diff options
Diffstat (limited to 'net')
29 files changed, 443 insertions, 255 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index f42bc2b26b85..4bf014e51f8c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -569,6 +569,7 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) * separate class since they always nest. */ static struct lock_class_key vlan_netdev_xmit_lock_key; +static struct lock_class_key vlan_netdev_addr_lock_key; static void vlan_dev_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, @@ -581,6 +582,9 @@ static void vlan_dev_set_lockdep_one(struct net_device *dev, static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) { + lockdep_set_class_and_subclass(&dev->addr_list_lock, + &vlan_netdev_addr_lock_key, + subclass); netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass); } diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 844ca5f1b2d4..c85bf8f678dc 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -398,10 +398,6 @@ int hci_register_sysfs(struct hci_dev *hdev) if (device_create_file(dev, bt_attrs[i]) < 0) BT_ERR("Failed to create device attribute"); - if (sysfs_create_link(&bt_class->subsys.kobj, - &dev->kobj, kobject_name(&dev->kobj)) < 0) - BT_ERR("Failed to create class symlink"); - return 0; } @@ -409,9 +405,6 @@ void hci_unregister_sysfs(struct hci_dev *hdev) { BT_DBG("%p name %s type %d", hdev, hdev->name, hdev->type); - sysfs_remove_link(&bt_class->subsys.kobj, - kobject_name(&hdev->dev.kobj)); - device_del(&hdev->dev); } diff --git a/net/core/dev.c b/net/core/dev.c index 106d5e6d987c..7463a2150b09 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -124,6 +124,8 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/in.h> +#include <linux/jhash.h> +#include <linux/random.h> #include "net-sysfs.h" @@ -259,7 +261,7 @@ static RAW_NOTIFIER_HEAD(netdev_chain); DEFINE_PER_CPU(struct softnet_data, softnet_data); -#ifdef CONFIG_DEBUG_LOCK_ALLOC +#ifdef CONFIG_LOCKDEP /* * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type @@ -299,6 +301,7 @@ static const char *netdev_lock_name[] = "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; +static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; static inline unsigned short netdev_lock_pos(unsigned short dev_type) { @@ -311,8 +314,8 @@ static inline unsigned short netdev_lock_pos(unsigned short dev_type) return ARRAY_SIZE(netdev_lock_type) - 1; } -static inline void netdev_set_lockdep_class(spinlock_t *lock, - unsigned short dev_type) +static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, + unsigned short dev_type) { int i; @@ -320,9 +323,22 @@ static inline void netdev_set_lockdep_class(spinlock_t *lock, lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], netdev_lock_name[i]); } + +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) +{ + int i; + + i = netdev_lock_pos(dev->type); + lockdep_set_class_and_name(&dev->addr_list_lock, + &netdev_addr_lock_key[i], + netdev_lock_name[i]); +} #else -static inline void netdev_set_lockdep_class(spinlock_t *lock, - unsigned short dev_type) +static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, + unsigned short dev_type) +{ +} +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { } #endif @@ -1325,7 +1341,8 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) void __netif_schedule(struct Qdisc *q) { - BUG_ON(q == &noop_qdisc); + if (WARN_ON_ONCE(q == &noop_qdisc)) + return; if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) { struct softnet_data *sd; @@ -1642,60 +1659,37 @@ out_kfree_skb: return 0; } -/** - * dev_queue_xmit - transmit a buffer - * @skb: buffer to transmit - * - * Queue a buffer for transmission to a network device. The caller must - * have set the device and priority and built the buffer before calling - * this function. The function can be called from an interrupt. - * - * A negative errno code is returned on a failure. A success does not - * guarantee the frame will be transmitted as it may be dropped due - * to congestion or traffic shaping. - * - * ----------------------------------------------------------------------------------- - * I notice this method can also return errors from the queue disciplines, - * including NET_XMIT_DROP, which is a positive value. So, errors can also - * be positive. - * - * Regardless of the return value, the skb is consumed, so it is currently - * difficult to retry a send to this method. (You can bump the ref count - * before sending to hold a reference for retry if you are careful.) - * - * When calling this method, interrupts MUST be enabled. This is because - * the BH enable code must have IRQs enabled so that it will not deadlock. - * --BLG - */ +static u32 simple_tx_hashrnd; +static int simple_tx_hashrnd_initialized = 0; static u16 simple_tx_hash(struct net_device *dev, struct sk_buff *skb) { - u32 *addr, *ports, hash, ihl; + u32 addr1, addr2, ports; + u32 hash, ihl; u8 ip_proto; - int alen; + + if (unlikely(!simple_tx_hashrnd_initialized)) { + get_random_bytes(&simple_tx_hashrnd, 4); + simple_tx_hashrnd_initialized = 1; + } switch (skb->protocol) { case __constant_htons(ETH_P_IP): ip_proto = ip_hdr(skb)->protocol; - addr = &ip_hdr(skb)->saddr; + addr1 = ip_hdr(skb)->saddr; + addr2 = ip_hdr(skb)->daddr; ihl = ip_hdr(skb)->ihl; - alen = 2; break; case __constant_htons(ETH_P_IPV6): ip_proto = ipv6_hdr(skb)->nexthdr; - addr = &ipv6_hdr(skb)->saddr.s6_addr32[0]; + addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3]; + addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3]; ihl = (40 >> 2); - alen = 8; break; default: return 0; } - ports = (u32 *) (skb_network_header(skb) + (ihl * 4)); - - hash = 0; - while (alen--) - hash ^= *addr++; switch (ip_proto) { case IPPROTO_TCP: @@ -1705,14 +1699,17 @@ static u16 simple_tx_hash(struct net_device *dev, struct sk_buff *skb) case IPPROTO_AH: case IPPROTO_SCTP: case IPPROTO_UDPLITE: - hash ^= *ports; + ports = *((u32 *) (skb_network_header(skb) + (ihl * 4))); break; default: + ports = 0; break; } - return hash % dev->real_num_tx_queues; + hash = jhash_3words(addr1, addr2, ports, simple_tx_hashrnd); + + return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32); } static struct netdev_queue *dev_pick_tx(struct net_device *dev, @@ -1729,6 +1726,31 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, return netdev_get_tx_queue(dev, queue_index); } +/** + * dev_queue_xmit - transmit a buffer + * @skb: buffer to transmit + * + * Queue a buffer for transmission to a network device. The caller must + * have set the device and priority and built the buffer before calling + * this function. The function can be called from an interrupt. + * + * A negative errno code is returned on a failure. A success does not + * guarantee the frame will be transmitted as it may be dropped due + * to congestion or traffic shaping. + * + * ----------------------------------------------------------------------------------- + * I notice this method can also return errors from the queue disciplines, + * including NET_XMIT_DROP, which is a positive value. So, errors can also + * be positive. + * + * Regardless of the return value, the skb is consumed, so it is currently + * difficult to retry a send to this method. (You can bump the ref count + * before sending to hold a reference for retry if you are careful.) + * + * When calling this method, interrupts MUST be enabled. This is because + * the BH enable code must have IRQs enabled so that it will not deadlock. + * --BLG + */ int dev_queue_xmit(struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -3843,7 +3865,7 @@ static void __netdev_init_queue_locks_one(struct net_device *dev, void *_unused) { spin_lock_init(&dev_queue->_xmit_lock); - netdev_set_lockdep_class(&dev_queue->_xmit_lock, dev->type); + netdev_set_xmit_lockdep_class(&dev_queue->_xmit_lock, dev->type); dev_queue->xmit_lock_owner = -1; } @@ -3888,6 +3910,7 @@ int register_netdevice(struct net_device *dev) net = dev_net(dev); spin_lock_init(&dev->addr_list_lock); + netdev_set_addr_lockdep_class(dev); netdev_init_queue_locks(dev); dev->iflink = -1; @@ -4198,7 +4221,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, { struct netdev_queue *tx; struct net_device *dev; - int alloc_size; + size_t alloc_size; void *p; BUG_ON(strlen(name) >= sizeof(dev->name)); @@ -4218,7 +4241,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, return NULL; } - tx = kzalloc(sizeof(struct netdev_queue) * queue_count, GFP_KERNEL); + tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL); if (!tx) { printk(KERN_ERR "alloc_netdev: Unable to allocate " "tx qdiscs.\n"); @@ -4677,6 +4700,26 @@ err_name: return -ENOMEM; } +char *netdev_drivername(struct net_device *dev, char *buffer, int len) +{ + struct device_driver *driver; + struct device *parent; + + if (len <= 0 || !buffer) + return buffer; + buffer[0] = 0; + + parent = dev->dev.parent; + + if (!parent) + return buffer; + + driver = parent->driver; + if (driver && driver->name) + strlcpy(buffer, driver->name, len); + return buffer; +} + static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); diff --git a/net/core/user_dma.c b/net/core/user_dma.c index c77aff9c6eb3..8c6b706963ff 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -34,6 +34,7 @@ #define NET_DMA_DEFAULT_COPYBREAK 4096 int sysctl_tcp_dma_copybreak = NET_DMA_DEFAULT_COPYBREAK; +EXPORT_SYMBOL(sysctl_tcp_dma_copybreak); /** * dma_skb_copy_datagram_iovec - Copy a datagram to an iovec. diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 40a46d482490..3a020720e40b 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -18,19 +18,7 @@ #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> - -#ifdef CONFIG_NF_CT_ACCT -static unsigned int -seq_print_counters(struct seq_file *s, - const struct ip_conntrack_counter *counter) -{ - return seq_printf(s, "packets=%llu bytes=%llu ", - (unsigned long long)counter->packets, - (unsigned long long)counter->bytes); -} -#else -#define seq_print_counters(x, y) 0 -#endif +#include <net/netfilter/nf_conntrack_acct.h> struct ct_iter_state { unsigned int bucket; @@ -127,7 +115,7 @@ static int ct_seq_show(struct seq_file *s, void *v) l3proto, l4proto)) return -ENOSPC; - if (seq_print_counters(s, &ct->counters[IP_CT_DIR_ORIGINAL])) + if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL)) return -ENOSPC; if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) @@ -138,7 +126,7 @@ static int ct_seq_show(struct seq_file *s, void *v) l3proto, l4proto)) return -ENOSPC; - if (seq_print_counters(s, &ct->counters[IP_CT_DIR_REPLY])) + if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) return -ENOSPC; if (test_bit(IPS_ASSURED_BIT, &ct->status)) diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index d2a887fc8d9b..6c6a3cba8d50 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -240,12 +240,12 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, This is only required for source (ie. NAT/masq) mappings. So far, we don't do local source mappings, so multiple manips not an issue. */ - if (maniptype == IP_NAT_MANIP_SRC) { + if (maniptype == IP_NAT_MANIP_SRC && + !