops->connect(sock, (struct sockaddr *) &xprt->addr, + status = kernel_connect(sock, (struct sockaddr *) &xprt->addr, sizeof(xprt->addr), O_NONBLOCK); dprintk("RPC: %p connect status %d connected %d sock state %d\n", xprt, -status, xprt_connected(xprt), sock->sk->sk_state); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index de6ec519272..b43a27828df 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -117,7 +117,7 @@ #include <net/checksum.h> #include <linux/security.h> -int sysctl_unix_max_dgram_qlen = 10; +int sysctl_unix_max_dgram_qlen __read_mostly = 10; struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; DEFINE_SPINLOCK(unix_table_lock); @@ -2060,10 +2060,7 @@ static int __init af_unix_init(void) int rc = -1; struct sk_buff *dummy_skb; - if (sizeof(struct unix_skb_parms) > sizeof(dummy_skb->cb)) { - printk(KERN_CRIT "%s: panic\n", __FUNCTION__); - goto out; - } + BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof(dummy_skb->cb)); rc = proto_register(&unix_proto, 1); if (rc != 0) { diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index 0c1c04322ba..0faab633258 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -6,14 +6,24 @@ config XFRM depends on NET config XFRM_USER - tristate "IPsec user configuration interface" + tristate "Transformation user configuration interface" depends on INET && XFRM ---help--- - Support for IPsec user configuration interface used - by native Linux tools. + Support for Transformation(XFRM) user configuration interface + like IPsec used by native Linux tools. If unsure, say Y. +config XFRM_SUB_POLICY + bool "Transformation sub policy support (EXPERIMENTAL)" + depends on XFRM && EXPERIMENTAL + ---help--- + Support sub policy for developers. By using sub policy with main + one, two policies can be applied to the same packet at once. + Policy which lives shorter time in kernel should be a sub. + + If unsure, say N. + config NET_KEY tristate "PF_KEY sockets" select XFRM diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 693aac1aa83..de3c1a625a4 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -2,6 +2,7 @@ # Makefile for the XFRM subsystem. # -obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_input.o xfrm_algo.o +obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ + xfrm_input.o xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o diff --git a/net/xfrm/xfrm_hash.c b/net/xfrm/xfrm_hash.c new file mode 100644 index 00000000000..37643bb8768 --- /dev/null +++ b/net/xfrm/xfrm_hash.c @@ -0,0 +1,41 @@ +/* xfrm_hash.c: Common hash table code. + * + * Copyright (C) 2006 David S. Miller (davem@davemloft.net) + */ + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/bootmem.h> +#include <linux/vmalloc.h> +#include <linux/slab.h> +#include <linux/xfrm.h> + +#include "xfrm_hash.h" + +struct hlist_head *xfrm_hash_alloc(unsigned int sz) +{ + struct hlist_head *n; + + if (sz <= PAGE_SIZE) + n = kmalloc(sz, GFP_KERNEL); + else if (hashdist) + n = __vmalloc(sz, GFP_KERNEL, PAGE_KERNEL); + else + n = (struct hlist_head *) + __get_free_pages(GFP_KERNEL, get_order(sz)); + + if (n) + memset(n, 0, sz); + + return n; +} + +void xfrm_hash_free(struct hlist_head *n, unsigned int sz) +{ + if (sz <= PAGE_SIZE) + kfree(n); + else if (hashdist) + vfree(n); + else + free_pages((unsigned long)n, get_order(sz)); +} diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h new file mode 100644 index 00000000000..d3abb0b7dc6 --- /dev/null +++ b/net/xfrm/xfrm_hash.h @@ -0,0 +1,128 @@ +#ifndef _XFRM_HASH_H +#define _XFRM_HASH_H + +#include <linux/xfrm.h> +#include <linux/socket.h> + +static inline unsigned int __xfrm4_addr_hash(xfrm_address_t *addr) +{ + return ntohl(addr->a4); +} + +static inline unsigned int __xfrm6_addr_hash(xfrm_address_t *addr) +{ + return ntohl(addr->a6[2] ^ addr->a6[3]); +} + +static inline unsigned int __xfrm4_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) +{ + return ntohl(daddr->a4 ^ saddr->a4); +} + +static inline unsigned int __xfrm6_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) +{ + return ntohl(daddr->a6[2] ^ daddr->a6[3] ^ + saddr->a6[2] ^ saddr->a6[3]); +} + +static inline unsigned int __xfrm_dst_hash(xfrm_address_t *daddr, xfrm_address_t *saddr, + u32 reqid, unsigned short family, + unsigned int hmask) +{ + unsigned int h = family ^ reqid; + switch (family) { + case AF_INET: + h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); + break; + case AF_INET6: + h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); + break; + } + return (h ^ (h >> 16)) & hmask; +} + +static inline unsigned __xfrm_src_hash(xfrm_address_t *saddr, + unsigned short family, + unsigned int hmask) +{ + unsigned int h = family; + switch (family) { + case AF_INET: + h ^= __xfrm4_addr_hash(saddr); + break; + case AF_INET6: + h ^= __xfrm6_addr_hash(saddr); + break; + }; + return (h ^ (h >> 16)) & hmask; +} + +static inline unsigned int +__xfrm_spi_hash(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family, + unsigned int hmask) +{ + unsigned int h = spi ^ proto; + switch (family) { + case AF_INET: + h ^= __xfrm4_addr_hash(daddr); + break; + case AF_INET6: + h ^= __xfrm6_addr_hash(daddr); + break; + } + return (h ^ (h >> 10) ^ (h >> 20)) & hmask; +} + +static inline unsigned int __idx_hash(u32 index, unsigned int hmask) +{ + return (index ^ (index >> 8)) & hmask; +} + +static inline unsigned int __sel_hash(struct xfrm_selector *sel, unsigned short family, unsigned int hmask) +{ + xfrm_address_t *daddr = &sel->daddr; + xfrm_address_t *saddr = &sel->saddr; + unsigned int h = 0; + + switch (family) { + case AF_INET: + if (sel->prefixlen_d != 32 || + sel->prefixlen_s != 32) + return hmask + 1; + + h = __xfrm4_daddr_saddr_hash(daddr, saddr); + break; + + case AF_INET6: + if (sel->prefixlen_d != 128 || + sel->prefixlen_s != 128) + return hmask + 1; + + h = __xfrm6_daddr_saddr_hash(daddr, saddr); + break; + }; + h ^= (h >> 16); + return h & hmask; +} + +static inline unsigned int __addr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, unsigned int hmask) +{ + unsigned int h = 0; + + switch (family) { + case AF_INET: + h = __xfrm4_daddr_saddr_hash(daddr, saddr); + break; + + case AF_INET6: + h = __xfrm6_daddr_saddr_hash(daddr, saddr); + break; + }; + h ^= (h >> 16); + return h & hmask; +} + +extern struct hlist_head *xfrm_hash_alloc(unsigned int sz); +extern void xfrm_hash_free(struct hlist_head *n, unsigned int sz); + +#endif /* _XFRM_HASH_H */ diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 891a6090cc0..dfc90bb1cf1 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -82,8 +82,6 @@ void __init xfrm_input_init(void) { secpath_cachep = kmem_cache_create("secpath_cache", sizeof(struct sec_path), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!secpath_cachep) - panic("XFRM: failed to allocate secpath_cache\n"); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 3da67ca2c3c..b6e2e79d726 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -22,16 +22,19 @@ #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/module.h> +#include <linux/cache.h> #include <net/xfrm.h> #include <net/ip.h> +#include "xfrm_hash.h" + DEFINE_MUTEX(xfrm_cfg_mutex); EXPORT_SYMBOL(xfrm_cfg_mutex); static DEFINE_RWLOCK(xfrm_policy_lock); -struct xfrm_policy *xfrm_policy_list[XFRM_POLICY_MAX*2]; -EXPORT_SYMBOL(xfrm_policy_list); +unsigned int xfrm_policy_count[XFRM_POLICY_MAX*2]; +EXPORT_SYMBOL(xfrm_policy_count); static DEFINE_RWLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo *xfrm_policy_afinfo[NPROTO]; @@ -39,8 +42,7 @@ static struct xfrm_policy_afinfo *xfrm_policy_afinfo[NPROTO]; static kmem_cache_t *xfrm_dst_cache __read_mostly; static struct work_struct xfrm_policy_gc_work; -static struct list_head xfrm_policy_gc_list = - LIST_HEAD_INIT(xfrm_policy_gc_list); +static HLIST_HEAD(xfrm_policy_gc_list); static DEFINE_SPINLOCK(xfrm_policy_gc_lock); static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family); @@ -310,8 +312,10 @@ struct xfrm_policy *xfrm_policy_alloc(gfp_t gfp) policy = kzalloc(sizeof(struct xfrm_policy), gfp); if (policy) { - atomic_set(&policy->refcnt, 1); + INIT_HLIST_NODE(&policy->bydst); + INIT_HLIST_NODE(&policy->byidx); rwlock_init(&policy->lock); + atomic_set(&policy->refcnt, 1); init_timer(&policy->timer); policy->timer.data = (unsigned long)policy; policy->timer.function = xfrm_policy_timer; @@ -357,17 +361,16 @@ static void xfrm_policy_gc_kill(struct xfrm_policy *policy) static void xfrm_policy_gc_task(void *data) { struct xfrm_policy *policy; - struct list_head *entry, *tmp; - struct list_head gc_list = LIST_HEAD_INIT(gc_list); + struct hlist_node *entry, *tmp; + struct hlist_head gc_list; spin_lock_bh(&xfrm_policy_gc_lock); - list_splice_init(&xfrm_policy_gc_list, &gc_list); + gc_list.first = xfrm_policy_gc_list.first; + INIT_HLIST_HEAD(&xfrm_policy_gc_list); spin_unlock_bh(&xfrm_policy_gc_lock); - list_for_each_safe(entry, tmp, &gc_list) { - policy = list_entry(entry, struct xfrm_policy, list); + hlist_for_each_entry_safe(policy, entry, tmp, &gc_list, bydst) xfrm_policy_gc_kill(policy); - } } /* Rule must be locked. Release descentant resources, announce @@ -389,70 +392,275 @@ static void xfrm_policy_kill(struct xfrm_policy *policy) } spin_lock(&xfrm_policy_gc_lock); - list_add(&policy->list, &xfrm_policy_gc_list); + hlist_add_head(&policy->bydst, &xfrm_policy_gc_list); spin_unlock(&xfrm_policy_gc_lock); schedule_work(&xfrm_policy_gc_work); } +struct xfrm_policy_hash { + struct hlist_head *table; + unsigned int hmask; +}; + +static struct hlist_head xfrm_policy_inexact[XFRM_POLICY_MAX*2]; +static struct xfrm_policy_hash xfrm_policy_bydst[XFRM_POLICY_MAX*2] __read_mostly; +static struct hlist_head *xfrm_policy_byidx __read_mostly; +static unsigned int xfrm_idx_hmask __read_mostly; +static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024; + +static inline unsigned int idx_hash(u32 index) +{ + return __idx_hash(index, xfrm_idx_hmask); +} + +static struct hlist_head *policy_hash_bysel(struct xfrm_selector *sel, unsigned short family, int dir) +{ + unsigned int hmask = xfrm_policy_bydst[dir].hmask; + unsigned int hash = __sel_hash(sel, family, hmask); + + return (hash == hmask + 1 ? + &xfrm_policy_inexact[dir] : + xfrm_policy_bydst[dir].table + hash); +} + +static struct hlist_head *policy_hash_direct(xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, int dir) +{ + unsigned int hmask = xfrm_policy_bydst[dir].hmask; + unsigned int hash = __addr_hash(daddr, saddr, family, hmask); + + return xfrm_policy_bydst[dir].table + hash; +} + +static void xfrm_dst_hash_transfer(struct hlist_head *list, + struct hlist_head *ndsttable, + unsigned int nhashmask) +{ + struct hlist_node *entry, *tmp; + struct xfrm_policy *pol; + + hlist_for_each_entry_safe(pol, entry, tmp, list, bydst) { + unsigned int h; + + h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr, + pol->family, nhashmask); + hlist_add_head(&pol->bydst, ndsttable+h); + } +} + +static void xfrm_idx_hash_transfer(struct hlist_head *list, + struct hlist_head *nidxtable, + unsigned int nhashmask) +{ + struct hlist_node *entry, *tmp; + struct xfrm_policy *pol; + + hlist_for_each_entry_safe(pol, entry, tmp, list, byidx) { + unsigned int h; + + h = __idx_hash(pol->index, nhashmask); + hlist_add_head(&pol->byidx, nidxtable+h); + } +} + +static unsigned long xfrm_new_hash_mask(unsigned int old_hmask) +{ + return ((old_hmask + 1) << 1) - 1; +} + +static void xfrm_bydst_resize(int dir) +{ + unsigned int hmask = xfrm_policy_bydst[dir].hmask; + unsigned int nhashmask = xfrm_new_hash_mask(hmask); + unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); + struct hlist_head *odst = xfrm_policy_bydst[dir].table; + struct hlist_head *ndst = xfrm_hash_alloc(nsize); + int i; + + if (!ndst) + return; + + write_lock_bh(&xfrm_policy_lock); + + for (i = hmask; i >= 0; i--) + xfrm_dst_hash_transfer(odst + i, ndst, nhashmask); + + xfrm_policy_bydst[dir].table = ndst; + xfrm_policy_bydst[dir].hmask = nhashmask; + + write_unlock_bh(&xfrm_policy_lock); + + xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); +} + +static void xfrm_byidx_resize(int total) +{ + unsigned int hmask = xfrm_idx_hmask; + unsigned int nhashmask = xfrm_new_hash_mask(hmask); + unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); + struct hlist_head *oidx = xfrm_policy_byidx; + struct hlist_head *nidx = xfrm_hash_alloc(nsize); + int i; + + if (!nidx) + return; + + write_lock_bh(&xfrm_policy_lock); + + for (i = hmask; i >= 0; i--) + xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); + + xfrm_policy_byidx = nidx; + xfrm_idx_hmask = nhashmask; + + write_unlock_bh(&xfrm_policy_lock); + + xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); +} + +static inline int xfrm_bydst_should_resize(int dir, int *total) +{ + unsigned int cnt = xfrm_policy_count[dir]; + unsigned int hmask = xfrm_policy_bydst[dir].hmask; + + if (total) + *total += cnt; + + if ((hmask + 1) < xfrm_policy_hashmax && + cnt > hmask) + return 1; + + return 0; +} + +static inline int xfrm_byidx_should_resize(int total) +{ + unsigned int hmask = xfrm_idx_hmask; + + if ((hmask + 1) < xfrm_policy_hashmax && + total > hmask) + return 1; + + return 0; +} + +static DEFINE_MUTEX(hash_resize_mutex); + +static void xfrm_hash_resize(void *__unused) +{ + int dir, total; + + mutex_lock(&hash_resize_mutex); + + total = 0; + for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { + if (xfrm_bydst_should_resize(dir, &total)) + xfrm_bydst_resize(dir); + } + if (xfrm_byidx_should_resize(total)) + xfrm_byidx_resize(total); + + mutex_unlock(&hash_resize_mutex); +} + +static DECLARE_WORK(xfrm_hash_work, xfrm_hash_resize, NULL); + /* Generate new index... KAME seems to generate them ordered by cost * of an absolute inpredictability of ordering of rules. This will not pass. */ -static u32 xfrm_gen_index(int dir) +static u32 xfrm_gen_index(u8 type, int dir) { - u32 idx; - struct xfrm_policy *p; static u32 idx_generator; for (;;) { + struct hlist_node *entry; + struct hlist_head *list; + struct xfrm_policy *p; + u32 idx; + int found; + idx = (idx_generator | dir); idx_generator += 8; if (idx == 0) idx = 8; - for (p = xfrm_policy_list[dir]; p; p = p->next) { - if (p->index == idx) + list = xfrm_policy_byidx + idx_hash(idx); + found = 0; + hlist_for_each_entry(p, entry, list, byidx) { + if (p->index == idx) { + found = 1; break; + } } - if (!p) + if (!found) return idx; } } +static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s2) +{ + u32 *p1 = (u32 *) s1; + u32 *p2 = (u32 *) s2; + int len = sizeof(struct xfrm_selector) / sizeof(u32); + int i; + + for (i = 0; i < len; i++) { + if (p1[i] != p2[i]) + return 1; + } + + return 0; +} + int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) { - struct xfrm_policy *pol, **p; - struct xfrm_policy *delpol = NULL; - struct xfrm_policy **newpos = NULL; + struct xfrm_policy *pol; + struct xfrm_policy *delpol; + struct hlist_head *chain; + struct hlist_node *entry, *newpos, *last; struct dst_entry *gc_list; write_lock_bh(&xfrm_policy_lock); - for (p = &xfrm_policy_list[dir]; (pol=*p)!=NULL;) { - if (!delpol && memcmp(&policy->selector, &pol->selector, sizeof(pol->selector)) == 0 && + chain = policy_hash_bysel(&policy->selector, policy->family, dir); + delpol = NULL; + newpos = NULL; + last = NULL; + hlist_for_each_entry(pol, entry, chain, bydst) { + if (!delpol && + pol->type == policy->type && + !selector_cmp(&pol->selector, &policy->selector) && xfrm_sec_ctx_match(pol->security, policy->security)) { if (excl) { write_unlock_bh(&xfrm_policy_lock); return -EEXIST; } - *p = pol->next; delpol = pol; if (policy->priority > pol->priority) continue; } else if (policy->priority >= pol->priority) { - p = &pol->next; + last = &pol->bydst; continue; } if (!newpos) - newpos = p; + newpos = &pol->bydst; if (delpol) break; - p = &pol->next; + last = &pol->bydst; } + if (!newpos) + newpos = last; if (newpos) - p = newpos; + hlist_add_after(newpos, &policy->bydst); + else + hlist_add_head(&policy->bydst, chain); xfrm_pol_hold(policy); - policy->next = *p; - *p = policy; + xfrm_policy_count[dir]++; atomic_inc(&flow_cache_genid); - policy->index = delpol ? delpol->index : xfrm_gen_index(dir); + if (delpol) { + hlist_del(&delpol->bydst); + hlist_del(&delpol->byidx); + xfrm_policy_count[dir]--; + } + policy->index = delpol ? delpol->index : xfrm_gen_index(policy->type, dir); + hlist_add_head(&policy->byidx, xfrm_policy_byidx+idx_hash(policy->index)); policy->curlft.add_time = (unsigned long)xtime.tv_sec; policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) @@ -461,10 +669,13 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) if (delpol) xfrm_policy_kill(delpol); + else if (xfrm_bydst_should_resize(dir, NULL)) + schedule_work(&xfrm_hash_work); read_lock_bh(&xfrm_policy_lock); gc_list = NULL; - for (policy = policy->next; policy; policy = policy->next) { + entry = &policy->bydst; + hlist_for_each_entry_continue(policy, entry, bydst) { struct dst_entry *dst; write_lock(&policy->lock); @@ -493,87 +704,146 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) } EXPORT_SYMBOL(xfrm_policy_insert); -struct xfrm_policy *xfrm_policy_bysel_ctx(int dir, struct xfrm_selector *sel, +struct xfrm_policy *xfrm_policy_bysel_ctx(u8 type, int dir, + struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete) { - struct xfrm_policy *pol, **p; + struct xfrm_policy *pol, *ret; + struct hlist_head *chain; + struct hlist_node *entry; write_lock_bh(&xfrm_policy_lock); - for (p = &xfrm_policy_list[dir]; (pol=*p)!=NULL; p = &pol->next) { - if ((memcmp(sel, &pol->selector, sizeof(*sel)) == 0) && - (xfrm_sec_ctx_match(ctx, pol->security))) { + chain = policy_hash_bysel(sel, sel->family, dir); + ret = NULL; + hlist_for_each_entry(pol, entry, chain, bydst) { + if (pol->type == type && + !selector_cmp(sel, &pol->selector) && + xfrm_sec_ctx_match(ctx, pol->security)) { xfrm_pol_hold(pol); - if (delete) - *p = pol->next; + if (delete) { + hlist_del(&pol->bydst); + hlist_del(&pol->byidx); + xfrm_policy_count[dir]--; + } + ret = pol; break; } } write_unlock_bh(&xfrm_policy_lock); - if (pol && delete) { + if (ret && delete) { atomic_inc(&flow_cache_genid); - xfrm_policy_kill(pol); + xfrm_policy_kill(ret); } - return pol; + return ret; } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(int dir, u32 id, int delete) +struct xfrm_policy *xfrm_policy_byid(u8 type, int dir, u32 id, int delete) { - struct xfrm_policy *pol, **p; + struct xfrm_policy *pol, *ret; + struct hlist_head *chain; + struct hlist_node *entry; write_lock_bh(&xfrm_policy_lock); - for (p = &xfrm_policy_list[dir]; (pol=*p)!=NULL; p = &pol->next) { - if (pol->index == id) { + chain = xfrm_policy_byidx + idx_hash(id); + ret = NULL; + hlist_for_each_entry(pol, entry, chain, byidx) { + if (pol->type == type && pol->index == id) { xfrm_pol_hold(pol); - if (delete) - *p = pol->next; + if (delete) { + hlist_del(&pol->bydst); + hlist_del(&pol->byidx); + xfrm_policy_count[dir]--; + } + ret = pol; break; } } write_unlock_bh(&xfrm_policy_lock); - if (pol && delete) { + if (ret && delete) { atomic_inc(&flow_cache_genid); - xfrm_policy_kill(pol); + xfrm_policy_kill(ret); } - return pol; + return ret; } EXPORT_SYMBOL(xfrm_policy_byid); -void xfrm_policy_flush(void) +void xfrm_policy_flush(u8 type) { - struct xfrm_policy *xp; int dir; write_lock_bh(&xfrm_policy_lock); for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { - while ((xp = xfrm_policy_list[dir]) != NULL) { - xfrm_policy_list[dir] = xp->next; + struct xfrm_policy *pol; + struct hlist_node *entry; + int i; + + again1: + hlist_for_each_entry(pol, entry, + &xfrm_policy_inexact[dir], bydst) { + if (pol->type != type) + continue; + hlist_del(&pol->bydst); + hlist_del(&pol->byidx); write_unlock_bh(&xfrm_policy_lock); - xfrm_policy_kill(xp); + xfrm_policy_kill(pol); write_lock_bh(&xfrm_policy_lock); + goto again1; } + + for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { + again2: + hlist_for_each_entry(pol, entry, + xfrm_policy_bydst[dir].table + i, + bydst) { + if (pol->type != type) + continue; + hlist_del(&pol->bydst); + hlist_del(&pol->byidx); + write_unlock_bh(&xfrm_policy_lock); + + xfrm_policy_kill(pol); + + write_lock_bh(&xfrm_policy_lock); + goto again2; + } + } + + xfrm_policy_count[dir] = 0; } atomic_inc(&flow_cache_genid); write_unlock_bh(&xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_policy_flush); -int xfrm_policy_walk(int (*func)(struct xfrm_policy *, int, int, void*), +int xfrm_policy_walk(u8 type, int (*func)(struct xfrm_policy *, int, int, void*), void *data) { - struct xfrm_policy *xp; - int dir; - int count = 0; - int error = 0; + struct xfrm_policy *pol; + struct hlist_node *entry; + int dir, count, error; read_lock_bh(&xfrm_policy_lock); + count = 0; for (dir = 0; dir < 2*XFRM_POLICY_MAX; dir++) { - for (xp = xfrm_policy_list[dir]; xp; xp = xp->next) - count++; + struct hlist_head *table = xfrm_policy_bydst[dir].table; + int i; + + hlist_for_each_entry(pol, entry, + &xfrm_policy_inexact[dir], bydst) { + if (pol->type == type) + count++; + } + for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { + hlist_for_each_entry(pol, entry, table + i, bydst) { + if (pol->type == type) + count++; + } + } } if (count == 0) { @@ -582,13 +852,28 @@ int xfrm_policy_walk(int (*func)(struct xfrm_policy *, int, int, void*), } for (dir = 0; dir < 2*XFRM_POLICY_MAX; dir++) { - for (xp = xfrm_policy_list[dir]; xp; xp = xp->next) { - error = func(xp, dir%XFRM_POLICY_MAX, --count, data); + struct hlist_head *table = xfrm_policy_bydst[dir].table; + int i; + + hlist_for_each_entry(pol, entry, + &xfrm_policy_inexact[dir], bydst) { + if (pol->type != type) + continue; + error = func(pol, dir % XFRM_POLICY_MAX, --count, data); if (error) goto out; } + for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { + hlist_for_each_entry(pol, entry, table + i, bydst) { + if (pol->type != type) + continue; + error = func(pol, dir % XFRM_POLICY_MAX, --count, data); + if (error) + goto out; + } + } } - + error = 0; out: read_unlock_bh(&xfrm_policy_lock); return error; @@ -597,29 +882,79 @@ EXPORT_SYMBOL(xfrm_policy_walk); /* Find policy to apply to this flow. */ -static void xfrm_policy_lookup(struct flowi *fl, u32 sk_sid, u16 family, u8 dir, - void **objp, atomic_t **obj_refp) +static int xfrm_policy_match(struct xfrm_policy *pol, struct flowi *fl, + u8 type, u16 family, int dir) { - struct xfrm_policy *pol; + struct xfrm_selector *sel = &pol->selector; + int match; - read_lock_bh(&xfrm_policy_lock); - for (pol = xfrm_policy_list[dir]; pol; pol = pol->next) { - struct xfrm_selector *sel = &pol->selector; - int match; + if (pol->family != family || + pol->type != type) + return 0; - if (pol->family != family) - continue; + match = xfrm_selector_match(sel, fl, family); + if (match) { + if (!security_xfrm_policy_lookup(pol, fl->secid, dir)) + return 1; + } - match = xfrm_selector_match(sel, fl, family); + return 0; +} - if (match) { - if (!security_xfrm_policy_lookup(pol, sk_sid, dir)) { - xfrm_pol_hold(pol); - break; - } +static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, + u16 family, u8 dir) +{ + struct xfrm_policy *pol, *ret; + xfrm_address_t *daddr, *saddr; + struct hlist_node *entry; + struct hlist_head *chain; + u32 priority = ~0U; + + daddr = xfrm_flowi_daddr(fl, family); + saddr = xfrm_flowi_saddr(fl, family); + if (unlikely(!daddr || !saddr)) + return NULL; + + read_lock_bh(&xfrm_policy_lock); + chain = policy_hash_direct(daddr, saddr, family, dir); + ret = NULL; + hlist_for_each_entry(pol, entry, chain, bydst) { + if (xfrm_policy_match(pol, fl, type, family, dir)) { + ret = pol; + priority = ret->priority; + break; + } + } + chain = &xfrm_policy_inexact[dir]; + hlist_for_each_entry(pol, entry, chain, bydst) { + if (xfrm_policy_match(pol, fl, type, family, dir) && + pol->priority < priority) { + ret = pol; + break; } } + if (ret) + xfrm_pol_hold(ret); read_unlock_bh(&xfrm_policy_lock); + + return ret; +} + +static void xfrm_policy_lookup(struct flowi *fl, u16 family, u8 dir, + void **objp, atomic_t **obj_refp) +{ + struct xfrm_policy *pol; + +#ifdef CONFIG_XFRM_SUB_POLICY + pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_SUB, fl, family, dir); + if (pol) + goto end; +#endif + pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, fl, family, dir); + +#ifdef CONFIG_XFRM_SUB_POLICY +end: +#endif if ((*objp = (void *) pol) != NULL) *obj_refp = &pol->refcnt; } @@ -641,7 +976,7 @@ static inline int policy_to_flow_dir(int dir) }; } -static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struct flowi *fl, u32 sk_sid) +static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struct flowi *fl) { struct xfrm_policy *pol; @@ -652,7 +987,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struc int err = 0; if (match) - err = security_xfrm_policy_lookup(pol, sk_sid, policy_to_flow_dir(dir)); + err = security_xfrm_policy_lookup(pol, fl->secid, policy_to_flow_dir(dir)); if (match && !err) xfrm_pol_hold(pol); @@ -665,24 +1000,29 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struc static void __xfrm_policy_link(struct xfrm_policy *pol, int dir) { - pol->next = xfrm_policy_list[dir]; - xfrm_policy_list[dir] = pol; + struct hlist_head *chain = policy_hash_bysel(&pol->selector, + pol->family, dir); + + hlist_add_head(&pol->bydst, chain); + hlist_add_head(&pol->byidx, xfrm_policy_byidx+idx_hash(pol->index)); + xfrm_policy_count[dir]++; xfrm_pol_hold(pol); + + if (xfrm_bydst_should_resize(dir, NULL)) + schedule_work(&xfrm_hash_work); } static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir) { - struct xfrm_policy **polp; + if (hlist_unhashed(&pol->bydst)) + return NULL; - for (polp = &xfrm_policy_list[dir]; - *polp != NULL; polp = &(*polp)->next) { - if (*polp == pol) { - *polp = pol->next; - return pol; - } - } - return NULL; + hlist_del(&pol->bydst); + hlist_del(&pol->byidx); + xfrm_policy_count[dir]--; + + return pol; } int xfrm_policy_delete(struct xfrm_policy *pol, int dir) @@ -704,12 +1044,17 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) { struct xfrm_policy *old_pol; +#ifdef CONFIG_XFRM_SUB_POLICY + if (pol && pol->type != XFRM_POLICY_TYPE_MAIN) + return -EINVAL; +#endif + write_lock_bh(&xfrm_policy_lock); old_pol = sk->sk_policy[dir]; sk->sk_policy[dir] = pol; if (pol) { pol->curlft.add_time = (unsigned long)xtime.tv_sec; - pol->index = xfrm_gen_index(XFRM_POLICY_MAX+dir); + pol->index = xfrm_gen_index(pol->type, XFRM_POLICY_MAX+dir); __xfrm_policy_link(pol, XFRM_POLICY_MAX+dir); } if (old_pol) @@ -738,6 +1083,7 @@ static struct xfrm_policy *clone_policy(struct xfrm_policy *old, int dir) newp->flags = old->flags; newp->xfrm_nr = old->xfrm_nr; newp->index = old->index; + newp->type = old->type; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); write_lock_bh(&xfrm_policy_lock); @@ -761,17 +1107,32 @@ int __xfrm_sk_clone_policy(struct sock *sk) return 0; } +static int +xfrm_get_saddr(xfrm_address_t *local, xfrm_address_t *remote, + unsigned short family) +{ + int err; + struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); + + if (unlikely(afinfo == NULL)) + return -EINVAL; + err = afinfo->get_saddr(local, remote); + xfrm_policy_put_afinfo(afinfo); + return err; +} + /* Resolve list of templates for the flow, given policy. */ static int -xfrm_tmpl_resolve(struct xfrm_policy *policy, struct flowi *fl, - struct xfrm_state **xfrm, - unsigned short family) +xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, + struct xfrm_state **xfrm, + unsigned short family) { int nx; int i, error; xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family); xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family); + xfrm_address_t tmp; for (nx=0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; @@ -779,9 +1140,15 @@ xfrm_tmpl_resolve(struct xfrm_policy *policy, struct flowi *fl, xfrm_address_t *local = saddr; struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i]; - if (tmpl->mode) { + if (tmpl->mode == XFRM_MODE_TUNNEL) { remote = &tmpl->id.daddr; local = &tmpl->saddr; + if (xfrm_addr_any(local, family)) { + error = xfrm_get_saddr(&tmp, remote, family); + if (error) + goto fail; + local = &tmp; + } } x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family); @@ -809,6 +1176,45 @@ fail: return error; } +static int +xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, struct flowi *fl, + struct xfrm_state **xfrm, + unsigned short family) +{ + struct xfrm_state *tp[XFRM_MAX_DEPTH]; + struct xfrm_state **tpp = (npols > 1) ? tp : xfrm; + int cnx = 0; + int error; + int ret; + int i; + + for (i = 0; i < npols; i++) { + if (cnx + pols[i]->xfrm_nr >= XFRM_MAX_DEPTH) { + error = -ENOBUFS; + goto fail; + } + + ret = xfrm_tmpl_resolve_one(pols[i], fl, &tpp[cnx], family); + if (ret < 0) { + error = ret; + goto fail; + } else + cnx += ret; + } + + /* found states are sorted for outbound processing */ + if (npols > 1) + xfrm_state_sort(xfrm, tpp, cnx, family); + + return cnx; + + fail: + for (cnx--; cnx>=0; cnx--) + xfrm_state_put(tpp[cnx]); + return error; + +} + /* Check that the bundle accepts the flow and its components are * still valid. */ @@ -855,6 +1261,11 @@ int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl, struct sock *sk, int flags) { struct xfrm_policy *policy; + struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; + int npols; + int pol_dead; + int xfrm_nr; + int pi; struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; struct dst_entry *dst, *dst_orig = *dst_p; int nx = 0; @@ -862,19 +1273,26 @@ int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl, u32 genid; u16 family; u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT); - u32 sk_sid = security_sk_sid(sk, fl, dir); + restart: genid = atomic_read(&flow_cache_genid); policy = NULL; + for (pi = 0; pi < ARRAY_SIZE(pols); pi++) + pols[pi] = NULL; + npols = 0; + pol_dead = 0; + xfrm_nr = 0; + if (sk && sk->sk_policy[1]) - policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, sk_sid); + policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); if (!policy) { /* To accelerate a bit... */ - if ((dst_orig->flags & DST_NOXFRM) || !xfrm_policy_list[XFRM_POLICY_OUT]) + if ((dst_orig->flags & DST_NOXFRM) || + !xfrm_policy_count[XFRM_POLICY_OUT]) return 0; - policy = flow_cache_lookup(fl, sk_sid, dst_orig->ops->family, + policy = flow_cache_lookup(fl, dst_orig->ops->family, dir, xfrm_policy_lookup); } @@ -883,6 +1301,9 @@ restart: family = dst_orig->ops->family; policy->curlft.use_time = (unsigned long)xtime.tv_sec; + pols[0] = policy; + npols ++; + xfrm_nr += pols[0]->xfrm_nr; switch (policy->action) { case XFRM_POLICY_BLOCK: @@ -891,11 +1312,13 @@ restart: goto error; case XFRM_POLICY_ALLOW: +#ifndef CONFIG_XFRM_SUB_POLICY if (policy->xfrm_nr == 0) { /* Flow passes not transformed. */ xfrm_pol_put(policy); return 0; } +#endif /* Try to find matching bundle. * @@ -911,7 +1334,36 @@ restart: if (dst) break; - nx = xfrm_tmpl_resolve(policy, fl, xfrm, family); +#ifdef CONFIG_XFRM_SUB_POLICY + if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { + pols[1] = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, + fl, family, + XFRM_POLICY_OUT); + if (pols[1]) { + if (pols[1]->action == XFRM_POLICY_BLOCK) { + err = -EPERM; + goto error; + } + npols ++; + xfrm_nr += pols[1]->xfrm_nr; + } + } + + /* + * Because neither flowi nor bundle information knows about + * transformation template size. On more than one policy usage + * we can realize whether all of them is bypass or not after + * they are searched. See above not-transformed bypass + * is surrounded by non-sub policy configuration, too. + */ + if (xfrm_nr == 0) { + /* Flow passes not transformed. */ + xfrm_pols_put(pols, npols); + return 0; + } + +#endif + nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family); if (unlikely(nx<0)) { err = nx; @@ -924,7 +1376,7 @@ restart: set_current_state(TASK_RUNNING); remove_wait_queue(&km_waitq, &wait); - nx = xfrm_tmpl_resolve(policy, fl, xfrm, family); + nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family); if (nx == -EAGAIN && signal_pending(current)) { err = -ERESTART; @@ -932,7 +1384,7 @@ restart: } if (nx == -EAGAIN || genid != atomic_read(&flow_cache_genid)) { - xfrm_pol_put(policy); + xfrm_pols_put(pols, npols); goto restart; } err = nx; @@ -942,7 +1394,7 @@ restart: } if (nx == 0) { /* Flow passes not transformed. */ - xfrm_pol_put(policy); + xfrm_pols_put(pols, npols); return 0; } @@ -956,8 +1408,14 @@ restart: goto error; } + for (pi = 0; pi < npols; pi++) { + read_lock_bh(&pols[pi]->lock); + pol_dead |= pols[pi]->dead; + read_unlock_bh(&pols[pi]->lock); + } + write_lock_bh(&policy->lock); - if (unlikely(policy->dead || stale_bundle(dst))) { + if (unlikely(pol_dead || stale_bundle(dst))) { /* Wow! While we worked on resolving, this * policy has gone. Retry. It is not paranoia, * we just cannot enlist new bundle to dead object. @@ -977,17 +1435,34 @@ restart: } *dst_p = dst; dst_release(dst_orig); - xfrm_pol_put(policy); + xfrm_pols_put(pols, npols); return 0; error: dst_release(dst_orig); - xfrm_pol_put(policy); + xfrm_pols_put(pols, npols); *dst_p = NULL; return err; } EXPORT_SYMBOL(xfrm_lookup); +static inline int +xfrm_secpath_reject(int idx, struct sk_buff *skb, struct flowi *fl) +{ + struct xfrm_state *x; + int err; + + if (!skb->sp || idx < 0 || idx >= skb->sp->len) + return 0; + x = skb->sp->xvec[idx]; + if (!x->type->reject) + return 0; + xfrm_state_hold(x); + err = x->type->reject(x, skb, fl); + xfrm_state_put(x); + return err; +} + /* When skb is transformed back to its "native" form, we have to * check policy restrictions. At the moment we make this in maximally * stupid way. Shame on me. :-) Of course, connected sockets must @@ -1004,10 +1479,19 @@ xfrm_state_ok(struct xfrm_tmpl *tmpl, struct xfrm_state *x, (x->id.spi == tmpl->id.spi || !tmpl->id.spi) && (x->props.reqid == tmpl->reqid || !tmpl->reqid) && x->props.mode == tmpl->mode && - (tmpl->aalgos & (1<<x->props.aalgo)) && - !(x->props.mode && xfrm_state_addr_cmp(tmpl, x, family)); + ((tmpl->aalgos & (1<<x->props.aalgo)) || + !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && + !(x->props.mode != XFRM_MODE_TRANSPORT && + xfrm_state_addr_cmp(tmpl, x, family)); } +/* + * 0 or more than 0 is returned when validation is succeeded (either bypass + * because of optional transport mode, or next index of the mathced secpath + * state with the template. + * -1 is returned when no matching template is found. + * Otherwise "-2 - errored_index" is returned. + */ static inline int xfrm_policy_ok(struct xfrm_tmpl *tmpl, struct sec_path *sp, int start, unsigned short family) @@ -1015,15 +1499,18 @@ xfrm_policy_ok(struct xfrm_tmpl *tmpl, struct sec_path *sp, int start, int idx = start; if (tmpl->optional) { - if (!tmpl->mode) + if (tmpl->mode == XFRM_MODE_TRANSPORT) return start; } else start = -1; for (; idx < sp->len; idx++) { if (xfrm_state_ok(tmpl, sp->xvec[idx], family)) return ++idx; - if (sp->xvec[idx]->props.mode) + if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { + if (start == -1) + start = -2-idx; break; + } } return start; } @@ -1032,21 +1519,25 @@ int xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, unsigned short family) { struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); + int err; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; afinfo->decode_session(skb, fl); + err = security_xfrm_decode_session(skb, &fl->secid); xfrm_policy_put_afinfo(afinfo); - return 0; + return err; } EXPORT_SYMBOL(xfrm_decode_session); -static inline int secpath_has_tunnel(struct sec_path *sp, int k) +static inline int secpath_has_nontransport(struct sec_path *sp, int k, int *idxp) { for (; k < sp->len; k++) { - if (sp->xvec[k]->props.mode) + if (sp->xvec[k]->props.mode != XFRM_MODE_TRANSPORT) { + *idxp = k; return 1; + } } return 0; @@ -1056,16 +1547,18 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { struct xfrm_policy *pol; + struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; + int npols = 0; + int xfrm_nr; + int pi; struct flowi fl; u8 fl_dir = policy_to_flow_dir(dir); - u32 sk_sid; + int xerr_idx = -1; if (xfrm_decode_session(skb, &fl, family) < 0) return 0; nf_nat_decode_session(skb, &fl, family); - sk_sid = security_sk_sid(sk, &fl, fl_dir); - /* First, check used SA against their selectors. */ if (skb->sp) { int i; @@ -1079,46 +1572,90 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol = NULL; if (sk && sk->sk_policy[dir]) - pol = xfrm_sk_policy_lookup(sk, dir, &fl, sk_sid); + pol = xfrm_sk_policy_lookup(sk, dir, &fl); if (!pol) - pol = flow_cache_lookup(&fl, sk_sid, family, fl_dir, + pol = flow_cache_lookup(&fl, family, fl_dir, xfrm_policy_lookup); - if (!pol) - return !skb->sp || !secpath_has_tunnel(skb->sp, 0); + if (!pol) { + if (skb->sp && secpath_has_nontransport(skb->sp, 0, &xerr_idx)) { + xfrm_secpath_reject(xerr_idx, skb, &fl); + return 0; + } + return 1; + } pol->curlft.use_time = (unsigned long)xtime.tv_sec; + pols[0] = pol; + npols ++; +#ifdef CONFIG_XFRM_SUB_POLICY + if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { + pols[1] = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, + &fl, family, + XFRM_POLICY_IN); + if (pols[1]) { + pols[1]->curlft.use_time = (unsigned long)xtime.tv_sec; + npols ++; + } + } +#endif + if (pol->action == XFRM_POLICY_ALLOW) { struct sec_path *sp; static struct sec_path dummy; + struct xfrm_tmpl *tp[XFRM_MAX_DEPTH]; + struct xfrm_tmpl *stp[XFRM_MAX_DEPTH]; + struct xfrm_tmpl **tpp = tp; + int ti = 0; int i, k; if ((sp = skb->sp) == NULL) sp = &dummy; + for (pi = 0; pi < npols; pi++) { + if (pols[pi] != pol && + pols[pi]->action != XFRM_POLICY_ALLOW) + goto reject; + if (ti + pols[pi]->xfrm_nr >= XFRM_MAX_DEPTH) + goto reject_error; + for (i = 0; i < pols[pi]->xfrm_nr; i++) + tpp[ti++] = &pols[pi]->xfrm_vec[i]; + } + xfrm_nr = ti; + if (npols > 1) { + xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); + tpp = stp; + } + /* For each tunnel xfrm, find the first matching tmpl. * For each tmpl before that, find corresponding xfrm. * Order is _important_. Later we will implement * some barriers, but at the moment barriers * are implied between each two transformations. */ - for (i = pol->xfrm_nr-1, k = 0; i >= 0; i--) { - k = xfrm_policy_ok(pol->xfrm_vec+i, sp, k, family); - if (k < 0) + for (i = xfrm_nr-1, k = 0; i >= 0; i--) { + k = xfrm_policy_ok(tpp[i], sp, k, family); + if (k < 0) { + if (k < -1) + /* "-2 - errored_index" returned */ + xerr_idx = -(2+k); goto reject; + } } - if (secpath_has_tunnel(sp, k)) + if (secpath_has_nontransport(sp, k, &xerr_idx)) goto reject; - xfrm_pol_put(pol); + xfrm_pols_put(pols, npols); return 1; } reject: - xfrm_pol_put(pol); + xfrm_secpath_reject(xerr_idx, skb, &fl); +reject_error: + xfrm_pols_put(pols, npols); return 0; } EXPORT_SYMBOL(__xfrm_policy_check); @@ -1166,7 +1703,7 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) static int stale_bundle(struct dst_entry *dst) { - return !xfrm_bundle_ok((struct xfrm_dst *)dst, NULL, AF_UNSPEC); + return !xfrm_bundle_ok((struct xfrm_dst *)dst, NULL, AF_UNSPEC, 0); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) @@ -1196,33 +1733,50 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) return dst; } +static void prune_one_bundle(struct xfrm_policy *pol, int (*func)(struct dst_entry *), struct dst_entry **gc_list_p) +{ + struct dst_entry *dst, **dstp; + + write_lock(&pol->lock); + dstp = &pol->bundles; + while ((dst=*dstp) != NULL) { + if (func(dst)) { + *dstp = dst->next; + dst->next = *gc_list_p; + *gc_list_p = dst; + } else { + dstp = &dst->next; + } + } + write_unlock(&pol->lock); +} + static void xfrm_prune_bundles(int (*func)(struct dst_entry *)) { - int i; - struct xfrm_policy *pol; - struct dst_entry *dst, **dstp, *gc_list = NULL; + struct dst_entry *gc_list = NULL; + int dir; read_lock_bh(&xfrm_policy_lock); - for (i=0; i<2*XFRM_POLICY_MAX; i++) { - for (pol = xfrm_policy_list[i]; pol; pol = pol->next) { - write_lock(&pol->lock); - dstp = &pol->bundles; - while ((dst=*dstp) != NULL) { - if (func(dst)) { - *dstp = dst->next; - dst->next = gc_list; - gc_list = dst; - } else { - dstp = &dst->next; - } - } - write_unlock(&pol->lock); + for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { + struct xfrm_policy *pol; + struct hlist_node *entry; + struct hlist_head *table; + int i; + + hlist_for_each_entry(pol, entry, + &xfrm_policy_inexact[dir], bydst) + prune_one_bundle(pol, func, &gc_list); + + table = xfrm_policy_bydst[dir].table; + for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { + hlist_for_each_entry(pol, entry, table + i, bydst) + prune_one_bundle(pol, func, &gc_list); } } read_unlock_bh(&xfrm_policy_lock); while (gc_list) { - dst = gc_list; + struct dst_entry *dst = gc_list; gc_list = dst->next; dst_free(dst); } @@ -1238,22 +1792,12 @@ static void __xfrm_garbage_collect(void) xfrm_prune_bundles(unused_bundle); } -int xfrm_flush_bundles(void) +static int xfrm_flush_bundles(void) { xfrm_prune_bundles(stale_bundle); return 0; } -static int always_true(struct dst_entry *dst) -{ - return 1; -} - -void xfrm_flush_all_bundles(void) -{ - xfrm_prune_bundles(always_true); -} - void xfrm_init_pmtu(struct dst_entry *dst) { do { @@ -1281,7 +1825,7 @@ EXPORT_SYMBOL(xfrm_init_pmtu); * still valid. */ -int xfrm_bundle_ok(struct xfrm_dst *first, struct flowi *fl, int family) +int xfrm_bundle_ok(struct xfrm_dst *first, struct flowi *fl, int family, int strict) { struct dst_entry *dst = &first->u.dst; struct xfrm_dst *last; @@ -1298,8 +1842,16 @@ int xfrm_bundle_ok(struct xfrm_dst *first, struct flowi *fl, int family) if (fl && !xfrm_selector_match(&dst->xfrm->sel, fl, family)) return 0; + if (fl && !security_xfrm_flow_state_match(fl, dst->xfrm)) + return 0; if (dst->xfrm->km.state != XFRM_STATE_VALID) return 0; + if (xdst->genid != dst->xfrm->genid) + return 0; + + if (strict && fl && dst->xfrm->props.mode != XFRM_MODE_TUNNEL && + !xfrm_state_addr_flow_check(dst->xfrm, fl, family)) + return 0; mtu = dst_mtu(dst->child); if (xdst->child_mtu_cached != mtu) { @@ -1448,12 +2000,33 @@ static struct notifier_block xfrm_dev_notifier = { static void __init xfrm_policy_init(void) { + unsigned int hmask, sz; + int dir; + xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", sizeof(struct xfrm_dst), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!xfrm_dst_cache) - panic("XFRM: failed to allocate xfrm_dst_cache\n"); + + hmask = 8 - 1; + sz = (hmask+1) * sizeof(struct hlist_head); + + xfrm_policy_byidx = xfrm_hash_alloc(sz); + xfrm_idx_hmask = hmask; + if (!xfrm_policy_byidx) + panic("XFRM: failed to allocate byidx hash\n"); + + for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { + struct xfrm_policy_hash *htab; + + INIT_HLIST_HEAD(&xfrm_policy_inexact[dir]); + + htab = &xfrm_policy_bydst[dir]; + htab->table = xfrm_hash_alloc(sz); + htab->hmask = hmask; + if (!htab->table) + panic("XFRM: failed to allocate bydst hash\n"); + } INIT_WORK(&xfrm_policy_gc_work, xfrm_policy_gc_task, NULL); register_netdevice_notifier(&xfrm_dev_notifier); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 0021aad5db4..9f63edd3934 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -18,8 +18,11 @@ #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/module.h> +#include <linux/cache.h> #include <asm/uaccess.h> +#include "xfrm_hash.h" + struct sock *xfrm_nl; EXPORT_SYMBOL(xfrm_nl); @@ -32,7 +35,7 @@ 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) - 2. Hash table by daddr to find what SAs exist for given + 2. Hash table by (daddr,family,reqid) to find what SAs exist for given destination/tunnel endpoint. (output) */ @@ -44,8 +47,123 @@ static DEFINE_SPINLOCK(xfrm_state_lock); * Main use is finding SA after policy selected tunnel or transport mode. * Also, it can be used by ah/esp icmp error handler to find offending SA. */ -static struct list_head xfrm_state_bydst[XFRM_DST_HSIZE]; -static struct list_head xfrm_state_byspi[XFRM_DST_HSIZE]; +static struct hlist_head *xfrm_state_bydst __read_mostly; +static struct hlist_head *xfrm_state_bysrc __read_mostly; +static struct hlist_head *xfrm_state_byspi __read_mostly; +static unsigned int xfrm_state_hmask __read_mostly; +static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; +static unsigned int xfrm_state_num; +static unsigned int xfrm_state_genid; + +static inline unsigned int xfrm_dst_hash(xfrm_address_t *daddr, + xfrm_address_t *saddr, + u32 reqid, + unsigned short family) +{ + return __xfrm_dst_hash(daddr, saddr, reqid, family, xfrm_state_hmask); +} + +static inline unsigned int xfrm_src_hash(xfrm_address_t *addr, + unsigned short family) +{ + return __xfrm_src_hash(addr, family, xfrm_state_hmask); +} + +static inline unsigned int +xfrm_spi_hash(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family) +{ + return __xfrm_spi_hash(daddr, spi, proto, family, xfrm_state_hmask); +} + +static void xfrm_hash_transfer(struct hlist_head *list, + struct hlist_head *ndsttable, + struct hlist_head *nsrctable, + struct hlist_head *nspitable, + unsigned int nhashmask) +{ + struct hlist_node *entry, *tmp; + struct xfrm_state *x; + + hlist_for_each_entry_safe(x, entry, tmp, list, bydst) { + unsigned int h; + + h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr, + x->props.reqid, x->props.family, + nhashmask); + hlist_add_head(&x->bydst, ndsttable+h); + + h = __xfrm_src_hash(&x->props.saddr, x->props.family, + nhashmask); + hlist_add_head(&x->bysrc, nsrctable+h); + + h = __xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, + x->props.family, nhashmask); + hlist_add_head(&x->byspi, nspitable+h); + } +} + +static unsigned long xfrm_hash_new_size(void) +{ + return ((xfrm_state_hmask + 1) << 1) * + sizeof(struct hlist_head); +} + +static DEFINE_MUTEX(hash_resize_mutex); + +static void xfrm_hash_resize(void *__unused) +{ + struct hlist_head *ndst, *nsrc, *nspi, *odst, *osrc, *ospi; + unsigned long nsize, osize; + unsigned int nhashmask, ohashmask; + int i; + + mutex_lock(&hash_resize_mutex); + + nsize = xfrm_hash_new_size(); + ndst = xfrm_hash_alloc(nsize); + if (!ndst) + goto out_unlock; + nsrc = xfrm_hash_alloc(nsize); + if (!nsrc) { + xfrm_hash_free(ndst, nsize); + goto out_unlock; + } + nspi = xfrm_hash_alloc(nsize); + if (!nspi) { + xfrm_hash_free(ndst, nsize); + xfrm_hash_free(nsrc, nsize); + goto out_unlock; + } + + spin_lock_bh(&xfrm_state_lock); + + nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; + for (i = xfrm_state_hmask; i >= 0; i--) + xfrm_hash_transfer(xfrm_state_bydst+i, ndst, nsrc, nspi, + nhashmask); + + odst = xfrm_state_bydst; + osrc = xfrm_state_bysrc; + ospi = xfrm_state_byspi; + ohashmask = xfrm_state_hmask; + + xfrm_state_bydst = ndst; + xfrm_state_bysrc = nsrc; + xfrm_state_byspi = nspi; + xfrm_state_hmask = nhashmask; + + spin_unlock_bh(&xfrm_state_lock); + + osize = (ohashmask + 1) * sizeof(struct hlist_head); + xfrm_hash_free(odst, osize); + xfrm_hash_free(osrc, osize); + xfrm_hash_free(ospi, osize); + +out_unlock: + mutex_unlock(&hash_resize_mutex); +} + +static DECLARE_WORK(xfrm_hash_work, xfrm_hash_resize, NULL); DECLARE_WAIT_QUEUE_HEAD(km_waitq); EXPORT_SYMBOL(km_waitq); @@ -54,11 +172,9 @@ static DEFINE_RWLOCK(xfrm_state_afinfo_lock); static struct xfrm_state_afinfo *xfrm_state_afinfo[NPROTO]; static struct work_struct xfrm_state_gc_work; -static struct list_head xfrm_state_gc_list = LIST_HEAD_INIT(xfrm_state_gc_list); +static HLIST_HEAD(xfrm_state_gc_list); static DEFINE_SPINLOCK(xfrm_state_gc_lock); -static int xfrm_state_gc_flush_bundles; - int __xfrm_state_delete(struct xfrm_state *x); static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned short family); @@ -69,14 +185,13 @@ 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(); + del_timer_sync(&x->timer); + del_timer_sync(&x->rtimer); kfree(x->aalg); kfree(x->ealg); kfree(x->calg); kfree(x->encap); + kfree(x->coaddr); if (x->mode) xfrm_put_mode(x->mode); if (x->type) { @@ -90,22 +205,17 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) static void xfrm_state_gc_task(void *data) { struct xfrm_state *x; - struct list_head *entry, *tmp; - struct list_head gc_list = LIST_HEAD_INIT(gc_list); - - if (xfrm_state_gc_flush_bundles) { - xfrm_state_gc_flush_bundles = 0; - xfrm_flush_bundles(); - } + struct hlist_node *entry, *tmp; + struct hlist_head gc_list; spin_lock_bh(&xfrm_state_gc_lock); - list_splice_init(&xfrm_state_gc_list, &gc_list); + gc_list.first = xfrm_state_gc_list.first; + INIT_HLIST_HEAD(&xfrm_state_gc_list); spin_unlock_bh(&xfrm_state_gc_lock); - list_for_each_safe(entry, tmp, &gc_list) { - x = list_entry(entry, struct xfrm_state, bydst); + hlist_for_each_entry_safe(x, entry, tmp, &gc_list, bydst) xfrm_state_gc_destroy(x); - } + wake_up(&km_waitq); } @@ -168,9 +278,9 @@ static void xfrm_timer_handler(unsigned long data) if (warn) km_state_expired(x, 0, 0); resched: - if (next != LONG_MAX && - !mod_timer(&x->timer, jiffies + make_jiffies(next))) - xfrm_state_hold(x); + if (next != LONG_MAX) + mod_timer(&x->timer, jiffies + make_jiffies(next)); + goto out; expired: @@ -185,7 +295,6 @@ expired: out: spin_unlock(&x->lock); - xfrm_state_put(x); } static void xfrm_replay_timer_handler(unsigned long data); @@ -199,8 +308,9 @@ struct xfrm_state *xfrm_state_alloc(void) if (x) { atomic_set(&x->refcnt, 1); atomic_set(&x->tunnel_users, 0); - INIT_LIST_HEAD(&x->bydst); - INIT_LIST_HEAD(&x->byspi); + INIT_HLIST_NODE(&x->bydst); + INIT_HLIST_NODE(&x->bysrc); + INIT_HLIST_NODE(&x->byspi); init_timer(&x->timer); x->timer.function = xfrm_timer_handler; x->timer.data = (unsigned long)x; @@ -225,7 +335,7 @@ void __xfrm_state_destroy(struct xfrm_state *x) BUG_TRAP(x->km.state == XFRM_STATE_DEAD); spin_lock_bh(&xfrm_state_gc_lock); - list_add(&x->bydst, &xfrm_state_gc_list); + hlist_add_head(&x->bydst, &xfrm_state_gc_list); spin_unlock_bh(&xfrm_state_gc_lock); schedule_work(&xfrm_state_gc_work); } @@ -238,27 +348,12 @@ int __xfrm_state_delete(struct xfrm_state *x) if (x->km.state != XFRM_STATE_DEAD) { x->km.state = XFRM_STATE_DEAD; spin_lock(&xfrm_state_lock); - list_del(&x->bydst); - __xfrm_state_put(x); - if (x->id.spi) { - list_del(&x->byspi); - __xfrm_state_put(x); - } + hlist_del(&x->bydst); + hlist_del(&x->bysrc); + if (x->id.spi) + hlist_del(&x->byspi); + xfrm_state_num--; 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 - * our caller holds. A larger value means that - * there are DSTs attached to this xfrm_state. - */ - if (atomic_read(&x->refcnt) > 2) { - xfrm_state_gc_flush_bundles = 1; - schedule_work(&xfrm_state_gc_work); - } /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that @@ -287,14 +382,15 @@ EXPORT_SYMBOL(xfrm_state_delete); void xfrm_state_flush(u8 proto) { int i; - struct xfrm_state *x; spin_lock_bh(&xfrm_state_lock); - for (i = 0; i < XFRM_DST_HSIZE; i++) { + for (i = 0; i <= xfrm_state_hmask; i++) { + struct hlist_node *entry; + struct xfrm_state *x; restart: - list_for_each_entry(x, xfrm_state_bydst+i, bydst) { + hlist_for_each_entry(x, entry, xfrm_state_bydst+i, bydst) { if (!xfrm_state_kern(x) && - (proto == IPSEC_PROTO_ANY || x->id.proto == proto)) { + xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); spin_unlock_bh(&xfrm_state_lock); @@ -325,29 +421,103 @@ xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl, return 0; } +static struct xfrm_state *__xfrm_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family) +{ + unsigned int h = xfrm_spi_hash(daddr, spi, proto, family); + struct xfrm_state *x; + struct hlist_node *entry; + + hlist_for_each_entry(x, entry, xfrm_state_byspi+h, byspi) { + if (x->props.family != family || + x->id.spi != spi || + x->id.proto != proto) + continue; + + switch (family) { + case AF_INET: + if (x->id.daddr.a4 != daddr->a4) + continue; + break; + case AF_INET6: + if (!ipv6_addr_equal((struct in6_addr *)daddr, + (struct in6_addr *) + x->id.daddr.a6)) + continue; + break; + }; + + xfrm_state_hold(x); + return x; + } + + return NULL; +} + +static struct xfrm_state *__xfrm_state_lookup_byaddr(xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family) +{ + unsigned int h = xfrm_src_hash(saddr, family); + struct xfrm_state *x; + struct hlist_node *entry; + + hlist_for_each_entry(x, entry, xfrm_state_bysrc+h, bysrc) { + if (x->props.family != family || + x->id.proto != proto) + continue; + + switch (family) { + case AF_INET: + if (x->id.daddr.a4 != daddr->a4 || + x->props.saddr.a4 != saddr->a4) + continue; + break; + case AF_INET6: + if (!ipv6_addr_equal((struct in6_addr *)daddr, + (struct in6_addr *) + x->id.daddr.a6) || + !ipv6_addr_equal((struct in6_addr *)saddr, + (struct in6_addr *) + x->props.saddr.a6)) + continue; + break; + }; + + xfrm_state_hold(x); + return x; + } + + return NULL; +} + +static inline struct xfrm_state * +__xfrm_state_locate(struct xfrm_state *x, int use_spi, int family) +{ + if (use_spi) + return __xfrm_state_lookup(&x->id.daddr, x->id.spi, + x->id.proto, family); + else + return __xfrm_state_lookup_byaddr(&x->id.daddr, + &x->props.saddr, + x->id.proto, family); +} + struct xfrm_state * xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family) { - unsigned h = xfrm_dst_hash(daddr, family); + unsigned int h = xfrm_dst_hash(daddr, saddr, tmpl->reqid, family); + struct hlist_node *entry; struct xfrm_state *x, *x0; int acquire_in_progress = 0; int error = 0; struct xfrm_state *best = NULL; - struct xfrm_state_afinfo *afinfo; - afinfo = xfrm_state_get_afinfo(family); - if (afinfo == NULL) { - *err = -EAFNOSUPPORT; - return NULL; - } - spin_lock_bh(&xfrm_state_lock); - list_for_each_entry(x, xfrm_state_bydst+h, bydst) { + hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == tmpl->reqid && + !