From 06c4648d46d1b757d6b9591a86810be79818b60c Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Wed, 26 May 2010 00:09:42 +0000 Subject: arp_notify: allow drivers to explicitly request a notification event. Currently such notifications are only generated when the device comes up or the address changes. However one use case for these notifications is to enable faster network recovery after a virtual machine migration (by causing switches to relearn their MAC tables). A migration appears to the network stack as a temporary loss of carrier and therefore does not trigger either of the current conditions. Rather than adding carrier up as a trigger (which can cause issues when interfaces a flapping) simply add an interface which the driver can use to explicitly trigger the notification. Signed-off-by: Ian Campbell Cc: Stephen Hemminger Cc: Jeremy Fitzhardinge Cc: David S. Miller Cc: netdev@vger.kernel.org Cc: stable@kernel.org Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ include/linux/notifier.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 40291f375024..a24916156f4e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1772,6 +1772,8 @@ extern void netif_carrier_on(struct net_device *dev); extern void netif_carrier_off(struct net_device *dev); +extern void netif_notify_peers(struct net_device *dev); + /** * netif_dormant_on - mark device as dormant. * @dev: network device diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 540703b555cb..22c2abb61974 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -210,6 +210,7 @@ static inline int notifier_to_errno(int ret) #define NETDEV_POST_INIT 0x0010 #define NETDEV_UNREGISTER_BATCH 0x0011 #define NETDEV_BONDING_DESLAVE 0x0012 +#define NETDEV_NOTIFY_PEERS 0x0012 #define SYS_DOWN 0x0001 /* Notify of system down */ #define SYS_RESTART SYS_DOWN -- cgit v1.2.3 From 38117d1495e587fbb10d6e55733139a27893cef5 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 31 May 2010 00:28:35 -0700 Subject: net: Fix NETDEV_NOTIFY_PEERS to not conflict with NETDEV_BONDING_DESLAVE. Signed-off-by: David S. Miller --- include/linux/notifier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 22c2abb61974..b2f1a4d83550 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -210,7 +210,7 @@ static inline int notifier_to_errno(int ret) #define NETDEV_POST_INIT 0x0010 #define NETDEV_UNREGISTER_BATCH 0x0011 #define NETDEV_BONDING_DESLAVE 0x0012 -#define NETDEV_NOTIFY_PEERS 0x0012 +#define NETDEV_NOTIFY_PEERS 0x0013 #define SYS_DOWN 0x0001 /* Notify of system down */ #define SYS_RESTART SYS_DOWN -- cgit v1.2.3 From bc135b23d01acf7ee926aaf75b0020c86d3869f9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Jun 2010 03:23:51 -0700 Subject: net: Define accessors to manipulate QDISC_STATE_RUNNING Define three helpers to manipulate QDISC_STATE_RUNNIG flag, that a second patch will move on another location. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 2 +- include/net/sch_generic.h | 15 +++++++++++++++ net/core/dev.c | 4 ++-- net/sched/sch_generic.c | 4 ++-- 4 files changed, 20 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9d4d87cc970e..d9549af6929a 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -95,7 +95,7 @@ extern void __qdisc_run(struct Qdisc *q); static inline void qdisc_run(struct Qdisc *q) { - if (!test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) + if (qdisc_run_begin(q)) __qdisc_run(q); } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 03ca5d826757..9707daed761e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -76,6 +76,21 @@ struct Qdisc { struct rcu_head rcu_head; }; +static inline bool qdisc_is_running(struct Qdisc *qdisc) +{ + return test_bit(__QDISC_STATE_RUNNING, &qdisc->state); +} + +static inline bool qdisc_run_begin(struct Qdisc *qdisc) +{ + return !test_and_set_bit(__QDISC_STATE_RUNNING, &qdisc->state); +} + +static inline void qdisc_run_end(struct Qdisc *qdisc) +{ + clear_bit(__QDISC_STATE_RUNNING, &qdisc->state); +} + struct Qdisc_class_ops { /* Child qdisc manipulation */ struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *); diff --git a/net/core/dev.c b/net/core/dev.c index 983a3c1d65c4..2733226d90b2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2047,7 +2047,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, kfree_skb(skb); rc = NET_XMIT_DROP; } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && - !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { + qdisc_run_begin(q)) { /* * This is a work-conserving queue; there are no old skbs * waiting to be sent out; and the qdisc is not running - @@ -2059,7 +2059,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (sch_direct_xmit(skb, q, dev, txq, root_lock)) __qdisc_run(q); else - clear_bit(__QDISC_STATE_RUNNING, &q->state); + qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index bd1892fe4b21..37b86eab6779 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -205,7 +205,7 @@ void __qdisc_run(struct Qdisc *q) } } - clear_bit(__QDISC_STATE_RUNNING, &q->state); + qdisc_run_end(q); } unsigned long dev_trans_start(struct net_device *dev) @@ -797,7 +797,7 @@ static bool some_qdisc_is_busy(struct net_device *dev) spin_lock_bh(root_lock); - val = (test_bit(__QDISC_STATE_RUNNING, &q->state) || + val = (qdisc_is_running(q) || test_bit(__QDISC_STATE_SCHED, &q->state)); spin_unlock_bh(root_lock); -- cgit v1.2.3 From 371121057607e3127e19b3fa094330181b5b031e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Jun 2010 03:24:13 -0700 Subject: net: QDISC_STATE_RUNNING dont need atomic bit ops __QDISC_STATE_RUNNING is always changed while qdisc lock is held. We can avoid two atomic operations in xmit path, if we move this bit in a new __state container. Location of this __state container is carefully chosen so that fast path only dirties one qdisc cache line. THROTTLED bit could later be moved into this __state location too, to avoid dirtying first qdisc cache line. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sch_generic.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9707daed761e..b3591e4a514c 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -23,11 +23,17 @@ struct qdisc_rate_table { }; enum qdisc_state_t { - __QDISC_STATE_RUNNING, __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, }; +/* + * following bits are only changed while qdisc lock is held + */ +enum qdisc___state_t { + __QDISC___STATE_RUNNING, +}; + struct qdisc_size_table { struct list_head list; struct tc_sizespec szopts; @@ -72,23 +78,24 @@ struct Qdisc { unsigned long state; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; + unsigned long __state; struct gnet_stats_queue qstats; struct rcu_head rcu_head; }; static inline bool qdisc_is_running(struct Qdisc *qdisc) { - return test_bit(__QDISC_STATE_RUNNING, &qdisc->state); + return test_bit(__QDISC___STATE_RUNNING, &qdisc->__state); } static inline bool qdisc_run_begin(struct Qdisc *qdisc) { - return !test_and_set_bit(__QDISC_STATE_RUNNING, &qdisc->state); + return !__test_and_set_bit(__QDISC___STATE_RUNNING, &qdisc->__state); } static inline void qdisc_run_end(struct Qdisc *qdisc) { - clear_bit(__QDISC_STATE_RUNNING, &qdisc->state); + __clear_bit(__QDISC___STATE_RUNNING, &qdisc->__state); } struct Qdisc_class_ops { -- cgit v1.2.3 From 79640a4ca6955e3ebdb7038508fa7a0cd7fa5527 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Jun 2010 05:09:29 -0700 Subject: net: add additional lock to qdisc to increase throughput When many cpus compete for sending frames on a given qdisc, the qdisc spinlock suffers from very high contention. The cpu owning __QDISC_STATE_RUNNING bit has same priority to acquire the lock, and cannot dequeue packets fast enough, since it must wait for this lock for each dequeued packet. One solution to this problem is to force all cpus spinning on a second lock before trying to get the main lock, when/if they see __QDISC_STATE_RUNNING already set. The owning cpu then compete with at most one other cpu for the main lock, allowing for higher dequeueing rate. Based on a previous patch from Alexander Duyck. I added the heuristic to avoid the atomic in fast path, and put the new lock far away from the cache line used by the dequeue worker. Also try to release the busylock lock as late as possible. Tests with following script gave a boost from ~50.000 pps to ~600.000 pps on a dual quad core machine (E5450 @3.00GHz), tg3 driver. (A single netperf flow can reach ~800.000 pps on this platform) for j in `seq 0 3`; do for i in `seq 0 7`; do netperf -H 192.168.0.1 -t UDP_STREAM -l 60 -N -T $i -- -m 6 & done done Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/sch_generic.h | 3 ++- net/core/dev.c | 29 +++++++++++++++++++++++++---- net/sched/sch_generic.c | 1 + 3 files changed, 28 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index b3591e4a514c..b35301b0c7b6 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -80,7 +80,8 @@ struct Qdisc { struct gnet_stats_basic_packed bstats; unsigned long __state; struct gnet_stats_queue qstats; - struct rcu_head rcu_head; + struct rcu_head rcu_head; + spinlock_t busylock; }; static inline bool qdisc_is_running(struct Qdisc *qdisc) diff --git a/net/core/dev.c b/net/core/dev.c index 2733226d90b2..ffca5c1066fa 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2040,8 +2040,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); + bool contended = qdisc_is_running(q); int rc; + /* + * Heuristic to force contended enqueues to serialize on a + * separate lock before trying to get qdisc main lock. + * This permits __QDISC_STATE_RUNNING owner to get the lock more often + * and dequeue packets faster. + */ + if (unlikely(contended)) + spin_lock(&q->busylock); + spin_lock(root_lock); if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { kfree_skb(skb); @@ -2056,19 +2066,30 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) skb_dst_force(skb); __qdisc_update_bstats(q, skb->len); - if (sch_direct_xmit(skb, q, dev, txq, root_lock)) + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { + if (unlikely(contended)) { + spin_unlock(&q->busylock); + contended = false; + } __qdisc_run(q); - else + } else qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { skb_dst_force(skb); rc = qdisc_enqueue_root(skb, q); - qdisc_run(q); + if (qdisc_run_begin(q)) { + if (unlikely(contended)) { + spin_unlock(&q->busylock); + contended = false; + } + __qdisc_run(q); + } } spin_unlock(root_lock); - + if (unlikely(contended)) + spin_unlock(&q->busylock); return rc; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 37b86eab6779..d20fcd2a5519 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -561,6 +561,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, INIT_LIST_HEAD(&sch->list); skb_queue_head_init(&sch->q); + spin_lock_init(&sch->busylock); sch->ops = ops; sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; -- cgit v1.2.3 From c2d9ba9bce8d7323ca96f239e1f505c14d6244fb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 1 Jun 2010 06:51:19 +0000 Subject: net: CONFIG_NET_NS reduction Use read_pnet() and write_pnet() to reduce number of ifdef CONFIG_NET_NS Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +----- include/net/cfg80211.h | 15 ++------------- include/net/genetlink.h | 15 ++------------- include/net/netfilter/nf_conntrack.h | 6 +----- include/net/sock.h | 10 ++-------- net/ipv6/addrlabel.c | 6 +----- net/netfilter/nf_conntrack_core.c | 8 ++------ 7 files changed, 11 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a24916156f4e..bd6b75317d5f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1087,11 +1087,7 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, static inline struct net *dev_net(const struct net_device *dev) { -#ifdef CONFIG_NET_NS - return dev->nd_net; -#else - return &init_net; -#endif + return read_pnet(&dev->nd_net); } static inline diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b44a2e5321a3..e7ebeb8bdf71 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1330,26 +1330,15 @@ struct wiphy { char priv[0] __attribute__((__aligned__(NETDEV_ALIGN))); }; -#ifdef CONFIG_NET_NS -static inline struct net *wiphy_net(struct wiphy *wiphy) -{ - return wiphy->_net; -} - -static inline void wiphy_net_set(struct wiphy *wiphy, struct net *net) -{ - wiphy->_net = net; -} -#else static inline struct net *wiphy_net(struct wiphy *wiphy) { - return &init_net; + return read_pnet(&wiphy->_net); } static inline void wiphy_net_set(struct wiphy *wiphy, struct net *net) { + write_pnet(&wiphy->_net, net); } -#endif /** * wiphy_priv - return priv from wiphy diff --git a/include/net/genetlink.h b/include/net/genetlink.h index eb551baafc04..f7dcd2c70412 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -68,26 +68,15 @@ struct genl_info { #endif }; -#ifdef CONFIG_NET_NS static inline struct net *genl_info_net(struct genl_info *info) { - return info->_net; + return read_pnet(&info->_net); } static inline void genl_info_net_set(struct genl_info *info, struct net *net) { - info->_net = net; + write_pnet(&info->_net, net); } -#else -static inline struct net *genl_info_net(struct genl_info *info) -{ - return &init_net; -} - -static inline void genl_info_net_set(struct genl_info *info, struct net *net) -{ -} -#endif /** * struct genl_ops - generic netlink operations diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index bde095f7e845..bbfdd9453087 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -152,11 +152,7 @@ extern struct net init_net; static inline struct net *nf_ct_net(const struct nf_conn *ct) { -#ifdef CONFIG_NET_NS - return ct->ct_net; -#else - return &init_net; -#endif + return read_pnet(&ct->ct_net); } /* Alter reply tuple (maybe alter helper). */ diff --git a/include/net/sock.h b/include/net/sock.h index ca241ea14875..3461e5d1e9ad 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1724,19 +1724,13 @@ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_e static inline struct net *sock_net(const struct sock *sk) { -#ifdef CONFIG_NET_NS - return sk->sk_net; -#else - return &init_net; -#endif + return read_pnet(&sk->sk_net); } static inline void sock_net_set(struct sock *sk, struct net *net) { -#ifdef CONFIG_NET_NS - sk->sk_net = net; -#endif + write_pnet(&sk->sk_net, net); } /* diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 8c4348cb1950..f0e774cea386 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -53,11 +53,7 @@ static struct ip6addrlbl_table static inline struct net *ip6addrlbl_net(const struct ip6addrlbl_entry *lbl) { -#ifdef CONFIG_NET_NS - return lbl->lbl_net; -#else - return &init_net; -#endif + return read_pnet(&lbl->lbl_net); } /* diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index eeeb8bc73982..77288980fae0 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -619,9 +619,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL; /* Don't set timer yet: wait for confirmation */ setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct); -#ifdef CONFIG_NET_NS - ct->ct_net = net; -#endif + write_pnet(&ct->ct_net, net); #ifdef CONFIG_NF_CONNTRACK_ZONES if (zone) { struct nf_conntrack_zone *nf_ct_zone; @@ -1363,9 +1361,7 @@ static int nf_conntrack_init_init_net(void) goto err_extend; #endif /* Set up fake conntrack: to never be deleted, not in any hashes */ -#ifdef CONFIG_NET_NS - nf_conntrack_untracked.ct_net = &init_net; -#endif + write_pnet(&nf_conntrack_untracked.ct_net, &init_net); atomic_set(&nf_conntrack_untracked.ct_general.use, 1); /* - and look it like as a confirmed connection */ set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status); -- cgit v1.2.3 From 614f60fa9d73a9e8fdff3df83381907fea7c5649 Mon Sep 17 00:00:00 2001 From: Scott McMillan Date: Wed, 2 Jun 2010 05:53:56 -0700 Subject: packet_mmap: expose hw packet timestamps to network packet capture utilities This patch adds a setting, PACKET_TIMESTAMP, to specify the packet timestamp source that is exported to capture utilities like tcpdump by packet_mmap. PACKET_TIMESTAMP accepts the same integer bit field as SO_TIMESTAMPING. However, only the SOF_TIMESTAMPING_SYS_HARDWARE and SOF_TIMESTAMPING_RAW_HARDWARE values are currently recognized by PACKET_TIMESTAMP. SOF_TIMESTAMPING_SYS_HARDWARE takes precedence over SOF_TIMESTAMPING_RAW_HARDWARE if both bits are set. If PACKET_TIMESTAMP is not set, a software timestamp generated inside the networking stack is used (the behavior before this setting was added). Signed-off-by: Scott McMillan Signed-off-by: David S. Miller --- Documentation/networking/packet_mmap.txt | 26 ++++++++++++++++++++++ include/linux/if_packet.h | 1 + net/packet/af_packet.c | 37 ++++++++++++++++++++++++++++++-- 3 files changed, 62 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index 98f71a5cef00..2546aa4dc232 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -493,6 +493,32 @@ The user can also use poll() to check if a buffer is available: pfd.events = POLLOUT; retval = poll(&pfd, 1, timeout); +------------------------------------------------------------------------------- ++ PACKET_TIMESTAMP +------------------------------------------------------------------------------- + +The PACKET_TIMESTAMP setting determines the source of the timestamp in +the packet meta information. If your NIC is capable of timestamping +packets in hardware, you can request those hardware timestamps to used. +Note: you may need to enable the generation of hardware timestamps with +SIOCSHWTSTAMP. + +PACKET_TIMESTAMP accepts the same integer bit field as +SO_TIMESTAMPING. However, only the SOF_TIMESTAMPING_SYS_HARDWARE +and SOF_TIMESTAMPING_RAW_HARDWARE values are recognized by +PACKET_TIMESTAMP. SOF_TIMESTAMPING_SYS_HARDWARE takes precedence over +SOF_TIMESTAMPING_RAW_HARDWARE if both bits are set. + + int req = 0; + req |= SOF_TIMESTAMPING_SYS_HARDWARE; + setsockopt(fd, SOL_PACKET, PACKET_TIMESTAMP, (void *) &req, sizeof(req)) + +If PACKET_TIMESTAMP is not set, a software timestamp generated inside +the networking stack is used (the behavior before this setting was added). + +See include/linux/net_tstamp.h and Documentation/networking/timestamping +for more information on hardware timestamps. + -------------------------------------------------------------------------------- + THANKS -------------------------------------------------------------------------------- diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 6ac23ef1801a..72bfa5a034dd 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -48,6 +48,7 @@ struct sockaddr_ll { #define PACKET_LOSS 14 #define PACKET_VNET_HDR 15 #define PACKET_TX_TIMESTAMP 16 +#define PACKET_TIMESTAMP 17 struct tpacket_stats { unsigned int tp_packets; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2078a277e06b..9a17f28b1253 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -83,6 +83,7 @@ #include #include #include +#include #ifdef CONFIG_INET #include @@ -202,6 +203,7 @@ struct packet_sock { unsigned int tp_hdrlen; unsigned int tp_reserve; unsigned int tp_loss:1; + unsigned int tp_tstamp; struct packet_type prot_hook ____cacheline_aligned_in_smp; }; @@ -656,6 +658,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct sk_buff *copy_skb = NULL; struct timeval tv; struct timespec ts; + struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); if (skb->pkt_type == PACKET_LOOPBACK) goto drop; @@ -737,7 +740,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h1->tp_snaplen = snaplen; h.h1->tp_mac = macoff; h.h1->tp_net = netoff; - if (skb->tstamp.tv64) + if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE) + && shhwtstamps->syststamp.tv64) + tv = ktime_to_timeval(shhwtstamps->syststamp); + else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE) + && shhwtstamps->hwtstamp.tv64) + tv = ktime_to_timeval(shhwtstamps->hwtstamp); + else if (skb->tstamp.tv64) tv = ktime_to_timeval(skb->tstamp); else do_gettimeofday(&tv); @@ -750,7 +759,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_snaplen = snaplen; h.h2->tp_mac = macoff; h.h2->tp_net = netoff; - if (skb->tstamp.tv64) + if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE) + && shhwtstamps->syststamp.tv64) + ts = ktime_to_timespec(shhwtstamps->syststamp); + else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE) + && shhwtstamps->hwtstamp.tv64) + ts = ktime_to_timespec(shhwtstamps->hwtstamp); + else if (skb->tstamp.tv64) ts = ktime_to_timespec(skb->tstamp); else getnstimeofday(&ts); @@ -2027,6 +2042,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv po->has_vnet_hdr = !!val; return 0; } + case PACKET_TIMESTAMP: + { + int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + + po->tp_tstamp = val; + return 0; + } default: return -ENOPROTOOPT; } @@ -2119,6 +2146,12 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, val = po->tp_loss; data = &val; break; + case PACKET_TIMESTAMP: + if (len > sizeof(int)) + len = sizeof(int); + val = po->tp_tstamp; + data = &val; + break; default: return -ENOPROTOOPT; } -- cgit v1.2.3 From 20c59de2e6b6bc74bbf714dcd4e720afe8d516cf Mon Sep 17 00:00:00 2001 From: Arnaud Ebalard Date: Tue, 1 Jun 2010 21:35:01 +0000 Subject: ipv6: Refactor update of IPv6 flowi destination address for srcrt (RH) option There are more than a dozen occurrences of following code in the IPv6 stack: if (opt && opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; ipv6_addr_copy(&final, &fl.fl6_dst); ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; } Replace those with a helper. Note that the helper overrides final_p in all cases. This is ok as final_p was previously initialized to NULL when declared. Signed-off-by: Arnaud Ebalard Signed-off-by: David S. Miller --- include/net/ipv6.h | 4 ++++ net/dccp/ipv6.c | 30 ++++++------------------------ net/ipv6/af_inet6.c | 9 ++------- net/ipv6/datagram.c | 18 ++++-------------- net/ipv6/exthdrs.c | 24 ++++++++++++++++++++++++ net/ipv6/inet6_connection_sock.c | 9 ++------- net/ipv6/raw.c | 10 ++-------- net/ipv6/syncookies.c | 9 ++------- net/ipv6/tcp_ipv6.c | 27 ++++++--------------------- net/ipv6/udp.c | 11 +++-------- 10 files changed, 55 insertions(+), 96 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 2600b69757b8..f5808d596aab 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -551,6 +551,10 @@ extern int ipv6_ext_hdr(u8 nexthdr); extern int ipv6_find_tlv(struct sk_buff *skb, int offset, int type); +extern struct in6_addr *fl6_update_dst(struct flowi *fl, + const struct ipv6_txoptions *opt, + struct in6_addr *orig); + /* * socket options (ipv6_sockglue.c) */ diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 091698899594..6e3f32575df7 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -248,7 +248,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; struct ipv6_txoptions *opt = NULL; - struct in6_addr *final_p = NULL, final; + struct in6_addr *final_p, final; struct flowi fl; int err = -1; struct dst_entry *dst; @@ -265,13 +265,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, opt = np->opt; - if (opt != NULL && opt->srcrt != NULL) { - const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; - - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, opt, &final); err = ip6_dst_lookup(sk, &dst, &fl); if (err) @@ -545,19 +539,13 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, goto out_overflow; if (dst == NULL) { - struct in6_addr *final_p = NULL, final; + struct in6_addr *final_p, final; struct flowi fl; memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_DCCP; ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - if (opt != NULL && opt->srcrt != NULL) { - const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; - - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, opt, &final); ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet_rsk(req)->rmt_port; @@ -885,7 +873,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - struct in6_addr *saddr = NULL, *final_p = NULL, final; + struct in6_addr *saddr = NULL, *final_p, final; struct flowi fl; struct dst_entry *dst; int addr_type; @@ -988,13 +976,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl.fl_ip_sport = inet->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; - - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, np->opt, &final); err = ip6_dst_lookup(sk, &dst, &fl); if (err) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e733942dafe1..94b1b9c954bf 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -651,7 +651,7 @@ int inet6_sk_rebuild_header(struct sock *sk) if (dst == NULL) { struct inet_sock *inet = inet_sk(sk); - struct in6_addr *final_p = NULL, final; + struct in6_addr *final_p, final; struct flowi fl; memset(&fl, 0, sizeof(fl)); @@ -665,12 +665,7 @@ int inet6_sk_rebuild_header(struct sock *sk) fl.fl_ip_sport = inet->inet_sport; security_sk_classify_flow(sk, &fl); - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, np->opt, &final); err = ip6_dst_lookup(sk, &dst, &fl); if (err) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 712684687c9a..7d929a22cbc2 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -38,10 +38,11 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_addr *daddr, *final_p = NULL, final; + struct in6_addr *daddr, *final_p, final; struct dst_entry *dst; struct flowi fl; struct ip6_flowlabel *flowlabel = NULL; + struct ipv6_txoptions *opt; int addr_type; int err; @@ -155,19 +156,8 @@ ipv4_connected: security_sk_classify_flow(sk, &fl); - if (flowlabel) { - if (flowlabel->opt && flowlabel->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) flowlabel->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } - } else if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + opt = flowlabel ? flowlabel->opt : np->opt; + final_p = fl6_update_dst(&fl, opt, &final); err = ip6_dst_lookup(sk, &dst, &fl); if (err) diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 8a659f92d17a..853a633a94d4 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -874,3 +874,27 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, return opt; } +/** + * fl6_update_dst - update flowi destination address with info given + * by srcrt option, if any. + * + * @fl: flowi for which fl6_dst is to be updated + * @opt: struct ipv6_txoptions in which to look for srcrt opt + * @orig: copy of original fl6_dst address if modified + * + * Returns NULL if no txoptions or no srcrt, otherwise returns orig + * and initial value of fl->fl6_dst set in orig + */ +struct in6_addr *fl6_update_dst(struct flowi *fl, + const struct ipv6_txoptions *opt, + struct in6_addr *orig) +{ + if (!opt || !opt->srcrt) + return NULL; + + ipv6_addr_copy(orig, &fl->fl6_dst); + ipv6_addr_copy(&fl->fl6_dst, ((struct rt0_hdr *)opt->srcrt)->addr); + return orig; +} + +EXPORT_SYMBOL_GPL(fl6_update_dst); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 0c5e3c3b7fd5..8a1628023bd1 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -185,7 +185,7 @@ int inet6_csk_xmit(struct sk_buff *skb) struct ipv6_pinfo *np = inet6_sk(sk); struct flowi fl; struct dst_entry *dst; - struct in6_addr *final_p = NULL, final; + struct in6_addr *final_p, final; memset(&fl, 0, sizeof(fl)); fl.proto = sk->sk_protocol; @@ -199,12 +199,7 @@ int inet6_csk_xmit(struct sk_buff *skb) fl.fl_ip_dport = inet->inet_dport; security_sk_classify_flow(sk, &fl); - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, np->opt, &final); dst = __inet6_csk_dst_check(sk, np->dst_cookie); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 4a4dcbe4f8b2..864eb8e03b1b 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -725,7 +725,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, { struct ipv6_txoptions opt_space; struct sockaddr_in6 * sin6 = (struct sockaddr_in6 *) msg->msg_name; - struct in6_addr *daddr, *final_p = NULL, final; + struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct raw6_sock *rp = raw6_sk(sk); @@ -847,13 +847,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) ipv6_addr_copy(&fl.fl6_src, &np->saddr); - /* merge ip6_build_xmit from ip6_output */ - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, opt, &final); if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) fl.oif = np->mcast_oif; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 34d1f0690d7e..12383705dbad 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -240,17 +240,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) * me if there is a preferred way. */ { - struct in6_addr *final_p = NULL, final; + struct in6_addr *final_p, final; struct flowi fl; memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_TCP; ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, np->opt, &final); ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); fl.oif = sk->sk_bound_dev_if; fl.mark = sk->sk_mark; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2b7c3a100e2c..e487080d02db 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -129,7 +129,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct inet_connection_sock *icsk = inet_csk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct in6_addr *saddr = NULL, *final_p = NULL, final; + struct in6_addr *saddr = NULL, *final_p, final; struct flowi fl; struct dst_entry *dst; int addr_type; @@ -250,12 +250,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl.fl_ip_dport = usin->sin6_port; fl.fl_ip_sport = inet->inet_sport; - if (np->opt && np->opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, np->opt, &final); security_sk_classify_flow(sk, &fl); @@ -477,7 +472,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff * skb; struct ipv6_txoptions *opt = NULL; - struct in6_addr * final_p = NULL, final; + struct in6_addr * final_p, final; struct flowi fl; struct dst_entry *dst; int err = -1; @@ -494,12 +489,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, security_req_classify_flow(req, &fl); opt = np->opt; - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, opt, &final); err = ip6_dst_lookup(sk, &dst, &fl); if (err) @@ -1392,18 +1382,13 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, goto out_overflow; if (dst == NULL) { - struct in6_addr *final_p = NULL, final; + struct in6_addr *final_p, final; struct flowi fl; memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_TCP; ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl, opt, &final); ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.oif = sk->sk_bound_dev_if; fl.mark = sk->sk_mark; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3048f906c042..4aea57dec75f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -929,7 +929,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name; - struct in6_addr *daddr, *final_p = NULL, final; + struct in6_addr *daddr, *final_p, final; struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct flowi fl; @@ -1099,14 +1099,9 @@ do_udp_sendmsg: ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.fl_ip_sport = inet->inet_sport; - /* merge ip6_build_xmit from ip6_output */ - if (opt && opt->srcrt) { - struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; + final_p = fl6_update_dst(&fl, opt, &final); + if (final_p) connected = 0; - } if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) { fl.oif = np->mcast_oif; -- cgit v1.2.3 From ab95bfe01f9872459c8678572ccadbf646badad0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 1 Jun 2010 21:52:08 +0000 Subject: net: replace hooks in __netif_receive_skb V5 What this patch does is it removes two receive frame hooks (for bridge and for macvlan) from __netif_receive_skb. These are replaced them with a single hook for both. It only supports one hook per device because it makes no sense to do bridging and macvlan on the same device. Then a network driver (of virtual netdev like macvlan or bridge) can register an rx_handler for needed net device. Signed-off-by: Jiri Pirko Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 19 +++++--- include/linux/if_bridge.h | 2 - include/linux/if_macvlan.h | 4 -- include/linux/netdevice.h | 7 +++ net/bridge/br.c | 2 - net/bridge/br_if.c | 8 +++ net/bridge/br_input.c | 12 +++-- net/bridge/br_private.h | 3 +- net/core/dev.c | 119 +++++++++++++++++++++------------------------ 9 files changed, 93 insertions(+), 83 deletions(-) (limited to 'include') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 87e8d4cb4057..53422ce26f7f 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -145,15 +145,16 @@ static void macvlan_broadcast(struct sk_buff *skb, } /* called under rcu_read_lock() from netif_receive_skb */ -static struct sk_buff *macvlan_handle_frame(struct macvlan_port *port, - struct sk_buff *skb) +static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb) { + struct macvlan_port *port; const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; const struct macvlan_dev *src; struct net_device *dev; unsigned int len; + port = rcu_dereference(skb->dev->macvlan_port); if (is_multicast_ether_addr(eth->h_dest)) { src = macvlan_hash_lookup(port, eth->h_source); if (!src) @@ -515,6 +516,7 @@ static int macvlan_port_create(struct net_device *dev) { struct macvlan_port *port; unsigned int i; + int err; if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK) return -EINVAL; @@ -528,13 +530,21 @@ static int macvlan_port_create(struct net_device *dev) for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_hash[i]); rcu_assign_pointer(dev->macvlan_port, port); - return 0; + + err = netdev_rx_handler_register(dev, macvlan_handle_frame); + if (err) { + rcu_assign_pointer(dev->macvlan_port, NULL); + kfree(port); + } + + return err; } static void macvlan_port_destroy(struct net_device *dev) { struct macvlan_port *port = dev->macvlan_port; + netdev_rx_handler_unregister(dev); rcu_assign_pointer(dev->macvlan_port, NULL); synchronize_rcu(); kfree(port); @@ -767,14 +777,12 @@ static int __init macvlan_init_module(void) int err; register_netdevice_notifier(&macvlan_notifier_block); - macvlan_handle_frame_hook = macvlan_handle_frame; err = macvlan_link_register(&macvlan_link_ops); if (err < 0) goto err1; return 0; err1: - macvlan_handle_frame_hook = NULL; unregister_netdevice_notifier(&macvlan_notifier_block); return err; } @@ -782,7 +790,6 @@ err1: static void __exit macvlan_cleanup_module(void) { rtnl_link_unregister(&macvlan_link_ops); - macvlan_handle_frame_hook = NULL; unregister_netdevice_notifier(&macvlan_notifier_block); } diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 938b7e81df95..0d241a5c4909 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -102,8 +102,6 @@ struct __fdb_entry { #include extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); -extern struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, - struct sk_buff *skb); extern int (*br_should_route_hook)(struct sk_buff *skb); #endif diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 9ea047aca795..c26a0e4f0ce8 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -84,8 +84,4 @@ extern int macvlan_link_register(struct rtnl_link_ops *ops); extern netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, struct net_device *dev); - -extern struct sk_buff *(*macvlan_handle_frame_hook)(struct macvlan_port *, - struct sk_buff *); - #endif /* _LINUX_IF_MACVLAN_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bd6b75317d5f..5156b806924c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -381,6 +381,8 @@ enum gro_result { }; typedef enum gro_result gro_result_t; +typedef struct sk_buff *rx_handler_func_t(struct sk_buff *skb); + extern void __napi_schedule(struct napi_struct *n); static inline int napi_disable_pending(struct napi_struct *n) @@ -957,6 +959,7 @@ struct net_device { #endif struct netdev_queue rx_queue; + rx_handler_func_t *rx_handler; struct netdev_queue *_tx ____cacheline_aligned_in_smp; @@ -1689,6 +1692,10 @@ static inline void napi_free_frags(struct napi_struct *napi) napi->skb = NULL; } +extern int netdev_rx_handler_register(struct net_device *dev, + rx_handler_func_t *rx_handler); +extern void netdev_rx_handler_unregister(struct net_device *dev); + extern void netif_nit_deliver(struct sk_buff *skb); extern int dev_valid_name(const char *name); extern int dev_ioctl(struct net *net, unsigned int cmd, void __user *); diff --git a/net/bridge/br.c b/net/bridge/br.c index 76357b547752..c8436fa31344 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -63,7 +63,6 @@ static int __init br_init(void) goto err_out4; brioctl_set(br_ioctl_deviceless_stub); - br_handle_frame_hook = br_handle_frame; #if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) br_fdb_test_addr_hook = br_fdb_test_addr; @@ -100,7 +99,6 @@ static void __exit br_deinit(void) br_fdb_test_addr_hook = NULL; #endif - br_handle_frame_hook = NULL; br_fdb_fini(); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 18b245e2c00e..d9242342837e 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -147,6 +147,7 @@ static void del_nbp(struct net_bridge_port *p) list_del_rcu(&p->list); + netdev_rx_handler_unregister(dev); rcu_assign_pointer(dev->br_port, NULL); br_multicast_del_port(p); @@ -429,6 +430,11 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) goto err2; rcu_assign_pointer(dev->br_port, p); + + err = netdev_rx_handler_register(dev, br_handle_frame); + if (err) + goto err3; + dev_disable_lro(dev); list_add_rcu(&p->list, &br->port_list); @@ -451,6 +457,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) br_netpoll_enable(br, dev); return 0; +err3: + rcu_assign_pointer(dev->br_port, NULL); err2: br_fdb_delete_by_port(br, p, 1); err1: diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index d36e700f7a26..99647d8f95c8 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -131,15 +131,19 @@ static inline int is_link_local(const unsigned char *dest) } /* - * Called via br_handle_frame_hook. * Return NULL if skb is handled - * note: already called with rcu_read_lock (preempt_disabled) + * note: already called with rcu_read_lock (preempt_disabled) from + * netif_receive_skb */ -struct sk_buff *br_handle_frame(struct net_bridge_port *p, struct sk_buff *skb) +struct sk_buff *br_handle_frame(struct sk_buff *skb) { + struct net_bridge_port *p; const unsigned char *dest = eth_hdr(skb)->h_dest; int (*rhook)(struct sk_buff *skb); + if (skb->pkt_type == PACKET_LOOPBACK) + return skb; + if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) goto drop; @@ -147,6 +151,8 @@ struct sk_buff *br_handle_frame(struct net_bridge_port *p, struct sk_buff *skb) if (!skb) return NULL; + p = rcu_dereference(skb->dev->br_port); + if (unlikely(is_link_local(dest))) { /* Pause frames shouldn't be passed up by driver anyway */ if (skb->protocol == htons(ETH_P_PAUSE)) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 0f4a74bc6a9b..c83519b555bb 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -331,8 +331,7 @@ extern void br_features_recompute(struct net_bridge *br); /* br_input.c */ extern int br_handle_frame_finish(struct sk_buff *skb); -extern struct sk_buff *br_handle_frame(struct net_bridge_port *p, - struct sk_buff *skb); +extern struct sk_buff *br_handle_frame(struct sk_buff *skb); /* br_ioctl.c */ extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); diff --git a/net/core/dev.c b/net/core/dev.c index ffca5c1066fa..ec01a5998d70 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2604,70 +2604,14 @@ static inline int deliver_skb(struct sk_buff *skb, return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } -#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE) - -#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \ + (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)) /* This hook is defined here for ATM LANE */ int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) __read_mostly; EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif -/* - * If bridge module is loaded call bridging hook. - * returns NULL if packet was consumed. - */ -struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, - struct sk_buff *skb) __read_mostly; -EXPORT_SYMBOL_GPL(br_handle_frame_hook); - -static inline struct sk_buff *handle_bridge(struct sk_buff *skb, - struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev) -{ - struct net_bridge_port *port; - - if (skb->pkt_type == PACKET_LOOPBACK || - (port = rcu_dereference(skb->dev->br_port)) == NULL) - return skb; - - if (*pt_prev) { - *ret = deliver_skb(skb, *pt_prev, orig_dev); - *pt_prev = NULL; - } - - return br_handle_frame_hook(port, skb); -} -#else -#define handle_bridge(skb, pt_prev, ret, orig_dev) (skb) -#endif - -#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE) -struct sk_buff *(*macvlan_handle_frame_hook)(struct macvlan_port *p, - struct sk_buff *skb) __read_mostly; -EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook); - -static inline struct sk_buff *handle_macvlan(struct sk_buff *skb, - struct packet_type **pt_prev, - int *ret, - struct net_device *orig_dev) -{ - struct macvlan_port *port; - - port = rcu_dereference(skb->dev->macvlan_port); - if (!port) - return skb; - - if (*pt_prev) { - *ret = deliver_skb(skb, *pt_prev, orig_dev); - *pt_prev = NULL; - } - return macvlan_handle_frame_hook(port, skb); -} -#else -#define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb) -#endif - #ifdef CONFIG_NET_CLS_ACT /* TODO: Maybe we should just force sch_ingress to be compiled in * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions @@ -2763,6 +2707,47 @@ void netif_nit_deliver(struct sk_buff *skb) rcu_read_unlock(); } +/** + * netdev_rx_handler_register - register receive handler + * @dev: device to register a handler for + * @rx_handler: receive handler to register + * + * Register a receive hander for a device. This handler will then be + * called from __netif_receive_skb. A negative errno code is returned + * on a failure. + * + * The caller must hold the rtnl_mutex. + */ +int netdev_rx_handler_register(struct net_device *dev, + rx_handler_func_t *rx_handler) +{ + ASSERT_RTNL(); + + if (dev->rx_handler) + return -EBUSY; + + rcu_assign_pointer(dev->rx_handler, rx_handler); + + return 0; +} +EXPORT_SYMBOL_GPL(netdev_rx_handler_register); + +/** + * netdev_rx_handler_unregister - unregister receive handler + * @dev: device to unregister a handler from + * + * Unregister a receive hander from a device. + * + * The caller must hold the rtnl_mutex. + */ +void netdev_rx_handler_unregister(struct net_device *dev) +{ + + ASSERT_RTNL(); + rcu_assign_pointer(dev->rx_handler, NULL); +} +EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); + static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, struct net_device *master) { @@ -2815,6 +2800,7 @@ EXPORT_SYMBOL(__skb_bond_should_drop); static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; + rx_handler_func_t *rx_handler; struct net_device *orig_dev; struct net_device *master; struct net_device *null_or_orig; @@ -2877,12 +2863,17 @@ static int __netif_receive_skb(struct sk_buff *skb) ncls: #endif - skb = handle_bridge(skb, &pt_prev, &ret, orig_dev); - if (!skb) - goto out; - skb = handle_macvlan(skb, &pt_prev, &ret, orig_dev); - if (!skb) - goto out; + /* Handle special case of bridge or macvlan */ + rx_handler = rcu_dereference(skb->dev->rx_handler); + if (rx_handler) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + skb = rx_handler(skb); + if (!skb) + goto out; + } /* * Make sure frames received on VLAN interfaces stacked on -- cgit v1.2.3 From 77c2061d10a408d0220c2b0e7faefe52d9c41008 Mon Sep 17 00:00:00 2001 From: Walter Goldens Date: Tue, 18 May 2010 04:44:54 -0700 Subject: wireless: fix several minor description typos Signed-off-by: Walter Goldens Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ath5k/eeprom.c | 2 +- drivers/net/wireless/ath/ath9k/hw.h | 2 +- drivers/net/wireless/iwmc3200wifi/hal.c | 2 +- drivers/net/wireless/libertas/scan.c | 2 +- drivers/net/wireless/orinoco/hermes_dld.c | 2 +- drivers/net/wireless/rt2x00/rt2x00dev.c | 2 +- drivers/net/wireless/zd1211rw/zd_mac.c | 2 +- drivers/net/wireless/zd1211rw/zd_usb.c | 2 +- include/linux/nl80211.h | 2 +- include/net/cfg80211.h | 2 +- net/mac80211/mlme.c | 2 +- net/mac80211/status.c | 2 +- net/mac80211/work.c | 2 +- 13 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/ath/ath5k/eeprom.c b/drivers/net/wireless/ath/ath5k/eeprom.c index ed0263672d6d..8490348379ae 100644 --- a/drivers/net/wireless/ath/ath5k/eeprom.c +++ b/drivers/net/wireless/ath/ath5k/eeprom.c @@ -715,7 +715,7 @@ ath5k_eeprom_convert_pcal_info_5111(struct ath5k_hw *ah, int mode, /* Only one curve for RF5111 * find out which one and place - * in in pd_curves. + * in pd_curves. * Note: ee_x_gain is reversed here */ for (idx = 0; idx < AR5K_EEPROM_N_PD_CURVES; idx++) { diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index 5cf0714f069c..ffc9249b02c5 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -461,7 +461,7 @@ struct ath9k_hw_version { #define AR_GENTMR_BIT(_index) (1 << (_index)) /* - * Using de Bruijin sequence to to look up 1's index in a 32 bit number + * Using de Bruijin sequence to look up 1's index in a 32 bit number * debruijn32 = 0000 0111 0111 1100 1011 0101 0011 0001 */ #define debruijn32 0x077CB531U diff --git a/drivers/net/wireless/iwmc3200wifi/hal.c b/drivers/net/wireless/iwmc3200wifi/hal.c index 9531b18cf72a..907ac890997c 100644 --- a/drivers/net/wireless/iwmc3200wifi/hal.c +++ b/drivers/net/wireless/iwmc3200wifi/hal.c @@ -54,7 +54,7 @@ * LMAC. If you look at LMAC commands you'll se that they * are actually regular iwlwifi target commands encapsulated * into a special UMAC command called UMAC passthrough. - * This is due to the fact the the host talks exclusively + * This is due to the fact the host talks exclusively * to the UMAC and so there needs to be a special UMAC * command for talking to the LMAC. * This is how a wifi command is layed out: diff --git a/drivers/net/wireless/libertas/scan.c b/drivers/net/wireless/libertas/scan.c index 24cd54b3a806..7d82f13bdf1d 100644 --- a/drivers/net/wireless/libertas/scan.c +++ b/drivers/net/wireless/libertas/scan.c @@ -666,7 +666,7 @@ void lbs_scan_worker(struct work_struct *work) /** * @brief Interpret a BSS scan response returned from the firmware * - * Parse the various fixed fields and IEs passed back for a a BSS probe + * Parse the various fixed fields and IEs passed back for a BSS probe * response or beacon from the scan command. Record information as needed * in the scan table struct bss_descriptor for that entry. * diff --git a/drivers/net/wireless/orinoco/hermes_dld.c b/drivers/net/wireless/orinoco/hermes_dld.c index 6da85e75fce0..f750f49bbd4e 100644 --- a/drivers/net/wireless/orinoco/hermes_dld.c +++ b/drivers/net/wireless/orinoco/hermes_dld.c @@ -68,7 +68,7 @@ struct dblock { } __attribute__ ((packed)); /* - * Plug Data References are located in in the image after the last data + * Plug Data References are located in the image after the last data * block. They refer to areas in the adapter memory where the plug data * items with matching ID should be written. */ diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c index 3ae468c4d760..2ed32e02a06f 100644 --- a/drivers/net/wireless/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/rt2x00/rt2x00dev.c @@ -224,7 +224,7 @@ void rt2x00lib_txdone(struct queue_entry *entry, /* * If the IV/EIV data was stripped from the frame before it was * passed to the hardware, we should now reinsert it again because - * mac80211 will expect the the same data to be present it the + * mac80211 will expect the same data to be present it the * frame as it was passed to us. */ if (test_bit(CONFIG_SUPPORT_HW_CRYPTO, &rt2x00dev->flags)) diff --git a/drivers/net/wireless/zd1211rw/zd_mac.c b/drivers/net/wireless/zd1211rw/zd_mac.c index b0b666019a93..163a8a06b22d 100644 --- a/drivers/net/wireless/zd1211rw/zd_mac.c +++ b/drivers/net/wireless/zd1211rw/zd_mac.c @@ -855,7 +855,7 @@ int zd_mac_rx(struct ieee80211_hw *hw, const u8 *buffer, unsigned int length) if (skb == NULL) return -ENOMEM; if (need_padding) { - /* Make sure the the payload data is 4 byte aligned. */ + /* Make sure the payload data is 4 byte aligned. */ skb_reserve(skb, 2); } diff --git a/drivers/net/wireless/zd1211rw/zd_usb.c b/drivers/net/wireless/zd1211rw/zd_usb.c index c257940b71b6..818e1480ca93 100644 --- a/drivers/net/wireless/zd1211rw/zd_usb.c +++ b/drivers/net/wireless/zd1211rw/zd_usb.c @@ -844,7 +844,7 @@ out: * @usb: a &struct zd_usb pointer * @urb: URB to be freed * - * Frees the the transmission URB, which means to put it on the free URB + * Frees the transmission URB, which means to put it on the free URB * list. */ static void free_tx_urb(struct zd_usb *usb, struct urb *urb) diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index b7c77f9712f4..64fb32b93a28 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -132,7 +132,7 @@ * %NL80211_ATTR_REG_RULE_POWER_MAX_ANT_GAIN and * %NL80211_ATTR_REG_RULE_POWER_MAX_EIRP. * @NL80211_CMD_REQ_SET_REG: ask the wireless core to set the regulatory domain - * to the the specified ISO/IEC 3166-1 alpha2 country code. The core will + * to the specified ISO/IEC 3166-1 alpha2 country code. The core will * store this as a valid request and then query userspace for it. * * @NL80211_CMD_GET_MESH_PARAMS: Get mesh networking properties for the diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b44a2e5321a3..049e507d2f82 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -89,7 +89,7 @@ enum ieee80211_channel_flags { * @max_power: maximum transmission power (in dBm) * @beacon_found: helper to regulatory code to indicate when a beacon * has been found on this channel. Use regulatory_hint_found_beacon() - * to enable this, this is is useful only on 5 GHz band. + * to enable this, this is useful only on 5 GHz band. * @orig_mag: internal use * @orig_mpwr: internal use */ diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0839c4e8fd2e..31e3386b8d43 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1763,7 +1763,7 @@ static void ieee80211_sta_work(struct work_struct *work) /* * ieee80211_queue_work() should have picked up most cases, - * here we'll pick the the rest. + * here we'll pick the rest. */ if (WARN(local->suspended, "STA MLME work scheduled while " "going to suspend\n")) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 94613af009f3..34da67995d94 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -47,7 +47,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, /* * This skb 'survived' a round-trip through the driver, and * hopefully the driver didn't mangle it too badly. However, - * we can definitely not rely on the the control information + * we can definitely not rely on the control information * being correct. Clear it so we don't get junk there, and * indicate that it needs new processing, but must not be * modified/encrypted again. diff --git a/net/mac80211/work.c b/net/mac80211/work.c index be3d4a698692..4157717ed786 100644 --- a/net/mac80211/work.c +++ b/net/mac80211/work.c @@ -840,7 +840,7 @@ static void ieee80211_work_work(struct work_struct *work) /* * ieee80211_queue_work() should have picked up most cases, - * here we'll pick the the rest. + * here we'll pick the rest. */ if (WARN(local->suspended, "work scheduled while going to suspend\n")) return; -- cgit v1.2.3 From 252aa631f88080920a7083ac5a5844ffc5463629 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 19 May 2010 12:17:12 +0200 Subject: cfg80211: make action channel type optional When sending action frames, we want to verify that we do that on the correct channel. However, checking the channel type in addition can get in the way, since the channel type could change on the fly during an association, and it's not useful to have the channel type anyway since it has no effect on the transmission. Therefore, make it optional to specify so that if wanted, it can still be checked, but is not required. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 1 + net/mac80211/cfg.c | 4 +++- net/mac80211/ieee80211_i.h | 1 + net/mac80211/mlme.c | 9 ++++++--- net/wireless/core.h | 1 + net/wireless/mlme.c | 3 ++- net/wireless/nl80211.c | 3 +++ 7 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 049e507d2f82..0c3c214772e7 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1168,6 +1168,7 @@ struct cfg80211_ops { int (*action)(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, + bool channel_type_valid, const u8 *buf, size_t len, u64 *cookie); int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c7000a6ca379..f8c49c5ad8aa 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1554,10 +1554,12 @@ static int ieee80211_cancel_remain_on_channel(struct wiphy *wiphy, static int ieee80211_action(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, + bool channel_type_valid, const u8 *buf, size_t len, u64 *cookie) { return ieee80211_mgd_action(IEEE80211_DEV_TO_SUB_IF(dev), chan, - channel_type, buf, len, cookie); + channel_type, channel_type_valid, + buf, len, cookie); } struct cfg80211_ops mac80211_config_ops = { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 1a9e2da37a93..d4677efd3a36 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -988,6 +988,7 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, int ieee80211_mgd_action(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, + bool channel_type_valid, const u8 *buf, size_t len, u64 *cookie); ieee80211_rx_result ieee80211_sta_rx_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 31e3386b8d43..29c3a75a7ad0 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2308,6 +2308,7 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, int ieee80211_mgd_action(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, + bool channel_type_valid, const u8 *buf, size_t len, u64 *cookie) { struct ieee80211_local *local = sdata->local; @@ -2315,9 +2316,11 @@ int ieee80211_mgd_action(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb; /* Check that we are on the requested channel for transmission */ - if ((chan != local->tmp_channel || - channel_type != local->tmp_channel_type) && - (chan != local->oper_channel || + if (chan != local->tmp_channel && + chan != local->oper_channel) + return -EBUSY; + if (channel_type_valid && + (channel_type != local->tmp_channel_type && channel_type != local->_oper_channel_type)) return -EBUSY; diff --git a/net/wireless/core.h b/net/wireless/core.h index ae930acf75e9..63d57ae399c3 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -339,6 +339,7 @@ int cfg80211_mlme_action(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, + bool channel_type_valid, const u8 *buf, size_t len, u64 *cookie); /* SME */ diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 48ead6f0426d..f69ae19f497f 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -827,6 +827,7 @@ int cfg80211_mlme_action(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type, + bool channel_type_valid, const u8 *buf, size_t len, u64 *cookie) { struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -855,7 +856,7 @@ int cfg80211_mlme_action(struct cfg80211_registered_device *rdev, /* Transmit the Action frame as requested by user space */ return rdev->ops->action(&rdev->wiphy, dev, chan, channel_type, - buf, len, cookie); + channel_type_valid, buf, len, cookie); } bool cfg80211_rx_action(struct net_device *dev, int freq, const u8 *buf, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index db71150b8040..90ab3c8519be 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4681,6 +4681,7 @@ static int nl80211_action(struct sk_buff *skb, struct genl_info *info) struct net_device *dev; struct ieee80211_channel *chan; enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; + bool channel_type_valid = false; u32 freq; int err; void *hdr; @@ -4722,6 +4723,7 @@ static int nl80211_action(struct sk_buff *skb, struct genl_info *info) err = -EINVAL; goto out; } + channel_type_valid = true; } freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); @@ -4745,6 +4747,7 @@ static int nl80211_action(struct sk_buff *skb, struct genl_info *info) goto free_msg; } err = cfg80211_mlme_action(rdev, dev, chan, channel_type, + channel_type_valid, nla_data(info->attrs[NL80211_ATTR_FRAME]), nla_len(info->attrs[NL80211_ATTR_FRAME]), &cookie); -- cgit v1.2.3 From b5f7e7554753e2cc3ef3bef0271fdb32027df2ba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Jun 2010 12:05:27 +0000 Subject: ipv4: add LINUX_MIB_IPRPFILTER snmp counter Christoph Lameter mentioned that packets could be dropped in input path because of rp_filter settings, without any SNMP counter being incremented. System administrator can have a hard time to track the problem. This patch introduces a new counter, LINUX_MIB_IPRPFILTER, incremented each time we drop a packet because Reverse Path Filter triggers. (We receive an IPv4 datagram on a given interface, and find the route to send an answer would use another interface) netstat -s | grep IPReversePathFilter IPReversePathFilter: 21714 Reported-by: Christoph Lameter Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/snmp.h | 1 + net/ipv4/fib_frontend.c | 6 ++++-- net/ipv4/ip_input.c | 3 +++ net/ipv4/proc.c | 1 + net/ipv4/route.c | 31 ++++++++++++++++++------------- 5 files changed, 27 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 52797714ade7..ebb0c80ffd6e 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -229,6 +229,7 @@ enum LINUX_MIB_TCPBACKLOGDROP, LINUX_MIB_TCPMINTTLDROP, /* RFC 5082 */ LINUX_MIB_TCPDEFERACCEPTDROP, + LINUX_MIB_IPRPFILTER, /* IP Reverse Path Filter (rp_filter) */ __LINUX_MIB_MAX }; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 4f0ed458c883..e830f7a123bd 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -284,7 +284,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, if (no_addr) goto last_resort; if (rpf == 1) - goto e_inval; + goto e_rpf; fl.oif = dev->ifindex; ret = 0; @@ -299,7 +299,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, last_resort: if (rpf) - goto e_inval; + goto e_rpf; *spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); *itag = 0; return 0; @@ -308,6 +308,8 @@ e_inval_res: fib_res_put(&res); e_inval: return -EINVAL; +e_rpf: + return -EXDEV; } static inline __be32 sk_extract_addr(struct sockaddr *addr) diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index d930dc5e4d85..d52c9da644cf 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -340,6 +340,9 @@ static int ip_rcv_finish(struct sk_buff *skb) else if (err == -ENETUNREACH) IP_INC_STATS_BH(dev_net(skb->dev), IPSTATS_MIB_INNOROUTES); + else if (err == -EXDEV) + NET_INC_STATS_BH(dev_net(skb->dev), + LINUX_MIB_IPRPFILTER); goto drop; } } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 3dc9914c1dce..e320ca6b3ef3 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -252,6 +252,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPBacklogDrop", LINUX_MIB_TCPBACKLOGDROP), SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP), SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP), + SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8495bceec764..d377b45005fc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1851,6 +1851,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, __be32 spec_dst; struct in_device *in_dev = in_dev_get(dev); u32 itag = 0; + int err; /* Primary sanity checks. */ @@ -1865,10 +1866,12 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (!ipv4_is_local_multicast(daddr)) goto e_inval; spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK); - } else if (fib_validate_source(saddr, 0, tos, 0, - dev, &spec_dst, &itag, 0) < 0) - goto e_inval; - + } else { + err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst, + &itag, 0); + if (err < 0) + goto e_err; + } rth = dst_alloc(&ipv4_dst_ops); if (!rth) goto e_nobufs; @@ -1920,8 +1923,10 @@ e_nobufs: return -ENOBUFS; e_inval: + err = -EINVAL; +e_err: in_dev_put(in_dev); - return -EINVAL; + return err; } @@ -1985,7 +1990,6 @@ static int __mkroute_input(struct sk_buff *skb, ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); - err = -EINVAL; goto cleanup; } @@ -2157,13 +2161,12 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto brd_input; if (res.type == RTN_LOCAL) { - int result; - result = fib_validate_source(saddr, daddr, tos, + err = fib_validate_source(saddr, daddr, tos, net->loopback_dev->ifindex, dev, &spec_dst, &itag, skb->mark); - if (result < 0) - goto martian_source; - if (result) + if (err < 0) + goto martian_source_keep_err; + if (err) flags |= RTCF_DIRECTSRC; spec_dst = daddr; goto local_input; @@ -2191,7 +2194,7 @@ brd_input: err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst, &itag, skb->mark); if (err < 0) - goto martian_source; + goto martian_source_keep_err; if (err) flags |= RTCF_DIRECTSRC; } @@ -2272,8 +2275,10 @@ e_nobufs: goto done; martian_source: + err = -EINVAL; +martian_source_keep_err: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); - goto e_inval; + goto done; } int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, -- cgit v1.2.3 From bc10502dba37d3b210efd9f3867212298f13b78e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Jun 2010 03:21:52 -0700 Subject: net: use __packed annotation cleanup patch. Use new __packed annotation in net/ and include/ (except netfilter) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/if_ether.h | 2 +- include/linux/if_fddi.h | 8 ++--- include/linux/if_frad.h | 2 +- include/linux/if_hippi.h | 8 ++--- include/linux/if_pppox.h | 8 ++--- include/linux/ipv6.h | 4 +-- include/linux/isdnif.h | 2 +- include/linux/mISDNif.h | 2 +- include/linux/nbd.h | 2 +- include/linux/ncp.h | 10 +++--- include/linux/ncp_fs_sb.h | 14 ++++---- include/linux/phonet.h | 4 +-- include/linux/rds.h | 12 +++---- include/linux/sctp.h | 80 +++++++++++++++++++++++----------------------- include/linux/wlp.h | 22 ++++++------- include/net/dn_dev.h | 8 ++--- include/net/dn_nsp.h | 16 +++++----- include/net/ip6_tunnel.h | 2 +- include/net/ipx.h | 8 ++--- include/net/mip6.h | 2 +- include/net/ndisc.h | 2 +- include/net/sctp/structs.h | 4 +-- include/rxrpc/packet.h | 8 ++--- net/bluetooth/bnep/bnep.h | 8 ++--- net/compat.c | 6 ++-- net/iucv/iucv.c | 14 ++++---- net/mac80211/cfg.c | 2 +- net/mac80211/ieee80211_i.h | 2 +- net/mac80211/rx.c | 2 +- net/sctp/sm_make_chunk.c | 2 +- 30 files changed, 133 insertions(+), 133 deletions(-) (limited to 'include') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index bed7a4682b90..c831467774d0 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -119,7 +119,7 @@ struct ethhdr { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ unsigned char h_source[ETH_ALEN]; /* source ether addr */ __be16 h_proto; /* packet type ID field */ -} __attribute__((packed)); +} __packed; #ifdef __KERNEL__ #include diff --git a/include/linux/if_fddi.h b/include/linux/if_fddi.h index 5459c5c09930..9947c39e62f6 100644 --- a/include/linux/if_fddi.h +++ b/include/linux/if_fddi.h @@ -67,7 +67,7 @@ struct fddi_8022_1_hdr { __u8 dsap; /* destination service access point */ __u8 ssap; /* source service access point */ __u8 ctrl; /* control byte #1 */ -} __attribute__ ((packed)); +} __packed; /* Define 802.2 Type 2 header */ struct fddi_8022_2_hdr { @@ -75,7 +75,7 @@ struct fddi_8022_2_hdr { __u8 ssap; /* source service access point */ __u8 ctrl_1; /* control byte #1 */ __u8 ctrl_2; /* control byte #2 */ -} __attribute__ ((packed)); +} __packed; /* Define 802.2 SNAP header */ #define FDDI_K_OUI_LEN 3 @@ -85,7 +85,7 @@ struct fddi_snap_hdr { __u8 ctrl; /* always 0x03 */ __u8 oui[FDDI_K_OUI_LEN]; /* organizational universal id */ __be16 ethertype; /* packet type ID field */ -} __attribute__ ((packed)); +} __packed; /* Define FDDI LLC frame header */ struct fddihdr { @@ -98,7 +98,7 @@ struct fddihdr { struct fddi_8022_2_hdr llc_8022_2; struct fddi_snap_hdr llc_snap; } hdr; -} __attribute__ ((packed)); +} __packed; #ifdef __KERNEL__ #include diff --git a/include/linux/if_frad.h b/include/linux/if_frad.h index 80b3a1056a5f..191ee0869bc1 100644 --- a/include/linux/if_frad.h +++ b/include/linux/if_frad.h @@ -135,7 +135,7 @@ struct frhdr __be16 PID; #define IP_NLPID pad -} __attribute__((packed)); +} __packed; /* see RFC 1490 for the definition of the following */ #define FRAD_I_UI 0x03 diff --git a/include/linux/if_hippi.h b/include/linux/if_hippi.h index 8d038eb8db5c..5fe5f307c6f5 100644 --- a/include/linux/if_hippi.h +++ b/include/linux/if_hippi.h @@ -104,7 +104,7 @@ struct hippi_fp_hdr { __be32 fixed; #endif __be32 d2_size; -} __attribute__ ((packed)); +} __packed; struct hippi_le_hdr { #if defined (__BIG_ENDIAN_BITFIELD) @@ -129,7 +129,7 @@ struct hippi_le_hdr { __u8 daddr[HIPPI_ALEN]; __u16 locally_administered; __u8 saddr[HIPPI_ALEN]; -} __attribute__ ((packed)); +} __packed; #define HIPPI_OUI_LEN 3 /* @@ -142,12 +142,12 @@ struct hippi_snap_hdr { __u8 ctrl; /* always 0x03 */ __u8 oui[HIPPI_OUI_LEN]; /* organizational universal id (zero)*/ __be16 ethertype; /* packet type ID field */ -} __attribute__ ((packed)); +} __packed; struct hippi_hdr { struct hippi_fp_hdr fp; struct hippi_le_hdr le; struct hippi_snap_hdr snap; -} __attribute__ ((packed)); +} __packed; #endif /* _LINUX_IF_HIPPI_H */ diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index a6577af0c4e6..1925e0c3f162 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -59,7 +59,7 @@ struct sockaddr_pppox { union{ struct pppoe_addr pppoe; }sa_addr; -}__attribute__ ((packed)); +} __packed; /* The use of the above union isn't viable because the size of this * struct must stay fixed over time -- applications use sizeof(struct @@ -70,7 +70,7 @@ struct sockaddr_pppol2tp { sa_family_t sa_family; /* address family, AF_PPPOX */ unsigned int sa_protocol; /* protocol identifier */ struct pppol2tp_addr pppol2tp; -}__attribute__ ((packed)); +} __packed; /* The L2TPv3 protocol changes tunnel and session ids from 16 to 32 * bits. So we need a different sockaddr structure. @@ -79,7 +79,7 @@ struct sockaddr_pppol2tpv3 { sa_family_t sa_family; /* address family, AF_PPPOX */ unsigned int sa_protocol; /* protocol identifier */ struct pppol2tpv3_addr pppol2tp; -} __attribute__ ((packed)); +} __packed; /********************************************************************* * @@ -129,7 +129,7 @@ struct pppoe_hdr { __be16 sid; __be16 length; struct pppoe_tag tag[0]; -} __attribute__ ((packed)); +} __packed; /* Length of entire PPPoE + PPP header */ #define PPPOE_SES_HLEN 8 diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 99e1ab7e3eec..940e21595351 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -58,7 +58,7 @@ struct ipv6_opt_hdr { /* * TLV encoded option data follows. */ -} __attribute__ ((packed)); /* required for some archs */ +} __packed; /* required for some archs */ #define ipv6_destopt_hdr ipv6_opt_hdr #define ipv6_hopopt_hdr ipv6_opt_hdr @@ -99,7 +99,7 @@ struct ipv6_destopt_hao { __u8 type; __u8 length; struct in6_addr addr; -} __attribute__ ((__packed__)); +} __packed; /* * IPv6 fixed header diff --git a/include/linux/isdnif.h b/include/linux/isdnif.h index b9b5a684ed69..b8c23f88dd54 100644 --- a/include/linux/isdnif.h +++ b/include/linux/isdnif.h @@ -317,7 +317,7 @@ typedef struct T30_s { __u8 r_scantime; __u8 r_id[FAXIDLEN]; __u8 r_code; -} __attribute__((packed)) T30_s; +} __packed T30_s; #define ISDN_TTY_FAX_CONN_IN 0 #define ISDN_TTY_FAX_CONN_OUT 1 diff --git a/include/linux/mISDNif.h b/include/linux/mISDNif.h index 78c3bed1c3f5..b5e7f2202484 100644 --- a/include/linux/mISDNif.h +++ b/include/linux/mISDNif.h @@ -251,7 +251,7 @@ struct mISDNhead { unsigned int prim; unsigned int id; -} __attribute__((packed)); +} __packed; #define MISDN_HEADER_LEN sizeof(struct mISDNhead) #define MAX_DATA_SIZE 2048 diff --git a/include/linux/nbd.h b/include/linux/nbd.h index 155719dab813..bb58854a8061 100644 --- a/include/linux/nbd.h +++ b/include/linux/nbd.h @@ -88,7 +88,7 @@ struct nbd_request { char handle[8]; __be64 from; __be32 len; -} __attribute__ ((packed)); +} __packed; /* * This is the reply packet that nbd-server sends back to the client after diff --git a/include/linux/ncp.h b/include/linux/ncp.h index 99f0adeeb3f3..3ace8370e61e 100644 --- a/include/linux/ncp.h +++ b/include/linux/ncp.h @@ -27,7 +27,7 @@ struct ncp_request_header { __u8 conn_high; __u8 function; __u8 data[0]; -} __attribute__((packed)); +} __packed; #define NCP_REPLY (0x3333) #define NCP_WATCHDOG (0x3E3E) @@ -42,7 +42,7 @@ struct ncp_reply_header { __u8 completion_code; __u8 connection_state; __u8 data[0]; -} __attribute__((packed)); +} __packed; #define NCP_VOLNAME_LEN (16) #define NCP_NUMBER_OF_VOLUMES (256) @@ -158,7 +158,7 @@ struct nw_info_struct { #ifdef __KERNEL__ struct nw_nfs_info nfs; #endif -} __attribute__((packed)); +} __packed; /* modify mask - use with MODIFY_DOS_INFO structure */ #define DM_ATTRIBUTES (cpu_to_le32(0x02)) @@ -190,12 +190,12 @@ struct nw_modify_dos_info { __u16 inheritanceGrantMask; __u16 inheritanceRevokeMask; __u32 maximumSpace; -} __attribute__((packed)); +} __packed; struct nw_search_sequence { __u8 volNumber; __u32 dirBase; __u32 sequence; -} __attribute__((packed)); +} __packed; #endif /* _LINUX_NCP_H */ diff --git a/include/linux/ncp_fs_sb.h b/include/linux/ncp_fs_sb.h index 5ec9ca671687..8da05bc098ca 100644 --- a/include/linux/ncp_fs_sb.h +++ b/include/linux/ncp_fs_sb.h @@ -104,13 +104,13 @@ struct ncp_server { unsigned int state; /* STREAM only: receiver state */ struct { - __u32 magic __attribute__((packed)); - __u32 len __attribute__((packed)); - __u16 type __attribute__((packed)); - __u16 p1 __attribute__((packed)); - __u16 p2 __attribute__((packed)); - __u16 p3 __attribute__((packed)); - __u16 type2 __attribute__((packed)); + __u32 magic __packed; + __u32 len __packed; + __u16 type __packed; + __u16 p1 __packed; + __u16 p2 __packed; + __u16 p3 __packed; + __u16 type2 __packed; } buf; /* STREAM only: temporary buffer */ unsigned char* ptr; /* STREAM only: pointer to data */ size_t len; /* STREAM only: length of data to receive */ diff --git a/include/linux/phonet.h b/include/linux/phonet.h index e5126cff9b2a..24426c3d6b5a 100644 --- a/include/linux/phonet.h +++ b/include/linux/phonet.h @@ -56,7 +56,7 @@ struct phonethdr { __be16 pn_length; __u8 pn_robj; __u8 pn_sobj; -} __attribute__((packed)); +} __packed; /* Common Phonet payload header */ struct phonetmsg { @@ -98,7 +98,7 @@ struct sockaddr_pn { __u8 spn_dev; __u8 spn_resource; __u8 spn_zero[sizeof(struct sockaddr) - sizeof(sa_family_t) - 3]; -} __attribute__ ((packed)); +} __packed; /* Well known address */ #define PN_DEV_PC 0x10 diff --git a/include/linux/rds.h b/include/linux/rds.h index cab4994c2f63..24bce3ded9ea 100644 --- a/include/linux/rds.h +++ b/include/linux/rds.h @@ -100,7 +100,7 @@ struct rds_info_counter { u_int8_t name[32]; u_int64_t value; -} __attribute__((packed)); +} __packed; #define RDS_INFO_CONNECTION_FLAG_SENDING 0x01 #define RDS_INFO_CONNECTION_FLAG_CONNECTING 0x02 @@ -115,7 +115,7 @@ struct rds_info_connection { __be32 faddr; u_int8_t transport[TRANSNAMSIZ]; /* null term ascii */ u_int8_t flags; -} __attribute__((packed)); +} __packed; struct rds_info_flow { __be32 laddr; @@ -123,7 +123,7 @@ struct rds_info_flow { u_int32_t bytes; __be16 lport; __be16 fport; -} __attribute__((packed)); +} __packed; #define RDS_INFO_MESSAGE_FLAG_ACK 0x01 #define RDS_INFO_MESSAGE_FLAG_FAST_ACK 0x02 @@ -136,7 +136,7 @@ struct rds_info_message { __be16 lport; __be16 fport; u_int8_t flags; -} __attribute__((packed)); +} __packed; struct rds_info_socket { u_int32_t sndbuf; @@ -146,7 +146,7 @@ struct rds_info_socket { __be16 connected_port; u_int32_t rcvbuf; u_int64_t inum; -} __attribute__((packed)); +} __packed; struct rds_info_tcp_socket { __be32 local_addr; @@ -158,7 +158,7 @@ struct rds_info_tcp_socket { u_int32_t last_sent_nxt; u_int32_t last_expected_una; u_int32_t last_seen_una; -} __attribute__((packed)); +} __packed; #define RDS_IB_GID_LEN 16 struct rds_info_rdma_connection { diff --git a/include/linux/sctp.h b/include/linux/sctp.h index c20d3ce673c0..c11a28706fa4 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -61,7 +61,7 @@ typedef struct sctphdr { __be16 dest; __be32 vtag; __le32 checksum; -} __attribute__((packed)) sctp_sctphdr_t; +} __packed sctp_sctphdr_t; #ifdef __KERNEL__ #include @@ -77,7 +77,7 @@ typedef struct sctp_chunkhdr { __u8 type; __u8 flags; __be16 length; -} __attribute__((packed)) sctp_chunkhdr_t; +} __packed sctp_chunkhdr_t; /* Section 3.2. Chunk Type Values. @@ -167,7 +167,7 @@ enum { SCTP_CHUNK_FLAG_T = 0x01 }; typedef struct sctp_paramhdr { __be16 type; __be16 length; -} __attribute__((packed)) sctp_paramhdr_t; +} __packed sctp_paramhdr_t; typedef enum { @@ -228,12 +228,12 @@ typedef struct sctp_datahdr { __be16 ssn; __be32 ppid; __u8 payload[0]; -} __attribute__((packed)) sctp_datahdr_t; +} __packed sctp_datahdr_t; typedef struct sctp_data_chunk { sctp_chunkhdr_t chunk_hdr; sctp_datahdr_t data_hdr; -} __attribute__((packed)) sctp_data_chunk_t; +} __packed sctp_data_chunk_t; /* DATA Chuck Specific Flags */ enum { @@ -259,78 +259,78 @@ typedef struct sctp_inithdr { __be16 num_inbound_streams; __be32 initial_tsn; __u8 params[0]; -} __attribute__((packed)) sctp_inithdr_t; +} __packed sctp_inithdr_t; typedef struct sctp_init_chunk { sctp_chunkhdr_t chunk_hdr; sctp_inithdr_t init_hdr; -} __attribute__((packed)) sctp_init_chunk_t; +} __packed sctp_init_chunk_t; /* Section 3.3.2.1. IPv4 Address Parameter (5) */ typedef struct sctp_ipv4addr_param { sctp_paramhdr_t param_hdr; struct in_addr addr; -} __attribute__((packed)) sctp_ipv4addr_param_t; +} __packed sctp_ipv4addr_param_t; /* Section 3.3.2.1. IPv6 Address Parameter (6) */ typedef struct sctp_ipv6addr_param { sctp_paramhdr_t param_hdr; struct in6_addr addr; -} __attribute__((packed)) sctp_ipv6addr_param_t; +} __packed sctp_ipv6addr_param_t; /* Section 3.3.2.1 Cookie Preservative (9) */ typedef struct sctp_cookie_preserve_param { sctp_paramhdr_t param_hdr; __be32 lifespan_increment; -} __attribute__((packed)) sctp_cookie_preserve_param_t; +} __packed sctp_cookie_preserve_param_t; /* Section 3.3.2.1 Host Name Address (11) */ typedef struct sctp_hostname_param { sctp_paramhdr_t param_hdr; uint8_t hostname[0]; -} __attribute__((packed)) sctp_hostname_param_t; +} __packed sctp_hostname_param_t; /* Section 3.3.2.1 Supported Address Types (12) */ typedef struct sctp_supported_addrs_param { sctp_paramhdr_t param_hdr; __be16 types[0]; -} __attribute__((packed)) sctp_supported_addrs_param_t; +} __packed sctp_supported_addrs_param_t; /* Appendix A. ECN Capable (32768) */ typedef struct sctp_ecn_capable_param { sctp_paramhdr_t param_hdr; -} __attribute__((packed)) sctp_ecn_capable_param_t; +} __packed sctp_ecn_capable_param_t; /* ADDIP Section 3.2.6 Adaptation Layer Indication */ typedef struct sctp_adaptation_ind_param { struct sctp_paramhdr param_hdr; __be32 adaptation_ind; -} __attribute__((packed)) sctp_adaptation_ind_param_t; +} __packed sctp_adaptation_ind_param_t; /* ADDIP Section 4.2.7 Supported Extensions Parameter */ typedef struct sctp_supported_ext_param { struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} __attribute__((packed)) sctp_supported_ext_param_t; +} __packed sctp_supported_ext_param_t; /* AUTH Section 3.1 Random */ typedef struct sctp_random_param { sctp_paramhdr_t param_hdr; __u8 random_val[0]; -} __attribute__((packed)) sctp_random_param_t; +} __packed sctp_random_param_t; /* AUTH Section 3.2 Chunk List */ typedef struct sctp_chunks_param { sctp_paramhdr_t param_hdr; __u8 chunks[0]; -} __attribute__((packed)) sctp_chunks_param_t; +} __packed sctp_chunks_param_t; /* AUTH Section 3.3 HMAC Algorithm */ typedef struct sctp_hmac_algo_param { sctp_paramhdr_t param_hdr; __be16 hmac_ids[0]; -} __attribute__((packed)) sctp_hmac_algo_param_t; +} __packed sctp_hmac_algo_param_t; /* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2): * The INIT ACK chunk is used to acknowledge the initiation of an SCTP @@ -342,13 +342,13 @@ typedef sctp_init_chunk_t sctp_initack_chunk_t; typedef struct sctp_cookie_param { sctp_paramhdr_t p; __u8 body[0]; -} __attribute__((packed)) sctp_cookie_param_t; +} __packed sctp_cookie_param_t; /* Section 3.3.3.1 Unrecognized Parameters (8) */ typedef struct sctp_unrecognized_param { sctp_paramhdr_t param_hdr; sctp_paramhdr_t unrecognized; -} __attribute__((packed)) sctp_unrecognized_param_t; +} __packed sctp_unrecognized_param_t; @@ -363,7 +363,7 @@ typedef struct sctp_unrecognized_param { typedef struct sctp_gap_ack_block { __be16 start; __be16 end; -} __attribute__((packed)) sctp_gap_ack_block_t; +} __packed sctp_gap_ack_block_t; typedef __be32 sctp_dup_tsn_t; @@ -378,12 +378,12 @@ typedef struct sctp_sackhdr { __be16 num_gap_ack_blocks; __be16 num_dup_tsns; sctp_sack_variable_t variable[0]; -} __attribute__((packed)) sctp_sackhdr_t; +} __packed sctp_sackhdr_t; typedef struct sctp_sack_chunk { sctp_chunkhdr_t chunk_hdr; sctp_sackhdr_t sack_hdr; -} __attribute__((packed)) sctp_sack_chunk_t; +} __packed sctp_sack_chunk_t; /* RFC 2960. Section 3.3.5 Heartbeat Request (HEARTBEAT) (4): @@ -395,12 +395,12 @@ typedef struct sctp_sack_chunk { typedef struct sctp_heartbeathdr { sctp_paramhdr_t info; -} __attribute__((packed)) sctp_heartbeathdr_t; +} __packed sctp_heartbeathdr_t; typedef struct sctp_heartbeat_chunk { sctp_chunkhdr_t chunk_hdr; sctp_heartbeathdr_t hb_hdr; -} __attribute__((packed)) sctp_heartbeat_chunk_t; +} __packed sctp_heartbeat_chunk_t; /* For the abort and shutdown ACK we must carry the init tag in the @@ -409,7 +409,7 @@ typedef struct sctp_heartbeat_chunk { */ typedef struct sctp_abort_chunk { sctp_chunkhdr_t uh; -} __attribute__((packed)) sctp_abort_chunk_t; +} __packed sctp_abort_chunk_t; /* For the graceful shutdown we must carry the tag (in common header) @@ -417,12 +417,12 @@ typedef struct sctp_abort_chunk { */ typedef struct sctp_shutdownhdr { __be32 cum_tsn_ack; -} __attribute__((packed)) sctp_shutdownhdr_t; +} __packed sctp_shutdownhdr_t; struct sctp_shutdown_chunk_t { sctp_chunkhdr_t chunk_hdr; sctp_shutdownhdr_t shutdown_hdr; -} __attribute__ ((packed)); +} __packed; /* RFC 2960. Section 3.3.10 Operation Error (ERROR) (9) */ @@ -430,12 +430,12 @@ typedef struct sctp_errhdr { __be16 cause; __be16 length; __u8 variable[0]; -} __attribute__((packed)) sctp_errhdr_t; +} __packed sctp_errhdr_t; typedef struct sctp_operr_chunk { sctp_chunkhdr_t chunk_hdr; sctp_errhdr_t err_hdr; -} __attribute__((packed)) sctp_operr_chunk_t; +} __packed sctp_operr_chunk_t; /* RFC 2960 3.3.10 - Operation Error * @@ -525,7 +525,7 @@ typedef struct sctp_ecnehdr { typedef struct sctp_ecne_chunk { sctp_chunkhdr_t chunk_hdr; sctp_ecnehdr_t ence_hdr; -} __attribute__((packed)) sctp_ecne_chunk_t; +} __packed sctp_ecne_chunk_t; /* RFC 2960. Appendix A. Explicit Congestion Notification. * Congestion Window Reduced (CWR) (13) @@ -537,7 +537,7 @@ typedef struct sctp_cwrhdr { typedef struct sctp_cwr_chunk { sctp_chunkhdr_t chunk_hdr; sctp_cwrhdr_t cwr_hdr; -} __attribute__((packed)) sctp_cwr_chunk_t; +} __packed sctp_cwr_chunk_t; /* PR-SCTP * 3.2 Forward Cumulative TSN Chunk Definition (FORWARD TSN) @@ -588,17 +588,17 @@ typedef struct sctp_cwr_chunk { struct sctp_fwdtsn_skip { __be16 stream; __be16 ssn; -} __attribute__((packed)); +} __packed; struct sctp_fwdtsn_hdr { __be32 new_cum_tsn; struct sctp_fwdtsn_skip skip[0]; -} __attribute((packed)); +} __packed; struct sctp_fwdtsn_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_fwdtsn_hdr fwdtsn_hdr; -} __attribute((packed)); +} __packed; /* ADDIP @@ -636,17 +636,17 @@ struct sctp_fwdtsn_chunk { typedef struct sctp_addip_param { sctp_paramhdr_t param_hdr; __be32 crr_id; -} __attribute__((packed)) sctp_addip_param_t; +} __packed sctp_addip_param_t; typedef struct sctp_addiphdr { __be32 serial; __u8 params[0]; -} __attribute__((packed)) sctp_addiphdr_t; +} __packed sctp_addiphdr_t; typedef struct sctp_addip_chunk { sctp_chunkhdr_t chunk_hdr; sctp_addiphdr_t addip_hdr; -} __attribute__((packed)) sctp_addip_chunk_t; +} __packed sctp_addip_chunk_t; /* AUTH * Section 4.1 Authentication Chunk (AUTH) @@ -701,11 +701,11 @@ typedef struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; __u8 hmac[0]; -} __attribute__((packed)) sctp_authhdr_t; +} __packed sctp_authhdr_t; typedef struct sctp_auth_chunk { sctp_chunkhdr_t chunk_hdr; sctp_authhdr_t auth_hdr; -} __attribute__((packed)) sctp_auth_chunk_t; +} __packed sctp_auth_chunk_t; #endif /* __LINUX_SCTP_H__ */ diff --git a/include/linux/wlp.h b/include/linux/wlp.h index ac95ce6606ac..c76fe2392506 100644 --- a/include/linux/wlp.h +++ b/include/linux/wlp.h @@ -300,7 +300,7 @@ struct wlp_ie { __le16 cycle_param; __le16 acw_anchor_addr; u8 wssid_hash_list[]; -} __attribute__((packed)); +} __packed; static inline int wlp_ie_hash_length(struct wlp_ie *ie) { @@ -324,7 +324,7 @@ static inline void wlp_ie_set_hash_length(struct wlp_ie *ie, int hash_length) */ struct wlp_nonce { u8 data[16]; -} __attribute__((packed)); +} __packed; /** * WLP UUID @@ -336,7 +336,7 @@ struct wlp_nonce { */ struct wlp_uuid { u8 data[16]; -} __attribute__((packed)); +} __packed; /** @@ -348,7 +348,7 @@ struct wlp_dev_type { u8 OUI[3]; u8 OUIsubdiv; __le16 subID; -} __attribute__((packed)); +} __packed; /** * WLP frame header @@ -357,7 +357,7 @@ struct wlp_dev_type { struct wlp_frame_hdr { __le16 mux_hdr; /* WLP_PROTOCOL_ID */ enum wlp_frame_type type:8; -} __attribute__((packed)); +} __packed; /** * WLP attribute field header @@ -368,7 +368,7 @@ struct wlp_frame_hdr { struct wlp_attr_hdr { __le16 type; __le16 length; -} __attribute__((packed)); +} __packed; /** * Device information commonly used together @@ -401,13 +401,13 @@ struct wlp_device_info { struct wlp_attr_##name { \ struct wlp_attr_hdr hdr; \ type name; \ -} __attribute__((packed)); +} __packed; #define wlp_attr_array(type, name) \ struct wlp_attr_##name { \ struct wlp_attr_hdr hdr; \ type name[]; \ -} __attribute__((packed)); +} __packed; /** * WLP association attribute fields @@ -483,7 +483,7 @@ struct wlp_wss_info { struct wlp_attr_accept_enrl accept; struct wlp_attr_wss_sec_status sec_stat; struct wlp_attr_wss_bcast bcast; -} __attribute__((packed)); +} __packed; /* WLP WSS Information */ wlp_attr_array(struct wlp_wss_info, wss_info) @@ -520,7 +520,7 @@ wlp_attr(u8, wlp_assc_err) struct wlp_frame_std_abbrv_hdr { struct wlp_frame_hdr hdr; u8 tag; -} __attribute__((packed)); +} __packed; /** * WLP association frames @@ -533,7 +533,7 @@ struct wlp_frame_assoc { struct wlp_attr_version version; struct wlp_attr_msg_type msg_type; u8 attr[]; -} __attribute__((packed)); +} __packed; /* Ethernet to dev address mapping */ struct wlp_eda { diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h index 511a459ec10f..0916bbf3bdff 100644 --- a/include/net/dn_dev.h +++ b/include/net/dn_dev.h @@ -101,7 +101,7 @@ struct dn_short_packet { __le16 dstnode; __le16 srcnode; __u8 forward; -} __attribute__((packed)); +} __packed; struct dn_long_packet { __u8 msgflg; @@ -115,7 +115,7 @@ struct dn_long_packet { __u8 visit_ct; __u8 s_class; __u8 pt; -} __attribute__((packed)); +} __packed; /*------------------------- DRP - Routing messages ---------------------*/ @@ -132,7 +132,7 @@ struct endnode_hello_message { __u8 mpd; __u8 datalen; __u8 data[2]; -} __attribute__((packed)); +} __packed; struct rtnode_hello_message { __u8 msgflg; @@ -144,7 +144,7 @@ struct rtnode_hello_message { __u8 area; __le16 timer; __u8 mpd; -} __attribute__((packed)); +} __packed; extern void dn_dev_init(void); diff --git a/include/net/dn_nsp.h b/include/net/dn_nsp.h index 17d43d2db5ec..e43a2893f132 100644 --- a/include/net/dn_nsp.h +++ b/include/net/dn_nsp.h @@ -74,18 +74,18 @@ struct nsp_data_seg_msg { __u8 msgflg; __le16 dstaddr; __le16 srcaddr; -} __attribute__((packed)); +} __packed; struct nsp_data_opt_msg { __le16 acknum; __le16 segnum; __le16 lsflgs; -} __attribute__((packed)); +} __packed; struct nsp_data_opt_msg1 { __le16 acknum; __le16 segnum; -} __attribute__((packed)); +} __packed; /* Acknowledgment Message (data/other data) */ @@ -94,13 +94,13 @@ struct nsp_data_ack_msg { __le16 dstaddr; __le16 srcaddr; __le16 acknum; -} __attribute__((packed)); +} __packed; /* Connect Acknowledgment Message */ struct nsp_conn_ack_msg { __u8 msgflg; __le16 dstaddr; -} __attribute__((packed)); +} __packed; /* Connect Initiate/Retransmit Initiate/Connect Confirm */ @@ -117,7 +117,7 @@ struct nsp_conn_init_msg { #define NSP_FC_MASK 0x0c /* FC type mask */ __u8 info; __le16 segsize; -} __attribute__((packed)); +} __packed; /* Disconnect Initiate/Disconnect Confirm */ struct nsp_disconn_init_msg { @@ -125,7 +125,7 @@ struct nsp_disconn_init_msg { __le16 dstaddr; __le16 srcaddr; __le16 reason; -} __attribute__((packed)); +} __packed; @@ -135,7 +135,7 @@ struct srcobj_fmt { __le16 grpcode; __le16 usrcode; __u8 dlen; -} __attribute__((packed)); +} __packed; /* * A collection of functions for manipulating the sequence diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index fbf9d1cda27b..fc94ec568a50 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -27,6 +27,6 @@ struct ipv6_tlv_tnl_enc_lim { __u8 type; /* type-code for option */ __u8 length; /* option length */ __u8 encap_limit; /* tunnel encapsulation limit */ -} __attribute__ ((packed)); +} __packed; #endif diff --git a/include/net/ipx.h b/include/net/ipx.h index ef51a668ba19..05d7e4a88b49 100644 --- a/include/net/ipx.h +++ b/include/net/ipx.h @@ -27,9 +27,9 @@ struct ipx_address { #define IPX_MAX_PPROP_HOPS 8 struct ipxhdr { - __be16 ipx_checksum __attribute__ ((packed)); + __be16 ipx_checksum __packed; #define IPX_NO_CHECKSUM cpu_to_be16(0xFFFF) - __be16 ipx_pktsize __attribute__ ((packed)); + __be16 ipx_pktsize __packed; __u8 ipx_tctrl; __u8 ipx_type; #define IPX_TYPE_UNKNOWN 0x00 @@ -38,8 +38,8 @@ struct ipxhdr { #define IPX_TYPE_SPX 0x05 /* SPX protocol */ #define IPX_TYPE_NCP 0x11 /* $lots for docs on this (SPIT) */ #define IPX_TYPE_PPROP 0x14 /* complicated flood fill brdcast */ - struct ipx_address ipx_dest __attribute__ ((packed)); - struct ipx_address ipx_source __attribute__ ((packed)); + struct ipx_address ipx_dest __packed; + struct ipx_address ipx_source __packed; }; static __inline__ struct ipxhdr *ipx_hdr(struct sk_buff *skb) diff --git a/include/net/mip6.h b/include/net/mip6.h index a83ad1982a90..26ba99b5a4b1 100644 --- a/include/net/mip6.h +++ b/include/net/mip6.h @@ -39,7 +39,7 @@ struct ip6_mh { __u16 ip6mh_cksum; /* Followed by type specific messages */ __u8 data[0]; -} __attribute__ ((__packed__)); +} __packed; #define IP6_MH_TYPE_BRR 0 /* Binding Refresh Request */ #define IP6_MH_TYPE_HOTI 1 /* HOTI Message */ diff --git a/include/net/ndisc.h b/include/net/ndisc.h index f76f22d05721..895997bc2ead 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -82,7 +82,7 @@ struct ra_msg { struct nd_opt_hdr { __u8 nd_opt_type; __u8 nd_opt_len; -} __attribute__((__packed__)); +} __packed; extern int ndisc_init(void); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 4b860116e096..f9e7473613bd 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -443,7 +443,7 @@ struct sctp_signed_cookie { __u8 signature[SCTP_SECRET_SIZE]; __u32 __pad; /* force sctp_cookie alignment to 64 bits */ struct sctp_cookie c; -} __attribute__((packed)); +} __packed; /* This is another convenience type to allocate memory for address * params for the maximum size and pass such structures around @@ -488,7 +488,7 @@ typedef struct sctp_sender_hb_info { union sctp_addr daddr; unsigned long sent_at; __u64 hb_nonce; -} __attribute__((packed)) sctp_sender_hb_info_t; +} __packed sctp_sender_hb_info_t; /* * RFC 2960 1.3.2 Sequenced Delivery within Streams diff --git a/include/rxrpc/packet.h b/include/rxrpc/packet.h index b69e6e173ea1..9b2c30897e50 100644 --- a/include/rxrpc/packet.h +++ b/include/rxrpc/packet.h @@ -65,7 +65,7 @@ struct rxrpc_header { }; __be16 serviceId; /* service ID */ -} __attribute__((packed)); +} __packed; #define __rxrpc_header_off(X) offsetof(struct rxrpc_header,X) @@ -120,7 +120,7 @@ struct rxrpc_ackpacket { #define RXRPC_ACK_TYPE_NACK 0 #define RXRPC_ACK_TYPE_ACK 1 -} __attribute__((packed)); +} __packed; /* * ACK packets can have a further piece of information tagged on the end @@ -141,7 +141,7 @@ struct rxkad_challenge { __be32 nonce; /* encrypted random number */ __be32 min_level; /* minimum security level */ __be32 __padding; /* padding to 8-byte boundary */ -} __attribute__((packed)); +} __packed; /*****************************************************************************/ /* @@ -164,7 +164,7 @@ struct rxkad_response { __be32 kvno; /* Kerberos key version number */ __be32 ticket_len; /* Kerberos ticket length */ -} __attribute__((packed)); +} __packed; /*****************************************************************************/ /* diff --git a/net/bluetooth/bnep/bnep.h b/net/bluetooth/bnep/bnep.h index 0d9e506f5d5a..70672544db86 100644 --- a/net/bluetooth/bnep/bnep.h +++ b/net/bluetooth/bnep/bnep.h @@ -86,26 +86,26 @@ struct bnep_setup_conn_req { __u8 ctrl; __u8 uuid_size; __u8 service[0]; -} __attribute__((packed)); +} __packed; struct bnep_set_filter_req { __u8 type; __u8 ctrl; __be16 len; __u8 list[0]; -} __attribute__((packed)); +} __packed; struct bnep_control_rsp { __u8 type; __u8 ctrl; __be16 resp; -} __attribute__((packed)); +} __packed; struct bnep_ext_hdr { __u8 type; __u8 len; __u8 data[0]; -} __attribute__((packed)); +} __packed; /* BNEP ioctl defines */ #define BNEPCONNADD _IOW('B', 200, int) diff --git a/net/compat.c b/net/compat.c index ec24d9edb025..1cf75905f132 100644 --- a/net/compat.c +++ b/net/compat.c @@ -531,7 +531,7 @@ struct compat_group_req { __u32 gr_interface; struct __kernel_sockaddr_storage gr_group __attribute__ ((aligned(4))); -} __attribute__ ((packed)); +} __packed; struct compat_group_source_req { __u32 gsr_interface; @@ -539,7 +539,7 @@ struct compat_group_source_req { __attribute__ ((aligned(4))); struct __kernel_sockaddr_storage gsr_source __attribute__ ((aligned(4))); -} __attribute__ ((packed)); +} __packed; struct compat_group_filter { __u32 gf_interface; @@ -549,7 +549,7 @@ struct compat_group_filter { __u32 gf_numsrc; struct __kernel_sockaddr_storage gf_slist[1] __attribute__ ((aligned(4))); -} __attribute__ ((packed)); +} __packed; #define __COMPAT_GF0_SIZE (sizeof(struct compat_group_filter) - \ sizeof(struct __kernel_sockaddr_storage)) diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index f28ad2cc8428..499c045d6910 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1463,7 +1463,7 @@ struct iucv_path_pending { u32 res3; u8 ippollfg; u8 res4[3]; -} __attribute__ ((packed)); +} __packed; static void iucv_path_pending(struct iucv_irq_data *data) { @@ -1524,7 +1524,7 @@ struct iucv_path_complete { u32 res3; u8 ippollfg; u8 res4[3]; -} __attribute__ ((packed)); +} __packed; static void iucv_path_complete(struct iucv_irq_data *data) { @@ -1554,7 +1554,7 @@ struct iucv_path_severed { u32 res4; u8 ippollfg; u8 res5[3]; -} __attribute__ ((packed)); +} __packed; static void iucv_path_severed(struct iucv_irq_data *data) { @@ -1590,7 +1590,7 @@ struct iucv_path_quiesced { u32 res4; u8 ippollfg; u8 res5[3]; -} __attribute__ ((packed)); +} __packed; static void iucv_path_quiesced(struct iucv_irq_data *data) { @@ -1618,7 +1618,7 @@ struct iucv_path_resumed { u32 res4; u8 ippollfg; u8 res5[3]; -} __attribute__ ((packed)); +} __packed; static void iucv_path_resumed(struct iucv_irq_data *data) { @@ -1649,7 +1649,7 @@ struct iucv_message_complete { u32 ipbfln2f; u8 ippollfg; u8 res2[3]; -} __attribute__ ((packed)); +} __packed; static void iucv_message_complete(struct iucv_irq_data *data) { @@ -1694,7 +1694,7 @@ struct iucv_message_pending { u32 ipbfln2f; u8 ippollfg; u8 res2[3]; -} __attribute__ ((packed)); +} __packed; static void iucv_message_pending(struct iucv_irq_data *data) { diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c7000a6ca379..a2ed0f7b5568 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -600,7 +600,7 @@ struct iapp_layer2_update { u8 ssap; /* 0 */ u8 control; u8 xid_info[3]; -} __attribute__ ((packed)); +} __packed; static void ieee80211_send_layer2_update(struct sta_info *sta) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 1a9e2da37a93..ec3e5c3e27bd 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1084,7 +1084,7 @@ struct ieee80211_tx_status_rtap_hdr { u8 padding_for_rate; __le16 tx_flags; u8 data_retries; -} __attribute__ ((packed)); +} __packed; /* HT */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 6e2a7bcd8cb8..2d9a2ee94e17 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2139,7 +2139,7 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, u8 rate_or_pad; __le16 chan_freq; __le16 chan_flags; - } __attribute__ ((packed)) *rthdr; + } __packed *rthdr; struct sk_buff *skb = rx->skb, *skb2; struct net_device *prev_dev = NULL; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index bd2a50b482ac..246f92924658 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1817,7 +1817,7 @@ malformed: struct __sctp_missing { __be32 num_missing; __be16 type; -} __attribute__((packed)); +} __packed; /* * Report a missing mandatory parameter. -- cgit v1.2.3 From 095dfdb0c479661f437b24b85e31f0d0b841eab6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 26 May 2010 17:19:25 +0200 Subject: mac80211: remove tx status ampdu_ack_map There's a single use of this struct member, but as it is write-only it clearly not necessary. Thus we can free up some space here, even if we don't need it right now it seems pointless to carry around the variable. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/iwlwifi/iwl-agn-tx.c | 1 - include/net/mac80211.h | 5 +---- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c index 52bec1040467..bde342b5df85 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c @@ -1252,7 +1252,6 @@ static int iwlagn_tx_status_reply_compressed_ba(struct iwl_priv *priv, info->flags |= IEEE80211_TX_STAT_ACK; info->flags |= IEEE80211_TX_STAT_AMPDU; info->status.ampdu_ack_len = successes; - info->status.ampdu_ack_map = bitmap; info->status.ampdu_len = agg->frame_count; iwlagn_hwrate_to_tx_control(priv, agg->rate_n_flags, info); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index de22cbfef232..f26440a46df0 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -412,8 +412,6 @@ struct ieee80211_tx_rate { * @driver_data: array of driver_data pointers * @ampdu_ack_len: number of acked aggregated frames. * relevant only if IEEE80211_TX_STAT_AMPDU was set. - * @ampdu_ack_map: block ack bit map for the aggregation. - * relevant only if IEEE80211_TX_STAT_AMPDU was set. * @ampdu_len: number of aggregated frames. * relevant only if IEEE80211_TX_STAT_AMPDU was set. * @ack_signal: signal strength of the ACK frame @@ -448,10 +446,9 @@ struct ieee80211_tx_info { struct { struct ieee80211_tx_rate rates[IEEE80211_TX_MAX_RATES]; u8 ampdu_ack_len; - u64 ampdu_ack_map; int ack_signal; u8 ampdu_len; - /* 7 bytes free */ + /* 15 bytes free */ } status; struct { struct ieee80211_tx_rate driver_rates[ -- cgit v1.2.3 From 2b2c009ecf71f4c66ff8420b63dddbc9737e04e3 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Thu, 27 May 2010 15:32:13 +0300 Subject: mac80211: Add support for hardware ARP query filtering Some hardware allow extended filtering of ARP frames not intended for the host. To perform such filtering, the hardware needs to know the current IP address(es) of the host, bound to its interface. Add support for ARP filtering to mac80211 by adding a new op to the driver interface, allowing to configure the current IP addresses. This op is called upon association with the currently configured address(es), and when associated whenever the IP address(es) change. This patch adds configuration of IPv4 addresses only, as IPv6 addresses don't need ARP filtering. Signed-off-by: Juuso Oikarinen Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 14 ++++++++++ net/mac80211/driver-ops.h | 17 ++++++++++++ net/mac80211/driver-trace.h | 25 ++++++++++++++++++ net/mac80211/ieee80211_i.h | 2 ++ net/mac80211/main.c | 63 ++++++++++++++++++++++++++++++++++++++++++++- net/mac80211/mlme.c | 11 +++++++- 6 files changed, 130 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f26440a46df0..74b9b49ddfae 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -19,6 +19,7 @@ #include #include #include +#include #include /** @@ -1532,6 +1533,16 @@ enum ieee80211_ampdu_mlme_action { * of the bss parameters has changed when a call is made. The callback * can sleep. * + * @configure_arp_filter: Configuration function for hardware ARP query filter. + * This function is called with all the IP addresses configured to the + * interface as argument - all ARP queries targeted to any of these + * addresses must pass through. If the hardware filter does not support + * enought addresses, hardware filtering must be disabled. The ifa_list + * argument may be NULL, indicating that filtering must be disabled. + * This function is called upon association complete with current + * address(es), and while associated whenever the IP address(es) change. + * The callback can sleep. + * * @prepare_multicast: Prepare for multicast filter configuration. * This callback is optional, and its return value is passed * to configure_filter(). This callback must be atomic. @@ -1671,6 +1682,9 @@ struct ieee80211_ops { struct ieee80211_vif *vif, struct ieee80211_bss_conf *info, u32 changed); + int (*configure_arp_filter)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct in_ifaddr *ifa_list); u64 (*prepare_multicast)(struct ieee80211_hw *hw, struct netdev_hw_addr_list *mc_list); void (*configure_filter)(struct ieee80211_hw *hw, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 4f2271316650..978850ee3a5f 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -83,6 +83,23 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local, trace_drv_bss_info_changed(local, sdata, info, changed); } +struct in_ifaddr; +static inline int drv_configure_arp_filter(struct ieee80211_local *local, + struct ieee80211_vif *vif, + struct in_ifaddr *ifa_list) +{ + int ret = 0; + + might_sleep(); + + if (local->ops->configure_arp_filter) + ret = local->ops->configure_arp_filter(&local->hw, vif, + ifa_list); + + trace_drv_configure_arp_filter(local, vif_to_sdata(vif), ifa_list, ret); + return ret; +} + static inline u64 drv_prepare_multicast(struct ieee80211_local *local, struct netdev_hw_addr_list *mc_list) { diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index 6a9b2342a9c2..577460da2ea1 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -219,6 +219,31 @@ TRACE_EVENT(drv_bss_info_changed, ) ); +TRACE_EVENT(drv_configure_arp_filter, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct in_ifaddr *ifa_list, int ret), + + TP_ARGS(local, sdata, ifa_list, ret), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + __field(int, ret) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + __entry->ret = ret; + ), + + TP_printk( + VIF_PR_FMT LOCAL_PR_FMT " ret:%d", + VIF_PR_ARG, LOCAL_PR_ARG, __entry->ret + ) +); + TRACE_EVENT(drv_prepare_multicast, TP_PROTO(struct ieee80211_local *local, int mc_count, u64 ret), diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index d4677efd3a36..47d67537f170 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -851,6 +851,7 @@ struct ieee80211_local { struct work_struct dynamic_ps_disable_work; struct timer_list dynamic_ps_timer; struct notifier_block network_latency_notifier; + struct notifier_block ifa_notifier; int user_power_level; /* in dBm */ int power_constr_level; /* in dBm */ @@ -997,6 +998,7 @@ void ieee80211_send_pspoll(struct ieee80211_local *local, void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency); int ieee80211_max_network_latency(struct notifier_block *nb, unsigned long data, void *dummy); +int ieee80211_set_arp_filter(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel_sw_ie *sw_elem, struct ieee80211_bss *bss, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index c8548e61f860..4051b232c6e6 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -329,6 +329,58 @@ static void ieee80211_recalc_smps_work(struct work_struct *work) mutex_unlock(&local->iflist_mtx); } +int ieee80211_set_arp_filter(struct ieee80211_sub_if_data *sdata) +{ + struct in_device *idev; + int ret = 0; + + BUG_ON(!sdata); + ASSERT_RTNL(); + + idev = sdata->dev->ip_ptr; + if (!idev) + return 0; + + ret = drv_configure_arp_filter(sdata->local, &sdata->vif, + idev->ifa_list); + return ret; +} + +static int ieee80211_ifa_changed(struct notifier_block *nb, + unsigned long data, void *arg) +{ + struct in_ifaddr *ifa = arg; + struct ieee80211_local *local = + container_of(nb, struct ieee80211_local, + ifa_notifier); + struct net_device *ndev = ifa->ifa_dev->dev; + struct wireless_dev *wdev = ndev->ieee80211_ptr; + struct ieee80211_sub_if_data *sdata; + struct ieee80211_if_managed *ifmgd; + + /* Make sure it's our interface that got changed */ + if (!wdev) + return NOTIFY_DONE; + + if (wdev->wiphy != local->hw.wiphy) + return NOTIFY_DONE; + + /* We are concerned about IP addresses only when associated */ + sdata = IEEE80211_DEV_TO_SUB_IF(ndev); + + /* ARP filtering is only supported in managed mode */ + if (sdata->vif.type != NL80211_IFTYPE_STATION) + return NOTIFY_DONE; + + ifmgd = &sdata->u.mgd; + mutex_lock(&ifmgd->mtx); + if (ifmgd->associated) + ieee80211_set_arp_filter(sdata); + mutex_unlock(&ifmgd->mtx); + + return NOTIFY_DONE; +} + struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, const struct ieee80211_ops *ops) { @@ -612,14 +664,22 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_max_network_latency; result = pm_qos_add_notifier(PM_QOS_NETWORK_LATENCY, &local->network_latency_notifier); - if (result) { rtnl_lock(); goto fail_pm_qos; } + local->ifa_notifier.notifier_call = ieee80211_ifa_changed; + result = register_inetaddr_notifier(&local->ifa_notifier); + if (result) + goto fail_ifa; + return 0; + fail_ifa: + pm_qos_remove_notifier(PM_QOS_NETWORK_LATENCY, + &local->network_latency_notifier); + rtnl_lock(); fail_pm_qos: ieee80211_led_exit(local); ieee80211_remove_interfaces(local); @@ -647,6 +707,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) pm_qos_remove_notifier(PM_QOS_NETWORK_LATENCY, &local->network_latency_notifier); + unregister_inetaddr_notifier(&local->ifa_notifier); rtnl_lock(); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 29c3a75a7ad0..7e720133358c 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2078,8 +2078,17 @@ static enum work_done_result ieee80211_assoc_done(struct ieee80211_work *wk, cfg80211_send_assoc_timeout(wk->sdata->dev, wk->filter_ta); return WORK_DONE_DESTROY; + } else { + mutex_unlock(&wk->sdata->u.mgd.mtx); + + /* + * configure ARP filter IP addresses to the driver, + * intentionally outside the mgd mutex. + */ + rtnl_lock(); + ieee80211_set_arp_filter(wk->sdata); + rtnl_unlock(); } - mutex_unlock(&wk->sdata->u.mgd.mtx); } cfg80211_send_rx_assoc(wk->sdata->dev, skb->data, skb->len); -- cgit v1.2.3 From 6a8579d0e62c0eac428184ce45e86bc46677724a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 27 May 2010 14:41:07 +0200 Subject: mac80211: clean up ieee80211_stop_tx_ba_session There's no sense in letting anything but internal mac80211 functions set the initiator to anything but WLAN_BACK_INITIATOR, since WLAN_BACK_RECIPIENT is only valid when we have received a frame from the peer, which we react to directly in mac80211. The debugfs code I recently added got this wrong as well. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/iwlwifi/iwl-agn-rs.c | 3 +-- include/net/mac80211.h | 6 ++---- net/mac80211/agg-tx.c | 7 +++---- net/mac80211/debugfs_sta.c | 3 +-- net/mac80211/driver-trace.h | 10 ++++------ 5 files changed, 11 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c index cf4a95bae4ff..40933a5de027 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rs.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rs.c @@ -313,8 +313,7 @@ static int rs_tl_turn_on_agg_for_tid(struct iwl_priv *priv, */ IWL_DEBUG_HT(priv, "Fail start Tx agg on tid: %d\n", tid); - ieee80211_stop_tx_ba_session(sta, tid, - WLAN_BACK_INITIATOR); + ieee80211_stop_tx_ba_session(sta, tid); } } else IWL_ERR(priv, "Fail finding valid aggregation tid: %d\n", tid); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 74b9b49ddfae..2e728611c572 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2345,16 +2345,14 @@ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, * ieee80211_stop_tx_ba_session - Stop a Block Ack session. * @sta: the station whose BA session to stop * @tid: the TID to stop BA. - * @initiator: if indicates initiator DELBA frame will be sent. * - * Return: error if no sta with matching da found, success otherwise + * Return: negative error if the TID is invalid, or no aggregation active * * Although mac80211/low level driver/user space application can estimate * the need to stop aggregation on a certain RA/TID, the session level * will be managed by the mac80211. */ -int ieee80211_stop_tx_ba_session(struct ieee80211_sta *sta, u16 tid, - enum ieee80211_back_parties initiator); +int ieee80211_stop_tx_ba_session(struct ieee80211_sta *sta, u16 tid); /** * ieee80211_stop_tx_ba_cb - low level driver ready to stop aggregate. diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index c163d0a149f4..feb15c4a1fad 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -538,14 +538,13 @@ int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, return ret; } -int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, - enum ieee80211_back_parties initiator) +int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - trace_api_stop_tx_ba_session(pubsta, tid, initiator); + trace_api_stop_tx_ba_session(pubsta, tid); if (!local->ops->ampdu_action) return -EINVAL; @@ -553,7 +552,7 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, if (tid >= STA_TID_NUM) return -EINVAL; - return __ieee80211_stop_tx_ba_session(sta, tid, initiator); + return __ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR); } EXPORT_SYMBOL(ieee80211_stop_tx_ba_session); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index e763f1529ddb..9f140612224a 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -210,8 +210,7 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu if (start) ret = ieee80211_start_tx_ba_session(&sta->sta, tid); else - ret = ieee80211_stop_tx_ba_session(&sta->sta, tid, - WLAN_BACK_RECIPIENT); + ret = ieee80211_stop_tx_ba_session(&sta->sta, tid); } else { __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, 3); ret = 0; diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index 577460da2ea1..6b90630151ab 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -876,25 +876,23 @@ TRACE_EVENT(api_start_tx_ba_cb, ); TRACE_EVENT(api_stop_tx_ba_session, - TP_PROTO(struct ieee80211_sta *sta, u16 tid, u16 initiator), + TP_PROTO(struct ieee80211_sta *sta, u16 tid), - TP_ARGS(sta, tid, initiator), + TP_ARGS(sta, tid), TP_STRUCT__entry( STA_ENTRY __field(u16, tid) - __field(u16, initiator) ), TP_fast_assign( STA_ASSIGN; __entry->tid = tid; - __entry->initiator = initiator; ), TP_printk( - STA_PR_FMT " tid:%d initiator:%d", - STA_PR_ARG, __entry->tid, __entry->initiator + STA_PR_FMT " tid:%d", + STA_PR_ARG, __entry->tid ) ); -- cgit v1.2.3 From 38a6cc7538d3c44b76f9dcea607a171adcc0208e Mon Sep 17 00:00:00 2001 From: Sujith Date: Wed, 19 May 2010 11:32:30 +0530 Subject: mac80211: Remove deprecated sta_notify commands STA_NOTIFY_ADD and STA_NOTIFY_REMOVE have no users anymore, and station addition/removal are indicated to drivers using sta_add() and sta_remove(), which can sleep. Signed-off-by: Sujith Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 6 +----- net/mac80211/driver-ops.h | 6 ------ 2 files changed, 1 insertion(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2e728611c572..e3c1d4794003 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -879,16 +879,12 @@ struct ieee80211_sta { * enum sta_notify_cmd - sta notify command * * Used with the sta_notify() callback in &struct ieee80211_ops, this - * indicates addition and removal of a station to station table, - * or if a associated station made a power state transition. + * indicates if an associated station made a power state transition. * - * @STA_NOTIFY_ADD: (DEPRECATED) a station was added to the station table - * @STA_NOTIFY_REMOVE: (DEPRECATED) a station being removed from the station table * @STA_NOTIFY_SLEEP: a station is now sleeping * @STA_NOTIFY_AWAKE: a sleeping station woke up */ enum sta_notify_cmd { - STA_NOTIFY_ADD, STA_NOTIFY_REMOVE, STA_NOTIFY_SLEEP, STA_NOTIFY_AWAKE, }; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 978850ee3a5f..d1139e4f88a9 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -269,9 +269,6 @@ static inline int drv_sta_add(struct ieee80211_local *local, if (local->ops->sta_add) ret = local->ops->sta_add(&local->hw, &sdata->vif, sta); - else if (local->ops->sta_notify) - local->ops->sta_notify(&local->hw, &sdata->vif, - STA_NOTIFY_ADD, sta); trace_drv_sta_add(local, sdata, sta, ret); @@ -286,9 +283,6 @@ static inline void drv_sta_remove(struct ieee80211_local *local, if (local->ops->sta_remove) local->ops->sta_remove(&local->hw, &sdata->vif, sta); - else if (local->ops->sta_notify) - local->ops->sta_notify(&local->hw, &sdata->vif, - STA_NOTIFY_REMOVE, sta); trace_drv_sta_remove(local, sdata, sta); } -- cgit v1.2.3 From 14f92952bf74a365ca7f9dfbec158e7c933ea723 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Thu, 3 Jun 2010 19:37:27 -0700 Subject: ssb: add dma_dev to ssb_device structure Add dma_dev, a pointer to struct device, to struct ssb_device. We pass it to the generic DMA API with SSB_BUSTYPE_PCI and SSB_BUSTYPE_SSB. ssb_devices_register() sets up it properly. This is preparation for replacing the ssb bus specific DMA API (ssb_dma_*) with the generic DMA API. Signed-off-by: FUJITA Tomonori Acked-by: Michael Buesch Cc: Gary Zambrano Cc: Stefano Brivio Cc: Larry Finger Cc: John W. Linville Acked-by: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: John W. Linville --- drivers/ssb/main.c | 2 ++ include/linux/ssb/ssb.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index 51275aac5b34..a732b396e602 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -486,6 +486,7 @@ static int ssb_devices_register(struct ssb_bus *bus) #ifdef CONFIG_SSB_PCIHOST sdev->irq = bus->host_pci->irq; dev->parent = &bus->host_pci->dev; + sdev->dma_dev = dev->parent; #endif break; case SSB_BUSTYPE_PCMCIA: @@ -501,6 +502,7 @@ static int ssb_devices_register(struct ssb_bus *bus) break; case SSB_BUSTYPE_SSB: dev->dma_mask = &dev->coherent_dma_mask; + sdev->dma_dev = dev; break; } diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index a2608bff9c78..0d5f04316b35 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -167,7 +167,7 @@ struct ssb_device { * is an optimization. */ const struct ssb_bus_ops *ops; - struct device *dev; + struct device *dev, *dma_dev; struct ssb_bus *bus; struct ssb_device_id id; -- cgit v1.2.3 From 467429b475e56f154f93b3b14fd75f238d14597a Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Thu, 3 Jun 2010 19:37:44 -0700 Subject: ssb: remove the ssb DMA API Now they are unnecessary. We can use the generic DMA API with any bus. Signed-off-by: FUJITA Tomonori Cc: Michael Buesch Cc: Gary Zambrano Cc: Stefano Brivio Cc: Larry Finger Cc: John W. Linville Cc: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: John W. Linville --- drivers/ssb/main.c | 74 ----------------------- include/linux/ssb/ssb.h | 157 ------------------------------------------------ 2 files changed, 231 deletions(-) (limited to 'include') diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index a732b396e602..7cee7f4eb60b 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -1228,80 +1228,6 @@ u32 ssb_dma_translation(struct ssb_device *dev) } EXPORT_SYMBOL(ssb_dma_translation); -int ssb_dma_set_mask(struct ssb_device *dev, u64 mask) -{ -#ifdef CONFIG_SSB_PCIHOST - int err; -#endif - - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - err = pci_set_dma_mask(dev->bus->host_pci, mask); - if (err) - return err; - err = pci_set_consistent_dma_mask(dev->bus->host_pci, mask); - return err; -#endif - case SSB_BUSTYPE_SSB: - return dma_set_mask(dev->dev, mask); - default: - __ssb_dma_not_implemented(dev); - } - return -ENOSYS; -} -EXPORT_SYMBOL(ssb_dma_set_mask); - -void * ssb_dma_alloc_consistent(struct ssb_device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp_flags) -{ - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - if (gfp_flags & GFP_DMA) { - /* Workaround: The PCI API does not support passing - * a GFP flag. */ - return dma_alloc_coherent(&dev->bus->host_pci->dev, - size, dma_handle, gfp_flags); - } - return pci_alloc_consistent(dev->bus->host_pci, size, dma_handle); -#endif - case SSB_BUSTYPE_SSB: - return dma_alloc_coherent(dev->dev, size, dma_handle, gfp_flags); - default: - __ssb_dma_not_implemented(dev); - } - return NULL; -} -EXPORT_SYMBOL(ssb_dma_alloc_consistent); - -void ssb_dma_free_consistent(struct ssb_device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - gfp_t gfp_flags) -{ - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - if (gfp_flags & GFP_DMA) { - /* Workaround: The PCI API does not support passing - * a GFP flag. */ - dma_free_coherent(&dev->bus->host_pci->dev, - size, vaddr, dma_handle); - return; - } - pci_free_consistent(dev->bus->host_pci, size, - vaddr, dma_handle); - return; -#endif - case SSB_BUSTYPE_SSB: - dma_free_coherent(dev->dev, size, vaddr, dma_handle); - return; - default: - __ssb_dma_not_implemented(dev); - } -} -EXPORT_SYMBOL(ssb_dma_free_consistent); - int ssb_bus_may_powerdown(struct ssb_bus *bus) { struct ssb_chipcommon *cc; diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 0d5f04316b35..623b704fdc42 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -470,14 +470,6 @@ extern u32 ssb_dma_translation(struct ssb_device *dev); #define SSB_DMA_TRANSLATION_MASK 0xC0000000 #define SSB_DMA_TRANSLATION_SHIFT 30 -extern int ssb_dma_set_mask(struct ssb_device *dev, u64 mask); - -extern void * ssb_dma_alloc_consistent(struct ssb_device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp_flags); -extern void ssb_dma_free_consistent(struct ssb_device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - gfp_t gfp_flags); - static inline void __cold __ssb_dma_not_implemented(struct ssb_device *dev) { #ifdef CONFIG_SSB_DEBUG @@ -486,155 +478,6 @@ static inline void __cold __ssb_dma_not_implemented(struct ssb_device *dev) #endif /* DEBUG */ } -static inline int ssb_dma_mapping_error(struct ssb_device *dev, dma_addr_t addr) -{ - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - return pci_dma_mapping_error(dev->bus->host_pci, addr); -#endif - break; - case SSB_BUSTYPE_SSB: - return dma_mapping_error(dev->dev, addr); - default: - break; - } - __ssb_dma_not_implemented(dev); - return -ENOSYS; -} - -static inline dma_addr_t ssb_dma_map_single(struct ssb_device *dev, void *p, - size_t size, enum dma_data_direction dir) -{ - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - return pci_map_single(dev->bus->host_pci, p, size, dir); -#endif - break; - case SSB_BUSTYPE_SSB: - return dma_map_single(dev->dev, p, size, dir); - default: - break; - } - __ssb_dma_not_implemented(dev); - return 0; -} - -static inline void ssb_dma_unmap_single(struct ssb_device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction dir) -{ - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - pci_unmap_single(dev->bus->host_pci, dma_addr, size, dir); - return; -#endif - break; - case SSB_BUSTYPE_SSB: - dma_unmap_single(dev->dev, dma_addr, size, dir); - return; - default: - break; - } - __ssb_dma_not_implemented(dev); -} - -static inline void ssb_dma_sync_single_for_cpu(struct ssb_device *dev, - dma_addr_t dma_addr, - size_t size, - enum dma_data_direction dir) -{ - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - pci_dma_sync_single_for_cpu(dev->bus->host_pci, dma_addr, - size, dir); - return; -#endif - break; - case SSB_BUSTYPE_SSB: - dma_sync_single_for_cpu(dev->dev, dma_addr, size, dir); - return; - default: - break; - } - __ssb_dma_not_implemented(dev); -} - -static inline void ssb_dma_sync_single_for_device(struct ssb_device *dev, - dma_addr_t dma_addr, - size_t size, - enum dma_data_direction dir) -{ - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - pci_dma_sync_single_for_device(dev->bus->host_pci, dma_addr, - size, dir); - return; -#endif - break; - case SSB_BUSTYPE_SSB: - dma_sync_single_for_device(dev->dev, dma_addr, size, dir); - return; - default: - break; - } - __ssb_dma_not_implemented(dev); -} - -static inline void ssb_dma_sync_single_range_for_cpu(struct ssb_device *dev, - dma_addr_t dma_addr, - unsigned long offset, - size_t size, - enum dma_data_direction dir) -{ - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - /* Just sync everything. That's all the PCI API can do. */ - pci_dma_sync_single_for_cpu(dev->bus->host_pci, dma_addr, - offset + size, dir); - return; -#endif - break; - case SSB_BUSTYPE_SSB: - dma_sync_single_range_for_cpu(dev->dev, dma_addr, offset, - size, dir); - return; - default: - break; - } - __ssb_dma_not_implemented(dev); -} - -static inline void ssb_dma_sync_single_range_for_device(struct ssb_device *dev, - dma_addr_t dma_addr, - unsigned long offset, - size_t size, - enum dma_data_direction dir) -{ - switch (dev->bus->bustype) { - case SSB_BUSTYPE_PCI: -#ifdef CONFIG_SSB_PCIHOST - /* Just sync everything. That's all the PCI API can do. */ - pci_dma_sync_single_for_device(dev->bus->host_pci, dma_addr, - offset + size, dir); - return; -#endif - break; - case SSB_BUSTYPE_SSB: - dma_sync_single_range_for_device(dev->dev, dma_addr, offset, - size, dir); - return; - default: - break; - } - __ssb_dma_not_implemented(dev); -} - - #ifdef CONFIG_SSB_PCIHOST /* PCI-host wrapper driver */ extern int ssb_pcihost_register(struct pci_driver *driver); -- cgit v1.2.3 From b78462ebc6a4ef9074aa80abebcdd470dc5f0ce0 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 2 Jun 2010 12:24:37 +0000 Subject: skbuff: add check for non-linear to warn_if_lro and needs_linearize We can avoid an unecessary cache miss by checking if the skb is non-linear before accessing gso_size/gso_type in skb_warn_if_lro, the same can also be done to avoid a cache miss on nr_frags if data_len is 0. Signed-off-by: Alexander Duyck Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- net/core/dev.c | 7 ++++--- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf243fc54959..645e78d395fd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2129,7 +2129,8 @@ static inline bool skb_warn_if_lro(const struct sk_buff *skb) /* LRO sets gso_size but not gso_type, whereas if GSO is really * wanted then gso_type will be set. */ struct skb_shared_info *shinfo = skb_shinfo(skb); - if (shinfo->gso_size != 0 && unlikely(shinfo->gso_type == 0)) { + if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 && + unlikely(shinfo->gso_type == 0)) { __skb_warn_lro_forwarding(skb); return true; } diff --git a/net/core/dev.c b/net/core/dev.c index ec01a5998d70..3abb3a6058be 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2103,9 +2103,10 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, static inline int skb_needs_linearize(struct sk_buff *skb, struct net_device *dev) { - return (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) || - (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) || - illegal_highdma(dev, skb))); + return skb_is_nonlinear(skb) && + ((skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) || + (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) || + illegal_highdma(dev, skb)))); } /** -- cgit v1.2.3 From bb1d912323d5dd50e1079e389f4e964be14f0ae3 Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Wed, 2 Jun 2010 08:40:18 +0000 Subject: bonding: allow user-controlled output slave selection v2: changed bonding module version, modified to apply on top of changes from previous patch in series, and updated documentation to elaborate on multiqueue awareness that now exists in bonding driver. This patch give the user the ability to control the output slave for round-robin and active-backup bonding. Similar functionality was discussed in the past, but Jay Vosburgh indicated he would rather see a feature like this added to existing modes rather than creating a completely new mode. Jay's thoughts as well as Neil's input surrounding some of the issues with the first implementation pushed us toward a design that relied on the queue_mapping rather than skb marks. Round-robin and active-backup modes were chosen as the first users of this slave selection as they seemed like the most logical choices when considering a multi-switch environment. Round-robin mode works without any modification, but active-backup does require inclusion of the first patch in this series and setting the 'all_slaves_active' flag. This will allow reception of unicast traffic on any of the backup interfaces. This was tested with IPv4-based filters as well as VLAN-based filters with good results. More information as well as a configuration example is available in the patch to Documentation/networking/bonding.txt. Signed-off-by: Andy Gospodarek Signed-off-by: Neil Horman Signed-off-by: David S. Miller --- Documentation/networking/bonding.txt | 84 ++++++++++++++++++++++++- drivers/net/bonding/bond_main.c | 75 +++++++++++++++++++++- drivers/net/bonding/bond_sysfs.c | 116 +++++++++++++++++++++++++++++++++++ drivers/net/bonding/bonding.h | 9 ++- include/linux/if_bonding.h | 1 + 5 files changed, 278 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 61f516b135b4..d0914781830e 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -49,6 +49,7 @@ Table of Contents 3.3 Configuring Bonding Manually with Ifenslave 3.3.1 Configuring Multiple Bonds Manually 3.4 Configuring Bonding Manually via Sysfs +3.5 Overriding Configuration for Special Cases 4. Querying Bonding Configuration 4.1 Bonding Configuration @@ -1318,8 +1319,87 @@ echo 2000 > /sys/class/net/bond1/bonding/arp_interval echo +eth2 > /sys/class/net/bond1/bonding/slaves echo +eth3 > /sys/class/net/bond1/bonding/slaves - -4. Querying Bonding Configuration +3.5 Overriding Configuration for Special Cases +---------------------------------------------- +When using the bonding driver, the physical port which transmits a frame is +typically selected by the bonding driver, and is not relevant to the user or +system administrator. The output port is simply selected using the policies of +the selected bonding mode. On occasion however, it is helpful to direct certain +classes of traffic to certain physical interfaces on output to implement +slightly more complex policies. For example, to reach a web server over a +bonded interface in which eth0 connects to a private network, while eth1 +connects via a public network, it may be desirous to bias the bond to send said +traffic over eth0 first, using eth1 only as a fall back, while all other traffic +can safely be sent over either interface. Such configurations may be achieved +using the traffic control utilities inherent in linux. + +By default the bonding driver is multiqueue aware and 16 queues are created +when the driver initializes (see Documentation/networking/multiqueue.txt +for details). If more or less queues are desired the module parameter +tx_queues can be used to change this value. There is no sysfs parameter +available as the allocation is done at module init time. + +The output of the file /proc/net/bonding/bondX has changed so the output Queue +ID is now printed for each slave: + +Bonding Mode: fault-tolerance (active-backup) +Primary Slave: None +Currently Active Slave: eth0 +MII Status: up +MII Polling Interval (ms): 0 +Up Delay (ms): 0 +Down Delay (ms): 0 + +Slave Interface: eth0 +MII Status: up +Link Failure Count: 0 +Permanent HW addr: 00:1a:a0:12:8f:cb +Slave queue ID: 0 + +Slave Interface: eth1 +MII Status: up +Link Failure Count: 0 +Permanent HW addr: 00:1a:a0:12:8f:cc +Slave queue ID: 2 + +The queue_id for a slave can be set using the command: + +# echo "eth1:2" > /sys/class/net/bond0/bonding/queue_id + +Any interface that needs a queue_id set should set it with multiple calls +like the one above until proper priorities are set for all interfaces. On +distributions that allow configuration via initscripts, multiple 'queue_id' +arguments can be added to BONDING_OPTS to set all needed slave queues. + +These queue id's can be used in conjunction with the tc utility to configure +a multiqueue qdisc and filters to bias certain traffic to transmit on certain +slave devices. For instance, say we wanted, in the above configuration to +force all traffic bound to 192.168.1.100 to use eth1 in the bond as its output +device. The following commands would accomplish this: + +# tc qdisc add dev bond0 handle 1 root multiq + +# tc filter add dev bond0 protocol ip parent 1: prio 1 u32 match ip dst \ + 192.168.1.100 action skbedit queue_mapping 2 + +These commands tell the kernel to attach a multiqueue queue discipline to the +bond0 interface and filter traffic enqueued to it, such that packets with a dst +ip of 192.168.1.100 have their output queue mapping value overwritten to 2. +This value is then passed into the driver, causing the normal output path +selection policy to be overridden, selecting instead qid 2, which maps to eth1. + +Note that qid values begin at 1. Qid 0 is reserved to initiate to the driver +that normal output policy selection should take place. One benefit to simply +leaving the qid for a slave to 0 is the multiqueue awareness in the bonding +driver that is now present. This awareness allows tc filters to be placed on +slave devices as well as bond devices and the bonding driver will simply act as +a pass-through for selecting output queues on the slave device rather than +output port selection. + +This feature first appeared in bonding driver version 3.7.0 and support for +output slave selection was limited to round-robin and active-backup modes. + +4 Querying Bonding Configuration ================================= 4.1 Bonding Configuration diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index f22f6bf43858..1b19276cff12 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -90,6 +90,7 @@ #define BOND_LINK_ARP_INTERV 0 static int max_bonds = BOND_DEFAULT_MAX_BONDS; +static int tx_queues = BOND_DEFAULT_TX_QUEUES; static int num_grat_arp = 1; static int num_unsol_na = 1; static int miimon = BOND_LINK_MON_INTERV; @@ -111,6 +112,8 @@ static struct bond_params bonding_defaults; module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); +module_param(tx_queues, int, 0); +MODULE_PARM_DESC(tx_queues, "Max number of transmit queues (default = 16)"); module_param(num_grat_arp, int, 0644); MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event"); module_param(num_unsol_na, int, 0644); @@ -1540,6 +1543,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) goto err_undo_flags; } + /* + * Set the new_slave's queue_id to be zero. Queue ID mapping + * is set via sysfs or module option if desired. + */ + new_slave->queue_id = 0; + /* Save slave's original mtu and then set it to match the bond */ new_slave->original_mtu = slave_dev->mtu; res = dev_set_mtu(slave_dev, bond->dev->mtu); @@ -3285,6 +3294,7 @@ static void bond_info_show_slave(struct seq_file *seq, else seq_puts(seq, "Aggregator ID: N/A\n"); } + seq_printf(seq, "Slave queue ID: %d\n", slave->queue_id); } static int bond_info_seq_show(struct seq_file *seq, void *v) @@ -4421,9 +4431,59 @@ static void bond_set_xmit_hash_policy(struct bonding *bond) } } +/* + * Lookup the slave that corresponds to a qid + */ +static inline int bond_slave_override(struct bonding *bond, + struct sk_buff *skb) +{ + int i, res = 1; + struct slave *slave = NULL; + struct slave *check_slave; + + read_lock(&bond->lock); + + if (!BOND_IS_OK(bond) || !skb->queue_mapping) + goto out; + + /* Find out if any slaves have the same mapping as this skb. */ + bond_for_each_slave(bond, check_slave, i) { + if (check_slave->queue_id == skb->queue_mapping) { + slave = check_slave; + break; + } + } + + /* If the slave isn't UP, use default transmit policy. */ + if (slave && slave->queue_id && IS_UP(slave->dev) && + (slave->link == BOND_LINK_UP)) { + res = bond_dev_queue_xmit(bond, skb, slave->dev); + } + +out: + read_unlock(&bond->lock); + return res; +} + +static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb) +{ + /* + * This helper function exists to help dev_pick_tx get the correct + * destination queue. Using a helper function skips the a call to + * skb_tx_hash and will put the skbs in the queue we expect on their + * way down to the bonding driver. + */ + return skb->queue_mapping; +} + static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) { - const struct bonding *bond = netdev_priv(dev); + struct bonding *bond = netdev_priv(dev); + + if (TX_QUEUE_OVERRIDE(bond->params.mode)) { + if (!bond_slave_override(bond, skb)) + return NETDEV_TX_OK; + } switch (bond->params.mode) { case BOND_MODE_ROUNDROBIN: @@ -4508,6 +4568,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_open = bond_open, .ndo_stop = bond_close, .ndo_start_xmit = bond_start_xmit, + .ndo_select_queue = bond_select_queue, .ndo_get_stats = bond_get_stats, .ndo_do_ioctl = bond_do_ioctl, .ndo_set_multicast_list = bond_set_multicast_list, @@ -4776,6 +4837,13 @@ static int bond_check_params(struct bond_params *params) } } + if (tx_queues < 1 || tx_queues > 255) { + pr_warning("Warning: tx_queues (%d) should be between " + "1 and 255, resetting to %d\n", + tx_queues, BOND_DEFAULT_TX_QUEUES); + tx_queues = BOND_DEFAULT_TX_QUEUES; + } + if ((all_slaves_active != 0) && (all_slaves_active != 1)) { pr_warning("Warning: all_slaves_active module parameter (%d), " "not of valid value (0/1), so it was set to " @@ -4953,6 +5021,7 @@ static int bond_check_params(struct bond_params *params) params->primary[0] = 0; params->primary_reselect = primary_reselect_value; params->fail_over_mac = fail_over_mac_value; + params->tx_queues = tx_queues; params->all_slaves_active = all_slaves_active; if (primary) { @@ -5040,8 +5109,8 @@ int bond_create(struct net *net, const char *name) rtnl_lock(); - bond_dev = alloc_netdev(sizeof(struct bonding), name ? name : "", - bond_setup); + bond_dev = alloc_netdev_mq(sizeof(struct bonding), name ? name : "", + bond_setup, tx_queues); if (!bond_dev) { pr_err("%s: eek! can't alloc netdev!\n", name); rtnl_unlock(); diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 066311a5e084..f9a034361a8e 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -1411,6 +1411,121 @@ static ssize_t bonding_show_ad_partner_mac(struct device *d, } static DEVICE_ATTR(ad_partner_mac, S_IRUGO, bonding_show_ad_partner_mac, NULL); +/* + * Show the queue_ids of the slaves in the current bond. + */ +static ssize_t bonding_show_queue_id(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct slave *slave; + int i, res = 0; + struct bonding *bond = to_bond(d); + + if (!rtnl_trylock()) + return restart_syscall(); + + read_lock(&bond->lock); + bond_for_each_slave(bond, slave, i) { + if (res > (PAGE_SIZE - 6)) { + /* not enough space for another interface name */ + if ((PAGE_SIZE - res) > 10) + res = PAGE_SIZE - 10; + res += sprintf(buf + res, "++more++ "); + break; + } + res += sprintf(buf + res, "%s:%d ", + slave->dev->name, slave->queue_id); + } + read_unlock(&bond->lock); + if (res) + buf[res-1] = '\n'; /* eat the leftover space */ + rtnl_unlock(); + return res; +} + +/* + * Set the queue_ids of the slaves in the current bond. The bond + * interface must be enslaved for this to work. + */ +static ssize_t bonding_store_queue_id(struct device *d, + struct device_attribute *attr, + const char *buffer, size_t count) +{ + struct slave *slave, *update_slave; + struct bonding *bond = to_bond(d); + u16 qid; + int i, ret = count; + char *delim; + struct net_device *sdev = NULL; + + if (!rtnl_trylock()) + return restart_syscall(); + + /* delim will point to queue id if successful */ + delim = strchr(buffer, ':'); + if (!delim) + goto err_no_cmd; + + /* + * Terminate string that points to device name and bump it + * up one, so we can read the queue id there. + */ + *delim = '\0'; + if (sscanf(++delim, "%hd\n", &qid) != 1) + goto err_no_cmd; + + /* Check buffer length, valid ifname and queue id */ + if (strlen(buffer) > IFNAMSIZ || + !dev_valid_name(buffer) || + qid > bond->params.tx_queues) + goto err_no_cmd; + + /* Get the pointer to that interface if it exists */ + sdev = __dev_get_by_name(dev_net(bond->dev), buffer); + if (!sdev) + goto err_no_cmd; + + read_lock(&bond->lock); + + /* Search for thes slave and check for duplicate qids */ + update_slave = NULL; + bond_for_each_slave(bond, slave, i) { + if (sdev == slave->dev) + /* + * We don't need to check the matching + * slave for dups, since we're overwriting it + */ + update_slave = slave; + else if (qid && qid == slave->queue_id) { + goto err_no_cmd_unlock; + } + } + + if (!update_slave) + goto err_no_cmd_unlock; + + /* Actually set the qids for the slave */ + update_slave->queue_id = qid; + + read_unlock(&bond->lock); +out: + rtnl_unlock(); + return ret; + +err_no_cmd_unlock: + read_unlock(&bond->lock); +err_no_cmd: + pr_info("invalid input for queue_id set for %s.\n", + bond->dev->name); + ret = -EPERM; + goto out; +} + +static DEVICE_ATTR(queue_id, S_IRUGO | S_IWUSR, bonding_show_queue_id, + bonding_store_queue_id); + + /* * Show and set the all_slaves_active flag. */ @@ -1489,6 +1604,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_ad_actor_key.attr, &dev_attr_ad_partner_key.attr, &dev_attr_ad_partner_mac.attr, + &dev_attr_queue_id.attr, &dev_attr_all_slaves_active.attr, NULL, }; diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index cecdea2a629f..c6fdd851579a 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -23,8 +23,8 @@ #include "bond_3ad.h" #include "bond_alb.h" -#define DRV_VERSION "3.6.0" -#define DRV_RELDATE "September 26, 2009" +#define DRV_VERSION "3.7.0" +#define DRV_RELDATE "June 2, 2010" #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" @@ -60,6 +60,9 @@ ((mode) == BOND_MODE_TLB) || \ ((mode) == BOND_MODE_ALB)) +#define TX_QUEUE_OVERRIDE(mode) \ + (((mode) == BOND_MODE_ACTIVEBACKUP) || \ + ((mode) == BOND_MODE_ROUNDROBIN)) /* * Less bad way to call ioctl from within the kernel; this needs to be * done some other way to get the call out of interrupt context. @@ -131,6 +134,7 @@ struct bond_params { char primary[IFNAMSIZ]; int primary_reselect; __be32 arp_targets[BOND_MAX_ARP_TARGETS]; + int tx_queues; int all_slaves_active; }; @@ -165,6 +169,7 @@ struct slave { u8 perm_hwaddr[ETH_ALEN]; u16 speed; u8 duplex; + u16 queue_id; struct ad_slave_info ad_info; /* HUGE - better to dynamically alloc */ struct tlb_slave_info tlb_info; }; diff --git a/include/linux/if_bonding.h b/include/linux/if_bonding.h index cd525fae3c98..2c7994372bde 100644 --- a/include/linux/if_bonding.h +++ b/include/linux/if_bonding.h @@ -83,6 +83,7 @@ #define BOND_DEFAULT_MAX_BONDS 1 /* Default maximum number of devices to support */ +#define BOND_DEFAULT_TX_QUEUES 16 /* Default number of tx queues per device */ /* hashing types */ #define BOND_XMIT_POLICY_LAYER2 0 /* layer 2 (MAC only), default */ #define BOND_XMIT_POLICY_LAYER34 1 /* layer 3+4 (IP ^ (TCP || UDP)) */ -- cgit v1.2.3 From a8b690f98baf9fb1902b8eeab801351ea603fa3a Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 7 Jun 2010 00:43:42 -0700 Subject: tcp: Fix slowness in read /proc/net/tcp This patch address a serious performance issue in reading the TCP sockets table (/proc/net/tcp). Reading the full table is done by a number of sequential read operations. At each read operation, a seek is done to find the last socket that was previously read. This seek operation requires that the sockets in the table need to be counted up to the current file position, and to count each of these requires taking a lock for each non-empty bucket. The whole algorithm is O(n^2). The fix is to cache the last bucket value, offset within the bucket, and the file position returned by the last read operation. On the next sequential read, the bucket and offset are used to find the last read socket immediately without needing ot scan the previous buckets the table. This algorithm t read the whole table is O(n). The improvement offered by this patch is easily show by performing cat'ing /proc/net/tcp on a machine with a lot of connections. With about 182K connections in the table, I see the following: - Without patch time cat /proc/net/tcp > /dev/null real 1m56.729s user 0m0.214s sys 1m56.344s - With patch time cat /proc/net/tcp > /dev/null real 0m0.894s user 0m0.290s sys 0m0.594s Signed-off-by: Tom Herbert Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 +- net/ipv4/tcp_ipv4.