(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) { if (find_appropriate_src(orig_tuple, tuple, range)) { pr_debug("get_unique_tuple: Found current src map\n"); - if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) - if (!nf_nat_used_tuple(tuple, ct)) - return; + if (!nf_nat_used_tuple(tuple, ct)) + return; } } diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index 4334d5cabc5b..14544320c545 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -318,11 +318,11 @@ static int mangle_content_len(struct sk_buff *skb, buffer, buflen); } -static unsigned mangle_sdp_packet(struct sk_buff *skb, const char **dptr, - unsigned int dataoff, unsigned int *datalen, - enum sdp_header_types type, - enum sdp_header_types term, - char *buffer, int buflen) +static int mangle_sdp_packet(struct sk_buff *skb, const char **dptr, + unsigned int dataoff, unsigned int *datalen, + enum sdp_header_types type, + enum sdp_header_types term, + char *buffer, int buflen) { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); @@ -330,9 +330,9 @@ static unsigned mangle_sdp_packet(struct sk_buff *skb, const char **dptr, if (ct_sip_get_sdp_header(ct, *dptr, dataoff, *datalen, type, term, &matchoff, &matchlen) <= 0) - return 0; + return -ENOENT; return mangle_packet(skb, dptr, datalen, matchoff, matchlen, - buffer, buflen); + buffer, buflen) ? 0 : -EINVAL; } static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, const char **dptr, @@ -346,8 +346,8 @@ static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, const char **dptr, unsigned int buflen; buflen = sprintf(buffer, NIPQUAD_FMT, NIPQUAD(addr->ip)); - if (!mangle_sdp_packet(skb, dptr, dataoff, datalen, type, term, - buffer, buflen)) + if (mangle_sdp_packet(skb, dptr, dataoff, datalen, type, term, + buffer, buflen)) return 0; return mangle_content_len(skb, dptr, datalen); @@ -381,15 +381,27 @@ static unsigned int ip_nat_sdp_session(struct sk_buff *skb, const char **dptr, /* Mangle session description owner and contact addresses */ buflen = sprintf(buffer, "%u.%u.%u.%u", NIPQUAD(addr->ip)); - if (!mangle_sdp_packet(skb, dptr, dataoff, datalen, + if (mangle_sdp_packet(skb, dptr, dataoff, datalen, SDP_HDR_OWNER_IP4, SDP_HDR_MEDIA, buffer, buflen)) return 0; - if (!mangle_sdp_packet(skb, dptr, dataoff, datalen, - SDP_HDR_CONNECTION_IP4, SDP_HDR_MEDIA, - buffer, buflen)) + switch (mangle_sdp_packet(skb, dptr, dataoff, datalen, + SDP_HDR_CONNECTION_IP4, SDP_HDR_MEDIA, + buffer, buflen)) { + case 0: + /* + * RFC 2327: + * + * Session description + * + * c=* (connection information - not required if included in all media) + */ + case -ENOENT: + break; + default: return 0; + } return mangle_content_len(skb, dptr, datalen); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1fa683c0ba9b..a00532de2a8c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -472,7 +472,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, } if (likely(sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; - if (unlikely(!OPTION_TS & opts->options)) + if (unlikely(!(OPTION_TS & opts->options))) size += TCPOLEN_SACKPERM_ALIGNED; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a751770947a3..383d17359d01 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1325,6 +1325,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; if (val != 0 && val < 8) /* Illegal coverage: use default (8) */ val = 8; + else if (val > USHORT_MAX) + val = USHORT_MAX; up->pcslen = val; up->pcflag |= UDPLITE_SEND_CC; break; @@ -1337,6 +1339,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; if (val != 0 && val < 8) /* Avoid silly minimal values. */ val = 8; + else if (val > USHORT_MAX) + val = USHORT_MAX; up->pcrlen = val; up->pcflag |= UDPLITE_RECV_CC; break; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9f4fcce6379b..74d543d504a1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -153,7 +153,7 @@ static int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); -struct ipv6_devconf ipv6_devconf __read_mostly = { +static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 4de2b9efcacb..08ea2de28d63 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -661,17 +661,17 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt) { - if (net->ipv6.ip6_fib_timer->expires == 0 && + if (!timer_pending(&net->ipv6.ip6_fib_timer) && (rt->rt6i_flags & (RTF_EXPIRES|RTF_CACHE))) - mod_timer(net->ipv6.ip6_fib_timer, jiffies + - net->ipv6.sysctl.ip6_rt_gc_interval); + mod_timer(&net->ipv6.ip6_fib_timer, + jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } void fib6_force_start_gc(struct net *net) { - if (net->ipv6.ip6_fib_timer->expires == 0) - mod_timer(net->ipv6.ip6_fib_timer, jiffies + - net->ipv6.sysctl.ip6_rt_gc_interval); + if (!timer_pending(&net->ipv6.ip6_fib_timer)) + mod_timer(&net->ipv6.ip6_fib_timer, + jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } /* @@ -1447,27 +1447,23 @@ void fib6_run_gc(unsigned long expires, struct net *net) gc_args.timeout = expires ? (int)expires : net->ipv6.sysctl.ip6_rt_gc_interval; } else { - local_bh_disable(); - if (!spin_trylock(&fib6_gc_lock)) { - mod_timer(net->ipv6.ip6_fib_timer, jiffies + HZ); - local_bh_enable(); + if (!spin_trylock_bh(&fib6_gc_lock)) { + mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); return; } gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval; } - gc_args.more = 0; - icmp6_dst_gc(&gc_args.more); + gc_args.more = icmp6_dst_gc(); fib6_clean_all(net, fib6_age, 0, NULL); if (gc_args.more) - mod_timer(net->ipv6.ip6_fib_timer, jiffies + - net->ipv6.sysctl.ip6_rt_gc_interval); - else { - del_timer(net->ipv6.ip6_fib_timer); - net->ipv6.ip6_fib_timer->expires = 0; - } + mod_timer(&net->ipv6.ip6_fib_timer, + round_jiffies(jiffies + + net->ipv6.sysctl.ip6_rt_gc_interval)); + else + del_timer(&net->ipv6.ip6_fib_timer); spin_unlock_bh(&fib6_gc_lock); } @@ -1478,24 +1474,15 @@ static void fib6_gc_timer_cb(unsigned long arg) static int fib6_net_init(struct net *net) { - int ret; - struct timer_list *timer; - - ret = -ENOMEM; - timer = kzalloc(sizeof(*timer), GFP_KERNEL); - if (!timer) - goto out; - - setup_timer(timer, fib6_gc_timer_cb, (unsigned long)net); - net->ipv6.ip6_fib_timer = timer; + setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) goto out_timer; - net->ipv6.fib_table_hash = - kzalloc(sizeof(*net->ipv6.fib_table_hash)*FIB_TABLE_HASHSZ, - GFP_KERNEL); + net->ipv6.fib_table_hash = kcalloc(FIB_TABLE_HASHSZ, + sizeof(*net->ipv6.fib_table_hash), + GFP_KERNEL); if (!net->ipv6.fib_table_hash) goto out_rt6_stats; @@ -1521,9 +1508,7 @@ static int fib6_net_init(struct net *net) #endif fib6_tables_init(net); - ret = 0; -out: - return ret; + return 0; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_fib6_main_tbl: @@ -1534,15 +1519,14 @@ out_fib_table_hash: out_rt6_stats: kfree(net->ipv6.rt6_stats); out_timer: - kfree(timer); - goto out; + return -ENOMEM; } static void fib6_net_exit(struct net *net) { rt6_ifdown(net, NULL); - del_timer_sync(net->ipv6.ip6_fib_timer); - kfree(net->ipv6.ip6_fib_timer); + del_timer_sync(&net->ipv6.ip6_fib_timer); + #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.fib6_local_tbl); #endif diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 615b328de251..86540b24b27c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -978,13 +978,12 @@ out: return &rt->u.dst; } -int icmp6_dst_gc(int *more) +int icmp6_dst_gc(void) { struct dst_entry *dst, *next, **pprev; - int freed; + int more = 0; next = NULL; - freed = 0; spin_lock_bh(&icmp6_dst_lock); pprev = &icmp6_dst_gc_list; @@ -993,16 +992,15 @@ int icmp6_dst_gc(int *more) if (!atomic_read(&dst->__refcnt)) { *pprev = dst->next; dst_free(dst); - freed++; } else { pprev = &dst->next; - (*more)++; + ++more; } } spin_unlock_bh(&icmp6_dst_lock); - return freed; + return more; } static int ip6_dst_gc(struct dst_ops *ops) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 316c7af1d2b1..ee898e74808d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -49,6 +49,15 @@ config NF_CT_ACCT Those counters can be used for flow-based accounting or the `connbytes' match. + Please note that currently this option only sets a default state. + You may change it at boot time with nf_conntrack.acct=0/1 kernel + paramater or by loading the nf_conntrack module with acct=0/1. + + You may also disable/enable it on a running system with: + sysctl net.netfilter.nf_conntrack_acct=0/1 + + This option will be removed in 2.6.29. + If unsure, say `N'. config NF_CONNTRACK_MARK diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 5c4b183f6422..3bd2cc556aea 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -1,6 +1,6 @@ netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o -nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o +nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o obj-$(CONFIG_NETFILTER) = netfilter.o diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c new file mode 100644 index 000000000000..59bd8b903a19 --- /dev/null +++ b/net/netfilter/nf_conntrack_acct.c @@ -0,0 +1,104 @@ +/* Accouting handling for netfilter. */ + +/* + * (C) 2008 Krzysztof Piotr Oledzki <ole@ans.pl> + * + * 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/netfilter.h> +#include <linux/kernel.h> +#include <linux/moduleparam.