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && @@ -367,7 +537,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, */ if (x->km.state == XFRM_STATE_VALID) { if (!xfrm_selector_match(&x->sel, fl, family) || - !xfrm_sec_ctx_match(pol->security, x->security)) + !security_xfrm_state_pol_flow_match(x, pol, fl)) continue; if (!best || best->km.dying > x->km.dying || @@ -379,7 +549,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, } else if (x->km.state == XFRM_STATE_ERROR || x->km.state == XFRM_STATE_EXPIRED) { if (xfrm_selector_match(&x->sel, fl, family) && - xfrm_sec_ctx_match(pol->security, x->security)) + security_xfrm_state_pol_flow_match(x, pol, fl)) error = -ESRCH; } } @@ -388,8 +558,8 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, x = best; if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && - (x0 = afinfo->state_lookup(daddr, tmpl->id.spi, - tmpl->id.proto)) != NULL) { + (x0 = __xfrm_state_lookup(daddr, tmpl->id.spi, + tmpl->id.proto, family)) != NULL) { xfrm_state_put(x0); error = -EEXIST; goto out; @@ -403,17 +573,24 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, * to current session. */ xfrm_init_tempsel(x, fl, tmpl, daddr, saddr, family); + error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid); + if (error) { + x->km.state = XFRM_STATE_DEAD; + xfrm_state_put(x); + x = NULL; + goto out; + } + if (km_query(x, tmpl, pol) == 0) { x->km.state = XFRM_STATE_ACQ; - list_add_tail(&x->bydst, xfrm_state_bydst+h); - xfrm_state_hold(x); + hlist_add_head(&x->bydst, xfrm_state_bydst+h); + h = xfrm_src_hash(saddr, family); + hlist_add_head(&x->bysrc, xfrm_state_bysrc+h); if (x->id.spi) { h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, family); - list_add(&x->byspi, xfrm_state_byspi+h); - xfrm_state_hold(x); + hlist_add_head(&x->byspi, xfrm_state_byspi+h); } x->lft.hard_add_expires_seconds = XFRM_ACQ_EXPIRES; - xfrm_state_hold(x); x->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ; add_timer(&x->timer); } else { @@ -429,59 +606,167 @@ out: else *err = acquire_in_progress ? -EAGAIN : error; spin_unlock_bh(&xfrm_state_lock); - xfrm_state_put_afinfo(afinfo); return x; } static void __xfrm_state_insert(struct xfrm_state *x) { - unsigned h = xfrm_dst_hash(&x->id.daddr, x->props.family); + unsigned int h; - list_add(&x->bydst, xfrm_state_bydst+h); - xfrm_state_hold(x); + x->genid = ++xfrm_state_genid; - h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family); + h = xfrm_dst_hash(&x->id.daddr, &x->props.saddr, + x->props.reqid, x->props.family); + hlist_add_head(&x->bydst, xfrm_state_bydst+h); - list_add(&x->byspi, xfrm_state_byspi+h); - xfrm_state_hold(x); + h = xfrm_src_hash(&x->props.saddr, x->props.family); + hlist_add_head(&x->bysrc, xfrm_state_bysrc+h); - if (!mod_timer(&x->timer, jiffies + HZ)) - xfrm_state_hold(x); + if (xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY)) { + h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, + x->props.family); - if (x->replay_maxage && - !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) - xfrm_state_hold(x); + hlist_add_head(&x->byspi, xfrm_state_byspi+h); + } + + mod_timer(&x->timer, jiffies + HZ); + if (x->replay_maxage) + mod_timer(&x->rtimer, jiffies + x->replay_maxage); wake_up(&km_waitq); + + xfrm_state_num++; + + if (x->bydst.next != NULL && + (xfrm_state_hmask + 1) < xfrm_state_hashmax && + xfrm_state_num > xfrm_state_hmask) + schedule_work(&xfrm_hash_work); +} + +/* xfrm_state_lock is held */ +static void __xfrm_state_bump_genids(struct xfrm_state *xnew) +{ + unsigned short family = xnew->props.family; + u32 reqid = xnew->props.reqid; + struct xfrm_state *x; + struct hlist_node *entry; + unsigned int h; + + h = xfrm_dst_hash(&xnew->id.daddr, &xnew->props.saddr, reqid, family); + hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) { + if (x->props.family == family && + x->props.reqid == reqid && + !xfrm_addr_cmp(&x->id.daddr, &xnew->id.daddr, family) && + !xfrm_addr_cmp(&x->props.saddr, &xnew->props.saddr, family)) + x->genid = xfrm_state_genid; + } } void xfrm_state_insert(struct xfrm_state *x) { spin_lock_bh(&xfrm_state_lock); + __xfrm_state_bump_genids(x); __xfrm_state_insert(x); spin_unlock_bh(&xfrm_state_lock); - - xfrm_flush_all_bundles(); } EXPORT_SYMBOL(xfrm_state_insert); +/* xfrm_state_lock is held */ +static struct xfrm_state *__find_acq_core(unsigned short family, u8 mode, u32 reqid, u8 proto, xfrm_address_t *daddr, xfrm_address_t *saddr, int create) +{ + unsigned int h = xfrm_dst_hash(daddr, saddr, reqid, family); + struct hlist_node *entry; + struct xfrm_state *x; + + hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) { + if (x->props.reqid != reqid || + x->props.mode != mode || + x->props.family != family || + x->km.state != XFRM_STATE_ACQ || + x->id.spi != 0) + continue; + + switch (family) { + case AF_INET: + if (x->id.daddr.a4 != daddr->a4 || + x->props.saddr.a4 != saddr->a4) + continue; + break; + case AF_INET6: + if (!ipv6_addr_equal((struct in6_addr *)x->id.daddr.a6, + (struct in6_addr *)daddr) || + !ipv6_addr_equal((struct in6_addr *) + x->props.saddr.a6, + (struct in6_addr *)saddr)) + continue; + break; + }; + + xfrm_state_hold(x); + return x; + } + + if (!create) + return NULL; + + x = xfrm_state_alloc(); + if (likely(x)) { + switch (family) { + case AF_INET: + x->sel.daddr.a4 = daddr->a4; + x->sel.saddr.a4 = saddr->a4; + x->sel.prefixlen_d = 32; + x->sel.prefixlen_s = 32; + x->props.saddr.a4 = saddr->a4; + x->id.daddr.a4 = daddr->a4; + break; + + case AF_INET6: + ipv6_addr_copy((struct in6_addr *)x->sel.daddr.a6, + (struct in6_addr *)daddr); + ipv6_addr_copy((struct in6_addr *)x->sel.saddr.a6, + (struct in6_addr *)saddr); + x->sel.prefixlen_d = 128; + x->sel.prefixlen_s = 128; + ipv6_addr_copy((struct in6_addr *)x->props.saddr.a6, + (struct in6_addr *)saddr); + ipv6_addr_copy((struct in6_addr *)x->id.daddr.a6, + (struct in6_addr *)daddr); + break; + }; + + x->km.state = XFRM_STATE_ACQ; + x->id.proto = proto; + x->props.family = family; + x->props.mode = mode; + x->props.reqid = reqid; + x->lft.hard_add_expires_seconds = XFRM_ACQ_EXPIRES; + xfrm_state_hold(x); + x->timer.expires = jiffies + XFRM_ACQ_EXPIRES*HZ; + add_timer(&x->timer); + hlist_add_head(&x->bydst, xfrm_state_bydst+h); + h = xfrm_src_hash(saddr, family); + hlist_add_head(&x->bysrc, xfrm_state_bysrc+h); + wake_up(&km_waitq); + } + + return x; +} + static struct xfrm_state *__xfrm_find_acq_byseq(u32 seq); int xfrm_state_add(struct xfrm_state *x) { - struct xfrm_state_afinfo *afinfo; struct xfrm_state *x1; int family; int err; + int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); family = x->props.family; - afinfo = xfrm_state_get_afinfo(family); - if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_lock); - x1 = afinfo->state_lookup(&x->id.daddr, x->id.spi, x->id.proto); + x1 = __xfrm_state_locate(x, use_spi, family); if (x1) { xfrm_state_put(x1); x1 = NULL; @@ -489,7 +774,7 @@ int xfrm_state_add(struct xfrm_state *x) goto out; } - if (x->km.seq) { + if (use_spi && x->km.seq) { x1 = __xfrm_find_acq_byseq(x->km.seq); if (x1 && xfrm_addr_cmp(&x1->id.daddr, &x->id.daddr, family)) { xfrm_state_put(x1); @@ -497,20 +782,17 @@ int xfrm_state_add(struct xfrm_state *x) } } - if (!x1) - x1 = afinfo->find_acq( - x->props.mode, x->props.reqid, x->id.proto, - &x->id.daddr, &x->props.saddr, 0); + if (use_spi && !x1) + x1 = __find_acq_core(family, x->props.mode, x->props.reqid, + x->id.proto, + &x->id.daddr, &x->props.saddr, 0); + __xfrm_state_bump_genids(x); __xfrm_state_insert(x); err = 0; out: spin_unlock_bh(&xfrm_state_lock); - xfrm_state_put_afinfo(afinfo); - - if (!err) - xfrm_flush_all_bundles(); if (x1) { xfrm_state_delete(x1); @@ -523,16 +805,12 @@ EXPORT_SYMBOL(xfrm_state_add); int xfrm_state_update(struct xfrm_state *x) { - struct xfrm_state_afinfo *afinfo; struct xfrm_state *x1; int err; - - afinfo = xfrm_state_get_afinfo(x->props.family); - if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; + int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); spin_lock_bh(&xfrm_state_lock); - x1 = afinfo->state_lookup(&x->id.daddr, x->id.spi, x->id.proto); + x1 = __xfrm_state_locate(x, use_spi, x->props.family); err = -ESRCH; if (!x1) @@ -552,7 +830,6 @@ int xfrm_state_update(struct xfrm_state *x) out: spin_unlock_bh(&xfrm_state_lock); - xfrm_state_put_afinfo(afinfo); if (err) return err; @@ -568,11 +845,15 @@ out: if (likely(x1->km.state == XFRM_STATE_VALID)) { if (x->encap && x1->encap) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); + if (x->coaddr && x1->coaddr) { + memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); + } + if (!use_spi && memcmp(&x1->sel, &x->sel, sizeof(x1->sel))) + memcpy(&x1->sel, &x->sel, sizeof(x1->sel)); memcpy(&x1->lft, &x->lft, sizeof(x1->lft)); x1->km.dying = 0; - if (!mod_timer(&x1->timer, jiffies + HZ)) - xfrm_state_hold(x1); + mod_timer(&x1->timer, jiffies + HZ); if (x1->curlft.use_time) xfrm_state_check_expire(x1); @@ -597,8 +878,7 @@ int xfrm_state_check_expire(struct xfrm_state *x) if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; - if (!mod_timer(&x->timer, jiffies)) - xfrm_state_hold(x); + mod_timer(&x->timer, jiffies); return -EINVAL; } @@ -640,46 +920,93 @@ xfrm_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family) { struct xfrm_state *x; - struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - if (!afinfo) - return NULL; spin_lock_bh(&xfrm_state_lock); - x = afinfo->state_lookup(daddr, spi, proto); + x = __xfrm_state_lookup(daddr, spi, proto, family); spin_unlock_bh(&xfrm_state_lock); - xfrm_state_put_afinfo(afinfo); return x; } EXPORT_SYMBOL(xfrm_state_lookup); struct xfrm_state * +xfrm_state_lookup_byaddr(xfrm_address_t *daddr, xfrm_address_t *saddr, + u8 proto, unsigned short family) +{ + struct xfrm_state *x; + + spin_lock_bh(&xfrm_state_lock); + x = __xfrm_state_lookup_byaddr(daddr, saddr, proto, family); + spin_unlock_bh(&xfrm_state_lock); + return x; +} +EXPORT_SYMBOL(xfrm_state_lookup_byaddr); + +struct xfrm_state * xfrm_find_acq(u8 mode, u32 reqid, u8 proto, xfrm_address_t *daddr, xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; + + spin_lock_bh(&xfrm_state_lock); + x = __find_acq_core(family, mode, reqid, proto, daddr, saddr, create); + spin_unlock_bh(&xfrm_state_lock); + + return x; +} +EXPORT_SYMBOL(xfrm_find_acq); + +#ifdef CONFIG_XFRM_SUB_POLICY +int +xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, + unsigned short family) +{ + int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (!afinfo) - return NULL; + return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_lock); - x = afinfo->find_acq(mode, reqid, proto, daddr, saddr, create); + if (afinfo->tmpl_sort) + err = afinfo->tmpl_sort(dst, src, n); spin_unlock_bh(&xfrm_state_lock); xfrm_state_put_afinfo(afinfo); - return x; + return err; } -EXPORT_SYMBOL(xfrm_find_acq); +EXPORT_SYMBOL(xfrm_tmpl_sort); + +int +xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, + unsigned short family) +{ + int err = 0; + struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); + if (!afinfo) + return -EAFNOSUPPORT; + + spin_lock_bh(&xfrm_state_lock); + if (afinfo->state_sort) + err = afinfo->state_sort(dst, src, n); + spin_unlock_bh(&xfrm_state_lock); + xfrm_state_put_afinfo(afinfo); + return err; +} +EXPORT_SYMBOL(xfrm_state_sort); +#endif /* Silly enough, but I'm lazy to build resolution list */ static struct xfrm_state *__xfrm_find_acq_byseq(u32 seq) { int i; - struct xfrm_state *x; - for (i = 0; i < XFRM_DST_HSIZE; i++) { - list_for_each_entry(x, xfrm_state_bydst+i, bydst) { - if (x->km.seq == seq && x->km.state == XFRM_STATE_ACQ) { + for (i = 0; i <= xfrm_state_hmask; i++) { + struct hlist_node *entry; + struct xfrm_state *x; + + hlist_for_each_entry(x, entry, xfrm_state_bydst+i, bydst) { + if (x->km.seq == seq && + x->km.state == XFRM_STATE_ACQ) { xfrm_state_hold(x); return x; } @@ -715,7 +1042,7 @@ EXPORT_SYMBOL(xfrm_get_acqseq); void xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi) { - u32 h; + unsigned int h; struct xfrm_state *x0; if (x->id.spi) @@ -745,8 +1072,7 @@ xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi) if (x->id.spi) { spin_lock_bh(&xfrm_state_lock); h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family); - list_add(&x->byspi, xfrm_state_byspi+h); - xfrm_state_hold(x); + hlist_add_head(&x->byspi, xfrm_state_byspi+h); spin_unlock_bh(&xfrm_state_lock); wake_up(&km_waitq); } @@ -758,13 +1084,14 @@ int xfrm_state_walk(u8 proto, int (*func)(struct xfrm_state *, int, void*), { int i; struct xfrm_state *x; + struct hlist_node *entry; int count = 0; int err = 0; spin_lock_bh(&xfrm_state_lock); - for (i = 0; i < XFRM_DST_HSIZE; i++) { - list_for_each_entry(x, xfrm_state_bydst+i, bydst) { - if (proto == IPSEC_PROTO_ANY || x->id.proto == proto) + for (i = 0; i <= xfrm_state_hmask; i++) { + hlist_for_each_entry(x, entry, xfrm_state_bydst+i, bydst) { + if (xfrm_id_proto_match(x->id.proto, proto)) count++; } } @@ -773,9 +1100,9 @@ int xfrm_state_walk(u8 proto, int (*func)(struct xfrm_state *, int, void*), goto out; } - for (i = 0; i < XFRM_DST_HSIZE; i++) { - list_for_each_entry(x, xfrm_state_bydst+i, bydst) { - if (proto != IPSEC_PROTO_ANY && x->id.proto != proto) + for (i = 0; i <= xfrm_state_hmask; i++) { + hlist_for_each_entry(x, entry, xfrm_state_bydst+i, bydst) { + if (!xfrm_id_proto_match(x->id.proto, proto)) continue; err = func(x, --count, data); if (err) @@ -832,10 +1159,8 @@ void xfrm_replay_notify(struct xfrm_state *x, int event) km_state_notify(x, &c); if (x->replay_maxage && - !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) { - xfrm_state_hold(x); + !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) x->xflags &= ~XFRM_TIME_DEFER; - } } EXPORT_SYMBOL(xfrm_replay_notify); @@ -853,7 +1178,6 @@ static void xfrm_replay_timer_handler(unsigned long data) } spin_unlock(&x->lock); - xfrm_state_put(x); } int xfrm_replay_check(struct xfrm_state *x, u32 seq) @@ -997,6 +1321,25 @@ void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid) } EXPORT_SYMBOL(km_policy_expired); +int km_report(u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) +{ + int err = -EINVAL; + int ret; + struct xfrm_mgr *km; + + read_lock(&xfrm_km_lock); + list_for_each_entry(km, &xfrm_km_list, list) { + if (km->report) { + ret = km->report(proto, sel, addr); + if (!ret) + err = ret; + } + } + read_unlock(&xfrm_km_lock); + return err; +} +EXPORT_SYMBOL(km_report); + int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen) { int err; @@ -1018,7 +1361,7 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen err = -EINVAL; read_lock(&xfrm_km_lock); list_for_each_entry(km, &xfrm_km_list, list) { - pol = km->compile_policy(sk->sk_family, optname, data, + pol = km->compile_policy(sk, optname, data, optlen, &err); if (err >= 0) break; @@ -1065,11 +1408,8 @@ int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo) write_lock_bh(&xfrm_state_afinfo_lock); if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL)) err = -ENOBUFS; - else { - afinfo->state_bydst = xfrm_state_bydst; - afinfo->state_byspi = xfrm_state_byspi; + else xfrm_state_afinfo[afinfo->family] = afinfo; - } write_unlock_bh(&xfrm_state_afinfo_lock); return err; } @@ -1086,11 +1426,8 @@ int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo) if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) { if (unlikely(xfrm_state_afinfo[afinfo->family] != afinfo)) err = -EINVAL; - else { + else xfrm_state_afinfo[afinfo->family] = NULL; - afinfo->state_byspi = NULL; - afinfo->state_bydst = NULL; - } } write_unlock_bh(&xfrm_state_afinfo_lock); return err; @@ -1206,12 +1543,17 @@ EXPORT_SYMBOL(xfrm_init_state); void __init xfrm_state_init(void) { - int i; + unsigned int sz; + + sz = sizeof(struct hlist_head) * 8; + + xfrm_state_bydst = xfrm_hash_alloc(sz); + xfrm_state_bysrc = xfrm_hash_alloc(sz); + xfrm_state_byspi = xfrm_hash_alloc(sz); + if (!xfrm_state_bydst || !xfrm_state_bysrc || !xfrm_state_byspi) + panic("XFRM: Cannot allocate bydst/bysrc/byspi hashes."); + xfrm_state_hmask = ((sz / sizeof(struct hlist_head)) - 1); - for (i=0; i<XFRM_DST_HSIZE; i++) { - INIT_LIST_HEAD(&xfrm_state_bydst[i]); - INIT_LIST_HEAD(&xfrm_state_byspi[i]); - } INIT_WORK(&xfrm_state_gc_work, xfrm_state_gc_task, NULL); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index fa79ddc4239..c59a78d2923 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -28,6 +28,9 @@ #include <net/xfrm.h> #include <net/netlink.h> #include <asm/uaccess.h> +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#include <linux/in6.h> +#endif static int verify_one_alg(struct rtattr **xfrma, enum xfrm_attr_type_t type) { @@ -87,6 +90,22 @@ static int verify_encap_tmpl(struct rtattr **xfrma) return 0; } +static int verify_one_addr(struct rtattr **xfrma, enum xfrm_attr_type_t type, + xfrm_address_t **addrp) +{ + struct rtattr *rt = xfrma[type - 1]; + + if (!rt) + return 0; + + if ((rt->rta_len - sizeof(*rt)) < sizeof(**addrp)) + return -EINVAL; + + if (addrp) + *addrp = RTA_DATA(rt); + + return 0; +} static inline int verify_sec_ctx_len(struct rtattr **xfrma) { @@ -157,6 +176,19 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, goto out; break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case IPPROTO_DSTOPTS: + case IPPROTO_ROUTING: + if (xfrma[XFRMA_ALG_COMP-1] || + xfrma[XFRMA_ALG_AUTH-1] || + xfrma[XFRMA_ALG_CRYPT-1] || + xfrma[XFRMA_ENCAP-1] || + xfrma[XFRMA_SEC_CTX-1] || + !xfrma[XFRMA_COADDR-1]) + goto out; + break; +#endif + default: goto out; }; @@ -171,11 +203,14 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, goto out; if ((err = verify_sec_ctx_len(xfrma))) goto out; + if ((err = verify_one_addr(xfrma, XFRMA_COADDR, NULL))) + goto out; err = -EINVAL; switch (p->mode) { - case 0: - case 1: + case XFRM_MODE_TRANSPORT: + case XFRM_MODE_TUNNEL: + case XFRM_MODE_ROUTEOPTIMIZATION: break; default: @@ -260,6 +295,24 @@ static int attach_sec_ctx(struct xfrm_state *x, struct rtattr *u_arg) return security_xfrm_state_alloc(x, uctx); } +static int attach_one_addr(xfrm_address_t **addrpp, struct rtattr *u_arg) +{ + struct rtattr *rta = u_arg; + xfrm_address_t *p, *uaddrp; + + if (!rta) + return 0; + + uaddrp = RTA_DATA(rta); + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + + memcpy(p, uaddrp, sizeof(*p)); + *addrpp = p; + return 0; +} + static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p) { memcpy(&x->id, &p->id, sizeof(x->id)); @@ -349,7 +402,8 @@ static struct xfrm_state *xfrm_state_construct(struct xfrm_usersa_info *p, goto error; if ((err = attach_encap_tmpl(&x->encap, xfrma[XFRMA_ENCAP-1]))) goto error; - + if ((err = attach_one_addr(&x->coaddr, xfrma[XFRMA_COADDR-1]))) + goto error; err = xfrm_init_state(x); if (err) goto error; @@ -418,16 +472,48 @@ out: return err; } +static struct xfrm_state *xfrm_user_state_lookup(struct xfrm_usersa_id *p, + struct rtattr **xfrma, + int *errp) +{ + struct xfrm_state *x = NULL; + int err; + + if (xfrm_id_proto_match(p->proto, IPSEC_PROTO_ANY)) { + err = -ESRCH; + x = xfrm_state_lookup(&p->daddr, p->spi, p->proto, p->family); + } else { + xfrm_address_t *saddr = NULL; + + err = verify_one_addr(xfrma, XFRMA_SRCADDR, &saddr); + if (err) + goto out; + + if (!saddr) { + err = -EINVAL; + goto out; + } + + x = xfrm_state_lookup_byaddr(&p->daddr, saddr, p->proto, + p->family); + } + + out: + if (!x && errp) + *errp = err; + return x; +} + static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) { struct xfrm_state *x; - int err; + int err = -ESRCH; struct km_event c; struct xfrm_usersa_id *p = NLMSG_DATA(nlh); - x = xfrm_state_lookup(&p->daddr, p->spi, p->proto, p->family); + x = xfrm_user_state_lookup(p, (struct rtattr **)xfrma, &err); if (x == NULL) - return -ESRCH; + return err; if ((err = security_xfrm_state_delete(x)) != 0) goto out; @@ -521,6 +607,13 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr) uctx->ctx_len = x->security->ctx_len; memcpy(uctx + 1, x->security->ctx_str, x->security->ctx_len); } + + if (x->coaddr) + RTA_PUT(skb, XFRMA_COADDR, sizeof(*x->coaddr), x->coaddr); + + if (x->lastused) + RTA_PUT(skb, XFRMA_LASTUSED, sizeof(x->lastused), &x->lastused); + nlh->nlmsg_len = skb->tail - b; out: sp->this_idx++; @@ -542,7 +635,7 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) info.nlmsg_flags = NLM_F_MULTI; info.this_idx = 0; info.start_idx = cb->args[0]; - (void) xfrm_state_walk(IPSEC_PROTO_ANY, dump_one_state, &info); + (void) xfrm_state_walk(0, dump_one_state, &info); cb->args[0] = info.this_idx; return skb->len; @@ -578,10 +671,9 @@ static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) struct xfrm_usersa_id *p = NLMSG_DATA(nlh); struct xfrm_state *x; struct sk_buff *resp_skb; - int err; + int err = -ESRCH; - x = xfrm_state_lookup(&p->daddr, p->spi, p->proto, p->family); - err = -ESRCH; + x = xfrm_user_state_lookup(p, (struct rtattr **)xfrma, &err); if (x == NULL) goto out_noput; @@ -694,6 +786,22 @@ static int verify_policy_dir(__u8 dir) return 0; } +static int verify_policy_type(__u8 type) +{ + switch (type) { + case XFRM_POLICY_TYPE_MAIN: +#ifdef CONFIG_XFRM_SUB_POLICY + case XFRM_POLICY_TYPE_SUB: +#endif + break; + + default: + return -EINVAL; + }; + + return 0; +} + static int verify_newpolicy_info(struct xfrm_userpolicy_info *p) { switch (p->share) { @@ -787,6 +895,29 @@ static int copy_from_user_tmpl(struct xfrm_policy *pol, struct rtattr **xfrma) return 0; } +static int copy_from_user_policy_type(u8 *tp, struct rtattr **xfrma) +{ + struct rtattr *rt = xfrma[XFRMA_POLICY_TYPE-1]; + struct xfrm_userpolicy_type *upt; + __u8 type = XFRM_POLICY_TYPE_MAIN; + int err; + + if (rt) { + if (rt->rta_len < sizeof(*upt)) + return -EINVAL; + + upt = RTA_DATA(rt); + type = upt->type; + } + + err = verify_policy_type(type); + if (err) + return err; + + *tp = type; + return 0; +} + static void copy_from_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_info *p) { xp->priority = p->priority; @@ -825,16 +956,20 @@ static struct xfrm_policy *xfrm_policy_construct(struct xfrm_userpolicy_info *p, copy_from_user_policy(xp, p); + err = copy_from_user_policy_type(&xp->type, xfrma); + if (err) + goto error; + if (!