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 86 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index a1449144848a..573166484413 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1413,7 +1413,8 @@ struct tcp_iter_state { sa_family_t family; enum tcp_seq_states state; struct sock *syn_wait_sk; - int bucket, sbucket, num, uid; + int bucket, offset, sbucket, num, uid; + loff_t last_pos; }; extern int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index acdc4c989853..7f976af27bf0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1980,6 +1980,11 @@ static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw) hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL; } +/* + * Get next listener socket follow cur. If cur is NULL, get first socket + * starting from bucket given in st->bucket; when st->bucket is zero the + * very first socket in the hash table is returned. + */ static void *listening_get_next(struct seq_file *seq, void *cur) { struct inet_connection_sock *icsk; @@ -1990,14 +1995,15 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct net *net = seq_file_net(seq); if (!sk) { - st->bucket = 0; - ilb = &tcp_hashinfo.listening_hash[0]; + ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock_bh(&ilb->lock); sk = sk_nulls_head(&ilb->head); + st->offset = 0; goto get_sk; } ilb = &tcp_hashinfo.listening_hash[st->bucket]; ++st->num; + ++st->offset; if (st->state == TCP_SEQ_STATE_OPENREQ) { struct request_sock *req = cur; @@ -2012,6 +2018,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur) } req = req->dl_next; } + st->offset = 0; if (++st->sbucket >= icsk->icsk_accept_queue.listen_opt->nr_table_entries) break; get_req: @@ -2047,6 +2054,7 @@ start_req: read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } spin_unlock_bh(&ilb->lock); + st->offset = 0; if (++st->bucket < INET_LHTABLE_SIZE) { ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock_bh(&ilb->lock); @@ -2060,7 +2068,12 @@ out: static void *listening_get_idx(struct seq_file *seq, loff_t *pos) { - void *rc = listening_get_next(seq, NULL); + struct tcp_iter_state *st = seq->private; + void *rc; + + st->bucket = 0; + st->offset = 0; + rc = listening_get_next(seq, NULL); while (rc && *pos) { rc = listening_get_next(seq, rc); @@ -2075,13 +2088,18 @@ static inline int empty_bucket(struct tcp_iter_state *st) hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain); } +/* + * Get first established socket starting from bucket given in st->bucket. + * If st->bucket is zero, the very first socket in the hash is returned. + */ static void *established_get_first(struct seq_file *seq) { struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); void *rc = NULL; - for (st->bucket = 0; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { + st->offset = 0; + for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { struct sock *sk; struct hlist_nulls_node *node; struct inet_timewait_sock *tw; @@ -2126,6 +2144,7 @@ static void *established_get_next(struct seq_file *seq, void *cur) struct net *net = seq_file_net(seq); ++st->num; + ++st->offset; if (st->state == TCP_SEQ_STATE_TIME_WAIT) { tw = cur; @@ -2142,6 +2161,7 @@ get_tw: st->state = TCP_SEQ_STATE_ESTABLISHED; /* Look for next non empty bucket */ + st->offset = 0; while (++st->bucket <= tcp_hashinfo.ehash_mask && empty_bucket(st)) ; @@ -2169,7 +2189,11 @@ out: static void *established_get_idx(struct seq_file *seq, loff_t pos) { - void *rc = established_get_first(seq); + struct tcp_iter_state *st = seq->private; + void *rc; + + st->bucket = 0; + rc = established_get_first(seq); while (rc && pos) { rc = established_get_next(seq, rc); @@ -2194,24 +2218,72 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos) return rc; } +static void *tcp_seek_last_pos(struct seq_file *seq) +{ + struct tcp_iter_state *st = seq->private; + int offset = st->offset; + int orig_num = st->num; + void *rc = NULL; + + switch (st->state) { + case TCP_SEQ_STATE_OPENREQ: + case TCP_SEQ_STATE_LISTENING: + if (st->bucket >= INET_LHTABLE_SIZE) + break; + st->state = TCP_SEQ_STATE_LISTENING; + rc = listening_get_next(seq, NULL); + while (offset-- && rc) + rc = listening_get_next(seq, rc); + if (rc) + break; + st->bucket = 0; + /* Fallthrough */ + case TCP_SEQ_STATE_ESTABLISHED: + case TCP_SEQ_STATE_TIME_WAIT: + st->state = TCP_SEQ_STATE_ESTABLISHED; + if (st->bucket > tcp_hashinfo.ehash_mask) + break; + rc = established_get_first(seq); + while (offset-- && rc) + rc = established_get_next(seq, rc); + } + + st->num = orig_num; + + return rc; +} + static void *tcp_seq_start(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; + void *rc; + + if (*pos && *pos == st->last_pos) { + rc = tcp_seek_last_pos(seq); + if (rc) + goto out; + } + st->state = TCP_SEQ_STATE_LISTENING; st->num = 0; - return *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; + st->bucket = 0; + st->offset = 0; + rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; + +out: + st->last_pos = *pos; + return rc; } static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + struct tcp_iter_state *st = seq->private; void *rc = NULL; - struct tcp_iter_state *st; if (v == SEQ_START_TOKEN) { rc = tcp_get_idx(seq, 0); goto out; } - st = seq->private; switch (st->state) { case TCP_SEQ_STATE_OPENREQ: @@ -2219,6 +2291,8 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) rc = listening_get_next(seq, v); if (!rc) { st->state = TCP_SEQ_STATE_ESTABLISHED; + st->bucket = 0; + st->offset = 0; rc = established_get_first(seq); } break; @@ -2229,6 +2303,7 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) } out: ++*pos; + st->last_pos = *pos; return rc; } @@ -2267,6 +2342,7 @@ static int tcp_seq_open(struct inode *inode, struct file *file) s = ((struct seq_file *)file->private_data)->private; s->family = afinfo->family; + s->last_pos = 0; return 0; } -- cgit v1.2.3 From 66018506e15bea62de4eefc3298f170b4bfcf5ef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 7 Jun 2010 03:12:08 +0000 Subject: ip: Router Alert RCU conversion Straightforward conversion to RCU. One rwlock becomes a spinlock, and is static. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- net/ipv4/ip_input.c | 11 +++-------- net/ipv4/ip_sockglue.c | 23 ++++++++++++++--------- 3 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 452f229c380a..9982c97f0bdc 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -62,10 +62,10 @@ struct ip_ra_chain { struct ip_ra_chain *next; struct sock *sk; void (*destructor)(struct sock *); + struct rcu_head rcu; }; extern struct ip_ra_chain *ip_ra_chain; -extern rwlock_t ip_ra_lock; /* IP flags. */ #define IP_CE 0x8000 /* Flag: "Congestion" */ diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index d52c9da644cf..d274078b1665 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -146,7 +146,7 @@ #include /* - * Process Router Attention IP option + * Process Router Attention IP option (RFC 2113) */ int ip_call_ra_chain(struct sk_buff *skb) { @@ -155,8 +155,7 @@ int ip_call_ra_chain(struct sk_buff *skb) struct sock *last = NULL; struct net_device *dev = skb->dev; - read_lock(&ip_ra_lock); - for (ra = ip_ra_chain; ra; ra = ra->next) { + for (ra = rcu_dereference(ip_ra_chain); ra; ra = rcu_dereference(ra->next)) { struct sock *sk = ra->sk; /* If socket is bound to an interface, only report @@ -167,10 +166,8 @@ int ip_call_ra_chain(struct sk_buff *skb) sk->sk_bound_dev_if == dev->ifindex) && net_eq(sock_net(sk), dev_net(dev))) { if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { - if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) { - read_unlock(&ip_ra_lock); + if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) return 1; - } } if (last) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -183,10 +180,8 @@ int ip_call_ra_chain(struct sk_buff *skb) if (last) { raw_rcv(last, skb); - read_unlock(&ip_ra_lock); return 1; } - read_unlock(&ip_ra_lock); return 0; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ce231780a2b1..08b9519a24f4 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -239,7 +239,12 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) sent to multicast group to reach destination designated router. */ struct ip_ra_chain *ip_ra_chain; -DEFINE_RWLOCK(ip_ra_lock); +static DEFINE_SPINLOCK(ip_ra_lock); + +static void ip_ra_free_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_ra_chain, rcu)); +} int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)) @@ -251,35 +256,35 @@ int ip_ra_control(struct sock *sk, unsigned char on, new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; - write_lock_bh(&ip_ra_lock); + spin_lock_bh(&ip_ra_lock); for (rap = &ip_ra_chain; (ra = *rap) != NULL; rap = &ra->next) { if (ra->sk == sk) { if (on) { - write_unlock_bh(&ip_ra_lock); + spin_unlock_bh(&ip_ra_lock); kfree(new_ra); return -EADDRINUSE; } - *rap = ra->next; - write_unlock_bh(&ip_ra_lock); + rcu_assign_pointer(*rap, ra->next); + spin_unlock_bh(&ip_ra_lock); if (ra->destructor) ra->destructor(sk); sock_put(sk); - kfree(ra); + call_rcu(&ra->rcu, ip_ra_free_rcu); return 0; } } if (new_ra == NULL) { - write_unlock_bh(&ip_ra_lock); + spin_unlock_bh(&ip_ra_lock); return -ENOBUFS; } new_ra->sk = sk; new_ra->destructor = destructor; new_ra->next = ra; - *rap = new_ra; + rcu_assign_pointer(*rap, new_ra); sock_hold(sk); - write_unlock_bh(&ip_ra_lock); + spin_unlock_bh(&ip_ra_lock); return 0; } -- cgit v1.2.3 From bb69ae049fcc986fcd742eb90ca0d44a7a49c9f1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 7 Jun 2010 11:42:13 +0000 Subject: anycast: Some RCU conversions - dev_get_by_flags() changed to dev_get_by_flags_rcu() - ipv6_sock_ac_join() dont touch dev & idev refcounts - ipv6_sock_ac_drop() dont touch dev & idev refcounts - ipv6_sock_ac_close() dont touch dev & idev refcounts - ipv6_dev_ac_dec() dount touch idev refcount - ipv6_chk_acast_addr() dont touch idev refcount Signed-off-by: Eric Dumazet CC: Hideaki YOSHIFUJI Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +-- net/core/dev.c | 14 +++----- net/ipv6/anycast.c | 90 ++++++++++++++++++++++------------------------- 3 files changed, 49 insertions(+), 59 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5156b806924c..c319f28d699d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1271,8 +1271,8 @@ extern void dev_add_pack(struct packet_type *pt); extern void dev_remove_pack(struct packet_type *pt); extern void __dev_remove_pack(struct packet_type *pt); -extern struct net_device *dev_get_by_flags(struct net *net, unsigned short flags, - unsigned short mask); +extern struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags, + unsigned short mask); extern struct net_device *dev_get_by_name(struct net *net, const char *name); extern struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); extern struct net_device *__dev_get_by_name(struct net *net, const char *name); diff --git a/net/core/dev.c b/net/core/dev.c index c8d127718ff1..6f330cee79a6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -803,35 +803,31 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) EXPORT_SYMBOL(dev_getfirstbyhwtype); /** - * dev_get_by_flags - find any device with given flags + * dev_get_by_flags_rcu - find any device with given flags * @net: the applicable net namespace * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. Returns NULL if a device - * is not found or a pointer to the device. The device returned has - * had a reference added and the pointer is safe until the user calls - * dev_put to indicate they have finished with it. + * is not found or a pointer to the device. Must be called inside + * rcu_read_lock(), and result refcount is unchanged. */ -struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags, +struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags, unsigned short mask) { struct net_device *dev, *ret; ret = NULL; - rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { - dev_hold(dev); ret = dev; break; } } - rcu_read_unlock(); return ret; } -EXPORT_SYMBOL(dev_get_by_flags); +EXPORT_SYMBOL(dev_get_by_flags_rcu); /** * dev_valid_name - check if name is okay for network device diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index b5b07054508a..f058fbd808c8 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -77,41 +77,40 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr) pac->acl_next = NULL; ipv6_addr_copy(&pac->acl_addr, addr); + rcu_read_lock(); if (ifindex == 0) { struct rt6_info *rt; rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { dev = rt->rt6i_dev; - dev_hold(dev); dst_release(&rt->u.dst); } else if (ishost) { err = -EADDRNOTAVAIL; - goto out_free_pac; + goto error; } else { /* router, no matching interface: just pick one */ - - dev = dev_get_by_flags(net, IFF_UP, IFF_UP|IFF_LOOPBACK); + dev = dev_get_by_flags_rcu(net, IFF_UP, + IFF_UP | IFF_LOOPBACK); } } else - dev = dev_get_by_index(net, ifindex); + dev = dev_get_by_index_rcu(net, ifindex); if (dev == NULL) { err = -ENODEV; - goto out_free_pac; + goto error; } - idev = in6_dev_get(dev); + idev = __in6_dev_get(dev); if (!idev) { if (ifindex) err = -ENODEV; else err = -EADDRNOTAVAIL; - goto out_dev_put; + goto error; } /* reset ishost, now that we have a specific device */ ishost = !idev->cnf.forwarding; - in6_dev_put(idev); pac->acl_ifindex = dev->ifindex; @@ -124,26 +123,22 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr) if (ishost) err = -EADDRNOTAVAIL; if (err) - goto out_dev_put; + goto error; } err = ipv6_dev_ac_inc(dev, addr); - if (err) - goto out_dev_put; - - write_lock_bh(&ipv6_sk_ac_lock); - pac->acl_next = np->ipv6_ac_list; - np->ipv6_ac_list = pac; - write_unlock_bh(&ipv6_sk_ac_lock); - - dev_put(dev); - - return 0; + if (!err) { + write_lock_bh(&ipv6_sk_ac_lock); + pac->acl_next = np->ipv6_ac_list; + np->ipv6_ac_list = pac; + write_unlock_bh(&ipv6_sk_ac_lock); + pac = NULL; + } -out_dev_put: - dev_put(dev); -out_free_pac: - sock_kfree_s(sk, pac, sizeof(*pac)); +error: + rcu_read_unlock(); + if (pac) + sock_kfree_s(sk, pac, sizeof(*pac)); return err; } @@ -176,11 +171,12 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, struct in6_addr *addr) write_unlock_bh(&ipv6_sk_ac_lock); - dev = dev_get_by_index(net, pac->acl_ifindex); - if (dev) { + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, pac->acl_ifindex); + if (dev) ipv6_dev_ac_dec(dev, &pac->acl_addr); - dev_put(dev); - } + rcu_read_unlock(); + sock_kfree_s(sk, pac, sizeof(*pac)); return 0; } @@ -199,13 +195,12 @@ void ipv6_sock_ac_close(struct sock *sk) write_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; + rcu_read_lock(); while (pac) { struct ipv6_ac_socklist *next = pac->acl_next; if (pac->acl_ifindex != prev_index) { - if (dev) - dev_put(dev); - dev = dev_get_by_index(net, pac->acl_ifindex); + dev = dev_get_by_index_rcu(net, pac->acl_ifindex); prev_index = pac->acl_ifindex; } if (dev) @@ -213,8 +208,7 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } - if (dev) - dev_put(dev); + rcu_read_unlock(); } #if 0 @@ -363,33 +357,32 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr) return 0; } +/* called with rcu_read_lock() */ static int ipv6_dev_ac_dec(struct net_device *dev, struct in6_addr *addr) { - int ret; - struct inet6_dev *idev = in6_dev_get(dev); + struct inet6_dev *idev = __in6_dev_get(dev); + if (idev == NULL) return -ENODEV; - ret = __ipv6_dev_ac_dec(idev, addr); - in6_dev_put(idev); - return ret; + return __ipv6_dev_ac_dec(idev, addr); } /* * check if the interface has this anycast address + * called with rcu_read_lock() */ static int ipv6_chk_acast_dev(struct net_device *dev, struct in6_addr *addr) { struct inet6_dev *idev; struct ifacaddr6 *aca; - idev = in6_dev_get(dev); + idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); for (aca = idev->ac_list; aca; aca = aca->aca_next) if (ipv6_addr_equal(&aca->aca_addr, addr)) break; read_unlock_bh(&idev->lock); - in6_dev_put(idev); return aca != NULL; } return 0; @@ -403,14 +396,15 @@ int ipv6_chk_acast_addr(struct net *net, struct net_device *dev, { int found = 0; - if (dev) - return ipv6_chk_acast_dev(dev, addr); rcu_read_lock(); - for_each_netdev_rcu(net, dev) - if (ipv6_chk_acast_dev(dev, addr)) { - found = 1; - break; - } + if (dev) + found = ipv6_chk_acast_dev(dev, addr); + else + for_each_netdev_rcu(net, dev) + if (ipv6_chk_acast_dev(dev, addr)) { + found = 1; + break; + } rcu_read_unlock(); return found; } -- cgit v1.2.3 From 339bb99e4a8ba1f8960eed21d50be808b35ad22a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Jun 2010 14:11:19 +0200 Subject: netfilter: xt_rateest: Better struct xt_rateest layout We currently dirty two cache lines in struct xt_rateest, this hurts SMP performance. This patch moves lock/bstats/rstats at beginning of structure so that they share a single cache line. Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- include/net/netfilter/xt_rateest.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h index ddbf37e19616..b1d780e21ce3 100644 --- a/include/net/netfilter/xt_rateest.h +++ b/include/net/netfilter/xt_rateest.h @@ -2,13 +2,17 @@ #define _XT_RATEEST_H struct xt_rateest { + /* keep lock and bstats on same cache line to speedup xt_rateest_tg() */ + struct gnet_stats_basic_packed bstats; + spinlock_t lock; + /* keep rstats and lock on same cache line to speedup xt_rateest_mt() */ + struct gnet_stats_rate_est rstats; + + /* following fields not accessed in hot path */ struct hlist_node list; char name[IFNAMSIZ]; unsigned int refcnt; - spinlock_t lock; struct gnet_estimator params; - struct gnet_stats_rate_est rstats; - struct gnet_stats_basic_packed bstats; }; extern struct xt_rateest *xt_rateest_lookup(const char *name); -- cgit v1.2.3 From abe37c4b84502d6931e04e94c9c2c45b4da8c889 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 7 Jun 2010 11:12:27 +0200 Subject: wireless: fix kernel-doc Fix a whole bunch of kernel-doc warnings and errors that crop up when running it on mac80211 and cfg80211; the latter isn't normally done so lots of bit-rot happened. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 117 +++++++++++++++++++++++++++++++++++++------------ include/net/mac80211.h | 4 +- 2 files changed, 90 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0c3c214772e7..22ab9d88cf4a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -37,6 +37,7 @@ * * @IEEE80211_BAND_2GHZ: 2.4GHz ISM band * @IEEE80211_BAND_5GHZ: around 5GHz band (4.9-5.7) + * @IEEE80211_NUM_BANDS: number of defined bands */ enum ieee80211_band { IEEE80211_BAND_2GHZ = NL80211_BAND_2GHZ, @@ -188,6 +189,7 @@ struct ieee80211_sta_ht_cap { * in this band. Must be sorted to give a valid "supported * rates" IE, i.e. CCK rates first, then OFDM. * @n_bitrates: Number of bitrates in @bitrates + * @ht_cap: HT capabilities in this band */ struct ieee80211_supported_band { struct ieee80211_channel *channels; @@ -225,6 +227,7 @@ struct vif_params { * @seq: sequence counter (IV/PN) for TKIP and CCMP keys, only used * with the get_key() callback, must be in little endian, * length given by @seq_len. + * @seq_len: length of @seq. */ struct key_params { u8 *key; @@ -237,6 +240,8 @@ struct key_params { /** * enum survey_info_flags - survey information flags * + * @SURVEY_INFO_NOISE_DBM: noise (in dBm) was filled in + * * Used by the driver to indicate which info in &struct survey_info * it has filled in during the get_survey(). */ @@ -247,13 +252,13 @@ enum survey_info_flags { /** * struct survey_info - channel survey response * - * Used by dump_survey() to report back per-channel survey information. - * * @channel: the channel this survey record reports, mandatory * @filled: bitflag of flags from &enum survey_info_flags * @noise: channel noise in dBm. This and all following fields are * optional * + * Used by dump_survey() to report back per-channel survey information. + * * This structure can later be expanded with things like * channel duty cycle etc. */ @@ -288,7 +293,7 @@ struct beacon_parameters { * * @PLINK_ACTION_INVALID: action 0 is reserved * @PLINK_ACTION_OPEN: start mesh peer link establishment - * @PLINK_ACTION_BLOCL: block traffic from this mesh peer + * @PLINK_ACTION_BLOCK: block traffic from this mesh peer */ enum plink_actions { PLINK_ACTION_INVALID, @@ -311,6 +316,8 @@ enum plink_actions { * (bitmask of BIT(NL80211_STA_FLAG_...)) * @listen_interval: listen interval or -1 for no change * @aid: AID or zero for no change + * @plink_action: plink action to take + * @ht_capa: HT capabilities of station */ struct station_parameters { u8 *supported_rates; @@ -448,13 +455,13 @@ enum monitor_flags { * Used by the driver to indicate which info in &struct mpath_info it has filled * in during get_station() or dump_station(). * - * MPATH_INFO_FRAME_QLEN: @frame_qlen filled - * MPATH_INFO_SN: @sn filled - * MPATH_INFO_METRIC: @metric filled - * MPATH_INFO_EXPTIME: @exptime filled - * MPATH_INFO_DISCOVERY_TIMEOUT: @discovery_timeout filled - * MPATH_INFO_DISCOVERY_RETRIES: @discovery_retries filled - * MPATH_INFO_FLAGS: @flags filled + * @MPATH_INFO_FRAME_QLEN: @frame_qlen filled + * @MPATH_INFO_SN: @sn filled + * @MPATH_INFO_METRIC: @metric filled + * @MPATH_INFO_EXPTIME: @exptime filled + * @MPATH_INFO_DISCOVERY_TIMEOUT: @discovery_timeout filled + * @MPATH_INFO_DISCOVERY_RETRIES: @discovery_retries filled + * @MPATH_INFO_FLAGS: @flags filled */ enum mpath_info_flags { MPATH_INFO_FRAME_QLEN = BIT(0), @@ -587,6 +594,7 @@ struct cfg80211_ssid { * @ie_len: length of ie in octets * @wiphy: the wiphy this was for * @dev: the interface + * @aborted: (internal) scan request was notified as aborted */ struct cfg80211_scan_request { struct cfg80211_ssid *ssids; @@ -623,6 +631,7 @@ enum cfg80211_signal_type { * This structure describes a BSS (which may also be a mesh network) * for use in scan results and similar. * + * @channel: channel this BSS is on * @bssid: BSSID of the BSS * @tsf: timestamp of last received update * @beacon_interval: the beacon interval as from the frame @@ -826,8 +835,8 @@ struct cfg80211_ibss_params { * @ssid: SSID * @ssid_len: Length of ssid in octets * @auth_type: Authentication type (algorithm) - * @assoc_ie: IEs for association request - * @assoc_ie_len: Length of assoc_ie in octets + * @ie: IEs for association request + * @ie_len: Length of assoc_ie in octets * @privacy: indicates whether privacy-enabled APs should be used * @crypto: crypto settings * @key_len: length of WEP key for shared key authentication @@ -850,10 +859,11 @@ struct cfg80211_connect_params { /** * enum wiphy_params_flags - set_wiphy_params bitfield values - * WIPHY_PARAM_RETRY_SHORT: wiphy->retry_short has changed - * WIPHY_PARAM_RETRY_LONG: wiphy->retry_long has changed - * WIPHY_PARAM_FRAG_THRESHOLD: wiphy->frag_threshold has changed - * WIPHY_PARAM_RTS_THRESHOLD: wiphy->rts_threshold has changed + * @WIPHY_PARAM_RETRY_SHORT: wiphy->retry_short has changed + * @WIPHY_PARAM_RETRY_LONG: wiphy->retry_long has changed + * @WIPHY_PARAM_FRAG_THRESHOLD: wiphy->frag_threshold has changed + * @WIPHY_PARAM_RTS_THRESHOLD: wiphy->rts_threshold has changed + * @WIPHY_PARAM_COVERAGE_CLASS: coverage class changed */ enum wiphy_params_flags { WIPHY_PARAM_RETRY_SHORT = 1 << 0, @@ -949,10 +959,16 @@ struct cfg80211_pmksa { * @del_beacon: Remove beacon configuration and stop sending the beacon. * * @add_station: Add a new station. - * * @del_station: Remove a station; @mac may be NULL to remove all stations. - * * @change_station: Modify a given station. + * @get_station: get station information for the station identified by @mac + * @dump_station: dump station callback -- resume dump at index @idx + * + * @add_mpath: add a fixed mesh path + * @del_mpath: delete a given mesh path + * @change_mpath: change a given mesh path + * @get_mpath: get a mesh path for the given parameters + * @dump_mpath: dump mesh path callback -- resume dump at index @idx * * @get_mesh_params: Put the current mesh parameters into *params * @@ -960,8 +976,6 @@ struct cfg80211_pmksa { * The mask is a bitfield which tells us which parameters to * set, and which to leave alone. * - * @set_mesh_cfg: set mesh parameters (by now, just mesh id) - * * @change_bss: Modify parameters for a given BSS. * * @set_txq_params: Set TX queue parameters @@ -1002,6 +1016,8 @@ struct cfg80211_pmksa { * @get_tx_power: store the current TX power into the dbm variable; * return 0 if successful * + * @set_wds_peer: set the WDS peer for a WDS interface + * * @rfkill_poll: polls the hw rfkill line, use cfg80211 reporting * functions to adjust rfkill hw state * @@ -1019,6 +1035,8 @@ struct cfg80211_pmksa { * * @testmode_cmd: run a test mode command * + * @set_bitrate_mask: set the bitrate mask configuration + * * @set_pmksa: Cache a PMKID for a BSSID. This is mostly useful for fullmac * devices running firmwares capable of generating the (re) association * RSN IE. It allows for faster roaming between WPA2 BSSIDs. @@ -1231,8 +1249,6 @@ struct mac_address { /** * struct wiphy - wireless hardware description - * @idx: the wiphy index assigned to this item - * @class_dev: the class device representing /sys/class/ieee80211/ * @reg_notifier: the driver's regulatory notification callback * @regd: the driver's regulatory domain, if one was requested via * the regulatory_hint() API. This can be used by the driver @@ -1246,7 +1262,7 @@ struct mac_address { * @frag_threshold: Fragmentation threshold (dot11FragmentationThreshold); * -1 = fragmentation disabled, only odd values >= 256 used * @rts_threshold: RTS threshold (dot11RTSThreshold); -1 = RTS/CTS disabled - * @net: the network namespace this wiphy currently lives in + * @_net: the network namespace this wiphy currently lives in * @perm_addr: permanent MAC address of this device * @addr_mask: If the device supports multiple MAC addresses by masking, * set this to a mask with variable bits set to 1, e.g. if the last @@ -1259,6 +1275,28 @@ struct mac_address { * by default for perm_addr. In this case, the mask should be set to * all-zeroes. In this case it is assumed that the device can handle * the same number of arbitrary MAC addresses. + * @debugfsdir: debugfs directory used for this wiphy, will be renamed + * automatically on wiphy renames + * @dev: (virtual) struct device for this wiphy + * @wext: wireless extension handlers + * @priv: driver private data (sized according to wiphy_new() parameter) + * @interface_modes: bitmask of interfaces types valid for this wiphy, + * must be set by driver + * @flags: wiphy flags, see &enum wiphy_flags + * @bss_priv_size: each BSS struct has private data allocated with it, + * this variable determines its size + * @max_scan_ssids: maximum number of SSIDs the device can scan for in + * any given scan + * @max_scan_ie_len: maximum length of user-controlled IEs device can + * add to probe request frames transmitted during a scan, must not + * include fixed IEs like supported rates + * @coverage_class: current coverage class + * @fw_version: firmware version for ethtool reporting + * @hw_version: hardware version for ethtool reporting + * @max_num_pmkids: maximum number of PMKIDs supported by device + * @privid: a pointer that drivers can use to identify if an arbitrary + * wiphy is theirs, e.g. in global notifiers + * @bands: information about bands/channels supported by this device */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -1472,13 +1510,14 @@ struct cfg80211_cached_keys; * @ssid: (private) Used by the internal configuration code * @ssid_len: (private) Used by the internal configuration code * @wext: (private) Used by the internal wireless extensions compat code - * @wext_bssid: (private) Used by the internal wireless extensions compat code * @use_4addr: indicates 4addr mode is used on this interface, must be * set by driver (if supported) on add_interface BEFORE registering the * netdev and may otherwise be used by driver read-only, will be update * by cfg80211 on change_interface * @action_registrations: list of registrations for action frames * @action_registrations_lock: lock for the list + * @mtx: mutex used to lock data in this struct + * @cleanup_work: work struct used for cleanup that can't be done directly */ struct wireless_dev { struct wiphy *wiphy; @@ -1552,11 +1591,13 @@ static inline void *wdev_priv(struct wireless_dev *wdev) /** * ieee80211_channel_to_frequency - convert channel number to frequency + * @chan: channel number */ extern int ieee80211_channel_to_frequency(int chan); /** * ieee80211_frequency_to_channel - convert frequency to channel number + * @freq: center frequency */ extern int ieee80211_frequency_to_channel(int freq); @@ -1571,6 +1612,8 @@ extern struct ieee80211_channel *__ieee80211_get_channel(struct wiphy *wiphy, int freq); /** * ieee80211_get_channel - get channel struct from wiphy for specified frequency + * @wiphy: the struct wiphy to get the channel for + * @freq: the center frequency of the channel */ static inline struct ieee80211_channel * ieee80211_get_channel(struct wiphy *wiphy, int freq) @@ -1631,9 +1674,6 @@ struct ieee80211_radiotap_vendor_namespaces { * @is_radiotap_ns: indicates whether the current namespace is the default * radiotap namespace or not * - * @overrides: override standard radiotap fields - * @n_overrides: number of overrides - * * @_rtheader: pointer to the radiotap header we are walking through * @_max_length: length of radiotap header in cpu byte ordering * @_arg_index: next argument index @@ -1949,10 +1989,12 @@ int cfg80211_wext_giwap(struct net_device *dev, void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted); /** - * cfg80211_inform_bss - inform cfg80211 of a new BSS + * cfg80211_inform_bss_frame - inform cfg80211 of a received BSS frame * * @wiphy: the wiphy reporting the BSS - * @bss: the found BSS + * @channel: The channel the frame was received on + * @mgmt: the management frame (probe response or beacon) + * @len: length of the management frame * @signal: the signal strength, type depends on the wiphy's signal_type * @gfp: context flags * @@ -1965,6 +2007,23 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, s32 signal, gfp_t gfp); +/** + * cfg80211_inform_bss - inform cfg80211 of a new BSS + * + * @wiphy: the wiphy reporting the BSS + * @channel: The channel the frame was received on + * @bssid: the BSSID of the BSS + * @timestamp: the TSF timestamp sent by the peer + * @capability: the capability field sent by the peer + * @beacon_interval: the beacon interval announced by the peer + * @ie: additional IEs sent by the peer + * @ielen: length of the additional IEs + * @signal: the signal strength, type depends on the wiphy's signal_type + * @gfp: context flags + * + * This informs cfg80211 that BSS information was found and + * the BSS should be updated/added. + */ struct cfg80211_bss* cfg80211_inform_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e3c1d4794003..abb3b1a9ddc9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -313,9 +313,10 @@ enum mac80211_tx_control_flags { IEEE80211_TX_INTFL_NL80211_FRAME_TX = BIT(21), IEEE80211_TX_CTL_LDPC = BIT(22), IEEE80211_TX_CTL_STBC = BIT(23) | BIT(24), -#define IEEE80211_TX_CTL_STBC_SHIFT 23 }; +#define IEEE80211_TX_CTL_STBC_SHIFT 23 + /** * enum mac80211_rate_control_flags - per-rate flags set by the * Rate Control algorithm. @@ -813,7 +814,6 @@ enum ieee80211_key_flags { * encrypted in hardware. * @alg: The key algorithm. * @flags: key flags, see &enum ieee80211_key_flags. - * @ap_addr: AP's MAC address * @keyidx: the key index (0-3) * @keylen: key material length * @key: key material. For ALG_TKIP the key is encoded as a 256-bit (32 byte) -- cgit v1.2.3 From 5bfddbd46a95c978f4d3c992339cbdf4f4b790a3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Jun 2010 16:09:52 +0200 Subject: netfilter: nf_conntrack: IPS_UNTRACKED bit NOTRACK makes all cpus share a cache line on nf_conntrack_untracked twice per packet. This is bad for performance. __read_mostly annotation is also a bad choice. This patch introduces IPS_UNTRACKED bit so that we can use later a per_cpu untrack structure more easily. A new helper, nf_ct_untracked_get() returns a pointer to nf_conntrack_untracked. Another one, nf_ct_untracked_status_or() is used by nf_nat_init() to add IPS_NAT_DONE_MASK bits to untracked status. nf_ct_is_untracked() prototype is changed to work on a nf_conn pointer. Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_common.h | 4 ++++ include/net/netfilter/nf_conntrack.h | 12 +++++++++--- include/net/netfilter/nf_conntrack_core.h | 2 +- net/ipv4/netfilter/nf_nat_core.c | 2 +- net/ipv4/netfilter/nf_nat_standalone.c | 2 +- net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 2 +- net/netfilter/nf_conntrack_core.c | 11 ++++++++--- net/netfilter/nf_conntrack_netlink.c | 2 +- net/netfilter/xt_CT.c | 4 ++-- net/netfilter/xt_NOTRACK.c | 2 +- net/netfilter/xt_TEE.c | 4 ++-- net/netfilter/xt_cluster.c | 2 +- net/netfilter/xt_conntrack.c | 11 ++++++----- net/netfilter/xt_socket.c | 2 +- net/netfilter/xt_state.c | 14 ++++++++------ 15 files changed, 47 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 14e6d32002c4..1afd18c855ec 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -76,6 +76,10 @@ enum ip_conntrack_status { /* Conntrack is a template */ IPS_TEMPLATE_BIT = 11, IPS_TEMPLATE = (1 << IPS_TEMPLATE_BIT), + + /* Conntrack is a fake untracked entry */ + IPS_UNTRACKED_BIT = 12, + IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT), }; /* Connection tracking event types */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index bde095f7e845..3bc38c70bbbe 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -261,7 +261,13 @@ extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, u32 seq); /* Fake conntrack entry for untracked connections */ -extern struct nf_conn nf_conntrack_untracked; +static inline struct nf_conn *nf_ct_untracked_get(void) +{ + extern struct nf_conn nf_conntrack_untracked; + + return &nf_conntrack_untracked; +} +extern void nf_ct_untracked_status_or(unsigned long bits); /* Iterate over all conntracks: if iter returns true, it's deleted. */ extern void @@ -289,9 +295,9 @@ static inline int nf_ct_is_dying(struct nf_conn *ct) return test_bit(IPS_DYING_BIT, &ct->status); } -static inline int nf_ct_is_untracked(const struct sk_buff *skb) +static inline int nf_ct_is_untracked(const struct nf_conn *ct) { - return (skb->nfct == &nf_conntrack_untracked.ct_general); + return test_bit(IPS_UNTRACKED_BIT, &ct->status); } extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 3d7524fba194..aced085132e7 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -60,7 +60,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) struct nf_conn *ct = (struct nf_conn *)skb->nfct; int ret = NF_ACCEPT; - if (ct && ct != &nf_conntrack_untracked) { + if (ct && !nf_ct_is_untracked(ct)) { if (!nf_ct_is_confirmed(ct)) ret = __nf_conntrack_confirm(skb); if (likely(ret == NF_ACCEPT)) diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 4f8bddb760c9..c7719b283ada 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -742,7 +742,7 @@ static int __init nf_nat_init(void) spin_unlock_bh(&nf_nat_lock); /* Initialize fake conntrack so that NAT will skip it */ - nf_conntrack_untracked.status |= IPS_NAT_DONE_MASK; + nf_ct_untracked_status_or(IPS_NAT_DONE_MASK); l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET); diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index beb25819c9c9..6723c682250d 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -98,7 +98,7 @@ nf_nat_fn(unsigned int hooknum, return NF_ACCEPT; /* Don't try to NAT if this packet is not conntracked */ - if (ct == &nf_conntrack_untracked) + if (nf_ct_is_untracked(ct)) return NF_ACCEPT; nat = nfct_nat(ct); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 9be81776415e..1df3c8b6bf47 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -208,7 +208,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl, type = icmp6h->icmp6_type - 130; if (type >= 0 && type < sizeof(noct_valid_new) && noct_valid_new[type]) { - skb->nfct = &nf_conntrack_untracked.ct_general; + skb->nfct = &nf_ct_untracked_get()->ct_general; skb->nfctinfo = IP_CT_NEW; nf_conntrack_get(skb->nfct); return NF_ACCEPT; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index eeeb8bc73982..6c1da212380d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -62,7 +62,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_max); -struct nf_conn nf_conntrack_untracked __read_mostly; +struct nf_conn nf_conntrack_untracked; EXPORT_SYMBOL_GPL(nf_conntrack_untracked); static int nf_conntrack_hash_rnd_initted; @@ -1321,6 +1321,12 @@ EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize); module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, &nf_conntrack_htable_size, 0600); +void nf_ct_untracked_status_or(unsigned long bits) +{ + nf_conntrack_untracked.status |= bits; +} +EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or); + static int nf_conntrack_init_init_net(void) { int max_factor = 8; @@ -1368,8 +1374,7 @@ static int nf_conntrack_init_init_net(void) #endif atomic_set(&nf_conntrack_untracked.ct_general.use, 1); /* - and look it like as a confirmed connection */ - set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status); - + nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); return 0; #ifdef CONFIG_NF_CONNTRACK_ZONES diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c42ff6aa441d..5bae1cd15eea 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -480,7 +480,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) int err; /* ignore our fake conntrack entry */ - if (ct == &nf_conntrack_untracked) + if (nf_ct_is_untracked(ct)) return 0; if (events & (1 << IPCT_DESTROY)) { diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 562bf3266e04..0cb6053f02fd 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -67,7 +67,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par) return -EINVAL; if (info->flags & XT_CT_NOTRACK) { - ct = &nf_conntrack_untracked; + ct = nf_ct_untracked_get(); atomic_inc(&ct->ct_general.use); goto out; } @@ -132,7 +132,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par) struct nf_conn *ct = info->ct; struct nf_conn_help *help; - if (ct != &nf_conntrack_untracked) { + if (!nf_ct_is_untracked(ct)) { help = nfct_help(ct); if (help) module_put(help->helper->me); diff --git a/net/netfilter/xt_NOTRACK.c b/net/netfilter/xt_NOTRACK.c index 512b9123252f..9d782181b6c8 100644 --- a/net/netfilter/xt_NOTRACK.c +++ b/net/netfilter/xt_NOTRACK.c @@ -23,7 +23,7 @@ notrack_tg(struct sk_buff *skb, const struct xt_action_param *par) If there is a real ct entry correspondig to this packet, it'll hang aroun till timing out. We don't deal with it for performance reasons. JK */ - skb->nfct = &nf_conntrack_untracked.ct_general; + skb->nfct = &nf_ct_untracked_get()->ct_general; skb->nfctinfo = IP_CT_NEW; nf_conntrack_get(skb->nfct); diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 859d9fd429c8..7a118267c4c4 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -104,7 +104,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) #ifdef WITH_CONNTRACK /* Avoid counting cloned packets towards the original connection. */ nf_conntrack_put(skb->nfct); - skb->nfct = &nf_conntrack_untracked.ct_general; + skb->nfct = &nf_ct_untracked_get()->ct_general; skb->nfctinfo = IP_CT_NEW; nf_conntrack_get(skb->nfct); #endif @@ -177,7 +177,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) #ifdef WITH_CONNTRACK nf_conntrack_put(skb->nfct); - skb->nfct = &nf_conntrack_untracked.ct_general; + skb->nfct = &nf_ct_untracked_get()->ct_general; skb->nfctinfo = IP_CT_NEW; nf_conntrack_get(skb->nfct); #endif diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index 30b95a1c1c89..f4af1bfafb1c 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -120,7 +120,7 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ct == NULL) return false; - if (ct == &nf_conntrack_untracked) + if (nf_ct_is_untracked(ct)) return false; if (ct->master) diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 39681f10291c..e536710ad916 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -123,11 +123,12 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par, ct = nf_ct_get(skb, &ctinfo); - if (ct == &nf_conntrack_untracked) - statebit = XT_CONNTRACK_STATE_UNTRACKED; - else if (ct != NULL) - statebit = XT_CONNTRACK_STATE_BIT(ctinfo); - else + if (ct) { + if (nf_ct_is_untracked(ct)) + statebit = XT_CONNTRACK_STATE_UNTRACKED; + else + statebit = XT_CONNTRACK_STATE_BIT(ctinfo); + } else statebit = XT_CONNTRACK_STATE_INVALID; if (info->match_flags & XT_CONNTRACK_STATE) { diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 3d54c236a1ba..1ca89908cbad 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -127,7 +127,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, * reply packet of an established SNAT-ted connection. */ ct = nf_ct_get(skb, &ctinfo); - if (ct && (ct != &nf_conntrack_untracked) && + if (ct && !nf_ct_is_untracked(ct) && ((iph->protocol != IPPROTO_ICMP && ctinfo == IP_CT_IS_REPLY + IP_CT_ESTABLISHED) || (iph->protocol == IPPROTO_ICMP && diff --git a/net/netfilter/xt_state.c b/net/netfilter/xt_state.c index e12e053d3782..a507922d80cd 100644 --- a/net/netfilter/xt_state.c +++ b/net/netfilter/xt_state.c @@ -26,14 +26,16 @@ state_mt(const struct sk_buff *skb, struct xt_action_param *par) const struct xt_state_info *sinfo = par->matchinfo; enum ip_conntrack_info ctinfo; unsigned int statebit; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - if (nf_ct_is_untracked(skb)) - statebit = XT_STATE_UNTRACKED; - else if (!nf_ct_get(skb, &ctinfo)) + if (!ct) statebit = XT_STATE_INVALID; - else - statebit = XT_STATE_BIT(ctinfo); - + else { + if (nf_ct_is_untracked(ct)) + statebit = XT_STATE_UNTRACKED; + else + statebit = XT_STATE_BIT(ctinfo); + } return (sinfo->statemask & statebit); } -- cgit v1.2.3 From b3c5163fe0193a74016dba1bb22491e0d1e9aaa4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Jun 2010 14:43:38 +0200 Subject: netfilter: nf_conntrack: per_cpu untracking NOTRACK makes all cpus share a cache line on nf_conntrack_untracked twice per packet, slowing down performance. This patch converts it to a per_cpu variable. Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- include/net/netfilter/nf_conntrack.h | 5 ++--- net/netfilter/nf_conntrack_core.c | 36 ++++++++++++++++++++++++++---------- 2 files changed, 28 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 3bc38c70bbbe..84a4b6fec99d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -261,11 +261,10 @@ extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, u32 seq); /* Fake conntrack entry for untracked connections */ +DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked); static inline struct nf_conn *nf_ct_untracked_get(void) { - extern struct nf_conn nf_conntrack_untracked; - - return &nf_conntrack_untracked; + return &__raw_get_cpu_var(nf_conntrack_untracked); } extern void nf_ct_untracked_status_or(unsigned long bits); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 6c1da212380d..9c661413b826 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -62,8 +62,8 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_max); -struct nf_conn nf_conntrack_untracked; -EXPORT_SYMBOL_GPL(nf_conntrack_untracked); +DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked); +EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked); static int nf_conntrack_hash_rnd_initted; static unsigned int nf_conntrack_hash_rnd; @@ -1183,10 +1183,21 @@ static void nf_ct_release_dying_list(struct net *net) spin_unlock_bh(&nf_conntrack_lock); } +static int untrack_refs(void) +{ + int cnt = 0, cpu; + + for_each_possible_cpu(cpu) { + struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu); + + cnt += atomic_read(&ct->ct_general.use) - 1; + } + return cnt; +} + static void nf_conntrack_cleanup_init_net(void) { - /* wait until all references to nf_conntrack_untracked are dropped */ - while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1) + while (untrack_refs() > 0) schedule(); nf_conntrack_helper_fini(); @@ -1323,14 +1334,17 @@ module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, void nf_ct_untracked_status_or(unsigned long bits) { - nf_conntrack_untracked.status |= bits; + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(nf_conntrack_untracked, cpu).status |= bits; } EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or); static int nf_conntrack_init_init_net(void) { int max_factor = 8; - int ret; + int ret, cpu; /* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB * machine has 512 buckets. >= 1GB machines have 16384 buckets. */ @@ -1369,10 +1383,12 @@ static int nf_conntrack_init_init_net(void) goto err_extend; #endif /* Set up fake conntrack: to never be deleted, not in any hashes */ -#ifdef CONFIG_NET_NS - nf_conntrack_untracked.ct_net = &init_net; -#endif - atomic_set(&nf_conntrack_untracked.ct_general.use, 1); + for_each_possible_cpu(cpu) { + struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu); + + write_pnet(&ct->ct_net, &init_net); + atomic_set(&ct->ct_general.use, 1); + } /* - and look it like as a confirmed connection */ nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); return 0; -- cgit v1.2.3 From 88e7594a9775e54dcd421cb246406dce62e48bee Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 7 Jun 2010 03:27:39 +0000 Subject: phonet: use call_rcu for phonet device free Use call_rcu rather than synchronize_rcu. Signed-off-by: Jiri Pirko Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/phonet/pn_dev.h | 1 + net/phonet/pn_dev.c | 15 +++++++++++---- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h index d7b989ca3d63..2d16783d5e20 100644 --- a/include/net/phonet/pn_dev.h +++ b/include/net/phonet/pn_dev.h @@ -34,6 +34,7 @@ struct phonet_device { struct list_head list; struct net_device *netdev; DECLARE_BITMAP(addrs, 64); + struct rcu_head rcu; }; int phonet_device_init(void); diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index c33da6576942..b18e48fae975 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -162,6 +162,14 @@ int phonet_address_add(struct net_device *dev, u8 addr) return err; } +static void phonet_device_rcu_free(struct rcu_head *head) +{ + struct phonet_device *pnd; + + pnd = container_of(head, struct phonet_device, rcu); + kfree(pnd); +} + int phonet_address_del(struct net_device *dev, u8 addr) { struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); @@ -179,10 +187,9 @@ int phonet_address_del(struct net_device *dev, u8 addr) pnd = NULL; mutex_unlock(&pndevs->lock); - if (pnd) { - synchronize_rcu(); - kfree(pnd); - } + if (pnd) + call_rcu(&pnd->rcu, phonet_device_rcu_free); + return err; } -- cgit v1.2.3 From 592fcb9dfafaa02dd0edc207bf5d3a0ee7a1f8df Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Jun 2010 16:21:07 +0000 Subject: ip: ip_ra_control() rcu fix commit 66018506e15b (ip: Router Alert RCU conversion) introduced RCU lookups to ip_call_ra_chain(). It missed proper deinit phase : When ip_ra_control() deletes an ip_ra_chain, it should make sure ip_call_ra_chain() users can not start to use socket during the rcu grace period. It should also delay the sock_put() after the grace period, or we risk a premature socket freeing and corruptions, as raw sockets are not rcu protected yet. This delay avoids using expensive atomic_inc_not_zero() in ip_call_ra_chain(). Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 5 ++++- net/ipv4/ip_sockglue.c | 19 +++++++++++++++---- 2 files changed, 19 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 9982c97f0bdc..d52f01180361 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -61,7 +61,10 @@ struct ipcm_cookie { struct ip_ra_chain { struct ip_ra_chain *next; struct sock *sk; - void (*destructor)(struct sock *); + union { + void (*destructor)(struct sock *); + struct sock *saved_sk; + }; struct rcu_head rcu; }; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 08b9519a24f4..47fff528ff39 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -241,9 +241,13 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) struct ip_ra_chain *ip_ra_chain; static DEFINE_SPINLOCK(ip_ra_lock); -static void ip_ra_free_rcu(struct rcu_head *head) + +static void ip_ra_destroy_rcu(struct rcu_head *head) { - kfree(container_of(head, struct ip_ra_chain, rcu)); + struct ip_ra_chain *ra = container_of(head, struct ip_ra_chain, rcu); + + sock_put(ra->saved_sk); + kfree(ra); } int ip_ra_control(struct sock *sk, unsigned char on, @@ -264,13 +268,20 @@ int ip_ra_control(struct sock *sk, unsigned char on, kfree(new_ra); return -EADDRINUSE; } + /* dont let ip_call_ra_chain() use sk again */ + ra->sk = NULL; rcu_assign_pointer(*rap, ra->next); spin_unlock_bh(&ip_ra_lock); if (ra->destructor) ra->destructor(sk); - sock_put(sk); - call_rcu(&ra->rcu, ip_ra_free_rcu); + /* + * Delay sock_put(sk) and kfree(ra) after one rcu grace + * period. This guarantee ip_call_ra_chain() dont need + * to mess with socket refcounts. + */ + ra->saved_sk = sk; + call_rcu(&ra->rcu, ip_ra_destroy_rcu); return 0; } } -- cgit v1.2.3 From d8d1f30b95a635dbd610dcc5eb641aca8f4768cf Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Thu, 10 Jun 2010 23:31:35 -0700 Subject: net-next: remove useless union keyword remove useless union keyword in rtable, rt6_info and dn_route. Since there is only one member in a union, the union keyword isn't useful. Signed-off-by: Changli Gao Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/infiniband/core/addr.c | 2 +- drivers/infiniband/hw/cxgb3/iwch_cm.c | 4 +- drivers/infiniband/hw/cxgb4/cm.c | 4 +- drivers/infiniband/hw/nes/nes_cm.c | 2 +- drivers/net/bonding/bond_main.c | 6 +- drivers/net/cnic.c | 2 +- drivers/scsi/cxgb3i/cxgb3i_offload.c | 4 +- include/net/dn_route.h | 4 +- include/net/ip6_fib.h | 10 +- include/net/ipip.h | 2 +- include/net/route.h | 6 +- net/atm/clip.c | 2 +- net/bridge/br_device.c | 2 +- net/bridge/br_netfilter.c | 20 +- net/dccp/ipv4.c | 4 +- net/decnet/dn_route.c | 158 ++++++------ net/ethernet/eth.c | 5 +- net/ipv4/af_inet.c | 4 +- net/ipv4/arp.c | 12 +- net/ipv4/datagram.c | 2 +- net/ipv4/icmp.c | 18 +- net/ipv4/igmp.c | 10 +- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/ip_forward.c | 10 +- net/ipv4/ip_gre.c | 14 +- net/ipv4/ip_input.c | 4 +- net/ipv4/ip_output.c | 60 ++--- net/ipv4/ipip.c | 8 +- net/ipv4/ipmr.c | 8 +- net/ipv4/netfilter.c | 8 +- net/ipv4/raw.c | 16 +- net/ipv4/route.c | 420 ++++++++++++++++---------------- net/ipv4/syncookies.c | 6 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/udp.c | 4 +- net/ipv4/xfrm4_policy.c | 2 +- net/ipv6/addrconf.c | 10 +- net/ipv6/anycast.c | 6 +- net/ipv6/fib6_rules.c | 10 +- net/ipv6/ip6_fib.c | 30 +-- net/ipv6/ip6_output.c | 38 +-- net/ipv6/ip6_tunnel.c | 8 +- net/ipv6/mcast.c | 4 +- net/ipv6/ndisc.c | 8 +- net/ipv6/raw.c | 12 +- net/ipv6/route.c | 300 +++++++++++------------ net/ipv6/sit.c | 8 +- net/l2tp/l2tp_ip.c | 6 +- net/netfilter/ipvs/ip_vs_xmit.c | 86 +++---- net/netfilter/nf_conntrack_h323_main.c | 12 +- net/netfilter/nf_conntrack_netbios_ns.c | 2 +- net/netfilter/xt_TCPMSS.c | 4 +- net/netfilter/xt_TEE.c | 4 +- net/rxrpc/ar-peer.c | 4 +- net/sctp/protocol.c | 4 +- 55 files changed, 694 insertions(+), 709 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 0b926e45afe2..a5ea1bce9689 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -215,7 +215,7 @@ static int addr4_resolve(struct sockaddr_in *src_in, neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->idev->dev); if (!neigh || !(neigh->nud_state & NUD_VALID)) { - neigh_event_send(rt->u.dst.neighbour, NULL); + neigh_event_send(rt->dst.neighbour, NULL); ret = -ENODATA; if (neigh) goto release; diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c index ebfb117ba68b..abd683ea326d 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.c +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c @@ -1364,7 +1364,7 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx) __func__); goto reject; } - dst = &rt->u.dst; + dst = &rt->dst; l2t = t3_l2t_get(tdev, dst->neighbour, dst->neighbour->dev); if (!l2t) { printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n", @@ -1932,7 +1932,7 @@ int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) err = -EHOSTUNREACH; goto fail3; } - ep->dst = &rt->u.dst; + ep->dst = &rt->dst; /* get a l2t entry */ ep->l2t = t3_l2t_get(ep->com.tdev, ep->dst->neighbour, diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 30ce0a8eca09..8b693c8c25e2 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1364,7 +1364,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb) __func__); goto reject; } - dst = &rt->u.dst; + dst = &rt->dst; if (dst->neighbour->dev->flags & IFF_LOOPBACK) { pdev = ip_dev_find(&init_net, peer_ip); BUG_ON(!pdev); @@ -1938,7 +1938,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) err = -EHOSTUNREACH; goto fail3; } - ep->dst = &rt->u.dst; + ep->dst = &rt->dst; /* get a l2t entry */ if (ep->dst->neighbour->dev->flags & IFF_LOOPBACK) { diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index 986d6f32dded..d876d0435cd4 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -1146,7 +1146,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi } if ((neigh == NULL) || (!(neigh->nud_state & NUD_VALID))) - neigh_event_send(rt->u.dst.neighbour, NULL); + neigh_event_send(rt->dst.neighbour, NULL); ip_rt_put(rt); return rc; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1b19276cff12..ac4f94b7da37 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2584,7 +2584,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) /* * This target is not on a VLAN */ - if (rt->u.dst.dev == bond->dev) { + if (rt->dst.dev == bond->dev) { ip_rt_put(rt); pr_debug("basa: rtdev == bond->dev: arp_send\n"); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], @@ -2595,7 +2595,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) vlan_id = 0; list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { vlan_dev = vlan_group_get_device(bond->vlgrp, vlan->vlan_id); - if (vlan_dev == rt->u.dst.dev) { + if (vlan_dev == rt->dst.dev) { vlan_id = vlan->vlan_id; pr_debug("basa: vlan match on %s %d\n", vlan_dev->name, vlan_id); @@ -2613,7 +2613,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) if (net_ratelimit()) { pr_warning("%s: no path to arp_ip_target %pI4 via rt.dev %s\n", bond->dev->name, &fl.fl4_dst, - rt->u.dst.dev ? rt->u.dst.dev->name : "NULL"); + rt->dst.dev ? rt->dst.dev->name : "NULL"); } ip_rt_put(rt); } diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c index fe925663d39a..908d89a4fe86 100644 --- a/drivers/net/cnic.c +++ b/drivers/net/cnic.c @@ -2824,7 +2824,7 @@ static int cnic_get_v4_route(struct sockaddr_in *dst_addr, err = ip_route_output_key(&init_net, &rt, &fl); if (!err) - *dst = &rt->u.dst; + *dst = &rt->dst; return err; #else return -ENETUNREACH; diff --git a/drivers/scsi/cxgb3i/cxgb3i_offload.c b/drivers/scsi/cxgb3i/cxgb3i_offload.c index a175be9c496f..3b6a06eebf7f 100644 --- a/drivers/scsi/cxgb3i/cxgb3i_offload.c +++ b/drivers/scsi/cxgb3i/cxgb3i_offload.c @@ -1587,7 +1587,7 @@ cxgb3i_find_dev(struct net_device *dev, __be32 ipaddr) err = ip_route_output_key(dev ? dev_net(dev) : &init_net, &rt, &fl); if (!err) - return (&rt->u.dst)->dev; + return (&rt->dst)->dev; return NULL; } @@ -1649,7 +1649,7 @@ int cxgb3i_c3cn_connect(struct net_device *dev, struct s3_conn *c3cn, c3cn->saddr.sin_addr.s_addr = rt->rt_src; /* now commit destination to connection */ - c3cn->dst_cache = &rt->u.dst; + c3cn->dst_cache = &rt->dst; /* try to establish an offloaded connection */ dev = cxgb3_egress_dev(c3cn->dst_cache->dev, c3cn, 0); diff --git a/include/net/dn_route.h b/include/net/dn_route.h index 60c9f22d8694..ccadab3aa3f6 100644 --- a/include/net/dn_route.h +++ b/include/net/dn_route.h @@ -65,9 +65,7 @@ extern void dn_rt_cache_flush(int delay); * packets to the originating host. */ struct dn_route { - union { - struct dst_entry dst; - } u; + struct dst_entry dst; struct flowi fl; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 4b1dc1161c37..062a823d311c 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -84,13 +84,11 @@ struct rt6key { struct fib6_table; struct rt6_info { - union { - struct dst_entry dst; - } u; + struct dst_entry dst; -#define rt6i_dev u.dst.dev -#define rt6i_nexthop u.dst.neighbour -#define rt6i_expires u.dst.expires +#define rt6i_dev dst.dev +#define rt6i_nexthop dst.neighbour +#define rt6i_expires dst.expires /* * Tail elements of dst_entry (__refcnt etc.) diff --git a/include/net/ipip.h b/include/net/ipip.h index 11e8513d2d07..65caea8b414f 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -50,7 +50,7 @@ struct ip_tunnel_prl_entry { int pkt_len = skb->len - skb_transport_offset(skb); \ \ skb->ip_summed = CHECKSUM_NONE; \ - ip_select_ident(iph, &rt->u.dst, NULL); \ + ip_select_ident(iph, &rt->dst, NULL); \ \ err = ip_local_out(skb); \ if (likely(net_xmit_eval(err) == 0)) { \ diff --git a/include/net/route.h b/include/net/route.h index af6cf4b4c9dc..bd732d62e1c3 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -50,9 +50,7 @@ struct fib_nh; struct inet_peer; struct rtable { - union { - struct dst_entry dst; - } u; + struct dst_entry dst; /* Cache lookup keys */ struct flowi fl; @@ -144,7 +142,7 @@ extern void fib_add_ifaddr(struct in_ifaddr *); static inline void ip_rt_put(struct rtable * rt) { if (rt) - dst_release(&rt->u.dst); + dst_release(&rt->dst); } #define IPTOS_RT_MASK (IPTOS_TOS_MASK & ~3) diff --git a/net/atm/clip.c b/net/atm/clip.c index 313aba11316b..95fdd1185067 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -522,7 +522,7 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip) error = ip_route_output_key(&init_net, &rt, &fl); if (error) return error; - neigh = __neigh_lookup(&clip_tbl, &ip, rt->u.dst.dev, 1); + neigh = __neigh_lookup(&clip_tbl, &ip, rt->dst.dev, 1); ip_rt_put(rt); if (!neigh) return -ENOMEM; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index eedf2c94820e..b898364beaf5 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -127,7 +127,7 @@ static int br_change_mtu(struct net_device *dev, int new_mtu) #ifdef CONFIG_BRIDGE_NETFILTER /* remember the MTU in the rtable for PMTU */ - br->fake_rtable.u.dst.metrics[RTAX_MTU - 1] = new_mtu; + br->fake_rtable.dst.metrics[RTAX_MTU - 1] = new_mtu; #endif return 0; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 44420992f72f..0685b2558ab5 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -117,12 +117,12 @@ void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; - atomic_set(&rt->u.dst.__refcnt, 1); - rt->u.dst.dev = br->dev; - rt->u.dst.path = &rt->u.dst; - rt->u.dst.metrics[RTAX_MTU - 1] = 1500; - rt->u.dst.flags = DST_NOXFRM; - rt->u.dst.ops = &fake_dst_ops; + atomic_set(&rt->dst.__refcnt, 1); + rt->dst.dev = br->dev; + rt->dst.path = &rt->dst; + rt->dst.metrics[RTAX_MTU - 1] = 1500; + rt->dst.flags = DST_NOXFRM; + rt->dst.ops = &fake_dst_ops; } static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) @@ -244,8 +244,8 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) kfree_skb(skb); return 0; } - dst_hold(&rt->u.dst); - skb_dst_set(skb, &rt->u.dst); + dst_hold(&rt->dst); + skb_dst_set(skb, &rt->dst); skb->dev = nf_bridge->physindev; nf_bridge_update_protocol(skb); @@ -396,8 +396,8 @@ bridged_dnat: kfree_skb(skb); return 0; } - dst_hold(&rt->u.dst); - skb_dst_set(skb, &rt->u.dst); + dst_hold(&rt->dst); + skb_dst_set(skb, &rt->dst); } skb->dev = nf_bridge->physindev; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index d9b11ef8694c..d4a166f0f391 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -105,7 +105,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto failure; /* OK, now commit destination to socket. */ - sk_setup_caps(sk, &rt->u.dst); + sk_setup_caps(sk, &rt->dst); dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr, inet->inet_daddr, @@ -475,7 +475,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, return NULL; } - return &rt->u.dst; + return &rt->dst; } static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 812e6dff6067..6585ea6d1182 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -146,13 +146,13 @@ static __inline__ unsigned dn_hash(__le16 src, __le16 dst) static inline void dnrt_free(struct dn_route *rt) { - call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free); + call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); } static inline void dnrt_drop(struct dn_route *rt) { - dst_release(&rt->u.dst); - call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free); + dst_release(&rt->dst); + call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); } static void dn_dst_check_expire(unsigned long dummy) @@ -167,13 +167,13 @@ static void dn_dst_check_expire(unsigned long dummy) spin_lock(&dn_rt_hash_table[i].lock); while((rt=*rtp) != NULL) { - if (atomic_read(&rt->u.dst.__refcnt) || - (now - rt->u.dst.lastuse) < expire) { - rtp = &rt->u.dst.dn_next; + if (atomic_read(&rt->dst.__refcnt) || + (now - rt->dst.lastuse) < expire) { + rtp = &rt->dst.dn_next; continue; } - *rtp = rt->u.dst.dn_next; - rt->u.dst.dn_next = NULL; + *rtp = rt->dst.dn_next; + rt->dst.dn_next = NULL; dnrt_free(rt); } spin_unlock(&dn_rt_hash_table[i].lock); @@ -198,13 +198,13 @@ static int dn_dst_gc(struct dst_ops *ops) rtp = &dn_rt_hash_table[i].chain; while((rt=*rtp) != NULL) { - if (atomic_read(&rt->u.dst.__refcnt) || - (now - rt->u.dst.lastuse) < expire) { - rtp = &rt->u.dst.dn_next; + if (atomic_read(&rt->dst.__refcnt) || + (now - rt->dst.lastuse) < expire) { + rtp = &rt->dst.dn_next; continue; } - *rtp = rt->u.dst.dn_next; - rt->u.dst.dn_next = NULL; + *rtp = rt->dst.dn_next; + rt->dst.dn_next = NULL; dnrt_drop(rt); break; } @@ -287,25 +287,25 @@ static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route * while((rth = *rthp) != NULL) { if (compare_keys(&rth->fl, &rt->fl)) { /* Put it first */ - *rthp = rth->u.dst.dn_next; - rcu_assign_pointer(rth->u.dst.dn_next, + *rthp = rth->dst.dn_next; + rcu_assign_pointer(rth->dst.dn_next, dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth); - dst_use(&rth->u.dst, now); + dst_use(&rth->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); dnrt_drop(rt); *rp = rth; return 0; } - rthp = &rth->u.dst.dn_next; + rthp = &rth->dst.dn_next; } - rcu_assign_pointer(rt->u.dst.dn_next, dn_rt_hash_table[hash].chain); + rcu_assign_pointer(rt->dst.dn_next, dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt); - dst_use(&rt->u.dst, now); + dst_use(&rt->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); *rp = rt; return 0; @@ -323,8 +323,8 @@ static void dn_run_flush(unsigned long dummy) goto nothing_to_declare; for(; rt; rt=next) { - next = rt->u.dst.dn_next; - rt->u.dst.dn_next = NULL; + next = rt->dst.dn_next; + rt->dst.dn_next = NULL; dst_free((struct dst_entry *)rt); } @@ -743,7 +743,7 @@ static int dn_forward(struct sk_buff *skb) /* Ensure that we have enough space for headers */ rt = (struct dn_route *)skb_dst(skb); header_len = dn_db->use_long ? 21 : 6; - if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+header_len)) + if (skb_cow(skb, LL_RESERVED_SPACE(rt->dst.dev)+header_len)) goto drop; /* @@ -752,7 +752,7 @@ static int dn_forward(struct sk_buff *skb) if (++cb->hops > 30) goto drop; - skb->dev = rt->u.dst.dev; + skb->dev = rt->dst.dev; /* * If packet goes out same interface it came in on, then set @@ -792,7 +792,7 @@ static int dn_rt_bug(struct sk_buff *skb) static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) { struct dn_fib_info *fi = res->fi; - struct net_device *dev = rt->u.dst.dev; + struct net_device *dev = rt->dst.dev; struct neighbour *n; unsigned mss; @@ -800,25 +800,25 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) if (DN_FIB_RES_GW(*res) && DN_FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = DN_FIB_RES_GW(*res); - memcpy(rt->u.dst.metrics, fi->fib_metrics, - sizeof(rt->u.dst.metrics)); + memcpy(rt->dst.metrics, fi->fib_metrics, + sizeof(rt->dst.metrics)); } rt->rt_type = res->type; - if (dev != NULL && rt->u.dst.neighbour == NULL) { + if (dev != NULL && rt->dst.neighbour == NULL) { n = __neigh_lookup_errno(&dn_neigh_table, &rt->rt_gateway, dev); if (IS_ERR(n)) return PTR_ERR(n); - rt->u.dst.neighbour = n; + rt->dst.neighbour = n; } - if (dst_metric(&rt->u.dst, RTAX_MTU) == 0 || - dst_metric(&rt->u.dst, RTAX_MTU) > rt->u.dst.dev->mtu) - rt->u.dst.metrics[RTAX_MTU-1] = rt->u.dst.dev->mtu; - mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->u.dst)); - if (dst_metric(&rt->u.dst, RTAX_ADVMSS) == 0 || - dst_metric(&rt->u.dst, RTAX_ADVMSS) > mss) - rt->u.dst.metrics[RTAX_ADVMSS-1] = mss; + if (dst_metric(&rt->dst, RTAX_MTU) == 0 || + dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu) + rt->dst.metrics[RTAX_MTU-1] = rt->dst.dev->mtu; + mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->dst)); + if (dst_metric(&rt->dst, RTAX_ADVMSS) == 0 || + dst_metric(&rt->dst, RTAX_ADVMSS) > mss) + rt->dst.metrics[RTAX_ADVMSS-1] = mss; return 0; } @@ -1096,8 +1096,8 @@ make_route: if (rt == NULL) goto e_nobufs; - atomic_set(&rt->u.dst.__refcnt, 1); - rt->u.dst.flags = DST_HOST; + atomic_set(&rt->dst.__refcnt, 1); + rt->dst.flags = DST_HOST; rt->fl.fld_src = oldflp->fld_src; rt->fl.fld_dst = oldflp->fld_dst; @@ -1113,17 +1113,17 @@ make_route: rt->rt_dst_map = fl.fld_dst; rt->rt_src_map = fl.fld_src; - rt->u.dst.dev = dev_out; + rt->dst.dev = dev_out; dev_hold(dev_out); - rt->u.dst.neighbour = neigh; + rt->dst.neighbour = neigh; neigh = NULL; - rt->u.dst.lastuse = jiffies; - rt->u.dst.output = dn_output; - rt->u.dst.input = dn_rt_bug; + rt->dst.lastuse = jiffies; + rt->dst.output = dn_output; + rt->dst.input = dn_rt_bug; rt->rt_flags = flags; if (flags & RTCF_LOCAL) - rt->u.dst.input = dn_nsp_rx; + rt->dst.input = dn_nsp_rx; err = dn_rt_set_next_hop(rt, &res); if (err) @@ -1152,7 +1152,7 @@ e_nobufs: err = -ENOBUFS; goto done; e_neighbour: - dst_free(&rt->u.dst); + dst_free(&rt->dst); goto e_nobufs; } @@ -1168,15 +1168,15 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowi *fl if (!(flags & MSG_TRYHARD)) { rcu_read_lock_bh(); for (rt = rcu_dereference_bh(dn_rt_hash_table[hash].chain); rt; - rt = rcu_dereference_bh(rt->u.dst.dn_next)) { + rt = rcu_dereference_bh(rt->dst.dn_next)) { if ((flp->fld_dst == rt->fl.fld_dst) && (flp->fld_src == rt->fl.fld_src) && (flp->mark == rt->fl.mark) && (rt->fl.iif == 0) && (rt->fl.oif == flp->oif)) { - dst_use(&rt->u.dst, jiffies); + dst_use(&rt->dst, jiffies); rcu_read_unlock_bh(); - *pprt = &rt->u.dst; + *pprt = &rt->dst; return 0; } } @@ -1375,29 +1375,29 @@ make_route: rt->fl.iif = in_dev->ifindex; rt->fl.mark = fl.mark; - rt->u.dst.flags = DST_HOST; - rt->u.dst.neighbour = neigh; - rt->u.dst.dev = out_dev; - rt->u.dst.lastuse = jiffies; - rt->u.dst.output = dn_rt_bug; + rt->dst.flags = DST_HOST; + rt->dst.neighbour = neigh; + rt->dst.dev = out_dev; + rt->dst.lastuse = jiffies; + rt->dst.output = dn_rt_bug; switch(res.type) { case RTN_UNICAST: - rt->u.dst.input = dn_forward; + rt->dst.input = dn_forward; break; case RTN_LOCAL: - rt->u.dst.output = dn_output; - rt->u.dst.input = dn_nsp_rx; - rt->u.dst.dev = in_dev; + rt->dst.output = dn_output; + rt->dst.input = dn_nsp_rx; + rt->dst.dev = in_dev; flags |= RTCF_LOCAL; break; default: case RTN_UNREACHABLE: case RTN_BLACKHOLE: - rt->u.dst.input = dst_discard; + rt->dst.input = dst_discard; } rt->rt_flags = flags; - if (rt->u.dst.dev) - dev_hold(rt->u.dst.dev); + if (rt->dst.dev) + dev_hold(rt->dst.dev); err = dn_rt_set_next_hop(rt, &res); if (err) @@ -1405,7 +1405,7 @@ make_route: hash = dn_hash(rt->fl.fld_src, rt->fl.fld_dst); dn_insert_route(rt, hash, &rt); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); done: if (neigh) @@ -1427,7 +1427,7 @@ e_nobufs: goto done; e_neighbour: - dst_free(&rt->u.dst); + dst_free(&rt->dst); goto done; } @@ -1442,13 +1442,13 @@ static int dn_route_input(struct sk_buff *skb) rcu_read_lock(); for(rt = rcu_dereference(dn_rt_hash_table[hash].chain); rt != NULL; - rt = rcu_dereference(rt->u.dst.dn_next)) { + rt = rcu_dereference(rt->dst.dn_next)) { if ((rt->fl.fld_src == cb->src) && (rt->fl.fld_dst == cb->dst) && (rt->fl.oif == 0) && (rt->fl.mark == skb->mark) && (rt->fl.iif == cb->iif)) { - dst_use(&rt->u.dst, jiffies); + dst_use(&rt->dst, jiffies); rcu_read_unlock(); skb_dst_set(skb, (struct dst_entry *)rt); return 0; @@ -1487,8 +1487,8 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, r->rtm_src_len = 16; RTA_PUT(skb, RTA_SRC, 2, &rt->fl.fld_src); } - if (rt->u.dst.dev) - RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->u.dst.dev->ifindex); + if (rt->dst.dev) + RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->dst.dev->ifindex); /* * Note to self - change this if input routes reverse direction when * they deal only with inputs and not with replies like they do @@ -1497,11 +1497,11 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, RTA_PUT(skb, RTA_PREFSRC, 2, &rt->rt_local_src); if (rt->rt_daddr != rt->rt_gateway) RTA_PUT(skb, RTA_GATEWAY, 2, &rt->rt_gateway); - if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) + if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0) goto rtattr_failure; - expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0; - if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0, expires, - rt->u.dst.error) < 0) + expires = rt->dst.expires ? rt->dst.expires - jiffies : 0; + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0, expires, + rt->dst.error) < 0) goto rtattr_failure; if (rt->fl.iif) RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fl.iif); @@ -1568,8 +1568,8 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void local_bh_enable(); memset(cb, 0, sizeof(struct dn_skb_cb)); rt = (struct dn_route *)skb_dst(skb); - if (!err && -rt->u.dst.error) - err = rt->u.dst.error; + if (!err && -rt->dst.error) + err = rt->dst.error; } else { int oif = 0; if (rta[RTA_OIF - 1]) @@ -1583,7 +1583,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void skb->dev = NULL; if (err) goto out_free; - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; @@ -1632,10 +1632,10 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock_bh(); for(rt = rcu_dereference_bh(dn_rt_hash_table[h].chain), idx = 0; rt; - rt = rcu_dereference_bh(rt->u.dst.dn_next), idx++) { + rt = rcu_dereference_bh(rt->dst.dn_next), idx++) { if (idx < s_idx) continue; - skb_dst_set(skb, dst_clone(&rt->u.dst)); + skb_dst_set(skb, dst_clone(&rt->dst)); if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1, NLM_F_MULTI) <= 0) { @@ -1678,7 +1678,7 @@ static struct dn_route *dn_rt_cache_get_next(struct seq_file *seq, struct dn_rou { struct dn_rt_cache_iter_state *s = seq->private; - rt = rt->u.dst.dn_next; + rt = rt->dst.dn_next; while(!rt) { rcu_read_unlock_bh(); if (--s->bucket < 0) @@ -1719,12 +1719,12 @@ static int dn_rt_cache_seq_show(struct seq_file *seq, void *v) char buf1[DN_ASCBUF_LEN], buf2[DN_ASCBUF_LEN]; seq_printf(seq, "%-8s %-7s %-7s %04d %04d %04d\n", - rt->u.dst.dev ? rt->u.dst.dev->name : "*", + rt->dst.dev ? rt->dst.dev->name : "*", dn_addr2asc(le16_to_cpu(rt->rt_daddr), buf1), dn_addr2asc(le16_to_cpu(rt->rt_saddr), buf2), - atomic_read(&rt->u.dst.__refcnt), - rt->u.dst.__use, - (int) dst_metric(&rt->u.dst, RTAX_RTT)); + atomic_read(&rt->dst.__refcnt), + rt->dst.__use, + (int) dst_metric(&rt->dst, RTAX_RTT)); return 0; } diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 61ec0329316c..215c83986a9d 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -158,7 +158,6 @@ EXPORT_SYMBOL(eth_rebuild_header); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) { struct ethhdr *eth; - unsigned char *rawp; skb->dev = dev; skb_reset_mac_header(skb); @@ -199,15 +198,13 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) 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. */ - if (*(unsigned short *)rawp == 0xFFFF) + if (skb->len >= 2 && *(unsigned short *)(skb->data) == 0xFFFF) return htons(ETH_P_802_3); /* diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 551ce564b035..d99e7e020189 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1100,7 +1100,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) if (err) return err; - sk_setup_caps(sk, &rt->u.dst); + sk_setup_caps(sk, &rt->dst); new_saddr = rt->rt_src; @@ -1166,7 +1166,7 @@ int inet_sk_rebuild_header(struct sock *sk) err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0); } if (!err) - sk_setup_caps(sk, &rt->u.dst); + sk_setup_caps(sk, &rt->dst); else { /* Routing failed... */ sk->sk_route_caps = 0; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 917d2d66162e..cf78f41830ca 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -427,7 +427,7 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) if (ip_route_output_key(net, &rt, &fl) < 0) return 1; - if (rt->u.dst.dev != dev) { + if (rt->dst.dev != dev) { NET_INC_STATS_BH(net, LINUX_MIB_ARPFILTER); flag = 1; } @@ -532,7 +532,7 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, struct in_device *out_dev; int imi, omi = -1; - if (rt->u.dst.dev == dev) + if (rt->dst.dev == dev) return 0; if (!IN_DEV_PROXY_ARP(in_dev)) @@ -545,7 +545,7 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, /* place to check for proxy_arp for routes */ - out_dev = __in_dev_get_rcu(rt->u.dst.dev); + out_dev = __in_dev_get_rcu(rt->dst.dev); if (out_dev) omi = IN_DEV_MEDIUM_ID(out_dev); @@ -576,7 +576,7 @@ static inline int arp_fwd_pvlan(struct in_device *in_dev, __be32 sip, __be32 tip) { /* Private VLAN is only concerned about the same ethernet segment */ - if (rt->u.dst.dev != dev) + if (rt->dst.dev != dev) return 0; /* Don't reply on self probes (often done by windowz boxes)*/ @@ -1042,7 +1042,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, struct rtable * rt; if ((err = ip_route_output_key(net, &rt, &fl)) != 0) return err; - dev = rt->u.dst.dev; + dev = rt->dst.dev; ip_rt_put(rt); if (!dev) return -EINVAL; @@ -1149,7 +1149,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r, struct rtable * rt; if ((err = ip_route_output_key(net, &rt, &fl)) != 0) return err; - dev = rt->u.dst.dev; + dev = rt->dst.dev; ip_rt_put(rt); if (!dev) return -EINVAL; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index fb2465811b48..fe3daa7f07a9 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -69,7 +69,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk->sk_state = TCP_ESTABLISHED; inet->inet_id = jiffies; - sk_dst_set(sk, &rt->u.dst); + sk_dst_set(sk, &rt->dst); return(0); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index bdb6c71e72a6..7569b21a3a2d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -271,7 +271,7 @@ int xrlim_allow(struct dst_entry *dst, int timeout) static inline int icmpv4_xrlim_allow(struct net *net, struct rtable *rt, int type, int code) { - struct dst_entry *dst = &rt->u.dst; + struct dst_entry *dst = &rt->dst; int rc = 1; if (type > NR_ICMP_TYPES) @@ -327,7 +327,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, struct sock *sk; struct sk_buff *skb; - sk = icmp_sk(dev_net((*rt)->u.dst.dev)); + sk = icmp_sk(dev_net((*rt)->dst.dev)); if (ip_append_data(sk, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, @@ -359,7 +359,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { struct ipcm_cookie ipc; struct rtable *rt = skb_rtable(skb); - struct net *net = dev_net(rt->u.dst.dev); + struct net *net = dev_net(rt->dst.dev); struct sock *sk; struct inet_sock *inet; __be32 daddr; @@ -427,7 +427,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) if (!rt) goto out; - net = dev_net(rt->u.dst.dev); + net = dev_net(rt->dst.dev); /* * Find the original header. It is expected to be valid, of course. @@ -596,9 +596,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ err = ip_route_input(skb_in, fl.fl4_dst, fl.fl4_src, - RT_TOS(tos), rt2->u.dst.dev); + RT_TOS(tos), rt2->dst.dev); - dst_release(&rt2->u.dst); + dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); skb_in->_skb_refdst = orefdst; /* restore old refdst */ } @@ -610,7 +610,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) XFRM_LOOKUP_ICMP); switch (err) { case 0: - dst_release(&rt->u.dst); + dst_release(&rt->dst); rt = rt2; break; case -EPERM: @@ -629,7 +629,7 @@ route_done: /* RFC says return as much as we can without exceeding 576 bytes. */ - room = dst_mtu(&rt->u.dst); + room = dst_mtu(&rt->dst); if (room > 576) room = 576; room -= sizeof(struct iphdr) + icmp_param.replyopts.optlen; @@ -972,7 +972,7 @@ int icmp_rcv(struct sk_buff *skb) { struct icmphdr *icmph; struct rtable *rt = skb_rtable(skb); - struct net *net = dev_net(rt->u.dst.dev); + struct net *net = dev_net(rt->dst.dev); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3294f547c481..b5580d422994 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -312,7 +312,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) return NULL; } - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); skb->dev = dev; skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -330,7 +330,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = rt->rt_src; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(pip, &rt->u.dst, NULL); + ip_select_ident(pip, &rt->dst, NULL); ((u8*)&pip[1])[0] = IPOPT_RA; ((u8*)&pip[1])[1] = 4; ((u8*)&pip[1])[2] = 0; @@ -660,7 +660,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, return -1; } - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -676,7 +676,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = rt->rt_src; iph->protocol = IPPROTO_IGMP; - ip_select_ident(iph, &rt->u.dst, NULL); + ip_select_ident(iph, &rt->dst, NULL); ((u8*)&iph[1])[0] = IPOPT_RA; ((u8*)&iph[1])[1] = 4; ((u8*)&iph[1])[2] = 0; @@ -1425,7 +1425,7 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) } if (!dev && !ip_route_output_key(net, &rt, &fl)) { - dev = rt->u.dst.dev; + dev = rt->dst.dev; ip_rt_put(rt); } if (dev) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 70eb3507c406..57c9e4d7b805 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -383,7 +383,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, goto no_route; if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) goto route_err; - return &rt->u.dst; + return &rt->dst; route_err: ip_rt_put(rt); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 56cdf68a074c..99461f09320f 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -87,16 +87,16 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway) goto sr_failed; - if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) && + if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { - IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS); + IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(dst_mtu(&rt->u.dst))); + htonl(dst_mtu(&rt->dst))); goto drop; } /* We are about to mangle packet. Copy it! */ - if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len)) + if (skb_cow(skb, LL_RESERVED_SPACE(rt->dst.dev)+rt->dst.header_len)) goto drop; iph = ip_hdr(skb); @@ -113,7 +113,7 @@ int ip_forward(struct sk_buff *skb) skb->priority = rt_tos2priority(iph->tos); return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev, - rt->u.dst.dev, ip_forward_finish); + rt->dst.dev, ip_forward_finish); sr_failed: /* diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 32618e11076d..749e54889e82 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -745,7 +745,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev goto tx_error; } } - tdev = rt->u.dst.dev; + tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); @@ -755,7 +755,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev df = tiph->frag_off; if (df) - mtu = dst_mtu(&rt->u.dst) - dev->hard_header_len - tunnel->hlen; + mtu = dst_mtu(&rt->dst) - dev->hard_header_len - tunnel->hlen; else mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; @@ -803,7 +803,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev tunnel->err_count = 0; } - max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->u.dst.header_len; + max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->dst.header_len; if (skb_headroom(skb) < max_headroom || skb_shared(skb)|| (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { @@ -830,7 +830,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* * Push down and install the IPIP header. @@ -853,7 +853,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit; #endif else - iph->ttl = dst_metric(&rt->u.dst, RTAX_HOPLIMIT); + iph->ttl = dst_metric(&rt->dst, RTAX_HOPLIMIT); } ((__be16 *)(iph + 1))[0] = tunnel->parms.o_flags; @@ -915,7 +915,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) .proto = IPPROTO_GRE }; struct rtable *rt; if (!ip_route_output_key(dev_net(dev), &rt, &fl)) { - tdev = rt->u.dst.dev; + tdev = rt->dst.dev; ip_rt_put(rt); } @@ -1174,7 +1174,7 @@ static int ipgre_open(struct net_device *dev) struct rtable *rt; if (ip_route_output_key(dev_net(dev), &rt, &fl)) return -EADDRNOTAVAIL; - dev = rt->u.dst.dev; + dev = rt->dst.dev; ip_rt_put(rt); if (__in_dev_get_rtnl(dev) == NULL) return -EADDRNOTAVAIL; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 08a3b121f908..db47a5a00ed2 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -356,10 +356,10 @@ static int ip_rcv_finish(struct sk_buff *skb) rt = skb_rtable(skb); if (rt->rt_type == RTN_MULTICAST) { - IP_UPD_PO_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INMCAST, + IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) - IP_UPD_PO_STATS_BH(dev_net(rt->u.dst.dev), IPSTATS_MIB_INBCAST, + IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INBCAST, skb->len); return dst_input(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9a4a6c96cb0d..6cbeb2e108de 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -151,15 +151,15 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->version = 4; iph->ihl = 5; iph->tos = inet->tos; - if (ip_dont_fragment(sk, &rt->u.dst)) + if (ip_dont_fragment(sk, &rt->dst)) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; - iph->ttl = ip_select_ttl(inet, &rt->u.dst); + iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = rt->rt_dst; iph->saddr = rt->rt_src; iph->protocol = sk->sk_protocol; - ip_select_ident(iph, &rt->u.dst, sk); + ip_select_ident(iph, &rt->dst, sk); if (opt && opt->optlen) { iph->ihl += opt->optlen>>2; @@ -240,7 +240,7 @@ int ip_mc_output(struct sk_buff *skb) { struct sock *sk = skb->sk; struct rtable *rt = skb_rtable(skb); - struct net_device *dev = rt->u.dst.dev; + struct net_device *dev = rt->dst.dev; /* * If the indicated interface is up and running, send the packet. @@ -359,9 +359,9 @@ int ip_queue_xmit(struct sk_buff *skb) if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0)) goto no_route; } - sk_setup_caps(sk, &rt->u.dst); + sk_setup_caps(sk, &rt->dst); } - skb_dst_set_noref(skb, &rt->u.dst); + skb_dst_set_noref(skb, &rt->dst); packet_routed: if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) @@ -372,11 +372,11 @@ packet_routed: skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff)); - if (ip_dont_fragment(sk, &rt->u.dst) && !skb->local_df) + if (ip_dont_fragment(sk, &rt->dst) && !skb->local_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; - iph->ttl = ip_select_ttl(inet, &rt->u.dst); + iph->ttl = ip_select_ttl(inet, &rt->dst); iph->protocol = sk->sk_protocol; iph->saddr = rt->rt_src; iph->daddr = rt->rt_dst; @@ -387,7 +387,7 @@ packet_routed: ip_options_build(skb, opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(iph, &rt->u.dst, sk, + ip_select_ident_more(iph, &rt->dst, sk, (skb_shinfo(skb)->gso_segs ?: 1) - 1); skb->priority = sk->sk_priority; @@ -452,7 +452,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) struct rtable *rt = skb_rtable(skb); int err = 0; - dev = rt->u.dst.dev; + dev = rt->dst.dev; /* * Point into the IP datagram header. @@ -473,7 +473,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) */ hlen = iph->ihl * 4; - mtu = dst_mtu(&rt->u.dst) - hlen; /* Size of data space */ + mtu = dst_mtu(&rt->dst) - hlen; /* Size of data space */ #ifdef CONFIG_BRIDGE_NETFILTER if (skb->nf_bridge) mtu -= nf_bridge_mtu_reduction(skb); @@ -586,7 +586,7 @@ slow_path: * 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); + ll_rs = LL_RESERVED_SPACE_EXTRA(rt->dst.dev, pad); mtu -= pad; /* @@ -833,13 +833,13 @@ int ip_append_data(struct sock *sk, */ *rtp = NULL; inet->cork.fragsize = mtu = inet->pmtudisc == IP_PMTUDISC_PROBE ? - rt->u.dst.dev->mtu : - dst_mtu(rt->u.dst.path); - inet->cork.dst = &rt->u.dst; + rt->dst.dev->mtu : + dst_mtu(rt->dst.path); + inet->cork.dst = &rt->dst; inet->cork.length = 0; sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; - if ((exthdrlen = rt->u.dst.header_len) != 0) { + if ((exthdrlen = rt->dst.header_len) != 0) { length += exthdrlen; transhdrlen += exthdrlen; } @@ -852,7 +852,7 @@ int ip_append_data(struct sock *sk, exthdrlen = 0; mtu = inet->cork.fragsize; } - hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); + hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; @@ -869,14 +869,14 @@ int ip_append_data(struct sock *sk, */ if (transhdrlen && length + fragheaderlen <= mtu && - rt->u.dst.dev->features & NETIF_F_V4_CSUM && + rt->dst.dev->features & NETIF_F_V4_CSUM && !exthdrlen) csummode = CHECKSUM_PARTIAL; inet->cork.length += length; if (((length> mtu) || !skb_queue_empty(&sk->sk_write_queue)) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->u.dst.dev->features & NETIF_F_UFO)) { + (rt->dst.dev->features & NETIF_F_UFO)) { err = ip_ufo_append_data(sk, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags); @@ -924,7 +924,7 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; if ((flags & MSG_MORE) && - !(rt->u.dst.dev->features&NETIF_F_SG)) + !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else alloclen = datalen + fragheaderlen; @@ -935,7 +935,7 @@ alloc_new_skb: * the last. */ if (datalen == length + fraggap) - alloclen += rt->u.dst.trailer_len; + alloclen += rt->dst.trailer_len; if (transhdrlen) { skb = sock_alloc_send_skb(sk, @@ -1008,7 +1008,7 @@ alloc_new_skb: if (copy > length) copy = length; - if (!(rt->u.dst.dev->features&NETIF_F_SG)) { + if (!(rt->dst.dev->features&NETIF_F_SG)) { unsigned int off; off = skb->len; @@ -1103,10 +1103,10 @@ ssize_t ip_append_page(struct sock *sk, struct page *page, if (inet->cork.flags & IPCORK_OPT) opt = inet->cork.opt; - if (!(rt->u.dst.dev->features&NETIF_F_SG)) + if (!