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_extend.h> +#include <net/netfilter/nf_conntrack_acct.h> + +#ifdef CONFIG_NF_CT_ACCT +#define NF_CT_ACCT_DEFAULT 1 +#else +#define NF_CT_ACCT_DEFAULT 0 +#endif + +int nf_ct_acct __read_mostly = NF_CT_ACCT_DEFAULT; +EXPORT_SYMBOL_GPL(nf_ct_acct); + +module_param_named(acct, nf_ct_acct, bool, 0644); +MODULE_PARM_DESC(acct, "Enable connection tracking flow accounting."); + +#ifdef CONFIG_SYSCTL +static struct ctl_table_header *acct_sysctl_header; +static struct ctl_table acct_sysctl_table[] = { + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nf_conntrack_acct", + .data = &nf_ct_acct, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + {} +}; +#endif /* CONFIG_SYSCTL */ + +unsigned int +seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir) +{ + struct nf_conn_counter *acct; + + acct = nf_conn_acct_find(ct); + if (!acct) + return 0; + + return seq_printf(s, "packets=%llu bytes=%llu ", + (unsigned long long)acct[dir].packets, + (unsigned long long)acct[dir].bytes); +}; +EXPORT_SYMBOL_GPL(seq_print_acct); + +static struct nf_ct_ext_type acct_extend __read_mostly = { + .len = sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]), + .align = __alignof__(struct nf_conn_counter[IP_CT_DIR_MAX]), + .id = NF_CT_EXT_ACCT, +}; + +int nf_conntrack_acct_init(void) +{ + int ret; + +#ifdef CONFIG_NF_CT_ACCT + printk(KERN_WARNING "CONFIG_NF_CT_ACCT is deprecated and will be removed soon. Plase use\n"); + printk(KERN_WARNING "nf_conntrack.acct=1 kernel paramater, acct=1 nf_conntrack module option or\n"); + printk(KERN_WARNING "sysctl net.netfilter.nf_conntrack_acct=1 to enable it.\n"); +#endif + + ret = nf_ct_extend_register(&acct_extend); + if (ret < 0) { + printk(KERN_ERR "nf_conntrack_acct: Unable to register extension\n"); + return ret; + } + +#ifdef CONFIG_SYSCTL + acct_sysctl_header = register_sysctl_paths(nf_net_netfilter_sysctl_path, + acct_sysctl_table); + + if (!acct_sysctl_header) { + nf_ct_extend_unregister(&acct_extend); + + printk(KERN_ERR "nf_conntrack_acct: can't register to sysctl.\n"); + return -ENOMEM; + } +#endif + + return 0; +} + +void nf_conntrack_acct_fini(void) +{ +#ifdef CONFIG_SYSCTL + unregister_sysctl_table(acct_sysctl_header); +#endif + nf_ct_extend_unregister(&acct_extend); +} diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 28d03e64200b..c519d090bdb9 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -37,6 +37,7 @@ #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> +#include <net/netfilter/nf_conntrack_acct.h> #define NF_CONNTRACK_VERSION "0.5.0" @@ -555,6 +556,8 @@ init_conntrack(const struct nf_conntrack_tuple *tuple, return NULL; } + nf_ct_acct_ext_add(ct, GFP_ATOMIC); + spin_lock_bh(&nf_conntrack_lock); exp = nf_ct_find_expectation(tuple); if (exp) { @@ -828,17 +831,16 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, } acct: -#ifdef CONFIG_NF_CT_ACCT if (do_acct) { - ct->counters[CTINFO2DIR(ctinfo)].packets++; - ct->counters[CTINFO2DIR(ctinfo)].bytes += - skb->len - skb_network_offset(skb); + struct nf_conn_counter *acct; - if ((ct->counters[CTINFO2DIR(ctinfo)].packets & 0x80000000) - || (ct->counters[CTINFO2DIR(ctinfo)].bytes & 0x80000000)) - event |= IPCT_COUNTER_FILLING; + acct = nf_conn_acct_find(ct); + if (acct) { + acct[CTINFO2DIR(ctinfo)].packets++; + acct[CTINFO2DIR(ctinfo)].bytes += + skb->len - skb_network_offset(skb); + } } -#endif spin_unlock_bh(&nf_conntrack_lock); @@ -853,15 +855,19 @@ bool __nf_ct_kill_acct(struct nf_conn *ct, const struct sk_buff *skb, int do_acct) { -#ifdef CONFIG_NF_CT_ACCT if (do_acct) { + struct nf_conn_counter *acct; + spin_lock_bh(&nf_conntrack_lock); - ct->counters[CTINFO2DIR(ctinfo)].packets++; - ct->counters[CTINFO2DIR(ctinfo)].bytes += - skb->len - skb_network_offset(skb); + acct = nf_conn_acct_find(ct); + if (acct) { + acct[CTINFO2DIR(ctinfo)].packets++; + acct[CTINFO2DIR(ctinfo)].bytes += + skb->len - skb_network_offset(skb); + } spin_unlock_bh(&nf_conntrack_lock); } -#endif + if (del_timer(&ct->timeout)) { ct->timeout.function((unsigned long)ct); return true; @@ -1029,6 +1035,7 @@ void nf_conntrack_cleanup(void) nf_conntrack_proto_fini(); nf_conntrack_helper_fini(); nf_conntrack_expect_fini(); + nf_conntrack_acct_fini(); } struct hlist_head *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced) @@ -1168,6 +1175,10 @@ int __init nf_conntrack_init(void) if (ret < 0) goto out_fini_expect; + ret = nf_conntrack_acct_init(); + if (ret < 0) + goto out_fini_helper; + /* For use by REJECT target */ rcu_assign_pointer(ip_ct_attach, nf_conntrack_attach); rcu_assign_pointer(nf_ct_destroy, destroy_conntrack); @@ -1180,6 +1191,8 @@ int __init nf_conntrack_init(void) return ret; +out_fini_helper: + nf_conntrack_helper_fini(); out_fini_expect: nf_conntrack_expect_fini(); out_fini_proto: diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 95a7967731f9..105a616c5c78 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -37,6 +37,7 @@ #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> +#include <net/netfilter/nf_conntrack_acct.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_protocol.h> @@ -206,22 +207,26 @@ nla_put_failure: return -1; } -#ifdef CONFIG_NF_CT_ACCT static int ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct, enum ip_conntrack_dir dir) { enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG; struct nlattr *nest_count; + const struct nf_conn_counter *acct; + + acct = nf_conn_acct_find(ct); + if (!acct) + return 0; nest_count = nla_nest_start(skb, type | NLA_F_NESTED); if (!nest_count) goto nla_put_failure; - NLA_PUT_BE32(skb, CTA_COUNTERS32_PACKETS, - htonl(ct->counters[dir].packets)); - NLA_PUT_BE32(skb, CTA_COUNTERS32_BYTES, - htonl(ct->counters[dir].bytes)); + NLA_PUT_BE64(skb, CTA_COUNTERS_PACKETS, + cpu_to_be64(acct[dir].packets)); + NLA_PUT_BE64(skb, CTA_COUNTERS_BYTES, + cpu_to_be64(acct[dir].bytes)); nla_nest_end(skb, nest_count); @@ -230,9 +235,6 @@ ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct, nla_put_failure: return -1; } -#else -#define ctnetlink_dump_counters(a, b, c) (0) -#endif #ifdef CONFIG_NF_CONNTRACK_MARK static inline int @@ -501,11 +503,6 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, goto nla_put_failure; #endif - if (events & IPCT_COUNTER_FILLING && - (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 || - ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0)) - goto nla_put_failure; - if (events & IPCT_RELATED && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; @@ -576,11 +573,15 @@ 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 + IPCTNL_MSG_CT_GET_CTRZERO) { + struct nf_conn_counter *acct; + + acct = nf_conn_acct_find(ct); + if (acct) + memset(acct, 0, sizeof(struct nf_conn_counter[IP_CT_DIR_MAX])); + } } if (cb->args[1]) { cb->args[1] = 0; @@ -832,14 +833,9 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, u_int8_t u3 = nfmsg->nfgen_family; int err = 0; - if (nlh->nlmsg_flags & NLM_F_DUMP) { -#ifndef CONFIG_NF_CT_ACCT - if (NFNL_MSG_TYPE(nlh->nlmsg_type) == IPCTNL_MSG_CT_GET_CTRZERO) - return -ENOTSUPP; -#endif + if (nlh->nlmsg_flags & NLM_F_DUMP) return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table, ctnetlink_done); - } if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3); @@ -1152,6 +1148,8 @@ ctnetlink_create_conntrack(struct nlattr *cda[], goto err; } + nf_ct_acct_ext_add(ct, GFP_KERNEL); + #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 41183a4d2d62..30aa5b94a771 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -482,11 +482,11 @@ static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, NLA_PUT_BE32(skb, CTA_PROTOINFO_SCTP_VTAG_ORIGINAL, - htonl(ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL])); + ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL]); NLA_PUT_BE32(skb, CTA_PROTOINFO_SCTP_VTAG_REPLY, - htonl(ct->proto.sctp.vtag[IP_CT_DIR_REPLY])); + ct->proto.sctp.vtag[IP_CT_DIR_REPLY]); read_unlock_bh(&sctp_lock); @@ -530,9 +530,9 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct) write_lock_bh(&sctp_lock); ct->proto.sctp.state = nla_get_u8(tb[CTA_PROTOINFO_SCTP_STATE]); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = - ntohl(nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_ORIGINAL])); + nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_ORIGINAL]); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = - ntohl(nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_REPLY])); + nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_REPLY]); write_unlock_bh(&sctp_lock); return 0; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 46ea542d0df9..869ef9349d0f 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -25,6 +25,7 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_acct.h> MODULE_LICENSE("GPL"); @@ -38,19 +39,6 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, } EXPORT_SYMBOL_GPL(print_tuple); -#ifdef CONFIG_NF_CT_ACCT -static unsigned int -seq_print_counters(struct seq_file *s, - const struct ip_conntrack_counter *counter) -{ - return seq_printf(s, "packets=%llu bytes=%llu ", - (unsigned long long)counter->packets, - (unsigned long long)counter->bytes); -} -#else -#define seq_print_counters(x, y) 0 -#endif - struct ct_iter_state { unsigned int bucket; }; @@ -146,7 +134,7 @@ static int ct_seq_show(struct seq_file *s, void *v) l3proto, l4proto)) return -ENOSPC; - if (seq_print_counters(s, &ct->counters[IP_CT_DIR_ORIGINAL])) + if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL)) return -ENOSPC; if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) @@ -157,7 +145,7 @@ static int ct_seq_show(struct seq_file *s, void *v) l3proto, l4proto)) return -ENOSPC; - if (seq_print_counters(s, &ct->counters[IP_CT_DIR_REPLY])) + if (seq_print_acct(s, ct, IP_CT_DIR_REPLY)) return -ENOSPC; if (test_bit(IPS_ASSURED_BIT, &ct->status)) diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index b8173af8c24a..9a35b57ab76d 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -453,6 +453,14 @@ __build_packet_message(struct nfulnl_instance *inst, } } + if (indev && skb_mac_header_was_set(skb)) { + NLA_PUT_BE16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)); + NLA_PUT_BE16(inst->skb, NFULA_HWLEN, + htons(skb->dev->hard_header_len)); + NLA_PUT(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, + skb_mac_header(skb)); + } + if (skb->tstamp.tv64) { struct nfulnl_msg_packet_timestamp ts; struct timeval tv = ktime_to_timeval(skb->tstamp); diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 217e2b686322..beb5094703cb 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -147,17 +147,21 @@ tcpmss_mangle_packet(struct sk_buff *skb, return TCPOLEN_MSS; } -static u_int32_t tcpmss_reverse_mtu4(const struct iphdr *iph) +static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb, + unsigned int family) { - struct flowi fl = { - .fl4_dst = iph->saddr, - }; + struct flowi fl = {}; const struct nf_afinfo *ai; struct rtable *rt = NULL; u_int32_t mtu = ~0U; + if (family == PF_INET) + fl.fl4_dst = ip_hdr(skb)->saddr; + else + fl.fl6_dst = ipv6_hdr(skb)->saddr; + rcu_read_lock(); - ai = nf_get_afinfo(AF_INET); + ai = nf_get_afinfo(family); if (ai != NULL) ai->route((struct dst_entry **)&rt, &fl); rcu_read_unlock(); @@ -178,7 +182,8 @@ tcpmss_tg4(struct sk_buff *skb, const struct net_device *in, __be16 newlen; int ret; - ret = tcpmss_mangle_packet(skb, targinfo, tcpmss_reverse_mtu4(iph), + ret = tcpmss_mangle_packet(skb, targinfo, + tcpmss_reverse_mtu(skb, PF_INET), iph->ihl * 4, sizeof(*iph) + sizeof(struct tcphdr)); if (ret < 0) @@ -193,28 +198,6 @@ tcpmss_tg4(struct sk_buff *skb, const struct net_device *in, } #if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) -static u_int32_t tcpmss_reverse_mtu6(const struct ipv6hdr *iph) -{ - struct flowi fl = { - .fl6_dst = iph->saddr, - }; - const struct nf_afinfo *ai; - struct rtable *rt = NULL; - u_int32_t mtu = ~0U; - - rcu_read_lock(); - ai = nf_get_afinfo(AF_INET6); - if (ai != NULL) - ai->route((struct dst_entry **)&rt, &fl); - rcu_read_unlock(); - - if (rt != NULL) { - mtu = dst_mtu(&rt->u.dst); - dst_release(&rt->u.dst); - } - return mtu; -} - static unsigned int tcpmss_tg6(struct sk_buff *skb, const struct net_device *in, const struct net_device *out, unsigned int hooknum, @@ -229,7 +212,8 @@ tcpmss_tg6(struct sk_buff *skb, const struct net_device *in, tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr); if (tcphoff < 0) return NF_DROP; - ret = tcpmss_mangle_packet(skb, targinfo, tcpmss_reverse_mtu6(ipv6h), + ret = tcpmss_mangle_packet(skb, targinfo, + tcpmss_reverse_mtu(skb, PF_INET6), tcphoff, sizeof(*ipv6h) + sizeof(struct tcphdr)); if (ret < 0) diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c index d7e8983cd37f..3e39c4fe1931 100644 --- a/net/netfilter/xt_connbytes.c +++ b/net/netfilter/xt_connbytes.c @@ -8,6 +8,7 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_connbytes.h> #include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_acct.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); @@ -27,12 +28,15 @@ connbytes_mt(const struct sk_buff *skb, const struct net_device *in, u_int64_t what = 0; /* initialize to make gcc happy */ u_int64_t bytes = 0; u_int64_t pkts = 0; - const struct ip_conntrack_counter *counters; + const struct nf_conn_counter *counters; ct = nf_ct_get(skb, &ctinfo); if (!ct) return false; - counters = ct->counters; + + counters = nf_conn_acct_find(ct); + if (!counters) + return false; switch (sinfo->what) { case XT_CONNBYTES_PKTS: diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index ed76baab4734..9f328593287e 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -173,7 +173,7 @@ time_mt(const struct sk_buff *skb, const struct net_device *in, __net_timestamp((struct sk_buff *)skb); stamp = ktime_to_ns(skb->tstamp); - do_div(stamp, NSEC_PER_SEC); + stamp = div_s64(stamp, NSEC_PER_SEC); if (info->flags & XT_TIME_LOCAL_TZ) /* Adjust for local timezone */ diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index fccc250f95f5..532e4faa29f7 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -73,6 +73,7 @@ static const struct proto_ops nr_proto_ops; * separate class since they always nest. */ static struct lock_class_key nr_netdev_xmit_lock_key; +static struct lock_class_key nr_netdev_addr_lock_key; static void nr_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, @@ -83,6 +84,7 @@ static void nr_set_lockdep_one(struct net_device *dev, static void nr_set_lockdep_key(struct net_device *dev) { + lockdep_set_class(&dev->addr_list_lock, &nr_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL); } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index dbc963b4f5fb..a7f1ce11bc22 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -74,6 +74,7 @@ ax25_address rose_callsign; * separate class since they always nest. */ static struct lock_class_key rose_netdev_xmit_lock_key; +static struct lock_class_key rose_netdev_addr_lock_key; static void rose_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, @@ -84,6 +85,7 @@ static void rose_set_lockdep_one(struct net_device *dev, static void rose_set_lockdep_key(struct net_device *dev) { + lockdep_set_class(&dev->addr_list_lock, &rose_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, rose_set_lockdep_one, NULL); } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 5219d5f9d754..b0601642e227 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -447,7 +447,7 @@ void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) } EXPORT_SYMBOL(qdisc_watchdog_cancel); -struct hlist_head *qdisc_class_hash_alloc(unsigned int n) +static struct hlist_head *qdisc_class_hash_alloc(unsigned int n) { unsigned int size = n * sizeof(struct hlist_head), i; struct hlist_head *h; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 0ddf69286f92..4ac7e3a8c253 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -212,9 +212,9 @@ static void dev_watchdog(unsigned long arg) if (some_queue_stopped && time_after(jiffies, (dev->trans_start + dev->watchdog_timeo))) { - printk(KERN_INFO "NETDEV WATCHDOG: %s: " - "transmit timed out\n", - dev->name); + char drivername[64]; + printk(KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit timed out\n", + dev->name, netdev_drivername(dev, drivername, 64)); dev->tx_timeout(dev); WARN_ON_ONCE(1); } @@ -356,44 +356,99 @@ static struct Qdisc noqueue_qdisc = { }; -static int fifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) +static