(err = copy_from_user_tmpl(xp, xfrma))) err = copy_from_user_sec_ctx(xp, xfrma); - - if (err) { - *errp = err; - kfree(xp); - xp = NULL; - } + if (err) + goto error; return xp; + error: + *errp = err; + kfree(xp); + return NULL; } static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) @@ -911,27 +1046,63 @@ rtattr_failure: return -1; } -static int copy_to_user_sec_ctx(struct xfrm_policy *xp, struct sk_buff *skb) +static int copy_sec_ctx(struct xfrm_sec_ctx *s, struct sk_buff *skb) { - if (xp->security) { - int ctx_size = sizeof(struct xfrm_sec_ctx) + - xp->security->ctx_len; - struct rtattr *rt = __RTA_PUT(skb, XFRMA_SEC_CTX, ctx_size); - struct xfrm_user_sec_ctx *uctx = RTA_DATA(rt); + int ctx_size = sizeof(struct xfrm_sec_ctx) + s->ctx_len; + struct rtattr *rt = __RTA_PUT(skb, XFRMA_SEC_CTX, ctx_size); + struct xfrm_user_sec_ctx *uctx = RTA_DATA(rt); + + uctx->exttype = XFRMA_SEC_CTX; + uctx->len = ctx_size; + uctx->ctx_doi = s->ctx_doi; + uctx->ctx_alg = s->ctx_alg; + uctx->ctx_len = s->ctx_len; + memcpy(uctx + 1, s->ctx_str, s->ctx_len); + return 0; - uctx->exttype = XFRMA_SEC_CTX; - uctx->len = ctx_size; - uctx->ctx_doi = xp->security->ctx_doi; - uctx->ctx_alg = xp->security->ctx_alg; - uctx->ctx_len = xp->security->ctx_len; - memcpy(uctx + 1, xp->security->ctx_str, xp->security->ctx_len); + rtattr_failure: + return -1; +} + +static inline int copy_to_user_state_sec_ctx(struct xfrm_state *x, struct sk_buff *skb) +{ + if (x->security) { + return copy_sec_ctx(x->security, skb); } return 0; +} - rtattr_failure: +static inline int copy_to_user_sec_ctx(struct xfrm_policy *xp, struct sk_buff *skb) +{ + if (xp->security) { + return copy_sec_ctx(xp->security, skb); + } + return 0; +} + +#ifdef CONFIG_XFRM_SUB_POLICY +static int copy_to_user_policy_type(struct xfrm_policy *xp, struct sk_buff *skb) +{ + struct xfrm_userpolicy_type upt; + + memset(&upt, 0, sizeof(upt)); + upt.type = xp->type; + + RTA_PUT(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt); + + return 0; + +rtattr_failure: return -1; } +#else +static inline int copy_to_user_policy_type(struct xfrm_policy *xp, struct sk_buff *skb) +{ + return 0; +} +#endif + static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr) { struct xfrm_dump_info *sp = ptr; @@ -955,6 +1126,8 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr goto nlmsg_failure; if (copy_to_user_sec_ctx(xp, skb)) goto nlmsg_failure; + if (copy_to_user_policy_type(xp, skb) < 0) + goto nlmsg_failure; nlh->nlmsg_len = skb->tail - b; out: @@ -976,7 +1149,10 @@ static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb) info.nlmsg_flags = NLM_F_MULTI; info.this_idx = 0; info.start_idx = cb->args[0]; - (void) xfrm_policy_walk(dump_one_policy, &info); + (void) xfrm_policy_walk(XFRM_POLICY_TYPE_MAIN, dump_one_policy, &info); +#ifdef CONFIG_XFRM_SUB_POLICY + (void) xfrm_policy_walk(XFRM_POLICY_TYPE_SUB, dump_one_policy, &info); +#endif cb->args[0] = info.this_idx; return skb->len; @@ -1012,6 +1188,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr { struct xfrm_policy *xp; struct xfrm_userpolicy_id *p; + __u8 type = XFRM_POLICY_TYPE_MAIN; int err; struct km_event c; int delete; @@ -1019,12 +1196,16 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr p = NLMSG_DATA(nlh); delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY; + err = copy_from_user_policy_type(&type, (struct rtattr **)xfrma); + if (err) + return err; + err = verify_policy_dir(p->dir); if (err) return err; if (p->index) - xp = xfrm_policy_byid(p->dir, p->index, delete); + xp = xfrm_policy_byid(type, p->dir, p->index, delete); else { struct rtattr **rtattrs = (struct rtattr **)xfrma; struct rtattr *rt = rtattrs[XFRMA_SEC_CTX-1]; @@ -1041,7 +1222,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr if ((err = security_xfrm_policy_alloc(&tmp, uctx))) return err; } - xp = xfrm_policy_bysel_ctx(p->dir, &p->sel, tmp.security, delete); + xp = xfrm_policy_bysel_ctx(type, p->dir, &p->sel, tmp.security, delete); security_xfrm_policy_free(&tmp); } if (xp == NULL) @@ -1224,9 +1405,16 @@ out: static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) { -struct km_event c; + struct km_event c; + __u8 type = XFRM_POLICY_TYPE_MAIN; + int err; + + err = copy_from_user_policy_type(&type, (struct rtattr **)xfrma); + if (err) + return err; - xfrm_policy_flush(); + xfrm_policy_flush(type); + c.data.type = type; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; c.pid = nlh->nlmsg_pid; @@ -1239,10 +1427,15 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, void * struct xfrm_policy *xp; struct xfrm_user_polexpire *up = NLMSG_DATA(nlh); struct xfrm_userpolicy_info *p = &up->pol; + __u8 type = XFRM_POLICY_TYPE_MAIN; int err = -ENOENT; + err = copy_from_user_policy_type(&type, (struct rtattr **)xfrma); + if (err) + return err; + if (p->index) - xp = xfrm_policy_byid(p->dir, p->index, 0); + xp = xfrm_policy_byid(type, p->dir, p->index, 0); else { struct rtattr **rtattrs = (struct rtattr **)xfrma; struct rtattr *rt = rtattrs[XFRMA_SEC_CTX-1]; @@ -1259,7 +1452,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, void * if ((err = security_xfrm_policy_alloc(&tmp, uctx))) return err; } - xp = xfrm_policy_bysel_ctx(p->dir, &p->sel, tmp.security, 0); + xp = xfrm_policy_bysel_ctx(type, p->dir, &p->sel, tmp.security, 0); security_xfrm_policy_free(&tmp); } @@ -1386,6 +1579,7 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [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), + [XFRM_MSG_REPORT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report), }; #undef XMSGSIZE @@ -1710,7 +1904,9 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, if (copy_to_user_tmpl(xp, skb) < 0) goto nlmsg_failure; - if (copy_to_user_sec_ctx(xp, skb)) + if (copy_to_user_state_sec_ctx(x, skb)) + goto nlmsg_failure; + if (copy_to_user_policy_type(xp, skb) < 0) goto nlmsg_failure; nlh->nlmsg_len = skb->tail - b; @@ -1744,7 +1940,7 @@ static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, /* User gives us xfrm_user_policy_info followed by an array of 0 * or more templates. */ -static struct xfrm_policy *xfrm_compile_policy(u16 family, int opt, +static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, u8 *data, int len, int *dir) { struct xfrm_userpolicy_info *p = (struct xfrm_userpolicy_info *)data; @@ -1752,7 +1948,7 @@ static struct xfrm_policy *xfrm_compile_policy(u16 family, int opt, struct xfrm_policy *xp; int nr; - switch (family) { + switch (sk->sk_family) { case AF_INET: if (opt != IP_XFRM_POLICY) { *dir = -EOPNOTSUPP; @@ -1792,8 +1988,18 @@ static struct xfrm_policy *xfrm_compile_policy(u16 family, int opt, } copy_from_user_policy(xp, p); + xp->type = XFRM_POLICY_TYPE_MAIN; copy_templates(xp, ut, nr); + if (!xp->security) { + int err = security_xfrm_sock_policy_alloc(xp, sk); + if (err) { + kfree(xp); + *dir = err; + return NULL; + } + } + *dir = p->dir; return xp; @@ -1816,6 +2022,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, goto nlmsg_failure; if (copy_to_user_sec_ctx(xp, skb)) goto nlmsg_failure; + if (copy_to_user_policy_type(xp, skb) < 0) + goto nlmsg_failure; upe->hard = !!hard; nlh->nlmsg_len = skb->tail - b; @@ -1887,6 +2095,8 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, struct km_event * copy_to_user_policy(xp, p, dir); if (copy_to_user_tmpl(xp, skb) < 0) goto nlmsg_failure; + if (copy_to_user_policy_type(xp, skb) < 0) + goto nlmsg_failure; nlh->nlmsg_len = skb->tail - b; @@ -1904,6 +2114,9 @@ static int xfrm_notify_policy_flush(struct km_event *c) struct nlmsghdr *nlh; struct sk_buff *skb; unsigned char *b; +#ifdef CONFIG_XFRM_SUB_POLICY + struct xfrm_userpolicy_type upt; +#endif int len = NLMSG_LENGTH(0); skb = alloc_skb(len, GFP_ATOMIC); @@ -1913,6 +2126,13 @@ static int xfrm_notify_policy_flush(struct km_event *c) nlh = NLMSG_PUT(skb, c->pid, c->seq, XFRM_MSG_FLUSHPOLICY, 0); + nlh->nlmsg_flags = 0; + +#ifdef CONFIG_XFRM_SUB_POLICY + memset(&upt, 0, sizeof(upt)); + upt.type = c->data.type; + RTA_PUT(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt); +#endif nlh->nlmsg_len = skb->tail - b; @@ -1920,6 +2140,9 @@ static int xfrm_notify_policy_flush(struct km_event *c) return netlink_broadcast(xfrm_nl, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); nlmsg_failure: +#ifdef CONFIG_XFRM_SUB_POLICY +rtattr_failure: +#endif kfree_skb(skb); return -1; } @@ -1944,19 +2167,64 @@ static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_ev } +static int build_report(struct sk_buff *skb, u8 proto, + struct xfrm_selector *sel, xfrm_address_t *addr) +{ + struct xfrm_user_report *ur; + struct nlmsghdr *nlh; + unsigned char *b = skb->tail; + + nlh = NLMSG_PUT(skb, 0, 0, XFRM_MSG_REPORT, sizeof(*ur)); + ur = NLMSG_DATA(nlh); + nlh->nlmsg_flags = 0; + + ur->proto = proto; + memcpy(&ur->sel, sel, sizeof(ur->sel)); + + if (addr) + RTA_PUT(skb, XFRMA_COADDR, sizeof(*addr), addr); + + nlh->nlmsg_len = skb->tail - b; + return skb->len; + +nlmsg_failure: +rtattr_failure: + skb_trim(skb, b - skb->data); + return -1; +} + +static int xfrm_send_report(u8 proto, struct xfrm_selector *sel, + xfrm_address_t *addr) +{ + struct sk_buff *skb; + size_t len; + + len = NLMSG_ALIGN(NLMSG_LENGTH(sizeof(struct xfrm_user_report))); + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + + if (build_report(skb, proto, sel, addr) < 0) + BUG(); + + NETLINK_CB(skb).dst_group = XFRMNLGRP_REPORT; + return netlink_broadcast(xfrm_nl, skb, 0, XFRMNLGRP_REPORT, GFP_ATOMIC); +} + static struct xfrm_mgr netlink_mgr = { .id = "netlink", .notify = xfrm_send_state_notify, .acquire = xfrm_send_acquire, .compile_policy = xfrm_compile_policy, .notify_policy = xfrm_send_policy_notify, + .report = xfrm_send_report, }; static int __init xfrm_user_init(void) { struct sock *nlsk; - printk(KERN_INFO "Initializing IPsec netlink socket\n"); + printk(KERN_INFO "Initializing XFRM netlink socket\n"); nlsk = netlink_kernel_create(NETLINK_XFRM, XFRMNLGRP_MAX, xfrm_netlink_rcv, THIS_MODULE); |