(rt->dst.dev->features&NETIF_F_SG)) return -EOPNOTSUPP; - hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); + hh_len = LL_RESERVED_SPACE(rt->dst.dev); mtu = inet->cork.fragsize; fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); @@ -1122,7 +1122,7 @@ ssize_t ip_append_page(struct sock *sk, struct page *page, inet->cork.length += size; if ((sk->sk_protocol == IPPROTO_UDP) && - (rt->u.dst.dev->features & NETIF_F_UFO)) { + (rt->dst.dev->features & NETIF_F_UFO)) { skb_shinfo(skb)->gso_size = mtu - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; } @@ -1274,8 +1274,8 @@ int ip_push_pending_frames(struct sock *sk) * If local_df is set too, we still allow to fragment this frame * locally. */ if (inet->pmtudisc >= IP_PMTUDISC_DO || - (skb->len <= dst_mtu(&rt->u.dst) && - ip_dont_fragment(sk, &rt->u.dst))) + (skb->len <= dst_mtu(&rt->dst) && + ip_dont_fragment(sk, &rt->dst))) df = htons(IP_DF); if (inet->cork.flags & IPCORK_OPT) @@ -1284,7 +1284,7 @@ int ip_push_pending_frames(struct sock *sk) if (rt->rt_type == RTN_MULTICAST) ttl = inet->mc_ttl; else - ttl = ip_select_ttl(inet, &rt->u.dst); + ttl = ip_select_ttl(inet, &rt->dst); iph = (struct iphdr *)skb->data; iph->version = 4; @@ -1295,7 +1295,7 @@ int ip_push_pending_frames(struct sock *sk) } iph->tos = inet->tos; iph->frag_off = df; - ip_select_ident(iph, &rt->u.dst, sk); + ip_select_ident(iph, &rt->dst, sk); iph->ttl = ttl; iph->protocol = sk->sk_protocol; iph->saddr = rt->rt_src; @@ -1308,7 +1308,7 @@ int ip_push_pending_frames(struct sock *sk) * on dst refcount */ inet->cork.dst = NULL; - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); if (iph->protocol == IPPROTO_ICMP) icmp_out_count(net, ((struct icmphdr *) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 7fd636711037..ec036731a70b 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -435,7 +435,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_error_icmp; } } - tdev = rt->u.dst.dev; + tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); @@ -446,7 +446,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) df |= old_iph->frag_off & htons(IP_DF); if (df) { - mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); + mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { stats->collisions++; @@ -503,7 +503,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* * Push down and install the IPIP header. @@ -552,7 +552,7 @@ static void ipip_tunnel_bind_dev(struct net_device *dev) .proto = IPPROTO_IPIP }; struct rtable *rt; if (!ip_route_output_key(dev_net(dev), &rt, &fl)) { - tdev = rt->u.dst.dev; + tdev = rt->dst.dev; ip_rt_put(rt); } dev->flags |= IFF_POINTOPOINT; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 856123fe32f9..8418afc357ee 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1551,9 +1551,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, goto out_free; } - dev = rt->u.dst.dev; + dev = rt->dst.dev; - if (skb->len+encap > dst_mtu(&rt->u.dst) && (ntohs(iph->frag_off) & IP_DF)) { + if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) { /* Do not fragment multicasts. Alas, IPv4 does not allow to send ICMP, so that packets will disappear to blackhole. @@ -1564,7 +1564,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, goto out_free; } - encap += LL_RESERVED_SPACE(dev) + rt->u.dst.header_len; + encap += LL_RESERVED_SPACE(dev) + rt->dst.header_len; if (skb_cow(skb, encap)) { ip_rt_put(rt); @@ -1575,7 +1575,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, vif->bytes_out += skb->len; skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); ip_decrease_ttl(ip_hdr(skb)); /* FIXME: forward and output firewalls used to be called here. diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 07de855e2175..cfbc79af21c3 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -43,7 +43,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) /* Drop old route. */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); } else { /* non-local src, find valid iif to satisfy * rp-filter when calling ip_route_input. */ @@ -53,11 +53,11 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) orefdst = skb->_skb_refdst; if (ip_route_input(skb, iph->daddr, iph->saddr, - RT_TOS(iph->tos), rt->u.dst.dev) != 0) { - dst_release(&rt->u.dst); + RT_TOS(iph->tos), rt->dst.dev) != 0) { + dst_release(&rt->dst); return -1; } - dst_release(&rt->u.dst); + dst_release(&rt->dst); refdst_drop(orefdst); } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 66cc3befcd44..009a7b2aa1ef 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -325,24 +325,24 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, int err; struct rtable *rt = *rtp; - if (length > rt->u.dst.dev->mtu) { + if (length > rt->dst.dev->mtu) { ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, - rt->u.dst.dev->mtu); + rt->dst.dev->mtu); return -EMSGSIZE; } if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, - length + LL_ALLOCATED_SPACE(rt->u.dst.dev) + 15, + length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; - skb_reserve(skb, LL_RESERVED_SPACE(rt->u.dst.dev)); + skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev)); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); *rtp = NULL; skb_reset_network_header(skb); @@ -375,7 +375,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(iph, &rt->u.dst, NULL); + ip_select_ident(iph, &rt->dst, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } @@ -384,7 +384,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, skb_transport_header(skb))->type); err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL, - rt->u.dst.dev, dst_output); + rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) @@ -606,7 +606,7 @@ out: return len; do_confirm: - dst_confirm(&rt->u.dst); + dst_confirm(&rt->dst); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 883b5c7195ac..a291edbbc97f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -286,10 +286,10 @@ static struct rtable *rt_cache_get_first(struct seq_file *seq) rcu_read_lock_bh(); r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); while (r) { - if (dev_net(r->u.dst.dev) == seq_file_net(seq) && + if (dev_net(r->dst.dev) == seq_file_net(seq) && r->rt_genid == st->genid) return r; - r = rcu_dereference_bh(r->u.dst.rt_next); + r = rcu_dereference_bh(r->dst.rt_next); } rcu_read_unlock_bh(); } @@ -301,7 +301,7 @@ static struct rtable *__rt_cache_get_next(struct seq_file *seq, { struct rt_cache_iter_state *st = seq->private; - r = r->u.dst.rt_next; + r = r->dst.rt_next; while (!r) { rcu_read_unlock_bh(); do { @@ -319,7 +319,7 @@ static struct rtable *rt_cache_get_next(struct seq_file *seq, { struct rt_cache_iter_state *st = seq->private; while ((r = __rt_cache_get_next(seq, r)) != NULL) { - if (dev_net(r->u.dst.dev) != seq_file_net(seq)) + if (dev_net(r->dst.dev) != seq_file_net(seq)) continue; if (r->rt_genid == st->genid) break; @@ -377,19 +377,19 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", - r->u.dst.dev ? r->u.dst.dev->name : "*", + r->dst.dev ? r->dst.dev->name : "*", (__force u32)r->rt_dst, (__force u32)r->rt_gateway, - r->rt_flags, atomic_read(&r->u.dst.__refcnt), - r->u.dst.__use, 0, (__force u32)r->rt_src, - (dst_metric(&r->u.dst, RTAX_ADVMSS) ? - (int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0), - dst_metric(&r->u.dst, RTAX_WINDOW), - (int)((dst_metric(&r->u.dst, RTAX_RTT) >> 3) + - dst_metric(&r->u.dst, RTAX_RTTVAR)), + r->rt_flags, atomic_read(&r->dst.__refcnt), + r->dst.__use, 0, (__force u32)r->rt_src, + (dst_metric(&r->dst, RTAX_ADVMSS) ? + (int)dst_metric(&r->dst, RTAX_ADVMSS) + 40 : 0), + dst_metric(&r->dst, RTAX_WINDOW), + (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) + + dst_metric(&r->dst, RTAX_RTTVAR)), r->fl.fl4_tos, - r->u.dst.hh ? atomic_read(&r->u.dst.hh->hh_refcnt) : -1, - r->u.dst.hh ? (r->u.dst.hh->hh_output == + r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1, + r->dst.hh ? (r->dst.hh->hh_output == dev_queue_xmit) : 0, r->rt_spec_dst, &len); @@ -608,13 +608,13 @@ static inline int ip_rt_proc_init(void) static inline void rt_free(struct rtable *rt) { - call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free); + call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); } static inline void rt_drop(struct rtable *rt) { ip_rt_put(rt); - call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free); + call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free); } static inline int rt_fast_clean(struct rtable *rth) @@ -622,13 +622,13 @@ static inline int rt_fast_clean(struct rtable *rth) /* Kill broadcast/multicast entries very aggresively, if they collide in hash table with more useful entries */ return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && - rth->fl.iif && rth->u.dst.rt_next; + rth->fl.iif && rth->dst.rt_next; } static inline int rt_valuable(struct rtable *rth) { return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) || - rth->u.dst.expires; + rth->dst.expires; } static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2) @@ -636,15 +636,15 @@ static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long t unsigned long age; int ret = 0; - if (atomic_read(&rth->u.dst.__refcnt)) + if (atomic_read(&rth->dst.__refcnt)) goto out; ret = 1; - if (rth->u.dst.expires && - time_after_eq(jiffies, rth->u.dst.expires)) + if (rth->dst.expires && + time_after_eq(jiffies, rth->dst.expires)) goto out; - age = jiffies - rth->u.dst.lastuse; + age = jiffies - rth->dst.lastuse; ret = 0; if ((age <= tmo1 && !rt_fast_clean(rth)) || (age <= tmo2 && rt_valuable(rth))) @@ -660,7 +660,7 @@ out: return ret; */ static inline u32 rt_score(struct rtable *rt) { - u32 score = jiffies - rt->u.dst.lastuse; + u32 score = jiffies - rt->dst.lastuse; score = ~score & ~(3<<30); @@ -700,12 +700,12 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) { - return net_eq(dev_net(rt1->u.dst.dev), dev_net(rt2->u.dst.dev)); + return net_eq(dev_net(rt1->dst.dev), dev_net(rt2->dst.dev)); } static inline int rt_is_expired(struct rtable *rth) { - return rth->rt_genid != rt_genid(dev_net(rth->u.dst.dev)); + return rth->rt_genid != rt_genid(dev_net(rth->dst.dev)); } /* @@ -734,7 +734,7 @@ static void rt_do_flush(int process_context) rth = rt_hash_table[i].chain; /* defer releasing the head of the list after spin_unlock */ - for (tail = rth; tail; tail = tail->u.dst.rt_next) + for (tail = rth; tail; tail = tail->dst.rt_next) if (!rt_is_expired(tail)) break; if (rth != tail) @@ -743,9 +743,9 @@ static void rt_do_flush(int process_context) /* call rt_free on entries after the tail requiring flush */ prev = &rt_hash_table[i].chain; for (p = *prev; p; p = next) { - next = p->u.dst.rt_next; + next = p->dst.rt_next; if (!rt_is_expired(p)) { - prev = &p->u.dst.rt_next; + prev = &p->dst.rt_next; } else { *prev = next; rt_free(p); @@ -760,7 +760,7 @@ static void rt_do_flush(int process_context) spin_unlock_bh(rt_hash_lock_addr(i)); for (; rth != tail; rth = next) { - next = rth->u.dst.rt_next; + next = rth->dst.rt_next; rt_free(rth); } } @@ -791,7 +791,7 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) while (aux != rth) { if (compare_hash_inputs(&aux->fl, &rth->fl)) return 0; - aux = aux->u.dst.rt_next; + aux = aux->dst.rt_next; } return ONE; } @@ -831,18 +831,18 @@ static void rt_check_expire(void) length = 0; spin_lock_bh(rt_hash_lock_addr(i)); while ((rth = *rthp) != NULL) { - prefetch(rth->u.dst.rt_next); + prefetch(rth->dst.rt_next); if (rt_is_expired(rth)) { - *rthp = rth->u.dst.rt_next; + *rthp = rth->dst.rt_next; rt_free(rth); continue; } - if (rth->u.dst.expires) { + if (rth->dst.expires) { /* Entry is expired even if it is in use */ - if (time_before_eq(jiffies, rth->u.dst.expires)) { + if (time_before_eq(jiffies, rth->dst.expires)) { nofree: tmo >>= 1; - rthp = &rth->u.dst.rt_next; + rthp = &rth->dst.rt_next; /* * We only count entries on * a chain with equal hash inputs once @@ -858,7 +858,7 @@ nofree: goto nofree; /* Cleanup aged off entries. */ - *rthp = rth->u.dst.rt_next; + *rthp = rth->dst.rt_next; rt_free(rth); } spin_unlock_bh(rt_hash_lock_addr(i)); @@ -999,10 +999,10 @@ static int rt_garbage_collect(struct dst_ops *ops) if (!rt_is_expired(rth) && !rt_may_expire(rth, tmo, expire)) { tmo >>= 1; - rthp = &rth->u.dst.rt_next; + rthp = &rth->dst.rt_next; continue; } - *rthp = rth->u.dst.rt_next; + *rthp = rth->dst.rt_next; rt_free(rth); goal--; } @@ -1068,7 +1068,7 @@ static int slow_chain_length(const struct rtable *head) while (rth) { length += has_noalias(head, rth); - rth = rth->u.dst.rt_next; + rth = rth->dst.rt_next; } return length >> FRACT_BITS; } @@ -1090,7 +1090,7 @@ restart: candp = NULL; now = jiffies; - if (!rt_caching(dev_net(rt->u.dst.dev))) { + if (!rt_caching(dev_net(rt->dst.dev))) { /* * If we're not caching, just tell the caller we * were successful and don't touch the route. The @@ -1108,7 +1108,7 @@ restart: */ if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { - int err = arp_bind_neighbour(&rt->u.dst); + int err = arp_bind_neighbour(&rt->dst); if (err) { if (net_ratelimit()) printk(KERN_WARNING @@ -1127,19 +1127,19 @@ restart: spin_lock_bh(rt_hash_lock_addr(hash)); while ((rth = *rthp) != NULL) { if (rt_is_expired(rth)) { - *rthp = rth->u.dst.rt_next; + *rthp = rth->dst.rt_next; rt_free(rth); continue; } if (compare_keys(&rth->fl, &rt->fl) && compare_netns(rth, rt)) { /* Put it first */ - *rthp = rth->u.dst.rt_next; + *rthp = rth->dst.rt_next; /* * Since lookup is lockfree, the deletion * must be visible to another weakly ordered CPU before * the insertion at the start of the hash chain. */ - rcu_assign_pointer(rth->u.dst.rt_next, + rcu_assign_pointer(rth->dst.rt_next, rt_hash_table[hash].chain); /* * Since lookup is lockfree, the update writes @@ -1147,18 +1147,18 @@ restart: */ rcu_assign_pointer(rt_hash_table[hash].chain, rth); - dst_use(&rth->u.dst, now); + dst_use(&rth->dst, now); spin_unlock_bh(rt_hash_lock_addr(hash)); rt_drop(rt); if (rp) *rp = rth; else - skb_dst_set(skb, &rth->u.dst); + skb_dst_set(skb, &rth->dst); return 0; } - if (!atomic_read(&rth->u.dst.__refcnt)) { + if (!atomic_read(&rth->dst.__refcnt)) { u32 score = rt_score(rth); if (score <= min_score) { @@ -1170,7 +1170,7 @@ restart: chain_length++; - rthp = &rth->u.dst.rt_next; + rthp = &rth->dst.rt_next; } if (cand) { @@ -1181,17 +1181,17 @@ restart: * only 2 entries per bucket. We will see. */ if (chain_length > ip_rt_gc_elasticity) { - *candp = cand->u.dst.rt_next; + *candp = cand->dst.rt_next; rt_free(cand); } } else { if (chain_length > rt_chain_length_max && slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) { - struct net *net = dev_net(rt->u.dst.dev); + struct net *net = dev_net(rt->dst.dev); int num = ++net->ipv4.current_rt_cache_rebuild_count; if (!rt_caching(net)) { printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n", - rt->u.dst.dev->name, num); + rt->dst.dev->name, num); } rt_emergency_hash_rebuild(net); spin_unlock_bh(rt_hash_lock_addr(hash)); @@ -1206,7 +1206,7 @@ restart: route or unicast forwarding path. */ if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { - int err = arp_bind_neighbour(&rt->u.dst); + int err = arp_bind_neighbour(&rt->dst); if (err) { spin_unlock_bh(rt_hash_lock_addr(hash)); @@ -1237,14 +1237,14 @@ restart: } } - rt->u.dst.rt_next = rt_hash_table[hash].chain; + rt->dst.rt_next = rt_hash_table[hash].chain; #if RT_CACHE_DEBUG >= 2 - if (rt->u.dst.rt_next) { + if (rt->dst.rt_next) { struct rtable *trt; printk(KERN_DEBUG "rt_cache @%02x: %pI4", hash, &rt->rt_dst); - for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next) + for (trt = rt->dst.rt_next; trt; trt = trt->dst.rt_next) printk(" . %pI4", &trt->rt_dst); printk("\n"); } @@ -1262,7 +1262,7 @@ skip_hashing: if (rp) *rp = rt; else - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); return 0; } @@ -1334,11 +1334,11 @@ static void rt_del(unsigned hash, struct rtable *rt) ip_rt_put(rt); while ((aux = *rthp) != NULL) { if (aux == rt || rt_is_expired(aux)) { - *rthp = aux->u.dst.rt_next; + *rthp = aux->dst.rt_next; rt_free(aux); continue; } - rthp = &aux->u.dst.rt_next; + rthp = &aux->dst.rt_next; } spin_unlock_bh(rt_hash_lock_addr(hash)); } @@ -1392,19 +1392,19 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, rth->fl.oif != ikeys[k] || rth->fl.iif != 0 || rt_is_expired(rth) || - !net_eq(dev_net(rth->u.dst.dev), net)) { - rthp = &rth->u.dst.rt_next; + !net_eq(dev_net(rth->dst.dev), net)) { + rthp = &rth->dst.rt_next; continue; } if (rth->rt_dst != daddr || rth->rt_src != saddr || - rth->u.dst.error || + rth->dst.error || rth->rt_gateway != old_gw || - rth->u.dst.dev != dev) + rth->dst.dev != dev) break; - dst_hold(&rth->u.dst); + dst_hold(&rth->dst); rt = dst_alloc(&ipv4_dst_ops); if (rt == NULL) { @@ -1414,20 +1414,20 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, /* Copy all the information. */ *rt = *rth; - rt->u.dst.__use = 1; - atomic_set(&rt->u.dst.__refcnt, 1); - rt->u.dst.child = NULL; - if (rt->u.dst.dev) - dev_hold(rt->u.dst.dev); + rt->dst.__use = 1; + atomic_set(&rt->dst.__refcnt, 1); + rt->dst.child = NULL; + if (rt->dst.dev) + dev_hold(rt->dst.dev); if (rt->idev) in_dev_hold(rt->idev); - rt->u.dst.obsolete = -1; - rt->u.dst.lastuse = jiffies; - rt->u.dst.path = &rt->u.dst; - rt->u.dst.neighbour = NULL; - rt->u.dst.hh = NULL; + rt->dst.obsolete = -1; + rt->dst.lastuse = jiffies; + rt->dst.path = &rt->dst; + rt->dst.neighbour = NULL; + rt->dst.hh = NULL; #ifdef CONFIG_XFRM - rt->u.dst.xfrm = NULL; + rt->dst.xfrm = NULL; #endif rt->rt_genid = rt_genid(net); rt->rt_flags |= RTCF_REDIRECTED; @@ -1436,23 +1436,23 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, rt->rt_gateway = new_gw; /* Redirect received -> path was valid */ - dst_confirm(&rth->u.dst); + dst_confirm(&rth->dst); if (rt->peer) atomic_inc(&rt->peer->refcnt); - if (arp_bind_neighbour(&rt->u.dst) || - !(rt->u.dst.neighbour->nud_state & + if (arp_bind_neighbour(&rt->dst) || + !(rt->dst.neighbour->nud_state & NUD_VALID)) { - if (rt->u.dst.neighbour) - neigh_event_send(rt->u.dst.neighbour, NULL); + if (rt->dst.neighbour) + neigh_event_send(rt->dst.neighbour, NULL); ip_rt_put(rth); rt_drop(rt); goto do_next; } - netevent.old = &rth->u.dst; - netevent.new = &rt->u.dst; + netevent.old = &rth->dst; + netevent.new = &rt->dst; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); @@ -1488,8 +1488,8 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) ip_rt_put(rt); ret = NULL; } else if ((rt->rt_flags & RTCF_REDIRECTED) || - (rt->u.dst.expires && - time_after_eq(jiffies, rt->u.dst.expires))) { + (rt->dst.expires && + time_after_eq(jiffies, rt->dst.expires))) { unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, rt->fl.oif, rt_genid(dev_net(dst->dev))); @@ -1527,7 +1527,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) int log_martians; rcu_read_lock(); - in_dev = __in_dev_get_rcu(rt->u.dst.dev); + in_dev = __in_dev_get_rcu(rt->dst.dev); if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) { rcu_read_unlock(); return; @@ -1538,30 +1538,30 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ - if (time_after(jiffies, rt->u.dst.rate_last + ip_rt_redirect_silence)) - rt->u.dst.rate_tokens = 0; + if (time_after(jiffies, rt->dst.rate_last + ip_rt_redirect_silence)) + rt->dst.rate_tokens = 0; /* Too many ignored redirects; do not send anything - * set u.dst.rate_last to the last seen redirected packet. + * set dst.rate_last to the last seen redirected packet. */ - if (rt->u.dst.rate_tokens >= ip_rt_redirect_number) { - rt->u.dst.rate_last = jiffies; + if (rt->dst.rate_tokens >= ip_rt_redirect_number) { + rt->dst.rate_last = jiffies; return; } /* Check for load limit; set rate_last to the latest sent * redirect. */ - if (rt->u.dst.rate_tokens == 0 || + if (rt->dst.rate_tokens == 0 || time_after(jiffies, - (rt->u.dst.rate_last + - (ip_rt_redirect_load << rt->u.dst.rate_tokens)))) { + (rt->dst.rate_last + + (ip_rt_redirect_load << rt->dst.rate_tokens)))) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway); - rt->u.dst.rate_last = jiffies; - ++rt->u.dst.rate_tokens; + rt->dst.rate_last = jiffies; + ++rt->dst.rate_tokens; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && - rt->u.dst.rate_tokens == ip_rt_redirect_number && + rt->dst.rate_tokens == ip_rt_redirect_number && net_ratelimit()) printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n", &rt->rt_src, rt->rt_iif, @@ -1576,7 +1576,7 @@ static int ip_error(struct sk_buff *skb) unsigned long now; int code; - switch (rt->u.dst.error) { + switch (rt->dst.error) { case EINVAL: default: goto out; @@ -1585,7 +1585,7 @@ static int ip_error(struct sk_buff *skb) break; case ENETUNREACH: code = ICMP_NET_UNREACH; - IP_INC_STATS_BH(dev_net(rt->u.dst.dev), + IP_INC_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INNOROUTES); break; case EACCES: @@ -1594,12 +1594,12 @@ static int ip_error(struct sk_buff *skb) } now = jiffies; - rt->u.dst.rate_tokens += now - rt->u.dst.rate_last; - if (rt->u.dst.rate_tokens > ip_rt_error_burst) - rt->u.dst.rate_tokens = ip_rt_error_burst; - rt->u.dst.rate_last = now; - if (rt->u.dst.rate_tokens >= ip_rt_error_cost) { - rt->u.dst.rate_tokens -= ip_rt_error_cost; + rt->dst.rate_tokens += now - rt->dst.rate_last; + if (rt->dst.rate_tokens > ip_rt_error_burst) + rt->dst.rate_tokens = ip_rt_error_burst; + rt->dst.rate_last = now; + if (rt->dst.rate_tokens >= ip_rt_error_cost) { + rt->dst.rate_tokens -= ip_rt_error_cost; icmp_send(skb, ICMP_DEST_UNREACH, code, 0); } @@ -1644,7 +1644,7 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, rcu_read_lock(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; - rth = rcu_dereference(rth->u.dst.rt_next)) { + rth = rcu_dereference(rth->dst.rt_next)) { unsigned short mtu = new_mtu; if (rth->fl.fl4_dst != daddr || @@ -1653,8 +1653,8 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, rth->rt_src != iph->saddr || rth->fl.oif != ikeys[k] || rth->fl.iif != 0 || - dst_metric_locked(&rth->u.dst, RTAX_MTU) || - !net_eq(dev_net(rth->u.dst.dev), net) || + dst_metric_locked(&rth->dst, RTAX_MTU) || + !net_eq(dev_net(rth->dst.dev), net) || rt_is_expired(rth)) continue; @@ -1662,22 +1662,22 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, /* BSD 4.2 compatibility hack :-( */ if (mtu == 0 && - old_mtu >= dst_mtu(&rth->u.dst) && + old_mtu >= dst_mtu(&rth->dst) && old_mtu >= 68 + (iph->ihl << 2)) old_mtu -= iph->ihl << 2; mtu = guess_mtu(old_mtu); } - if (mtu <= dst_mtu(&rth->u.dst)) { - if (mtu < dst_mtu(&rth->u.dst)) { - dst_confirm(&rth->u.dst); + if (mtu <= dst_mtu(&rth->dst)) { + if (mtu < dst_mtu(&rth->dst)) { + dst_confirm(&rth->dst); if (mtu < ip_rt_min_pmtu) { mtu = ip_rt_min_pmtu; - rth->u.dst.metrics[RTAX_LOCK-1] |= + rth->dst.metrics[RTAX_LOCK-1] |= (1 << RTAX_MTU); } - rth->u.dst.metrics[RTAX_MTU-1] = mtu; - dst_set_expires(&rth->u.dst, + rth->dst.metrics[RTAX_MTU-1] = mtu; + dst_set_expires(&rth->dst, ip_rt_mtu_expires); } est_mtu = mtu; @@ -1750,7 +1750,7 @@ static void ipv4_link_failure(struct sk_buff *skb) rt = skb_rtable(skb); if (rt) - dst_set_expires(&rt->u.dst, 0); + dst_set_expires(&rt->dst, 0); } static int ip_rt_bug(struct sk_buff *skb) @@ -1778,11 +1778,11 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) if (rt->fl.iif == 0) src = rt->rt_src; - else if (fib_lookup(dev_net(rt->u.dst.dev), &rt->fl, &res) == 0) { + else if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0) { src = FIB_RES_PREFSRC(res); fib_res_put(&res); } else - src = inet_select_addr(rt->u.dst.dev, rt->rt_gateway, + src = inet_select_addr(rt->dst.dev, rt->rt_gateway, RT_SCOPE_UNIVERSE); memcpy(addr, &src, 4); } @@ -1790,10 +1790,10 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) #ifdef CONFIG_NET_CLS_ROUTE static void set_class_tag(struct rtable *rt, u32 tag) { - if (!(rt->u.dst.tclassid & 0xFFFF)) - rt->u.dst.tclassid |= tag & 0xFFFF; - if (!(rt->u.dst.tclassid & 0xFFFF0000)) - rt->u.dst.tclassid |= tag & 0xFFFF0000; + if (!(rt->dst.tclassid & 0xFFFF)) + rt->dst.tclassid |= tag & 0xFFFF; + if (!(rt->dst.tclassid & 0xFFFF0000)) + rt->dst.tclassid |= tag & 0xFFFF0000; } #endif @@ -1805,30 +1805,30 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = FIB_RES_GW(*res); - memcpy(rt->u.dst.metrics, fi->fib_metrics, - sizeof(rt->u.dst.metrics)); + memcpy(rt->dst.metrics, fi->fib_metrics, + sizeof(rt->dst.metrics)); if (fi->fib_mtu == 0) { - rt->u.dst.metrics[RTAX_MTU-1] = rt->u.dst.dev->mtu; - if (dst_metric_locked(&rt->u.dst, RTAX_MTU) && + rt->dst.metrics[RTAX_MTU-1] = rt->dst.dev->mtu; + if (dst_metric_locked(&rt->dst, RTAX_MTU) && rt->rt_gateway != rt->rt_dst && - rt->u.dst.dev->mtu > 576) - rt->u.dst.metrics[RTAX_MTU-1] = 576; + rt->dst.dev->mtu > 576) + rt->dst.metrics[RTAX_MTU-1] = 576; } #ifdef CONFIG_NET_CLS_ROUTE - rt->u.dst.tclassid = FIB_RES_NH(*res).nh_tclassid; + rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid; #endif } else - rt->u.dst.metrics[RTAX_MTU-1]= rt->u.dst.dev->mtu; - - if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0) - rt->u.dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl; - if (dst_mtu(&rt->u.dst) > IP_MAX_MTU) - rt->u.dst.metrics[RTAX_MTU-1] = IP_MAX_MTU; - if (dst_metric(&rt->u.dst, RTAX_ADVMSS) == 0) - rt->u.dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->u.dst.dev->mtu - 40, + rt->dst.metrics[RTAX_MTU-1]= rt->dst.dev->mtu; + + if (dst_metric(&rt->dst, RTAX_HOPLIMIT) == 0) + rt->dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl; + if (dst_mtu(&rt->dst) > IP_MAX_MTU) + rt->dst.metrics[RTAX_MTU-1] = IP_MAX_MTU; + if (dst_metric(&rt->dst, RTAX_ADVMSS) == 0) + rt->dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->dst.dev->mtu - 40, ip_rt_min_advmss); - if (dst_metric(&rt->u.dst, RTAX_ADVMSS) > 65535 - 40) - rt->u.dst.metrics[RTAX_ADVMSS-1] = 65535 - 40; + if (dst_metric(&rt->dst, RTAX_ADVMSS) > 65535 - 40) + rt->dst.metrics[RTAX_ADVMSS-1] = 65535 - 40; #ifdef CONFIG_NET_CLS_ROUTE #ifdef CONFIG_IP_MULTIPLE_TABLES @@ -1873,13 +1873,13 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (!rth) goto e_nobufs; - rth->u.dst.output = ip_rt_bug; - rth->u.dst.obsolete = -1; + rth->dst.output = ip_rt_bug; + rth->dst.obsolete = -1; - atomic_set(&rth->u.dst.__refcnt, 1); - rth->u.dst.flags= DST_HOST; + atomic_set(&rth->dst.__refcnt, 1); + rth->dst.flags= DST_HOST; if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) - rth->u.dst.flags |= DST_NOPOLICY; + rth->dst.flags |= DST_NOPOLICY; rth->fl.fl4_dst = daddr; rth->rt_dst = daddr; rth->fl.fl4_tos = tos; @@ -1887,13 +1887,13 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->fl.fl4_src = saddr; rth->rt_src = saddr; #ifdef CONFIG_NET_CLS_ROUTE - rth->u.dst.tclassid = itag; + rth->dst.tclassid = itag; #endif rth->rt_iif = rth->fl.iif = dev->ifindex; - rth->u.dst.dev = init_net.loopback_dev; - dev_hold(rth->u.dst.dev); - rth->idev = in_dev_get(rth->u.dst.dev); + rth->dst.dev = init_net.loopback_dev; + dev_hold(rth->dst.dev); + rth->idev = in_dev_get(rth->dst.dev); rth->fl.oif = 0; rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; @@ -1901,13 +1901,13 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_flags = RTCF_MULTICAST; rth->rt_type = RTN_MULTICAST; if (our) { - rth->u.dst.input= ip_local_deliver; + rth->dst.input= ip_local_deliver; rth->rt_flags |= RTCF_LOCAL; } #ifdef CONFIG_IP_MROUTE if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) - rth->u.dst.input = ip_mr_input; + rth->dst.input = ip_mr_input; #endif RT_CACHE_STAT_INC(in_slow_mc); @@ -2016,12 +2016,12 @@ static int __mkroute_input(struct sk_buff *skb, goto cleanup; } - atomic_set(&rth->u.dst.__refcnt, 1); - rth->u.dst.flags= DST_HOST; + atomic_set(&rth->dst.__refcnt, 1); + rth->dst.flags= DST_HOST; if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) - rth->u.dst.flags |= DST_NOPOLICY; + rth->dst.flags |= DST_NOPOLICY; if (IN_DEV_CONF_GET(out_dev, NOXFRM)) - rth->u.dst.flags |= DST_NOXFRM; + rth->dst.flags |= DST_NOXFRM; rth->fl.fl4_dst = daddr; rth->rt_dst = daddr; rth->fl.fl4_tos = tos; @@ -2031,16 +2031,16 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = daddr; rth->rt_iif = rth->fl.iif = in_dev->dev->ifindex; - rth->u.dst.dev = (out_dev)->dev; - dev_hold(rth->u.dst.dev); - rth->idev = in_dev_get(rth->u.dst.dev); + rth->dst.dev = (out_dev)->dev; + dev_hold(rth->dst.dev); + rth->idev = in_dev_get(rth->dst.dev); rth->fl.oif = 0; rth->rt_spec_dst= spec_dst; - rth->u.dst.obsolete = -1; - rth->u.dst.input = ip_forward; - rth->u.dst.output = ip_output; - rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev)); + rth->dst.obsolete = -1; + rth->dst.input = ip_forward; + rth->dst.output = ip_output; + rth->rt_genid = rt_genid(dev_net(rth->dst.dev)); rt_set_nexthop(rth, res, itag); @@ -2074,7 +2074,7 @@ static int ip_mkroute_input(struct sk_buff *skb, /* put it into the cache */ hash = rt_hash(daddr, saddr, fl->iif, - rt_genid(dev_net(rth->u.dst.dev))); + rt_genid(dev_net(rth->dst.dev))); return rt_intern_hash(hash, rth, NULL, skb, fl->iif); } @@ -2197,14 +2197,14 @@ local_input: if (!rth) goto e_nobufs; - rth->u.dst.output= ip_rt_bug; - rth->u.dst.obsolete = -1; + rth->dst.output= ip_rt_bug; + rth->dst.obsolete = -1; rth->rt_genid = rt_genid(net); - atomic_set(&rth->u.dst.__refcnt, 1); - rth->u.dst.flags= DST_HOST; + atomic_set(&rth->dst.__refcnt, 1); + rth->dst.flags= DST_HOST; if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) - rth->u.dst.flags |= DST_NOPOLICY; + rth->dst.flags |= DST_NOPOLICY; rth->fl.fl4_dst = daddr; rth->rt_dst = daddr; rth->fl.fl4_tos = tos; @@ -2212,20 +2212,20 @@ local_input: rth->fl.fl4_src = saddr; rth->rt_src = saddr; #ifdef CONFIG_NET_CLS_ROUTE - rth->u.dst.tclassid = itag; + rth->dst.tclassid = itag; #endif rth->rt_iif = rth->fl.iif = dev->ifindex; - rth->u.dst.dev = net->loopback_dev; - dev_hold(rth->u.dst.dev); - rth->idev = in_dev_get(rth->u.dst.dev); + rth->dst.dev = net->loopback_dev; + dev_hold(rth->dst.dev); + rth->idev = in_dev_get(rth->dst.dev); rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; - rth->u.dst.input= ip_local_deliver; + rth->dst.input= ip_local_deliver; rth->rt_flags = flags|RTCF_LOCAL; if (res.type == RTN_UNREACHABLE) { - rth->u.dst.input= ip_error; - rth->u.dst.error= -err; + rth->dst.input= ip_error; + rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } rth->rt_type = res.type; @@ -2291,21 +2291,21 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, hash = rt_hash(daddr, saddr, iif, rt_genid(net)); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; - rth = rcu_dereference(rth->u.dst.rt_next)) { + rth = rcu_dereference(rth->dst.rt_next)) { if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) | ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) | (rth->fl.iif ^ iif) | rth->fl.oif | (rth->fl.fl4_tos ^ tos)) == 0 && rth->fl.mark == skb->mark && - net_eq(dev_net(rth->u.dst.dev), net) && + net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { if (noref) { - dst_use_noref(&rth->u.dst, jiffies); - skb_dst_set_noref(skb, &rth->u.dst); + dst_use_noref(&rth->dst, jiffies); + skb_dst_set_noref(skb, &rth->dst); } else { - dst_use(&rth->u.dst, jiffies); - skb_dst_set(skb, &rth->u.dst); + dst_use(&rth->dst, jiffies); + skb_dst_set(skb, &rth->dst); } RT_CACHE_STAT_INC(in_hit); rcu_read_unlock(); @@ -2412,12 +2412,12 @@ static int __mkroute_output(struct rtable **result, goto cleanup; } - atomic_set(&rth->u.dst.__refcnt, 1); - rth->u.dst.flags= DST_HOST; + atomic_set(&rth->dst.__refcnt, 1); + rth->dst.flags= DST_HOST; if (IN_DEV_CONF_GET(in_dev, NOXFRM)) - rth->u.dst.flags |= DST_NOXFRM; + rth->dst.flags |= DST_NOXFRM; if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) - rth->u.dst.flags |= DST_NOPOLICY; + rth->dst.flags |= DST_NOPOLICY; rth->fl.fl4_dst = oldflp->fl4_dst; rth->fl.fl4_tos = tos; @@ -2429,35 +2429,35 @@ static int __mkroute_output(struct rtable **result, rth->rt_iif = oldflp->oif ? : dev_out->ifindex; /* get references to the devices that are to be hold by the routing cache entry */ - rth->u.dst.dev = dev_out; + rth->dst.dev = dev_out; dev_hold(dev_out); rth->idev = in_dev_get(dev_out); rth->rt_gateway = fl->fl4_dst; rth->rt_spec_dst= fl->fl4_src; - rth->u.dst.output=ip_output; - rth->u.dst.obsolete = -1; + rth->dst.output=ip_output; + rth->dst.obsolete = -1; rth->rt_genid = rt_genid(dev_net(dev_out)); RT_CACHE_STAT_INC(out_slow_tot); if (flags & RTCF_LOCAL) { - rth->u.dst.input = ip_local_deliver; + rth->dst.input = ip_local_deliver; rth->rt_spec_dst = fl->fl4_dst; } if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { rth->rt_spec_dst = fl->fl4_src; if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { - rth->u.dst.output = ip_mc_output; + rth->dst.output = ip_mc_output; RT_CACHE_STAT_INC(out_slow_mc); } #ifdef CONFIG_IP_MROUTE if (res->type == RTN_MULTICAST) { if (IN_DEV_MFORWARD(in_dev) && !ipv4_is_local_multicast(oldflp->fl4_dst)) { - rth->u.dst.input = ip_mr_input; - rth->u.dst.output = ip_mc_output; + rth->dst.input = ip_mr_input; + rth->dst.output = ip_mc_output; } } #endif @@ -2712,7 +2712,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, rcu_read_lock_bh(); for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth; - rth = rcu_dereference_bh(rth->u.dst.rt_next)) { + rth = rcu_dereference_bh(rth->dst.rt_next)) { if (rth->fl.fl4_dst == flp->fl4_dst && rth->fl.fl4_src == flp->fl4_src && rth->fl.iif == 0 && @@ -2720,9 +2720,9 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, rth->fl.mark == flp->mark && !((rth->fl.fl4_tos ^ flp->fl4_tos) & (IPTOS_RT_MASK | RTO_ONLINK)) && - net_eq(dev_net(rth->u.dst.dev), net) && + net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { - dst_use(&rth->u.dst, jiffies); + dst_use(&rth->dst, jiffies); RT_CACHE_STAT_INC(out_hit); rcu_read_unlock_bh(); *rp = rth; @@ -2759,15 +2759,15 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi dst_alloc(&ipv4_dst_blackhole_ops); if (rt) { - struct dst_entry *new = &rt->u.dst; + struct dst_entry *new = &rt->dst; atomic_set(&new->__refcnt, 1); new->__use = 1; new->input = dst_discard; new->output = dst_discard; - memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32)); + memcpy(new->metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32)); - new->dev = ort->u.dst.dev; + new->dev = ort->dst.dev; if (new->dev) dev_hold(new->dev); @@ -2791,7 +2791,7 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi dst_free(new); } - dst_release(&(*rp)->u.dst); + dst_release(&(*rp)->dst); *rp = rt; return (rt ? 0 : -ENOMEM); } @@ -2861,11 +2861,11 @@ static int rt_fill_info(struct net *net, r->rtm_src_len = 32; NLA_PUT_BE32(skb, RTA_SRC, rt->fl.fl4_src); } - if (rt->u.dst.dev) - NLA_PUT_U32(skb, RTA_OIF, rt->u.dst.dev->ifindex); + if (rt->dst.dev) + NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex); #ifdef CONFIG_NET_CLS_ROUTE - if (rt->u.dst.tclassid) - NLA_PUT_U32(skb, RTA_FLOW, rt->u.dst.tclassid); + if (rt->dst.tclassid) + NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid); #endif if (rt->fl.iif) NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst); @@ -2875,11 +2875,11 @@ static int rt_fill_info(struct net *net, if (rt->rt_dst != rt->rt_gateway) NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway); - if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) + if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0) goto nla_put_failure; - error = rt->u.dst.error; - expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0; + error = rt->dst.error; + expires = rt->dst.expires ? rt->dst.expires - jiffies : 0; if (rt->peer) { id = atomic_read(&rt->peer->ip_id_count) & 0xffff; if (rt->peer->tcp_ts_stamp) { @@ -2911,7 +2911,7 @@ static int rt_fill_info(struct net *net, NLA_PUT_U32(skb, RTA_IIF, rt->fl.iif); } - if (rtnl_put_cacheinfo(skb, &rt->u.dst, id, ts, tsage, + if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage, expires, error) < 0) goto nla_put_failure; @@ -2976,8 +2976,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void local_bh_enable(); rt = skb_rtable(skb); - if (err == 0 && rt->u.dst.error) - err = -rt->u.dst.error; + if (err == 0 && rt->dst.error) + err = -rt->dst.error; } else { struct flowi fl = { .nl_u = { @@ -2995,7 +2995,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void if (err) goto errout_free; - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; @@ -3031,12 +3031,12 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; rcu_read_lock_bh(); for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt; - rt = rcu_dereference_bh(rt->u.dst.rt_next), idx++) { - if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx) + rt = rcu_dereference_bh(rt->dst.rt_next), idx++) { + if (!net_eq(dev_net(rt->dst.dev), net) || idx < s_idx) continue; if (rt_is_expired(rt)) continue; - skb_dst_set_noref(skb, &rt->u.dst); + skb_dst_set_noref(skb, &rt->dst); if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1, NLM_F_MULTI) <= 0) { diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 5c48124332de..02bef6aa8b30 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -354,15 +354,15 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, } /* Try to redo what tcp_v4_send_synack did. */ - req->window_clamp = tp->window_clamp ? :dst_metric(&rt->u.dst, RTAX_WINDOW); + req->window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, &req->rcv_wnd, &req->window_clamp, ireq->wscale_ok, &rcv_wscale, - dst_metric(&rt->u.dst, RTAX_INITRWND)); + dst_metric(&rt->dst, RTAX_INITRWND)); ireq->rcv_wscale = rcv_wscale; - ret = get_cookie_sock(sk, skb, req, &rt->u.dst); + ret = get_cookie_sock(sk, skb, req, &rt->dst); out: return ret; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7f976af27bf0..7f9515c0379f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -237,7 +237,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; - sk_setup_caps(sk, &rt->u.dst); + sk_setup_caps(sk, &rt->dst); if (!tp->write_seq) tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index eec4ff456e33..32e0bef60d0a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -914,7 +914,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, !sock_flag(sk, SOCK_BROADCAST)) goto out; if (connected) - sk_dst_set(sk, dst_clone(&rt->u.dst)); + sk_dst_set(sk, dst_clone(&rt->dst)); } if (msg->msg_flags&MSG_CONFIRM) @@ -978,7 +978,7 @@ out: return err; do_confirm: - dst_confirm(&rt->u.dst); + dst_confirm(&rt->dst); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 1705476670ef..349327092c9e 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -37,7 +37,7 @@ static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, fl.fl4_src = saddr->a4; err = __ip_route_output_key(net, &rt, &fl); - dst = &rt->u.dst; + dst = &rt->dst; if (err) dst = ERR_PTR(err); return dst; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e1a698df5706..b97bb1f30808 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -557,7 +557,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) pr_warning("Freeing alive inet6 address %p\n", ifp); return; } - dst_release(&ifp->rt->u.dst); + dst_release(&ifp->rt->dst); call_rcu(&ifp->rcu, inet6_ifa_finish_destroy_rcu); } @@ -823,7 +823,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) rt->rt6i_flags |= RTF_EXPIRES; } } - dst_release(&rt->u.dst); + dst_release(&rt->dst); } out: @@ -1863,7 +1863,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) dev, expires, flags); } if (rt) - dst_release(&rt->u.dst); + dst_release(&rt->dst); } /* Try to figure out our local address for this prefix */ @@ -4093,11 +4093,11 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (ifp->idev->cnf.forwarding) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); - dst_hold(&ifp->rt->u.dst); + dst_hold(&ifp->rt->dst); if (ifp->state == INET6_IFADDR_STATE_DEAD && ip6_del_rt(ifp->rt)) - dst_free(&ifp->rt->u.dst); + dst_free(&ifp->rt->dst); break; } } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index f058fbd808c8..0e5e943446f0 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -84,7 +84,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, struct in6_addr *addr) rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { dev = rt->rt6i_dev; - dst_release(&rt->u.dst); + dst_release(&rt->dst); } else if (ishost) { err = -EADDRNOTAVAIL; goto error; @@ -244,7 +244,7 @@ static void aca_put(struct ifacaddr6 *ac) { if (atomic_dec_and_test(&ac->aca_refcnt)) { in6_dev_put(ac->aca_idev); - dst_release(&ac->aca_rt->u.dst); + dst_release(&ac->aca_rt->dst); kfree(ac); } } @@ -350,7 +350,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, struct in6_addr *addr) write_unlock_bh(&idev->lock); addrconf_leave_solict(idev, &aca->aca_addr); - dst_hold(&aca->aca_rt->u.dst); + dst_hold(&aca->aca_rt->dst); ip6_del_rt(aca->aca_rt); aca_put(aca); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 8e44f8f9c188..b1108ede18e1 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -43,8 +43,8 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl, if (arg.result) return arg.result; - dst_hold(&net->ipv6.ip6_null_entry->u.dst); - return &net->ipv6.ip6_null_entry->u.dst; + dst_hold(&net->ipv6.ip6_null_entry->dst); + return &net->ipv6.ip6_null_entry->dst; } static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, @@ -86,7 +86,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, struct in6_addr saddr; if (ipv6_dev_get_saddr(net, - ip6_dst_idev(&rt->u.dst)->dev, + ip6_dst_idev(&rt->dst)->dev, &flp->fl6_dst, rt6_flags2srcprefs(flags), &saddr)) @@ -99,12 +99,12 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto out; } again: - dst_release(&rt->u.dst); + dst_release(&rt->dst); rt = NULL; goto out; discard_pkt: - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); out: arg->result = rt; return rt == NULL ? -EAGAIN : 0; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 92a122b7795d..b6a585909d35 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -165,7 +165,7 @@ static __inline__ void node_free(struct fib6_node * fn) static __inline__ void rt6_release(struct rt6_info *rt) { if (atomic_dec_and_test(&rt->rt6i_ref)) - dst_free(&rt->u.dst); + dst_free(&rt->dst); } static void fib6_link_table(struct net *net, struct fib6_table *tb) @@ -278,7 +278,7 @@ static int fib6_dump_node(struct fib6_walker_t *w) int res; struct rt6_info *rt; - for (rt = w->leaf; rt; rt = rt->u.dst.rt6_next) { + for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { res = rt6_dump_route(rt, w->args); if (res < 0) { /* Frame is full, suspend walking */ @@ -619,7 +619,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, ins = &fn->leaf; - for (iter = fn->leaf; iter; iter=iter->u.dst.rt6_next) { + for (iter = fn->leaf; iter; iter=iter->dst.rt6_next) { /* * Search for duplicates */ @@ -647,7 +647,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (iter->rt6i_metric > rt->rt6i_metric) break; - ins = &iter->u.dst.rt6_next; + ins = &iter->dst.rt6_next; } /* Reset round-robin state, if necessary */ @@ -658,7 +658,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, * insert node */ - rt->u.dst.rt6_next = iter; + rt->dst.rt6_next = iter; *ins = rt; rt->rt6i_node = fn; atomic_inc(&rt->rt6i_ref); @@ -799,7 +799,7 @@ out: atomic_inc(&pn->leaf->rt6i_ref); } #endif - dst_free(&rt->u.dst); + dst_free(&rt->dst); } return err; @@ -810,7 +810,7 @@ out: st_failure: if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) fib6_repair_tree(info->nl_net, fn); - dst_free(&rt->u.dst); + dst_free(&rt->dst); return err; #endif } @@ -1108,7 +1108,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, RT6_TRACE("fib6_del_route\n"); /* Unlink it */ - *rtp = rt->u.dst.rt6_next; + *rtp = rt->dst.rt6_next; rt->rt6i_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; @@ -1122,14 +1122,14 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, FOR_WALKERS(w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); - w->leaf = rt->u.dst.rt6_next; + w->leaf = rt->dst.rt6_next; if (w->leaf == NULL) w->state = FWS_U; } } read_unlock(&fib6_walker_lock); - rt->u.dst.rt6_next = NULL; + rt->dst.rt6_next = NULL; /* If it was last route, expunge its radix tree node */ if (fn->leaf == NULL) { @@ -1168,7 +1168,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) struct rt6_info **rtp; #if RT6_DEBUG >= 2 - if (rt->u.dst.obsolete>0) { + if (rt->dst.obsolete>0) { WARN_ON(fn != NULL); return -ENOENT; } @@ -1195,7 +1195,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) * Walk the leaf entries looking for ourself */ - for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->u.dst.rt6_next) { + for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->dst.rt6_next) { if (*rtp == rt) { fib6_del_route(fn, rtp, info); return 0; @@ -1334,7 +1334,7 @@ static int fib6_clean_node(struct fib6_walker_t *w) .nl_net = c->net, }; - for (rt = w->leaf; rt; rt = rt->u.dst.rt6_next) { + for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { res = c->func(rt, c->arg); if (res < 0) { w->leaf = rt; @@ -1448,8 +1448,8 @@ static int fib6_age(struct rt6_info *rt, void *arg) } gc_args.more++; } else if (rt->rt6i_flags & RTF_CACHE) { - if (atomic_read(&rt->u.dst.__refcnt) == 0 && - time_after_eq(now, rt->u.dst.lastuse + gc_args.timeout)) { + if (atomic_read(&rt->dst.__refcnt) == 0 && + time_after_eq(now, rt->dst.lastuse + gc_args.timeout)) { RT6_TRACE("aging clone %p\n", rt); return -1; } else if ((rt->rt6i_flags & RTF_GATEWAY) && diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 89425af0684c..d40b330c0ee6 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -698,7 +698,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); for (;;) { /* Prepare header of the next frame, @@ -726,7 +726,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) err = output(skb); if(!err) - IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst), + IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); if (err || !frag) @@ -740,9 +740,9 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) kfree(tmp_hdr); if (err == 0) { - IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst), + IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); - dst_release(&rt->u.dst); + dst_release(&rt->dst); return 0; } @@ -752,9 +752,9 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) frag = skb; } - IP6_INC_STATS(net, ip6_dst_idev(&rt->u.dst), + IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); - dst_release(&rt->u.dst); + dst_release(&rt->dst); return err; } @@ -785,7 +785,7 @@ slow_path: * Allocate buffer. */ - if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) { + if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->dst.dev), GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); @@ -798,7 +798,7 @@ slow_path: */ ip6_copy_metadata(frag, skb); - skb_reserve(frag, LL_RESERVED_SPACE(rt->u.dst.dev)); + skb_reserve(frag, LL_RESERVED_SPACE(rt->dst.dev)); skb_put(frag, len + hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + hlen); @@ -1156,24 +1156,24 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, /* need source address above miyazawa*/ } - dst_hold(&rt->u.dst); - inet->cork.dst = &rt->u.dst; + dst_hold(&rt->dst); + inet->cork.dst = &rt->dst; inet->cork.fl = *fl; np->cork.hop_limit = hlimit; np->cork.tclass = tclass; mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ? - rt->u.dst.dev->mtu : dst_mtu(rt->u.dst.path); + rt->dst.dev->mtu : dst_mtu(rt->dst.path); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } inet->cork.fragsize = mtu; - if (dst_allfrag(rt->u.dst.path)) + if (dst_allfrag(rt->dst.path)) inet->cork.flags |= IPCORK_ALLFRAG; inet->cork.length = 0; sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; - exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0) - + exthdrlen = rt->dst.header_len + (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; length += exthdrlen; transhdrlen += exthdrlen; @@ -1186,7 +1186,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, mtu = inet->cork.fragsize; } - hh_len = LL_RESERVED_SPACE(rt->u.dst.dev); + hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); @@ -1224,7 +1224,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, } if (proto == IPPROTO_UDP && - (rt->u.dst.dev->features & NETIF_F_UFO)) { + (rt->dst.dev->features & NETIF_F_UFO)) { err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len, fragheaderlen, @@ -1270,7 +1270,7 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; if ((flags & MSG_MORE) && - !(rt->u.dst.dev->features&NETIF_F_SG)) + !