const u8 prio2band[TC_PRIO_MAX+1] = + { 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 }; + +/* 3-band FIFO queue: old style, but should be a bit faster than + generic prio+fifo combination. + */ + +#define PFIFO_FAST_BANDS 3 + +static inline struct sk_buff_head *prio2list(struct sk_buff *skb, + struct Qdisc *qdisc) +{ + struct sk_buff_head *list = qdisc_priv(qdisc); + return list + prio2band[skb->priority & TC_PRIO_MAX]; +} + +static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) { - struct sk_buff_head *list = &qdisc->q; + struct sk_buff_head *list = prio2list(skb, qdisc); - if (skb_queue_len(list) < qdisc_dev(qdisc)->tx_queue_len) + if (skb_queue_len(list) < qdisc_dev(qdisc)->tx_queue_len) { + qdisc->q.qlen++; return __qdisc_enqueue_tail(skb, qdisc, list); + } return qdisc_drop(skb, qdisc); } -static struct sk_buff *fifo_fast_dequeue(struct Qdisc* qdisc) +static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) { - struct sk_buff_head *list = &qdisc->q; + int prio; + struct sk_buff_head *list = qdisc_priv(qdisc); - if (!skb_queue_empty(list)) - return __qdisc_dequeue_head(qdisc, list); + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { + if (!skb_queue_empty(list + prio)) { + qdisc->q.qlen--; + return __qdisc_dequeue_head(qdisc, list + prio); + } + } return NULL; } -static int fifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc) +static int pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc) { - return __qdisc_requeue(skb, qdisc, &qdisc->q); + qdisc->q.qlen++; + return __qdisc_requeue(skb, qdisc, prio2list(skb, qdisc)); } -static void fifo_fast_reset(struct Qdisc* qdisc) +static void pfifo_fast_reset(struct Qdisc* qdisc) { - __qdisc_reset_queue(qdisc, &qdisc->q); + int prio; + struct sk_buff_head *list = qdisc_priv(qdisc); + + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) + __qdisc_reset_queue(qdisc, list + prio); + qdisc->qstats.backlog = 0; + qdisc->q.qlen = 0; } -static struct Qdisc_ops fifo_fast_ops __read_mostly = { - .id = "fifo_fast", - .priv_size = 0, - .enqueue = fifo_fast_enqueue, - .dequeue = fifo_fast_dequeue, - .requeue = fifo_fast_requeue, - .reset = fifo_fast_reset, +static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) +{ + struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; + + memcpy(&opt.priomap, prio2band, TC_PRIO_MAX+1); + NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + return skb->len; + +nla_put_failure: + return -1; +} + +static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt) +{ + int prio; + struct sk_buff_head *list = qdisc_priv(qdisc); + + for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) + skb_queue_head_init(list + prio); + + return 0; +} + +static struct Qdisc_ops pfifo_fast_ops __read_mostly = { + .id = "pfifo_fast", + .priv_size = PFIFO_FAST_BANDS * sizeof(struct sk_buff_head), + .enqueue = pfifo_fast_enqueue, + .dequeue = pfifo_fast_dequeue, + .requeue = pfifo_fast_requeue, + .init = pfifo_fast_init, + .reset = pfifo_fast_reset, + .dump = pfifo_fast_dump, .owner = THIS_MODULE, }; @@ -522,7 +577,7 @@ static void attach_one_default_qdisc(struct net_device *dev, if (dev->tx_queue_len) { qdisc = qdisc_create_dflt(dev, dev_queue, - &fifo_fast_ops, TC_H_ROOT); + &pfifo_fast_ops, TC_H_ROOT); if (!qdisc) { printk(KERN_INFO "%s: activation failed\n", dev->name); return; @@ -550,9 +605,9 @@ void dev_activate(struct net_device *dev) int need_watchdog; /* No queueing discipline is attached to device; - * create default one i.e. fifo_fast for devices, - * which need queueing and noqueue_qdisc for - * virtual interfaces. + create default one i.e. pfifo_fast for devices, + which need queueing and noqueue_qdisc for + virtual interfaces */ if (dev_all_qdisc_sleeping_noop(dev)) @@ -576,7 +631,6 @@ static void dev_deactivate_queue(struct net_device *dev, void *_qdisc_default) { struct Qdisc *qdisc_default = _qdisc_default; - struct sk_buff *skb = NULL; struct Qdisc *qdisc; qdisc = dev_queue->qdisc; @@ -588,8 +642,6 @@ static void dev_deactivate_queue(struct net_device *dev, spin_unlock_bh(qdisc_lock(qdisc)); } - - kfree_skb(skb); } static bool some_qdisc_is_running(struct net_device *dev, int lock) diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 70ead8dc3485..4328ad5439c9 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -71,6 +71,8 @@ static void sctp_mark_missing(struct sctp_outq *q, static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn); +static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout); + /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, struct sctp_chunk *ch) @@ -712,7 +714,7 @@ int sctp_outq_uncork(struct sctp_outq *q) * locking concerns must be made. Today we use the sock lock to protect * this function. */ -int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) +static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) { struct sctp_packet *packet; struct sctp_packet singleton; diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 5dd89831eceb..f268910620be 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -519,8 +519,3 @@ int __init sctp_remaddr_proc_init(void) return 0; } - -void sctp_assoc_proc_exit(void) -{ - remove_proc_entry("remaddr", proc_net_sctp); -} |