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else alloclen = datalen + fragheaderlen; @@ -1281,7 +1281,7 @@ alloc_new_skb: * because we have no idea if we're the last one. */ if (datalen == length + fraggap) - alloclen += rt->u.dst.trailer_len; + alloclen += rt->dst.trailer_len; /* * We just reserve space for fragment header. @@ -1358,7 +1358,7 @@ alloc_new_skb: if (copy > length) copy = length; - if (!(rt->u.dst.dev->features&NETIF_F_SG)) { + if (!(rt->dst.dev->features&NETIF_F_SG)) { unsigned int off; off = skb->len; @@ -1503,7 +1503,7 @@ int ip6_push_pending_frames(struct sock *sk) skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb_dst_set(skb, dst_clone(&rt->u.dst)); + skb_dst_set(skb, dst_clone(&rt->dst)); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 8f39893d8081..0fd027f3f47e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -552,7 +552,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (ip_route_output_key(dev_net(skb->dev), &rt, &fl)) goto out; - skb2->dev = rt->u.dst.dev; + skb2->dev = rt->dst.dev; /* route "incoming" packet */ if (rt->rt_flags & RTCF_LOCAL) { @@ -562,7 +562,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, fl.fl4_src = eiph->saddr; fl.fl4_tos = eiph->tos; if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) || - rt->u.dst.dev->type != ARPHRD_TUNNEL) { + rt->dst.dev->type != ARPHRD_TUNNEL) { ip_rt_put(rt); goto out; } @@ -626,7 +626,7 @@ ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, icmpv6_send(skb2, rel_type, rel_code, rel_info); if (rt) - dst_release(&rt->u.dst); + dst_release(&rt->dst); kfree_skb(skb2); } @@ -1135,7 +1135,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; } - dst_release(&rt->u.dst); + dst_release(&rt->dst); } } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 3e36d1538b6e..d1444b95ad7e 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -158,7 +158,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) rt = rt6_lookup(net, addr, NULL, 0, 0); if (rt) { dev = rt->rt6i_dev; - dst_release(&rt->u.dst); + dst_release(&rt->dst); } } else dev = dev_get_by_index_rcu(net, ifindex); @@ -248,7 +248,7 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, if (rt) { dev = rt->rt6i_dev; dev_hold(dev); - dst_release(&rt->u.dst); + dst_release(&rt->dst); } } else dev = dev_get_by_index_rcu(net, ifindex); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 0abdc242ddb7..1fc46fc60efd 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1229,7 +1229,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) ND_PRINTK0(KERN_ERR "ICMPv6 RA: %s() got default router without neighbour.\n", __func__); - dst_release(&rt->u.dst); + dst_release(&rt->dst); in6_dev_put(in6_dev); return; } @@ -1244,7 +1244,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; if (rt) - rt->u.dst.metrics[RTAX_HOPLIMIT-1] = ra_msg->icmph.icmp6_hop_limit; + rt->dst.metrics[RTAX_HOPLIMIT-1] = ra_msg->icmph.icmp6_hop_limit; } skip_defrtr: @@ -1363,7 +1363,7 @@ skip_linkparms: in6_dev->cnf.mtu6 = mtu; if (rt) - rt->u.dst.metrics[RTAX_MTU-1] = mtu; + rt->dst.metrics[RTAX_MTU-1] = mtu; rt6_mtu_change(skb->dev, mtu); } @@ -1384,7 +1384,7 @@ skip_linkparms: } out: if (rt) - dst_release(&rt->u.dst); + dst_release(&rt->dst); else if (neigh) neigh_release(neigh); in6_dev_put(in6_dev); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 968b96490729..e677937a07fc 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -611,23 +611,23 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, int err; struct rt6_info *rt = (struct rt6_info *)*dstp; - if (length > rt->u.dst.dev->mtu) { - ipv6_local_error(sk, EMSGSIZE, fl, rt->u.dst.dev->mtu); + if (length > rt->dst.dev->mtu) { + ipv6_local_error(sk, EMSGSIZE, fl, rt->dst.dev->mtu); return -EMSGSIZE; } if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, - length + LL_ALLOCATED_SPACE(rt->u.dst.dev) + 15, + length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; - skb_reserve(skb, LL_RESERVED_SPACE(rt->u.dst.dev)); + skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev)); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); *dstp = NULL; skb_put(skb, length); @@ -643,7 +643,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, - rt->u.dst.dev, dst_output); + rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 252d76199c41..f7702850d45c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -126,16 +126,14 @@ static struct dst_ops ip6_dst_blackhole_ops = { }; static struct rt6_info ip6_null_entry_template = { - .u = { - .dst = { - .__refcnt = ATOMIC_INIT(1), - .__use = 1, - .obsolete = -1, - .error = -ENETUNREACH, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, - .input = ip6_pkt_discard, - .output = ip6_pkt_discard_out, - } + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .obsolete = -1, + .error = -ENETUNREACH, + .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, + .input = ip6_pkt_discard, + .output = ip6_pkt_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), .rt6i_protocol = RTPROT_KERNEL, @@ -149,16 +147,14 @@ static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct sk_buff *skb); static struct rt6_info ip6_prohibit_entry_template = { - .u = { - .dst = { - .__refcnt = ATOMIC_INIT(1), - .__use = 1, - .obsolete = -1, - .error = -EACCES, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, - .input = ip6_pkt_prohibit, - .output = ip6_pkt_prohibit_out, - } + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .obsolete = -1, + .error = -EACCES, + .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, + .input = ip6_pkt_prohibit, + .output = ip6_pkt_prohibit_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), .rt6i_protocol = RTPROT_KERNEL, @@ -167,16 +163,14 @@ static struct rt6_info ip6_prohibit_entry_template = { }; static struct rt6_info ip6_blk_hole_entry_template = { - .u = { - .dst = { - .__refcnt = ATOMIC_INIT(1), - .__use = 1, - .obsolete = -1, - .error = -EINVAL, - .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, - .input = dst_discard, - .output = dst_discard, - } + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .obsolete = -1, + .error = -EINVAL, + .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, + .input = dst_discard, + .output = dst_discard, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), .rt6i_protocol = RTPROT_KERNEL, @@ -249,7 +243,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net, if (!oif && ipv6_addr_any(saddr)) goto out; - for (sprt = rt; sprt; sprt = sprt->u.dst.rt6_next) { + for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) { struct net_device *dev = sprt->rt6i_dev; if (oif) { @@ -407,10 +401,10 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = NULL; for (rt = rr_head; rt && rt->rt6i_metric == metric; - rt = rt->u.dst.rt6_next) + rt = rt->dst.rt6_next) match = find_match(rt, oif, strict, &mpri, match); for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric; - rt = rt->u.dst.rt6_next) + rt = rt->dst.rt6_next) match = find_match(rt, oif, strict, &mpri, match); return match; @@ -432,7 +426,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) if (!match && (strict & RT6_LOOKUP_F_REACHABLE)) { - struct rt6_info *next = rt0->u.dst.rt6_next; + struct rt6_info *next = rt0->dst.rt6_next; /* no entries matched; do round-robin */ if (!next || next->rt6i_metric != rt0->rt6i_metric) @@ -517,7 +511,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, rt->rt6i_expires = jiffies + HZ * lifetime; rt->rt6i_flags |= RTF_EXPIRES; } - dst_release(&rt->u.dst); + dst_release(&rt->dst); } return 0; } @@ -555,7 +549,7 @@ restart: rt = rt6_device_match(net, rt, &fl->fl6_src, fl->oif, flags); BACKTRACK(net, &fl->fl6_src); out: - dst_use(&rt->u.dst, jiffies); + dst_use(&rt->dst, jiffies); read_unlock_bh(&table->tb6_lock); return rt; @@ -643,7 +637,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; - rt->u.dst.flags |= DST_HOST; + rt->dst.flags |= DST_HOST; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { @@ -677,7 +671,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad if (net_ratelimit()) printk(KERN_WARNING "Neighbour table overflow.\n"); - dst_free(&rt->u.dst); + dst_free(&rt->dst); return NULL; } rt->rt6i_nexthop = neigh; @@ -694,7 +688,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; - rt->u.dst.flags |= DST_HOST; + rt->dst.flags |= DST_HOST; rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop); } return rt; @@ -726,7 +720,7 @@ restart: rt->rt6i_flags & RTF_CACHE) goto out; - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) @@ -739,10 +733,10 @@ restart: #endif } - dst_release(&rt->u.dst); + dst_release(&rt->dst); rt = nrt ? : net->ipv6.ip6_null_entry; - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); if (nrt) { err = ip6_ins_rt(nrt); if (!err) @@ -756,7 +750,7 @@ restart: * Race condition! In the gap, when table->tb6_lock was * released someone could insert this route. Relookup. */ - dst_release(&rt->u.dst); + dst_release(&rt->dst); goto relookup; out: @@ -764,11 +758,11 @@ out: reachable = 0; goto restart_2; } - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); out2: - rt->u.dst.lastuse = jiffies; - rt->u.dst.__use++; + rt->dst.lastuse = jiffies; + rt->dst.__use++; return rt; } @@ -835,15 +829,15 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl struct dst_entry *new = NULL; if (rt) { - new = &rt->u.dst; + new = &rt->dst; atomic_set(&new->__refcnt, 1); new->__use = 1; new->input = dst_discard; new->output = dst_discard; - memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32)); - new->dev = ort->u.dst.dev; + memcpy(new->metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32)); + new->dev = ort->dst.dev; if (new->dev) dev_hold(new->dev); rt->rt6i_idev = ort->rt6i_idev; @@ -912,7 +906,7 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { if (rt->rt6i_flags&RTF_CACHE) { - dst_set_expires(&rt->u.dst, 0); + dst_set_expires(&rt->dst, 0); rt->rt6i_flags |= RTF_EXPIRES; } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) rt->rt6i_node->fn_sernum = -1; @@ -986,14 +980,14 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->rt6i_dev = dev; rt->rt6i_idev = idev; rt->rt6i_nexthop = neigh; - atomic_set(&rt->u.dst.__refcnt, 1); - rt->u.dst.metrics[RTAX_HOPLIMIT-1] = 255; - rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst)); - rt->u.dst.output = ip6_output; + atomic_set(&rt->dst.__refcnt, 1); + rt->dst.metrics[RTAX_HOPLIMIT-1] = 255; + rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); + rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst)); + rt->dst.output = ip6_output; #if 0 /* there's no chance to use these for ndisc */ - rt->u.dst.flags = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST + rt->dst.flags = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST ? DST_HOST : 0; ipv6_addr_copy(&rt->rt6i_dst.addr, addr); @@ -1001,14 +995,14 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, #endif spin_lock_bh(&icmp6_dst_lock); - rt->u.dst.next = icmp6_dst_gc_list; - icmp6_dst_gc_list = &rt->u.dst; + rt->dst.next = icmp6_dst_gc_list; + icmp6_dst_gc_list = &rt->dst; spin_unlock_bh(&icmp6_dst_lock); fib6_force_start_gc(net); out: - return &rt->u.dst; + return &rt->dst; } int icmp6_dst_gc(void) @@ -1159,7 +1153,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } - rt->u.dst.obsolete = -1; + rt->dst.obsolete = -1; rt->rt6i_expires = (cfg->fc_flags & RTF_EXPIRES) ? jiffies + clock_t_to_jiffies(cfg->fc_expires) : 0; @@ -1171,16 +1165,16 @@ int ip6_route_add(struct fib6_config *cfg) addr_type = ipv6_addr_type(&cfg->fc_dst); if (addr_type & IPV6_ADDR_MULTICAST) - rt->u.dst.input = ip6_mc_input; + rt->dst.input = ip6_mc_input; else - rt->u.dst.input = ip6_forward; + rt->dst.input = ip6_forward; - rt->u.dst.output = ip6_output; + rt->dst.output = ip6_output; 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; + rt->dst.flags = DST_HOST; #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); @@ -1208,9 +1202,9 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } } - rt->u.dst.output = ip6_pkt_discard_out; - rt->u.dst.input = ip6_pkt_discard; - rt->u.dst.error = -ENETUNREACH; + rt->dst.output = ip6_pkt_discard_out; + rt->dst.input = ip6_pkt_discard; + rt->dst.error = -ENETUNREACH; rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP; goto install_route; } @@ -1244,7 +1238,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; if (dev) { if (dev != grt->rt6i_dev) { - dst_release(&grt->u.dst); + dst_release(&grt->dst); goto out; } } else { @@ -1255,7 +1249,7 @@ int ip6_route_add(struct fib6_config *cfg) } if (!(grt->rt6i_flags&RTF_GATEWAY)) err = 0; - dst_release(&grt->u.dst); + dst_release(&grt->dst); if (err) goto out; @@ -1294,18 +1288,18 @@ install_route: goto out; } - rt->u.dst.metrics[type - 1] = nla_get_u32(nla); + rt->dst.metrics[type - 1] = nla_get_u32(nla); } } } - if (dst_metric(&rt->u.dst, RTAX_HOPLIMIT) == 0) - rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1; - if (!dst_mtu(&rt->u.dst)) - rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev); - if (!dst_metric(&rt->u.dst, RTAX_ADVMSS)) - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst)); - rt->u.dst.dev = dev; + if (dst_metric(&rt->dst, RTAX_HOPLIMIT) == 0) + rt->dst.metrics[RTAX_HOPLIMIT-1] = -1; + if (!dst_mtu(&rt->dst)) + rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev); + if (!dst_metric(&rt->dst, RTAX_ADVMSS)) + rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst)); + rt->dst.dev = dev; rt->rt6i_idev = idev; rt->rt6i_table = table; @@ -1319,7 +1313,7 @@ out: if (idev) in6_dev_put(idev); if (rt) - dst_free(&rt->u.dst); + dst_free(&rt->dst); return err; } @@ -1336,7 +1330,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) write_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); - dst_release(&rt->u.dst); + dst_release(&rt->dst); write_unlock_bh(&table->tb6_lock); @@ -1369,7 +1363,7 @@ static int ip6_route_del(struct fib6_config *cfg) &cfg->fc_src, cfg->fc_src_len); if (fn) { - for (rt = fn->leaf; rt; rt = rt->u.dst.rt6_next) { + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { if (cfg->fc_ifindex && (rt->rt6i_dev == NULL || rt->rt6i_dev->ifindex != cfg->fc_ifindex)) @@ -1379,7 +1373,7 @@ static int ip6_route_del(struct fib6_config *cfg) continue; if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric) continue; - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); return __ip6_del_rt(rt, &cfg->fc_nlinfo); @@ -1421,7 +1415,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, 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.dst.rt6_next) { + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { /* * Current route is on-link; redirect is always invalid. * @@ -1445,7 +1439,7 @@ restart: rt = net->ipv6.ip6_null_entry; BACKTRACK(net, &fl->fl6_src); out: - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); @@ -1513,10 +1507,10 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, * Look, redirects are sent only in response to data packets, * so that this nexthop apparently is reachable. --ANK */ - dst_confirm(&rt->u.dst); + dst_confirm(&rt->dst); /* Duplicate redirect: silently ignore. */ - if (neigh == rt->u.dst.neighbour) + if (neigh == rt->dst.neighbour) goto out; nrt = ip6_rt_copy(rt); @@ -1529,20 +1523,20 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, ipv6_addr_copy(&nrt->rt6i_dst.addr, dest); nrt->rt6i_dst.plen = 128; - nrt->u.dst.flags |= DST_HOST; + nrt->dst.flags |= DST_HOST; ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key); nrt->rt6i_nexthop = neigh_clone(neigh); /* Reset pmtu, it may be better */ - nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev); - nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dev_net(neigh->dev), - dst_mtu(&nrt->u.dst)); + nrt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev); + nrt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dev_net(neigh->dev), + dst_mtu(&nrt->dst)); if (ip6_ins_rt(nrt)) goto out; - netevent.old = &rt->u.dst; - netevent.new = &nrt->u.dst; + netevent.old = &rt->dst; + netevent.new = &nrt->dst; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); if (rt->rt6i_flags&RTF_CACHE) { @@ -1551,7 +1545,7 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, } out: - dst_release(&rt->u.dst); + dst_release(&rt->dst); } /* @@ -1570,7 +1564,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, if (rt == NULL) return; - if (pmtu >= dst_mtu(&rt->u.dst)) + if (pmtu >= dst_mtu(&rt->dst)) goto out; if (pmtu < IPV6_MIN_MTU) { @@ -1588,7 +1582,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, They are sent only in response to data packets, so that this nexthop apparently is reachable. --ANK */ - dst_confirm(&rt->u.dst); + dst_confirm(&rt->dst); /* Host route. If it is static, it would be better not to override it, but add new one, so that @@ -1596,10 +1590,10 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, would return automatically. */ if (rt->rt6i_flags & RTF_CACHE) { - rt->u.dst.metrics[RTAX_MTU-1] = pmtu; + rt->dst.metrics[RTAX_MTU-1] = pmtu; if (allfrag) - rt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; - dst_set_expires(&rt->u.dst, net->ipv6.sysctl.ip6_rt_mtu_expires); + rt->dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + dst_set_expires(&rt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires); rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES; goto out; } @@ -1615,9 +1609,9 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, nrt = rt6_alloc_clone(rt, daddr); if (nrt) { - nrt->u.dst.metrics[RTAX_MTU-1] = pmtu; + nrt->dst.metrics[RTAX_MTU-1] = pmtu; if (allfrag) - nrt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; + nrt->dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG; /* According to RFC 1981, detecting PMTU increase shouldn't be * happened within 5 mins, the recommended timer is 10 mins. @@ -1625,13 +1619,13 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, * which is 10 mins. After 10 mins the decreased pmtu is expired * and detecting PMTU increase will be automatically happened. */ - dst_set_expires(&nrt->u.dst, net->ipv6.sysctl.ip6_rt_mtu_expires); + dst_set_expires(&nrt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires); nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES; ip6_ins_rt(nrt); } out: - dst_release(&rt->u.dst); + dst_release(&rt->dst); } /* @@ -1644,18 +1638,18 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops); if (rt) { - rt->u.dst.input = ort->u.dst.input; - rt->u.dst.output = ort->u.dst.output; - - memcpy(rt->u.dst.metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32)); - rt->u.dst.error = ort->u.dst.error; - rt->u.dst.dev = ort->u.dst.dev; - if (rt->u.dst.dev) - dev_hold(rt->u.dst.dev); + rt->dst.input = ort->dst.input; + rt->dst.output = ort->dst.output; + + memcpy(rt->dst.metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32)); + rt->dst.error = ort->dst.error; + rt->dst.dev = ort->dst.dev; + if (rt->dst.dev) + dev_hold(rt->dst.dev); rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); - rt->u.dst.lastuse = jiffies; + rt->dst.lastuse = jiffies; rt->rt6i_expires = 0; ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway); @@ -1689,14 +1683,14 @@ static struct rt6_info *rt6_get_route_info(struct net *net, if (!fn) goto out; - for (rt = fn->leaf; rt; rt = rt->u.dst.rt6_next) { + for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { if (rt->rt6i_dev->ifindex != ifindex) continue; if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) continue; if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) continue; - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); break; } out: @@ -1744,14 +1738,14 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d return NULL; write_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt=rt->u.dst.rt6_next) { + for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) { if (dev == rt->rt6i_dev && ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&rt->rt6i_gateway, addr)) break; } if (rt) - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); write_unlock_bh(&table->tb6_lock); return rt; } @@ -1790,9 +1784,9 @@ void rt6_purge_dflt_routers(struct net *net) restart: read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->u.dst.rt6_next) { + for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { - dst_hold(&rt->u.dst); + dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); ip6_del_rt(rt); goto restart; @@ -1930,15 +1924,15 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, dev_hold(net->loopback_dev); in6_dev_hold(idev); - rt->u.dst.flags = DST_HOST; - rt->u.dst.input = ip6_input; - rt->u.dst.output = ip6_output; + rt->dst.flags = DST_HOST; + rt->dst.input = ip6_input; + rt->dst.output = ip6_output; rt->rt6i_dev = net->loopback_dev; rt->rt6i_idev = idev; - rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->u.dst)); - rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1; - rt->u.dst.obsolete = -1; + rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev); + rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst)); + rt->dst.metrics[RTAX_HOPLIMIT-1] = -1; + rt->dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; if (anycast) @@ -1947,7 +1941,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_flags |= RTF_LOCAL; neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway); if (IS_ERR(neigh)) { - dst_free(&rt->u.dst); + dst_free(&rt->dst); /* We are casting this because that is the return * value type. But an errno encoded pointer is the @@ -1962,7 +1956,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); - atomic_set(&rt->u.dst.__refcnt, 1); + atomic_set(&rt->dst.__refcnt, 1); return rt; } @@ -2033,12 +2027,12 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) PMTU discouvery. */ if (rt->rt6i_dev == arg->dev && - !dst_metric_locked(&rt->u.dst, RTAX_MTU) && - (dst_mtu(&rt->u.dst) >= arg->mtu || - (dst_mtu(&rt->u.dst) < arg->mtu && - dst_mtu(&rt->u.dst) == idev->cnf.mtu6))) { - rt->u.dst.metrics[RTAX_MTU-1] = arg->mtu; - rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, arg->mtu); + !dst_metric_locked(&rt->dst, RTAX_MTU) && + (dst_mtu(&rt->dst) >= arg->mtu || + (dst_mtu(&rt->dst) < arg->mtu && + dst_mtu(&rt->dst) == idev->cnf.mtu6))) { + rt->dst.metrics[RTAX_MTU-1] = arg->mtu; + rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, arg->mtu); } return 0; } @@ -2252,20 +2246,20 @@ static int rt6_fill_node(struct net *net, #endif NLA_PUT_U32(skb, RTA_IIF, iif); } else if (dst) { - struct inet6_dev *idev = ip6_dst_idev(&rt->u.dst); + struct inet6_dev *idev = ip6_dst_idev(&rt->dst); struct in6_addr saddr_buf; if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, dst, 0, &saddr_buf) == 0) NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } - if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) + if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0) goto nla_put_failure; - if (rt->u.dst.neighbour) - NLA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key); + if (rt->dst.neighbour) + NLA_PUT(skb, RTA_GATEWAY, 16, &rt->dst.neighbour->primary_key); - if (rt->u.dst.dev) + if (rt->dst.dev) NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex); NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric); @@ -2277,8 +2271,8 @@ static int rt6_fill_node(struct net *net, else expires = INT_MAX; - if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0, - expires, rt->u.dst.error) < 0) + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0, + expires, rt->dst.error) < 0) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2364,7 +2358,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr)); rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, @@ -2416,12 +2410,12 @@ static int ip6_route_dev_notify(struct notifier_block *this, struct net *net = dev_net(dev); if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) { - net->ipv6.ip6_null_entry->u.dst.dev = dev; + net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES - net->ipv6.ip6_prohibit_entry->u.dst.dev = dev; + net->ipv6.ip6_prohibit_entry->dst.dev = dev; net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev); - net->ipv6.ip6_blk_hole_entry->u.dst.dev = dev; + net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); #endif } @@ -2464,8 +2458,8 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) seq_puts(m, "00000000000000000000000000000000"); } seq_printf(m, " %08x %08x %08x %08x %8s\n", - rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt), - rt->u.dst.__use, rt->rt6i_flags, + rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), + rt->dst.__use, rt->rt6i_flags, rt->rt6i_dev ? rt->rt6i_dev->name : ""); return 0; } @@ -2646,9 +2640,9 @@ static int __net_init ip6_route_net_init(struct net *net) GFP_KERNEL); if (!net->ipv6.ip6_null_entry) goto out_ip6_dst_ops; - net->ipv6.ip6_null_entry->u.dst.path = + net->ipv6.ip6_null_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; - net->ipv6.ip6_null_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; + net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, @@ -2656,18 +2650,18 @@ static int __net_init ip6_route_net_init(struct net *net) GFP_KERNEL); if (!net->ipv6.ip6_prohibit_entry) goto out_ip6_null_entry; - net->ipv6.ip6_prohibit_entry->u.dst.path = + net->ipv6.ip6_prohibit_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_prohibit_entry; - net->ipv6.ip6_prohibit_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; + net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), GFP_KERNEL); if (!net->ipv6.ip6_blk_hole_entry) goto out_ip6_prohibit_entry; - net->ipv6.ip6_blk_hole_entry->u.dst.path = + net->ipv6.ip6_blk_hole_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; - net->ipv6.ip6_blk_hole_entry->u.dst.ops = &net->ipv6.ip6_dst_ops; + net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; #endif net->ipv6.sysctl.flush_delay = 0; @@ -2742,12 +2736,12 @@ int __init ip6_route_init(void) /* Registering of the loopback is done before this portion of code, * the loopback reference in rt6_info will not be taken, do it * manually for init_net */ - init_net.ipv6.ip6_null_entry->u.dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES - init_net.ipv6.ip6_prohibit_entry->u.dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); - init_net.ipv6.ip6_blk_hole_entry->u.dst.dev = init_net.loopback_dev; + init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #endif ret = fib6_init(); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 702c532ec21e..4699cd3c3118 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -712,7 +712,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, stats->tx_carrier_errors++; goto tx_error_icmp; } - tdev = rt->u.dst.dev; + tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); @@ -721,7 +721,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (df) { - mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); + mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { stats->collisions++; @@ -780,7 +780,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags = 0; skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* * Push down and install the IPIP header. @@ -829,7 +829,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) .proto = IPPROTO_IPV6 }; struct rtable *rt; if (!ip_route_output_key(dev_net(dev), &rt, &fl)) { - tdev = rt->u.dst.dev; + tdev = rt->dst.dev; ip_rt_put(rt); } dev->flags |= IFF_POINTOPOINT; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 0852512d392c..226a0ae3bcfd 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -348,7 +348,7 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len sk->sk_state = TCP_ESTABLISHED; inet->inet_id = jiffies; - sk_dst_set(sk, &rt->u.dst); + sk_dst_set(sk, &rt->dst); write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); @@ -496,9 +496,9 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0)) goto no_route; } - sk_setup_caps(sk, &rt->u.dst); + sk_setup_caps(sk, &rt->dst); } - skb_dst_set(skb, dst_clone(&rt->u.dst)); + skb_dst_set(skb, dst_clone(&rt->dst)); /* Queue the packet to IP for output */ rc = ip_queue_xmit(skb); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 93c15a107b2c..02b078e11cf3 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -90,10 +90,10 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos) &dest->addr.ip); return NULL; } - __ip_vs_dst_set(dest, rtos, dst_clone(&rt->u.dst)); + __ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst)); IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n", &dest->addr.ip, - atomic_read(&rt->u.dst.__refcnt), rtos); + atomic_read(&rt->dst.__refcnt), rtos); } spin_unlock(&dest->dst_lock); } else { @@ -148,10 +148,10 @@ __ip_vs_get_out_rt_v6(struct ip_vs_conn *cp) &dest->addr.in6); return NULL; } - __ip_vs_dst_set(dest, 0, dst_clone(&rt->u.dst)); + __ip_vs_dst_set(dest, 0, dst_clone(&rt->dst)); IP_VS_DBG(10, "new dst %pI6, refcnt=%d\n", &dest->addr.in6, - atomic_read(&rt->u.dst.__refcnt)); + atomic_read(&rt->dst.__refcnt)); } spin_unlock(&dest->dst_lock); } else { @@ -198,7 +198,7 @@ do { \ (skb)->ipvs_property = 1; \ skb_forward_csum(skb); \ NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \ - (rt)->u.dst.dev, dst_output); \ + (rt)->dst.dev, dst_output); \ } while (0) @@ -245,7 +245,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, } /* MTU checking */ - mtu = dst_mtu(&rt->u.dst); + mtu = dst_mtu(&rt->dst); if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) { ip_rt_put(rt); icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); @@ -265,7 +265,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* drop old route */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -309,9 +309,9 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* MTU checking */ - mtu = dst_mtu(&rt->u.dst); + mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { - dst_release(&rt->u.dst); + dst_release(&rt->dst); icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; @@ -323,13 +323,13 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, */ skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(skb == NULL)) { - dst_release(&rt->u.dst); + dst_release(&rt->dst); return NF_STOLEN; } /* drop old route */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -376,7 +376,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_icmp; /* MTU checking */ - mtu = dst_mtu(&rt->u.dst); + mtu = dst_mtu(&rt->dst); if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) { ip_rt_put(rt); icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); @@ -388,12 +388,12 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!skb_make_writable(skb, sizeof(struct iphdr))) goto tx_error_put; - if (skb_cow(skb, rt->u.dst.dev->hard_header_len)) + if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; /* drop old route */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) @@ -452,9 +452,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_icmp; /* MTU checking */ - mtu = dst_mtu(&rt->u.dst); + mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { - dst_release(&rt->u.dst); + dst_release(&rt->dst); icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL_PKT(0, pp, skb, 0, "ip_vs_nat_xmit_v6(): frag needed for"); @@ -465,12 +465,12 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (!skb_make_writable(skb, sizeof(struct ipv6hdr))) goto tx_error_put; - if (skb_cow(skb, rt->u.dst.dev->hard_header_len)) + if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; /* drop old route */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) @@ -498,7 +498,7 @@ tx_error: kfree_skb(skb); return NF_STOLEN; tx_error_put: - dst_release(&rt->u.dst); + dst_release(&rt->dst); goto tx_error; } #endif @@ -549,9 +549,9 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(tos)))) goto tx_error_icmp; - tdev = rt->u.dst.dev; + tdev = rt->dst.dev; - mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); + mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { ip_rt_put(rt); IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__); @@ -601,7 +601,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* drop old route */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* * Push down and install the IPIP header. @@ -615,7 +615,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = rt->rt_dst; iph->saddr = rt->rt_src; iph->ttl = old_iph->ttl; - ip_select_ident(iph, &rt->u.dst, NULL); + ip_select_ident(iph, &rt->dst, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -660,12 +660,12 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (!rt) goto tx_error_icmp; - tdev = rt->u.dst.dev; + tdev = rt->dst.dev; - mtu = dst_mtu(&rt->u.dst) - sizeof(struct ipv6hdr); + mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr); /* TODO IPv6: do we need this check in IPv6? */ if (mtu < 1280) { - dst_release(&rt->u.dst); + dst_release(&rt->dst); IP_VS_DBG_RL("%s(): mtu less than 1280\n", __func__); goto tx_error; } @@ -674,7 +674,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - dst_release(&rt->u.dst); + dst_release(&rt->dst); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -689,7 +689,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { - dst_release(&rt->u.dst); + dst_release(&rt->dst); kfree_skb(skb); IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; @@ -707,7 +707,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* drop old route */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* * Push down and install the IPIP header. @@ -760,7 +760,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_icmp; /* MTU checking */ - mtu = dst_mtu(&rt->u.dst); + mtu = dst_mtu(&rt->dst); if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); ip_rt_put(rt); @@ -780,7 +780,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* drop old route */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -813,10 +813,10 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_icmp; /* MTU checking */ - mtu = dst_mtu(&rt->u.dst); + mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - dst_release(&rt->u.dst); + dst_release(&rt->dst); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; } @@ -827,13 +827,13 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, */ skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(skb == NULL)) { - dst_release(&rt->u.dst); + dst_release(&rt->dst); return NF_STOLEN; } /* drop old route */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; @@ -888,7 +888,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_icmp; /* MTU checking */ - mtu = dst_mtu(&rt->u.dst); + mtu = dst_mtu(&rt->dst); if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) { ip_rt_put(rt); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); @@ -900,12 +900,12 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, if (!skb_make_writable(skb, offset)) goto tx_error_put; - if (skb_cow(skb, rt->u.dst.dev->hard_header_len)) + if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; /* drop the old route when skb is not shared */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); ip_vs_nat_icmp(skb, pp, cp, 0); @@ -963,9 +963,9 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_icmp; /* MTU checking */ - mtu = dst_mtu(&rt->u.dst); + mtu = dst_mtu(&rt->dst); if (skb->len > mtu) { - dst_release(&rt->u.dst); + dst_release(&rt->dst); icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error; @@ -975,12 +975,12 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (!skb_make_writable(skb, offset)) goto tx_error_put; - if (skb_cow(skb, rt->u.dst.dev->hard_header_len)) + if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; /* drop the old route when skb is not shared */ skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); + skb_dst_set(skb, &rt->dst); ip_vs_nat_icmp_v6(skb, pp, cp, 0); @@ -1001,7 +1001,7 @@ out: LeaveFunction(10); return rc; tx_error_put: - dst_release(&rt->u.dst); + dst_release(&rt->dst); goto tx_error; } #endif diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 6eaee7c8a337..b969025cf82f 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -734,11 +734,11 @@ static int callforward_do_filter(const union nf_inet_addr *src, if (!afinfo->route((struct dst_entry **)&rt1, &fl1)) { if (!afinfo->route((struct dst_entry **)&rt2, &fl2)) { if (rt1->rt_gateway == rt2->rt_gateway && - rt1->u.dst.dev == rt2->u.dst.dev) + rt1->dst.dev == rt2->dst.dev) ret = 1; - dst_release(&rt2->u.dst); + dst_release(&rt2->dst); } - dst_release(&rt1->u.dst); + dst_release(&rt1->dst); } break; } @@ -753,11 +753,11 @@ static int callforward_do_filter(const union nf_inet_addr *src, if (!afinfo->route((struct dst_entry **)&rt2, &fl2)) { if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, sizeof(rt1->rt6i_gateway)) && - rt1->u.dst.dev == rt2->u.dst.dev) + rt1->dst.dev == rt2->dst.dev) ret = 1; - dst_release(&rt2->u.dst); + dst_release(&rt2->dst); } - dst_release(&rt1->u.dst); + dst_release(&rt1->dst); } break; } diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c index 497b2224536f..aadde018a072 100644 --- a/net/netfilter/nf_conntrack_netbios_ns.c +++ b/net/netfilter/nf_conntrack_netbios_ns.c @@ -61,7 +61,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, goto out; rcu_read_lock(); - in_dev = __in_dev_get_rcu(rt->u.dst.dev); + in_dev = __in_dev_get_rcu(rt->dst.dev); if (in_dev != NULL) { for_primary_ifa(in_dev) { if (ifa->ifa_broadcast == iph->daddr) { diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 62ec021fbd50..1841388c770a 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -165,8 +165,8 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb, rcu_read_unlock(); if (rt != NULL) { - mtu = dst_mtu(&rt->u.dst); - dst_release(&rt->u.dst); + mtu = dst_mtu(&rt->dst); + dst_release(&rt->dst); } return mtu; } diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 859d9fd429c8..c77a85bbd9eb 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -77,8 +77,8 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info) return false; skb_dst_drop(skb); - skb_dst_set(skb, &rt->u.dst); - skb->dev = rt->u.dst.dev; + skb_dst_set(skb, &rt->dst); + skb->dev = rt->dst.dev; skb->protocol = htons(ETH_P_IP); return true; } diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c index f0f85b0123f7..9f1729bd60de 100644 --- a/net/rxrpc/ar-peer.c +++ b/net/rxrpc/ar-peer.c @@ -64,8 +64,8 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer) return; } - peer->if_mtu = dst_mtu(&rt->u.dst); - dst_release(&rt->u.dst); + peer->if_mtu = dst_mtu(&rt->dst); + dst_release(&rt->dst); _leave(" [if_mtu %u]", peer->if_mtu); } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 182749867c72..a0e1a7fdebbf 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -490,7 +490,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, __func__, &fl.fl4_dst, &fl.fl4_src); if (!ip_route_output_key(&init_net, &rt, &fl)) { - dst = &rt->u.dst; + dst = &rt->dst; } /* If there is no association or if a source address is passed, no @@ -534,7 +534,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, fl.fl4_src = laddr->a.v4.sin_addr.s_addr; fl.fl_ip_sport = laddr->a.v4.sin_port; if (!ip_route_output_key(&init_net, &rt, &fl)) { - dst = &rt->u.dst; + dst = &rt->dst; goto out_unlock; } } -- cgit v1.2.3 From c7de2cf053420d63bac85133469c965d4b1083e1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Jun 2010 02:09:23 +0000 Subject: pkt_sched: gen_kill_estimator() rcu fixes gen_kill_estimator() API is incomplete or not well documented, since caller should make sure an RCU grace period is respected before freeing stats_lock. This was partially addressed in commit 5d944c640b4 (gen_estimator: deadlock fix), but same problem exist for all gen_kill_estimator() users, if lock they use is not already RCU protected. A code review shows xt_RATEEST.c, act_api.c, act_police.c have this problem. Other are ok because they use qdisc lock, already RCU protected. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/act_api.h | 2 ++ include/net/netfilter/xt_rateest.h | 1 + net/core/gen_estimator.c | 1 + net/netfilter/xt_RATEEST.c | 12 +++++++++++- net/sched/act_api.c | 11 ++++++++++- net/sched/act_police.c | 12 +++++++++++- 6 files changed, 36 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index c05fd717c588..bab385f13ac3 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -20,6 +20,7 @@ struct tcf_common { struct gnet_stats_queue tcfc_qstats; struct gnet_stats_rate_est tcfc_rate_est; spinlock_t tcfc_lock; + struct rcu_head tcfc_rcu; }; #define tcf_next common.tcfc_next #define tcf_index common.tcfc_index @@ -32,6 +33,7 @@ struct tcf_common { #define tcf_qstats common.tcfc_qstats #define tcf_rate_est common.tcfc_rate_est #define tcf_lock common.tcfc_lock +#define tcf_rcu common.tcfc_rcu struct tcf_police { struct tcf_common common; diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h index ddbf37e19616..5e1427795928 100644 --- a/include/net/netfilter/xt_rateest.h +++ b/include/net/netfilter/xt_rateest.h @@ -9,6 +9,7 @@ struct xt_rateest { struct gnet_estimator params; struct gnet_stats_rate_est rstats; struct gnet_stats_basic_packed bstats; + struct rcu_head rcu; }; extern struct xt_rateest *xt_rateest_lookup(const char *name); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 785e5276a300..9fbe7f7429b0 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -263,6 +263,7 @@ static void __gen_kill_estimator(struct rcu_head *head) * * Removes the rate estimator specified by &bstats and &rate_est. * + * Note : Caller should respect an RCU grace period before freeing stats_lock */ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est) diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 69c01e10f8af..de079abd5bc8 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -60,13 +60,22 @@ struct xt_rateest *xt_rateest_lookup(const char *name) } EXPORT_SYMBOL_GPL(xt_rateest_lookup); +static void xt_rateest_free_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct xt_rateest, rcu)); +} + void xt_rateest_put(struct xt_rateest *est) { mutex_lock(&xt_rateest_mutex); if (--est->refcnt == 0) { hlist_del(&est->list); gen_kill_estimator(&est->bstats, &est->rstats); - kfree(est); + /* + * gen_estimator est_timer() might access est->lock or bstats, + * wait a RCU grace period before freeing 'est' + */ + call_rcu(&est->rcu, xt_rateest_free_rcu); } mutex_unlock(&xt_rateest_mutex); } @@ -179,6 +188,7 @@ static int __init xt_rateest_tg_init(void) static void __exit xt_rateest_tg_fini(void) { xt_unregister_target(&xt_rateest_tg_reg); + rcu_barrier(); /* Wait for completion of call_rcu()'s (xt_rateest_free_rcu) */ } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 972378f47f3c..23b25f89e7e0 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -26,6 +26,11 @@ #include #include +static void tcf_common_free_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct tcf_common, tcfc_rcu)); +} + void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) { unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask); @@ -38,7 +43,11 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) write_unlock_bh(hinfo->lock); gen_kill_estimator(&p->tcfc_bstats, &p->tcfc_rate_est); - kfree(p); + /* + * gen_estimator est_timer() might access p->tcfc_lock + * or bstats, wait a RCU grace period before freeing p + */ + call_rcu(&p->tcfc_rcu, tcf_common_free_rcu); return; } } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 654f73dff7c1..537a48732e9e 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -97,6 +97,11 @@ nla_put_failure: goto done; } +static void tcf_police_free_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct tcf_police, tcf_rcu)); +} + static void tcf_police_destroy(struct tcf_police *p) { unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK); @@ -113,7 +118,11 @@ static void tcf_police_destroy(struct tcf_police *p) qdisc_put_rtab(p->tcfp_R_tab); if (p->tcfp_P_tab) qdisc_put_rtab(p->tcfp_P_tab); - kfree(p); + /* + * gen_estimator est_timer() might access p->tcf_lock + * or bstats, wait a RCU grace period before freeing p + */ + call_rcu(&p->tcf_rcu, tcf_police_free_rcu); return; } } @@ -397,6 +406,7 @@ static void __exit police_cleanup_module(void) { tcf_unregister_action(&act_police_ops); + rcu_barrier(); /* Wait for completion of call_rcu()'s (tcf_police_free_rcu) */ } module_init(police_init_module); -- cgit v1.2.3 From be1f3c2c027cc5ad735df6a45a542ed1db7ec48b Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 8 Jun 2010 07:19:54 +0000 Subject: net: Enable 64-bit net device statistics on 32-bit architectures Use struct rtnl_link_stats64 as the statistics structure. On 32-bit architectures, insert 32 bits of padding after/before each field of struct net_device_stats to make its layout compatible with struct rtnl_link_stats64. Add an anonymous union in net_device; move stats into the union and add struct rtnl_link_stats64 stats64. Add net_device_ops::ndo_get_stats64, implementations of which will return a pointer to struct rtnl_link_stats64. Drivers that implement this operation must not update the structure asynchronously. Change dev_get_stats() to call ndo_get_stats64 if available, and to return a pointer to struct rtnl_link_stats64. Change callers of dev_get_stats() accordingly. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 13 +++--- include/linux/if_link.h | 3 +- include/linux/netdevice.h | 91 ++++++++++++++++++++++++----------------- net/8021q/vlanproc.c | 13 +++--- net/core/dev.c | 19 +++++---- net/core/net-sysfs.c | 12 +++--- net/core/rtnetlink.c | 6 +-- 7 files changed, 90 insertions(+), 67 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ac4f94b7da37..a95a41b74b4e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3804,20 +3804,21 @@ static int bond_close(struct net_device *bond_dev) return 0; } -static struct net_device_stats *bond_get_stats(struct net_device *bond_dev) +static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct net_device_stats *stats = &bond_dev->stats; - struct net_device_stats local_stats; + struct rtnl_link_stats64 *stats = &bond_dev->stats64; + struct rtnl_link_stats64 local_stats; struct slave *slave; int i; - memset(&local_stats, 0, sizeof(struct net_device_stats)); + memset(&local_stats, 0, sizeof(local_stats)); read_lock_bh(&bond->lock); bond_for_each_slave(bond, slave, i) { - const struct net_device_stats *sstats = dev_get_stats(slave->dev); + const struct rtnl_link_stats64 *sstats = + dev_get_stats(slave->dev); local_stats.rx_packets += sstats->rx_packets; local_stats.rx_bytes += sstats->rx_bytes; @@ -4569,7 +4570,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_stop = bond_close, .ndo_start_xmit = bond_start_xmit, .ndo_select_queue = bond_select_queue, - .ndo_get_stats = bond_get_stats, + .ndo_get_stats64 = bond_get_stats, .ndo_do_ioctl = bond_do_ioctl, .ndo_set_multicast_list = bond_set_multicast_list, .ndo_change_mtu = bond_change_mtu, diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 85c812db5a3f..7fcad2e1be3d 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -4,7 +4,7 @@ #include #include -/* The struct should be in sync with struct net_device_stats */ +/* This struct should be in sync with struct rtnl_link_stats64 */ struct rtnl_link_stats { __u32 rx_packets; /* total packets received */ __u32 tx_packets; /* total packets transmitted */ @@ -37,6 +37,7 @@ struct rtnl_link_stats { __u32 tx_compressed; }; +/* The main device statistics structure */ struct rtnl_link_stats64 { __u64 rx_packets; /* total packets received */ __u64 tx_packets; /* total packets transmitted */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c319f28d699d..4fbccc5f609a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -159,45 +159,49 @@ static inline bool dev_xmit_complete(int rc) #define MAX_HEADER (LL_MAX_HEADER + 48) #endif -#endif /* __KERNEL__ */ - /* - * Network device statistics. Akin to the 2.0 ether stats but - * with byte counters. + * Old network device statistics. Fields are native words + * (unsigned long) so they can be read and written atomically. + * Each field is padded to 64 bits for compatibility with + * rtnl_link_stats64. */ +#if BITS_PER_LONG == 64 +#define NET_DEVICE_STATS_DEFINE(name) unsigned long name +#elif defined(__LITTLE_ENDIAN) +#define NET_DEVICE_STATS_DEFINE(name) unsigned long name, pad_ ## name +#else +#define NET_DEVICE_STATS_DEFINE(name) unsigned long pad_ ## name, name +#endif + struct net_device_stats { - unsigned long rx_packets; /* total packets received */ - unsigned long tx_packets; /* total packets transmitted */ - unsigned long rx_bytes; /* total bytes received */ - unsigned long tx_bytes; /* total bytes transmitted */ - unsigned long rx_errors; /* bad packets received */ - unsigned long tx_errors; /* packet transmit problems */ - unsigned long rx_dropped; /* no space in linux buffers */ - unsigned long tx_dropped; /* no space available in linux */ - unsigned long multicast; /* multicast packets received */ - unsigned long collisions; - - /* detailed rx_errors: */ - unsigned long rx_length_errors; - unsigned long rx_over_errors; /* receiver ring buff overflow */ - unsigned long rx_crc_errors; /* recved pkt with crc error */ - unsigned long rx_frame_errors; /* recv'd frame alignment error */ - unsigned long rx_fifo_errors; /* recv'r fifo overrun */ - unsigned long rx_missed_errors; /* receiver missed packet */ - - /* detailed tx_errors */ - unsigned long tx_aborted_errors; - unsigned long tx_carrier_errors; - unsigned long tx_fifo_errors; - unsigned long tx_heartbeat_errors; - unsigned long tx_window_errors; - - /* for cslip etc */ - unsigned long rx_compressed; - unsigned long tx_compressed; + NET_DEVICE_STATS_DEFINE(rx_packets); + NET_DEVICE_STATS_DEFINE(tx_packets); + NET_DEVICE_STATS_DEFINE(rx_bytes); + NET_DEVICE_STATS_DEFINE(tx_bytes); + NET_DEVICE_STATS_DEFINE(rx_errors); + NET_DEVICE_STATS_DEFINE(tx_errors); + NET_DEVICE_STATS_DEFINE(rx_dropped); + NET_DEVICE_STATS_DEFINE(tx_dropped); + NET_DEVICE_STATS_DEFINE(multicast); + NET_DEVICE_STATS_DEFINE(collisions); + NET_DEVICE_STATS_DEFINE(rx_length_errors); + NET_DEVICE_STATS_DEFINE(rx_over_errors); + NET_DEVICE_STATS_DEFINE(rx_crc_errors); + NET_DEVICE_STATS_DEFINE(rx_frame_errors); + NET_DEVICE_STATS_DEFINE(rx_fifo_errors); + NET_DEVICE_STATS_DEFINE(rx_missed_errors); + NET_DEVICE_STATS_DEFINE(tx_aborted_errors); + NET_DEVICE_STATS_DEFINE(tx_carrier_errors); + NET_DEVICE_STATS_DEFINE(tx_fifo_errors); + NET_DEVICE_STATS_DEFINE(tx_heartbeat_errors); + NET_DEVICE_STATS_DEFINE(tx_window_errors); + NET_DEVICE_STATS_DEFINE(rx_compressed); + NET_DEVICE_STATS_DEFINE(tx_compressed); }; +#endif /* __KERNEL__ */ + /* Media selection options. */ enum { @@ -662,10 +666,19 @@ struct netdev_rx_queue { * Callback uses when the transmitter has not made any progress * for dev->watchdog ticks. * + * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev); * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage - * statistics. If not defined, the counters in dev->stats will - * be used. + * statistics. Drivers must do one of the following: + * 1. Define @ndo_get_stats64 to update a rtnl_link_stats64 structure + * (which should normally be dev->stats64) and return a ponter to + * it. The structure must not be changed asynchronously. + * 2. Define @ndo_get_stats to update a net_device_stats64 structure + * (which should normally be dev->stats) and return a pointer to + * it. The structure may be changed asynchronously only if each + * field is written atomically. + * 3. Update dev->stats asynchronously and atomically, and define + * neither operation. * * void (*ndo_vlan_rx_register)(struct net_device *dev, struct vlan_group *grp); * If device support VLAN receive accleration @@ -720,6 +733,7 @@ struct net_device_ops { struct neigh_parms *); void (*ndo_tx_timeout) (struct net_device *dev); + struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); void (*ndo_vlan_rx_register)(struct net_device *dev, @@ -869,7 +883,10 @@ struct net_device { int ifindex; int iflink; - struct net_device_stats stats; + union { + struct rtnl_link_stats64 stats64; + struct net_device_stats stats; + }; #ifdef CONFIG_WIRELESS_EXT /* List of functions to handle Wireless Extensions (instead of ioctl). @@ -2121,7 +2138,7 @@ extern void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ extern void dev_load(struct net *net, const char *name); extern void dev_mcast_init(void); -extern const struct net_device_stats *dev_get_stats(struct net_device *dev); +extern const struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev); extern void dev_txq_stats_fold(const struct net_device *dev, struct net_device_stats *stats); extern int netdev_max_backlog; diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index afead353e215..df56f5ce887c 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -278,8 +278,9 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset) { struct net_device *vlandev = (struct net_device *) seq->private; const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev); - const struct net_device_stats *stats; + const struct rtnl_link_stats64 *stats; static const char fmt[] = "%30s %12lu\n"; + static const char fmt64[] = "%30s %12llu\n"; int i; if (!is_vlan_dev(vlandev)) @@ -291,12 +292,12 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset) vlandev->name, dev_info->vlan_id, (int)(dev_info->flags & 1), vlandev->priv_flags); - seq_printf(seq, fmt, "total frames received", stats->rx_packets); - seq_printf(seq, fmt, "total bytes received", stats->rx_bytes); - seq_printf(seq, fmt, "Broadcast/Multicast Rcvd", stats->multicast); + seq_printf(seq, fmt64, "total frames received", stats->rx_packets); + seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes); + seq_printf(seq, fmt64, "Broadcast/Multicast Rcvd", stats->multicast); seq_puts(seq, "\n"); - seq_printf(seq, fmt, "total frames transmitted", stats->tx_packets); - seq_printf(seq, fmt, "total bytes transmitted", stats->tx_bytes); + seq_printf(seq, fmt64, "total frames transmitted", stats->tx_packets); + seq_printf(seq, fmt64, "total bytes transmitted", stats->tx_bytes); seq_printf(seq, fmt, "total headroom inc", dev_info->cnt_inc_headroom_on_tx); seq_printf(seq, fmt, "total encap on xmit", diff --git a/net/core/dev.c b/net/core/dev.c index 277844901ce3..a1abc10db08a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3701,10 +3701,10 @@ void dev_seq_stop(struct seq_file *seq, void *v) static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { - const struct net_device_stats *stats = dev_get_stats(dev); + const struct rtnl_link_stats64 *stats = dev_get_stats(dev); - seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " - "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", + seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " + "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, @@ -5281,18 +5281,21 @@ EXPORT_SYMBOL(dev_txq_stats_fold); * @dev: device to get statistics from * * Get network statistics from device. The device driver may provide - * its own method by setting dev->netdev_ops->get_stats; otherwise - * the internal statistics structure is used. + * its own method by setting dev->netdev_ops->get_stats64 or + * dev->netdev_ops->get_stats; otherwise the internal statistics + * structure is used. */ -const struct net_device_stats *dev_get_stats(struct net_device *dev) +const struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_get_stats64) + return ops->ndo_get_stats64(dev); if (ops->ndo_get_stats) - return ops->ndo_get_stats(dev); + return (struct rtnl_link_stats64 *)ops->ndo_get_stats(dev); dev_txq_stats_fold(dev, &dev->stats); - return &dev->stats; + return &dev->stats64; } EXPORT_SYMBOL(dev_get_stats); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 99e7052d7323..ea3bb4c3b87d 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -29,6 +29,7 @@ static const char fmt_hex[] = "%#x\n"; static const char fmt_long_hex[] = "%#lx\n"; static const char fmt_dec[] = "%d\n"; static const char fmt_ulong[] = "%lu\n"; +static const char fmt_u64[] = "%llu\n"; static inline int dev_isalive(const struct net_device *dev) { @@ -324,14 +325,13 @@ static ssize_t netstat_show(const struct device *d, struct net_device *dev = to_net_dev(d); ssize_t ret = -EINVAL; - WARN_ON(offset > sizeof(struct net_device_stats) || - offset % sizeof(unsigned long) != 0); + WARN_ON(offset > sizeof(struct rtnl_link_stats64) || + offset % sizeof(u64) != 0); read_lock(&dev_base_lock); if (dev_isalive(dev)) { - const struct net_device_stats *stats = dev_get_stats(dev); - ret = sprintf(buf, fmt_ulong, - *(unsigned long *)(((u8 *) stats) + offset)); + const struct rtnl_link_stats64 *stats = dev_get_stats(dev); + ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *) stats) + offset)); } read_unlock(&dev_base_lock); return ret; @@ -343,7 +343,7 @@ static ssize_t show_##name(struct device *d, \ struct device_attribute *attr, char *buf) \ { \ return netstat_show(d, attr, buf, \ - offsetof(struct net_device_stats, name)); \ + offsetof(struct rtnl_link_stats64, name)); \ } \ static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1a2af24e9e3d..e645778e9b7e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -579,7 +579,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, } static void copy_rtnl_link_stats(struct rtnl_link_stats *a, - const struct net_device_stats *b) + const struct rtnl_link_stats64 *b) { a->rx_packets = b->rx_packets; a->tx_packets = b->tx_packets; @@ -610,7 +610,7 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->tx_compressed = b->tx_compressed; } -static void copy_rtnl_link_stats64(void *v, const struct net_device_stats *b) +static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) { struct rtnl_link_stats64 a; @@ -791,7 +791,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, { struct ifinfomsg *ifm; struct nlmsghdr *nlh; - const struct net_device_stats *stats; + const struct rtnl_link_stats64 *stats; struct nlattr *attr; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); -- cgit v1.2.3 From f5c5440d40a24c5dc8030cde0a03debe87de4afb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 14 Jun 2010 16:15:23 +0200 Subject: netfilter: nfnetlink_log: RCU conversion, part 2 - must use atomic_inc_not_zero() in instance_lookup_get() - must use hlist_add_head_rcu() instead of hlist_add_head() - must use hlist_del_rcu() instead of hlist_del() - Introduce NFULNL_COPY_DISABLED to stop lockless reader from using an instance, before we do final instance_put() on it. Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_log.h | 1 + net/netfilter/nfnetlink_log.c | 18 ++++++++++++------ 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h index d3bab7a2c9b7..1d0b84aa1d42 100644 --- a/include/linux/netfilter/nfnetlink_log.h +++ b/include/linux/netfilter/nfnetlink_log.h @@ -89,6 +89,7 @@ enum nfulnl_attr_config { #define NFULNL_COPY_NONE 0x00 #define NFULNL_COPY_META 0x01 #define NFULNL_COPY_PACKET 0x02 +#define NFULNL_COPY_DISABLED 0x03 #define NFULNL_CFG_F_SEQ 0x0001 #define NFULNL_CFG_F_SEQ_GLOBAL 0x0002 diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 8ec23ec568e7..fb86a51bb65a 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -109,8 +109,8 @@ instance_lookup_get(u_int16_t group_num) rcu_read_lock_bh(); inst = __instance_lookup(group_num); - if (inst) - instance_get(inst); + if (inst && !atomic_inc_not_zero(&inst->use)) + inst = NULL; rcu_read_unlock_bh(); return inst; @@ -171,7 +171,7 @@ instance_create(u_int16_t group_num, int pid) inst->copy_mode = NFULNL_COPY_PACKET; inst->copy_range = NFULNL_COPY_RANGE_MAX; - hlist_add_head(&inst->hlist, + hlist_add_head_rcu(&inst->hlist, &instance_table[instance_hashfn(group_num)]); spin_unlock_bh(&instances_lock); @@ -185,18 +185,23 @@ out_unlock: static void __nfulnl_flush(struct nfulnl_instance *inst); +/* called with BH disabled */ static void __instance_destroy(struct nfulnl_instance *inst) { /* first pull it out of the global list */ - hlist_del(&inst->hlist); + hlist_del_rcu(&inst->hlist); /* then flush all pending packets from skb */ - spin_lock_bh(&inst->lock); + spin_lock(&inst->lock); + + /* lockless readers wont be able to use us */ + inst->copy_mode = NFULNL_COPY_DISABLED; + if (inst->skb) __nfulnl_flush(inst); - spin_unlock_bh(&inst->lock); + spin_unlock(&inst->lock); /* and finally put the refcount */ instance_put(inst); @@ -624,6 +629,7 @@ nfulnl_log_packet(u_int8_t pf, size += nla_total_size(data_len); break; + case NFULNL_COPY_DISABLED: default: goto unlock_and_release; } -- cgit v1.2.3 From 5d22c89b9bea17a0e48e7534a9b237885e2c0809 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 10 Jun 2010 10:21:40 +0200 Subject: mac80211: remove non-irqsafe aggregation callbacks The non-irqsafe aggregation start/stop done callbacks are currently only used by ath9k_htc, and can cause callbacks into the driver again. This might lead to locking issues, which will only get worse as we modify locking. To avoid trouble, remove the non-irqsafe versions and change ath9k_htc to use those instead. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ath9k/htc_drv_main.c | 6 ++--- include/net/mac80211.h | 32 +++++---------------------- net/mac80211/agg-tx.c | 2 -- net/mac80211/ieee80211_i.h | 2 ++ 4 files changed, 10 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c index 7aefbc638770..8c463f5965fb 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c @@ -510,13 +510,13 @@ void ath9k_htc_aggr_work(struct work_struct *work) ret = ath9k_htc_aggr_oper(priv, wk->vif, wk->sta_addr, wk->tid, true); if (!ret) - ieee80211_start_tx_ba_cb(wk->vif, wk->sta_addr, - wk->tid); + ieee80211_start_tx_ba_cb_irqsafe(wk->vif, wk->sta_addr, + wk->tid); break; case IEEE80211_AMPDU_TX_STOP: ath9k_htc_aggr_oper(priv, wk->vif, wk->sta_addr, wk->tid, false); - ieee80211_stop_tx_ba_cb(wk->vif, wk->sta_addr, wk->tid); + ieee80211_stop_tx_ba_cb_irqsafe(wk->vif, wk->sta_addr, wk->tid); break; default: ath_print(ath9k_hw_common(priv->ah), ATH_DBG_FATAL, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index abb3b1a9ddc9..7f9401b3d3c8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1445,7 +1445,7 @@ enum ieee80211_filter_flags { * * Note that drivers MUST be able to deal with a TX aggregation * session being stopped even before they OK'ed starting it by - * calling ieee80211_start_tx_ba_cb(_irqsafe), because the peer + * calling ieee80211_start_tx_ba_cb_irqsafe, because the peer * might receive the addBA frame and send a delBA right away! * * @IEEE80211_AMPDU_RX_START: start Rx aggregation @@ -2313,17 +2313,6 @@ void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, */ int ieee80211_start_tx_ba_session(struct ieee80211_sta *sta, u16 tid); -/** - * ieee80211_start_tx_ba_cb - low level driver ready to aggregate. - * @vif: &struct ieee80211_vif pointer from the add_interface callback - * @ra: receiver address of the BA session recipient. - * @tid: the TID to BA on. - * - * This function must be called by low level driver once it has - * finished with preparations for the BA session. - */ -void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid); - /** * ieee80211_start_tx_ba_cb_irqsafe - low level driver ready to aggregate. * @vif: &struct ieee80211_vif pointer from the add_interface callback @@ -2331,8 +2320,8 @@ void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid); * @tid: the TID to BA on. * * This function must be called by low level driver once it has - * finished with preparations for the BA session. - * This version of the function is IRQ-safe. + * finished with preparations for the BA session. It can be called + * from any context. */ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid); @@ -2350,17 +2339,6 @@ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, */ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *sta, u16 tid); -/** - * ieee80211_stop_tx_ba_cb - low level driver ready to stop aggregate. - * @vif: &struct ieee80211_vif pointer from the add_interface callback - * @ra: receiver address of the BA session recipient. - * @tid: the desired TID to BA on. - * - * This function must be called by low level driver once it has - * finished with preparations for the BA session tear down. - */ -void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid); - /** * ieee80211_stop_tx_ba_cb_irqsafe - low level driver ready to stop aggregate. * @vif: &struct ieee80211_vif pointer from the add_interface callback @@ -2368,8 +2346,8 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid); * @tid: the desired TID to BA on. * * This function must be called by low level driver once it has - * finished with preparations for the BA session tear down. - * This version of the function is IRQ-safe. + * finished with preparations for the BA session tear down. It + * can be called from any context. */ void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 7d8656d51c6b..5a7ef51e3020 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -479,7 +479,6 @@ void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid) spin_unlock_bh(&sta->lock); rcu_read_unlock(); } -EXPORT_SYMBOL(ieee80211_start_tx_ba_cb); void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid) @@ -619,7 +618,6 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid) spin_unlock_bh(&sta->lock); rcu_read_unlock(); } -EXPORT_SYMBOL(ieee80211_stop_tx_ba_cb); void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 71bdd8b3c3f4..a3ae51308039 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1119,6 +1119,8 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_back_parties initiator); +void ieee80211_start_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u16 tid); +void ieee80211_stop_tx_ba_cb(struct ieee80211_vif *vif, u8 *ra, u8 tid); /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, -- cgit v1.2.3 From 85ad181ea78861f69b007599cec9e6ba33fcdf8a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 10 Jun 2010 10:21:49 +0200 Subject: mac80211: allow drivers to sleep in ampdu_action Allow drivers to sleep, and indicate this in the documentation. ath9k has some locking I don't understand, so keep it safe and disable BHs in it, all other drivers look fine with the context change. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ath9k/main.c | 4 ++++ include/net/mac80211.h | 2 +- net/mac80211/driver-ops.h | 3 +-- 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index b8b76dd2c11e..e1b8456f3d2c 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -1769,6 +1769,8 @@ static int ath9k_ampdu_action(struct ieee80211_hw *hw, struct ath_softc *sc = aphy->sc; int ret = 0; + local_bh_disable(); + switch (action) { case IEEE80211_AMPDU_RX_START: if (!(sc->sc_flags & SC_OP_RXAGGR)) @@ -1798,6 +1800,8 @@ static int ath9k_ampdu_action(struct ieee80211_hw *hw, "Unknown AMPDU action\n"); } + local_bh_enable(); + return ret; } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7f9401b3d3c8..bbae3d9b1176 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1640,7 +1640,7 @@ enum ieee80211_ampdu_mlme_action { * is the first frame we expect to perform the action on. Notice * that TX/RX_STOP can pass NULL for this parameter. * Returns a negative error code on failure. - * The callback must be atomic. + * The callback can sleep. * * @get_survey: Return per-channel survey information * diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 7e86c6f89be9..a4fcbcc4f458 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -352,11 +352,10 @@ static inline int drv_ampdu_action(struct ieee80211_local *local, might_sleep(); - local_bh_disable(); if (local->ops->ampdu_action) ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action, sta, tid, ssn); - local_bh_enable(); + trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn, ret); return ret; } -- cgit v1.2.3 From fbd2c8dcbc69616d2e15b8a269a86b3a05d45aea Mon Sep 17 00:00:00 2001 From: Teemu Paasikivi Date: Mon, 14 Jun 2010 12:55:31 +0300 Subject: mac80211: Set basic rates while joining ibss network This patch adds support to nl80211 and mac80211 to set basic rates when joining/creating ibss network. Original patch was posted by Johannes Berg on the linux-wireless posting list. Signed-off-by: Johannes Berg Signed-off-by: Teemu Paasikivi Signed-off-by: John W. Linville --- include/net/cfg80211.h | 2 ++ net/mac80211/ibss.c | 4 +++- net/mac80211/ieee80211_i.h | 2 ++ net/wireless/nl80211.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 56 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 22ab9d88cf4a..64374f4cb7c6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -810,6 +810,7 @@ struct cfg80211_disassoc_request { * @beacon_interval: beacon interval to use * @privacy: this is a protected network, keys will be configured * after joining + * @basic_rates: bitmap of basic rates to use when creating the IBSS */ struct cfg80211_ibss_params { u8 *ssid; @@ -818,6 +819,7 @@ struct cfg80211_ibss_params { u8 *ie; u8 ssid_len, ie_len; u16 beacon_interval; + u32 basic_rates; bool channel_fixed; bool privacy; }; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index bfd7286488c7..9f4e64ed8b83 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -172,6 +172,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, rcu_assign_pointer(ifibss->presp, skb); sdata->vif.bss_conf.beacon_int = beacon_int; + sdata->vif.bss_conf.basic_rates = basic_rates; bss_change = BSS_CHANGED_BEACON_INT; bss_change |= ieee80211_reset_erp_info(sdata); bss_change |= BSS_CHANGED_BSSID; @@ -529,7 +530,7 @@ static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata) sdata->drop_unencrypted = 0; __ieee80211_sta_join_ibss(sdata, bssid, sdata->vif.bss_conf.beacon_int, - ifibss->channel, 3, /* first two are basic */ + ifibss->channel, ifibss->basic_rates, capability, 0); } @@ -859,6 +860,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, sdata->u.ibss.fixed_bssid = false; sdata->u.ibss.privacy = params->privacy; + sdata->u.ibss.basic_rates = params->basic_rates; sdata->vif.bss_conf.beacon_int = params->beacon_interval; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 9d753a02a2e4..c3c2be3f8a2c 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -387,6 +387,8 @@ struct ieee80211_if_ibss { unsigned long request; unsigned long last_scan_completed; + u32 basic_rates; + bool timer_running; bool fixed_bssid; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c65e67e9231c..41529aca794c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3955,6 +3955,55 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) } } + if (info->attrs[NL80211_ATTR_BSS_BASIC_RATES]) { + u8 *rates = + nla_data(info->attrs[NL80211_ATTR_BSS_BASIC_RATES]); + int n_rates = + nla_len(info->attrs[NL80211_ATTR_BSS_BASIC_RATES]); + struct ieee80211_supported_band *sband = + wiphy->bands[ibss.channel->band]; + int i, j; + + if (n_rates == 0) { + err = -EINVAL; + goto out; + } + + for (i = 0; i < n_rates; i++) { + int rate = (rates[i] & 0x7f) * 5; + bool found = false; + + for (j = 0; j < sband->n_bitrates; j++) { + if (sband->bitrates[j].bitrate == rate) { + found = true; + ibss.basic_rates |= BIT(j); + break; + } + } + if (!found) { + err = -EINVAL; + goto out; + } + } + } else { + /* + * If no rates were explicitly configured, + * use the mandatory rate set for 11b or + * 11a for maximum compatibility. + */ + struct ieee80211_supported_band *sband = + wiphy->bands[ibss.channel->band]; + int j; + u32 flag = ibss.channel->band == IEEE80211_BAND_5GHZ ? + IEEE80211_RATE_MANDATORY_A : + IEEE80211_RATE_MANDATORY_B; + + for (j = 0; j < sband->n_bitrates; j++) { + if (sband->bitrates[j].flags & flag) + ibss.basic_rates |= BIT(j); + } + } + err = cfg80211_join_ibss(rdev, dev, &ibss, connkeys); out: -- cgit v1.2.3 From 685429623f88d84f98bd5daffc3c427c408740d4 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Wed, 9 Jun 2010 13:43:26 +0300 Subject: mac80211: Fix circular locking dependency in ARP filter handling There is a circular locking dependency when configuring the hardware ARP filters on association, occurring when flushing the mac80211 workqueue. This is what happens: [ 92.026800] ======================================================= [ 92.030507] [ INFO: possible circular locking dependency detected ] [ 92.030507] 2.6.34-04781-g2b2c009 #85 [ 92.030507] ------------------------------------------------------- [ 92.030507] modprobe/5225 is trying to acquire lock: [ 92.030507] ((wiphy_name(local->hw.wiphy))){+.+.+.}, at: [] flush_workq ueue+0x0/0xb0 [ 92.030507] [ 92.030507] but task is already holding lock: [ 92.030507] (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0x12/0x20 [ 92.030507] [ 92.030507] which lock already depends on the new lock. [ 92.030507] [ 92.030507] [ 92.030507] the existing dependency chain (in reverse order) is: [ 92.030507] [ 92.030507] -> #2 (rtnl_mutex){+.+.+.}: [ 92.030507] [] lock_acquire+0xdb/0x110 [ 92.030507] [] mutex_lock_nested+0x44/0x300 [ 92.030507] [] rtnl_lock+0x12/0x20 [ 92.030507] [] ieee80211_assoc_done+0x6c/0xe0 [mac80211] [ 92.030507] [] ieee80211_work_work+0x31d/0x1280 [mac80211] [ 92.030507] -> #1 ((&local->work_work)){+.+.+.}: [ 92.030507] [] lock_acquire+0xdb/0x110 [ 92.030507] [] worker_thread+0x22a/0x370 [ 92.030507] [] kthread+0x96/0xb0 [ 92.030507] [] kernel_thread_helper+0x4/0x10 [ 92.030507] [ 92.030507] -> #0 ((wiphy_name(local->hw.wiphy))){+.+.+.}: [ 92.030507] [] __lock_acquire+0x1c0c/0x1d50 [ 92.030507] [] lock_acquire+0xdb/0x110 [ 92.030507] [] flush_workqueue+0x4e/0xb0 [ 92.030507] [] ieee80211_stop_device+0x2b/0xb0 [mac80211] [ 92.030507] [] ieee80211_stop+0x3e5/0x680 [mac80211] The locking in this case is quite complex. Fix the problem by rewriting the way the hardware ARP filter list is handled - i.e. make a copy of the address list to the bss_conf struct, and provide that list to the hardware driver when needed. The current patch will enable filtering also in promiscuous mode. This may need to be changed in the future. Reported-by: Reinette Chatre Signed-off-by: Juuso Oikarinen Signed-off-by: John W. Linville --- include/net/mac80211.h | 35 +++++++++++++++++------------ net/mac80211/driver-ops.h | 17 -------------- net/mac80211/driver-trace.h | 22 ------------------ net/mac80211/ieee80211_i.h | 2 ++ net/mac80211/iface.c | 3 +++ net/mac80211/main.c | 54 ++++++++++++++++++++++++++++----------------- net/mac80211/mlme.c | 34 +++++++++++++++------------- 7 files changed, 79 insertions(+), 88 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index bbae3d9b1176..3a47877f4965 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -19,7 +19,6 @@ #include #include #include -#include #include /** @@ -147,6 +146,7 @@ struct ieee80211_low_level_stats { * enabled/disabled (beaconing modes) * @BSS_CHANGED_CQM: Connection quality monitor config changed * @BSS_CHANGED_IBSS: IBSS join status changed + * @BSS_CHANGED_ARP_FILTER: Hardware ARP filter address list or state changed. */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, @@ -161,10 +161,18 @@ enum ieee80211_bss_change { BSS_CHANGED_BEACON_ENABLED = 1<<9, BSS_CHANGED_CQM = 1<<10, BSS_CHANGED_IBSS = 1<<11, + BSS_CHANGED_ARP_FILTER = 1<<12, /* when adding here, make sure to change ieee80211_reconfig */ }; +/* + * The maximum number of IPv4 addresses listed for ARP filtering. If the number + * of addresses for an interface increase beyond this value, hardware ARP + * filtering will be disabled. + */ +#define IEEE80211_BSS_ARP_ADDR_LIST_LEN 4 + /** * struct ieee80211_bss_conf - holds the BSS's changing parameters * @@ -200,6 +208,15 @@ enum ieee80211_bss_change { * @cqm_rssi_thold: Connection quality monitor RSSI threshold, a zero value * implies disabled * @cqm_rssi_hyst: Connection quality monitor RSSI hysteresis + * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The + * may filter ARP queries targeted for other addresses than listed here. + * The driver must allow ARP queries targeted for all address listed here + * to pass through. An empty list implies no ARP queries need to pass. + * @arp_addr_cnt: Number of addresses currently on the list. + * @arp_filter_enabled: Enable ARP filtering - if enabled, the hardware may + * filter ARP queries based on the @arp_addr_list, if disabled, the + * hardware must not perform any ARP filtering. Note, that the filter will + * be enabled also in promiscuous mode. */ struct ieee80211_bss_conf { const u8 *bssid; @@ -220,6 +237,9 @@ struct ieee80211_bss_conf { s32 cqm_rssi_thold; u32 cqm_rssi_hyst; enum nl80211_channel_type channel_type; + __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; + u8 arp_addr_cnt; + bool arp_filter_enabled; }; /** @@ -1529,16 +1549,6 @@ enum ieee80211_ampdu_mlme_action { * of the bss parameters has changed when a call is made. The callback * can sleep. * - * @configure_arp_filter: Configuration function for hardware ARP query filter. - * This function is called with all the IP addresses configured to the - * interface as argument - all ARP queries targeted to any of these - * addresses must pass through. If the hardware filter does not support - * enought addresses, hardware filtering must be disabled. The ifa_list - * argument may be NULL, indicating that filtering must be disabled. - * This function is called upon association complete with current - * address(es), and while associated whenever the IP address(es) change. - * The callback can sleep. - * * @prepare_multicast: Prepare for multicast filter configuration. * This callback is optional, and its return value is passed * to configure_filter(). This callback must be atomic. @@ -1678,9 +1688,6 @@ struct ieee80211_ops { struct ieee80211_vif *vif, struct ieee80211_bss_conf *info, u32 changed); - int (*configure_arp_filter)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct in_ifaddr *ifa_list); u64 (*prepare_multicast)(struct ieee80211_hw *hw, struct netdev_hw_addr_list *mc_list); void (*configure_filter)(struct ieee80211_hw *hw, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 965d64f68567..c33317320eee 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -89,23 +89,6 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local, trace_drv_return_void(local); } -struct in_ifaddr; -static inline int drv_configure_arp_filter(struct ieee80211_local *local, - struct ieee80211_vif *vif, - struct in_ifaddr *ifa_list) -{ - int ret = 0; - - might_sleep(); - - trace_drv_configure_arp_filter(local, vif_to_sdata(vif)); - if (local->ops->configure_arp_filter) - ret = local->ops->configure_arp_filter(&local->hw, vif, - ifa_list); - trace_drv_return_int(local, ret); - return ret; -} - static inline u64 drv_prepare_multicast(struct ieee80211_local *local, struct netdev_hw_addr_list *mc_list) { diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index 06444ea67bc4..8da31caff931 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -251,28 +251,6 @@ TRACE_EVENT(drv_bss_info_changed, ) ); -TRACE_EVENT(drv_configure_arp_filter, - TP_PROTO(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata), - - TP_ARGS(local, sdata), - - TP_STRUCT__entry( - LOCAL_ENTRY - VIF_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - VIF_ASSIGN; - ), - - TP_printk( - VIF_PR_FMT LOCAL_PR_FMT, - VIF_PR_ARG, LOCAL_PR_ARG - ) -); - TRACE_EVENT(drv_prepare_multicast, TP_PROTO(struct ieee80211_local *local, int mc_count), diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c3c2be3f8a2c..9b3c3f971d28 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -514,6 +514,8 @@ struct ieee80211_sub_if_data { struct work_struct work; struct sk_buff_head skb_queue; + bool arp_filter_state; + /* * AP this belongs to: self in AP mode and * corresponding AP in VLAN mode, NULL for diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 490be2f3af27..910729fc18cd 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1076,6 +1076,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->wdev.wiphy = local->hw.wiphy; sdata->local = local; sdata->dev = ndev; +#ifdef CONFIG_INET + sdata->arp_filter_state = true; +#endif for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) skb_queue_head_init(&sdata->fragments[i].skb_list); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index c2e46e88f3c9..a1bf46c64b93 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -317,23 +318,6 @@ static void ieee80211_recalc_smps_work(struct work_struct *work) } #ifdef CONFIG_INET -int ieee80211_set_arp_filter(struct ieee80211_sub_if_data *sdata) -{ - struct in_device *idev; - int ret = 0; - - BUG_ON(!sdata); - ASSERT_RTNL(); - - idev = sdata->dev->ip_ptr; - if (!idev) - return 0; - - ret = drv_configure_arp_filter(sdata->local, &sdata->vif, - idev->ifa_list); - return ret; -} - static int ieee80211_ifa_changed(struct notifier_block *nb, unsigned long data, void *arg) { @@ -343,8 +327,11 @@ static int ieee80211_ifa_changed(struct notifier_block *nb, ifa_notifier); struct net_device *ndev = ifa->ifa_dev->dev; struct wireless_dev *wdev = ndev->ieee80211_ptr; + struct in_device *idev; struct ieee80211_sub_if_data *sdata; + struct ieee80211_bss_conf *bss_conf; struct ieee80211_if_managed *ifmgd; + int c = 0; if (!netif_running(ndev)) return NOTIFY_DONE; @@ -356,17 +343,44 @@ static int ieee80211_ifa_changed(struct notifier_block *nb, if (wdev->wiphy != local->hw.wiphy) return NOTIFY_DONE; - /* We are concerned about IP addresses only when associated */ sdata = IEEE80211_DEV_TO_SUB_IF(ndev); + bss_conf = &sdata->vif.bss_conf; /* ARP filtering is only supported in managed mode */ if (sdata->vif.type != NL80211_IFTYPE_STATION) return NOTIFY_DONE; + idev = sdata->dev->ip_ptr; + if (!idev) + return NOTIFY_DONE; + ifmgd = &sdata->u.mgd; mutex_lock(&ifmgd->mtx); - if (ifmgd->associated) - ieee80211_set_arp_filter(sdata); + + /* Copy the addresses to the bss_conf list */ + ifa = idev->ifa_list; + while (c < IEEE80211_BSS_ARP_ADDR_LIST_LEN && ifa) { + bss_conf->arp_addr_list[c] = ifa->ifa_address; + ifa = ifa->ifa_next; + c++; + } + + /* If not all addresses fit the list, disable filtering */ + if (ifa) { + sdata->arp_filter_state = false; + c = 0; + } else { + sdata->arp_filter_state = true; + } + bss_conf->arp_addr_cnt = c; + + /* Configure driver only if associated */ + if (ifmgd->associated) { + bss_conf->arp_filter_enabled = sdata->arp_filter_state; + ieee80211_bss_info_change_notify(sdata, + BSS_CHANGED_ARP_FILTER); + } + mutex_unlock(&ifmgd->mtx); return NOTIFY_DONE; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 583b34686a26..74479c2d12d4 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -806,11 +806,12 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, { struct ieee80211_bss *bss = (void *)cbss->priv; struct ieee80211_local *local = sdata->local; + struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; bss_info_changed |= BSS_CHANGED_ASSOC; /* set timing information */ - sdata->vif.bss_conf.beacon_int = cbss->beacon_interval; - sdata->vif.bss_conf.timestamp = cbss->tsf; + bss_conf->beacon_int = cbss->beacon_interval; + bss_conf->timestamp = cbss->tsf; bss_info_changed |= BSS_CHANGED_BEACON_INT; bss_info_changed |= ieee80211_handle_bss_capability(sdata, @@ -835,7 +836,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, ieee80211_led_assoc(local, 1); - sdata->vif.bss_conf.assoc = 1; + bss_conf->assoc = 1; /* * For now just always ask the driver to update the basic rateset * when we have associated, we aren't checking whether it actually @@ -848,9 +849,15 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, /* Tell the driver to monitor connection quality (if supported) */ if ((local->hw.flags & IEEE80211_HW_SUPPORTS_CQM_RSSI) && - sdata->vif.bss_conf.cqm_rssi_thold) + bss_conf->cqm_rssi_thold) bss_info_changed |= BSS_CHANGED_CQM; + /* Enable ARP filtering */ + if (bss_conf->arp_filter_enabled != sdata->arp_filter_state) { + bss_conf->arp_filter_enabled = sdata->arp_filter_state; + bss_info_changed |= BSS_CHANGED_ARP_FILTER; + } + ieee80211_bss_info_change_notify(sdata, bss_info_changed); mutex_lock(&local->iflist_mtx); @@ -932,6 +939,12 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_hw_config(local, config_changed); + /* Disable ARP filtering */ + if (sdata->vif.bss_conf.arp_filter_enabled) { + sdata->vif.bss_conf.arp_filter_enabled = false; + changed |= BSS_CHANGED_ARP_FILTER; + } + /* The BSSID (not really interesting) and HT changed */ changed |= BSS_CHANGED_BSSID | BSS_CHANGED_HT; ieee80211_bss_info_change_notify(sdata, changed); @@ -2018,18 +2031,9 @@ static enum work_done_result ieee80211_assoc_done(struct ieee80211_work *wk, cfg80211_send_assoc_timeout(wk->sdata->dev, wk->filter_ta); return WORK_DONE_DESTROY; - } else { - mutex_unlock(&wk->sdata->u.mgd.mtx); -#ifdef CONFIG_INET - /* - * configure ARP filter IP addresses to the driver, - * intentionally outside the mgd mutex. - */ - rtnl_lock(); - ieee80211_set_arp_filter(wk->sdata); - rtnl_unlock(); -#endif } + + mutex_unlock(&wk->sdata->u.mgd.mtx); } cfg80211_send_rx_assoc(wk->sdata->dev, skb->data, skb->len); -- cgit v1.2.3 From 1be3b5fe9dffe3300f995584d8f996dd20e29412 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 14 Jun 2010 08:53:26 +0000 Subject: ethtool: Revert incorrect indentation changes commit 97f8aefbbfb5aa5c9944e5fa8149f1fdaf71c7b6 "net: fix ethtool coding style errors and warnings" changed the indentation of several macro definitions in ethtool.h. These definitions line up in the diff where there is an extra character at the start of each line, but not in the resulting file. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 276b40a16835..2c8af093d8b3 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -586,29 +586,29 @@ struct ethtool_ops { #define ETHTOOL_GREGS 0x00000004 /* Get NIC registers. */ #define ETHTOOL_GWOL 0x00000005 /* Get wake-on-lan options. */ #define ETHTOOL_SWOL 0x00000006 /* Set wake-on-lan options. */ -#define ETHTOOL_GMSGLVL 0x00000007 /* Get driver message level */ -#define ETHTOOL_SMSGLVL 0x00000008 /* Set driver msg level. */ +#define ETHTOOL_GMSGLVL 0x00000007 /* Get driver message level */ +#define ETHTOOL_SMSGLVL 0x00000008 /* Set driver msg level. */ #define ETHTOOL_NWAY_RST 0x00000009 /* Restart autonegotiation. */ #define ETHTOOL_GLINK 0x0000000a /* Get link status (ethtool_value) */ -#define ETHTOOL_GEEPROM 0x0000000b /* Get EEPROM data */ -#define ETHTOOL_SEEPROM 0x0000000c /* Set EEPROM data. */ +#define ETHTOOL_GEEPROM 0x0000000b /* Get EEPROM data */ +#define ETHTOOL_SEEPROM 0x0000000c /* Set EEPROM data. */ #define ETHTOOL_GCOALESCE 0x0000000e /* Get coalesce config */ #define ETHTOOL_SCOALESCE 0x0000000f /* Set coalesce config. */ #define ETHTOOL_GRINGPARAM 0x00000010 /* Get ring parameters */ #define ETHTOOL_SRINGPARAM 0x00000011 /* Set ring parameters. */ #define ETHTOOL_GPAUSEPARAM 0x00000012 /* Get pause parameters */ #define ETHTOOL_SPAUSEPARAM 0x00000013 /* Set pause parameters. */ -#define ETHTOOL_GRXCSUM 0x00000014 /* Get RX hw csum enable (ethtool_value) */ -#define ETHTOOL_SRXCSUM 0x00000015 /* Set RX hw csum enable (ethtool_value) */ -#define ETHTOOL_GTXCSUM 0x00000016 /* Get TX hw csum enable (ethtool_value) */ -#define ETHTOOL_STXCSUM 0x00000017 /* Set TX hw csum enable (ethtool_value) */ +#define ETHTOOL_GRXCSUM 0x00000014 /* Get RX hw csum enable (ethtool_value) */ +#define ETHTOOL_SRXCSUM 0x00000015 /* Set RX hw csum enable (ethtool_value) */ +#define ETHTOOL_GTXCSUM 0x00000016 /* Get TX hw csum enable (ethtool_value) */ +#define ETHTOOL_STXCSUM 0x00000017 /* Set TX hw csum enable (ethtool_value) */ #define ETHTOOL_GSG 0x00000018 /* Get scatter-gather enable * (ethtool_value) */ #define ETHTOOL_SSG 0x00000019 /* Set scatter-gather enable * (ethtool_value). */ #define ETHTOOL_TEST 0x0000001a /* execute NIC self-test. */ #define ETHTOOL_GSTRINGS 0x0000001b /* get specified string set */ -#define ETHTOOL_PHYS_ID 0x0000001c /* identify the NIC */ +#define ETHTOOL_PHYS_ID 0x0000001c /* identify the NIC */ #define ETHTOOL_GSTATS 0x0000001d /* get NIC-specific statistics */ #define ETHTOOL_GTSO 0x0000001e /* Get TSO enable (ethtool_value) */ #define ETHTOOL_STSO 0x0000001f /* Set TSO enable (ethtool_value) */ @@ -619,8 +619,8 @@ struct ethtool_ops { #define ETHTOOL_SGSO 0x00000024 /* Set GSO enable (ethtool_value) */ #define ETHTOOL_GFLAGS 0x00000025 /* Get flags bitmap(ethtool_value) */ #define ETHTOOL_SFLAGS 0x00000026 /* Set flags bitmap(ethtool_value) */ -#define ETHTOOL_GPFLAGS 0x00000027 /* Get driver-private flags bitmap */ -#define ETHTOOL_SPFLAGS 0x00000028 /* Set driver-private flags bitmap */ +#define ETHTOOL_GPFLAGS 0x00000027 /* Get driver-private flags bitmap */ +#define ETHTOOL_SPFLAGS 0x00000028 /* Set driver-private flags bitmap */ #define ETHTOOL_GRXFH 0x00000029 /* Get RX flow hash configuration */ #define ETHTOOL_SRXFH 0x0000002a /* Set RX flow hash configuration */ @@ -645,18 +645,18 @@ struct ethtool_ops { /* Indicates what features are supported by the interface. */ #define SUPPORTED_10baseT_Half (1 << 0) #define SUPPORTED_10baseT_Full (1 << 1) -#define SUPPORTED_100baseT_Half (1 << 2) -#define SUPPORTED_100baseT_Full (1 << 3) +#define SUPPORTED_100baseT_Half (1 << 2) +#define SUPPORTED_100baseT_Full (1 << 3) #define SUPPORTED_1000baseT_Half (1 << 4) #define SUPPORTED_1000baseT_Full (1 << 5) #define SUPPORTED_Autoneg (1 << 6) #define SUPPORTED_TP (1 << 7) #define SUPPORTED_AUI (1 << 8) #define SUPPORTED_MII (1 << 9) -#define SUPPORTED_FIBRE (1 << 10) +#define SUPPORTED_FIBRE (1 << 10) #define SUPPORTED_BNC (1 << 11) #define SUPPORTED_10000baseT_Full (1 << 12) -#define SUPPORTED_Pause (1 << 13) +#define SUPPORTED_Pause (1 << 13) #define SUPPORTED_Asym_Pause (1 << 14) #define SUPPORTED_2500baseX_Full (1 << 15) #define SUPPORTED_Backplane (1 << 16) @@ -666,8 +666,8 @@ struct ethtool_ops { #define SUPPORTED_10000baseR_FEC (1 << 20) /* Indicates what features are advertised by the interface. */ -#define ADVERTISED_10baseT_Half (1 << 0) -#define ADVERTISED_10baseT_Full (1 << 1) +#define ADVERTISED_10baseT_Half (1 << 0) +#define ADVERTISED_10baseT_Full (1 << 1) #define ADVERTISED_100baseT_Half (1 << 2) #define ADVERTISED_100baseT_Full (1 << 3) #define ADVERTISED_1000baseT_Half (1 << 4) @@ -706,12 +706,12 @@ struct ethtool_ops { #define DUPLEX_FULL 0x01 /* Which connector port. */ -#define PORT_TP 0x00 +#define PORT_TP 0x00 #define PORT_AUI 0x01 #define PORT_MII 0x02 #define PORT_FIBRE 0x03 #define PORT_BNC 0x04 -#define PORT_DA 0x05 +#define PORT_DA 0x05 #define PORT_NONE 0xef #define PORT_OTHER 0xff @@ -725,7 +725,7 @@ struct ethtool_ops { /* Enable or disable autonegotiation. If this is set to enable, * the forced link modes above are completely ignored. */ -#define AUTONEG_DISABLE 0x00 +#define AUTONEG_DISABLE 0x00 #define AUTONEG_ENABLE 0x01 /* Mode MDI or MDI-X */ -- cgit v1.2.3 From 0902b469bd25065aa0688c3cee6f11744c817e7c Mon Sep 17 00:00:00 2001 From: Luciano Coelho Date: Tue, 15 Jun 2010 15:04:00 +0200 Subject: netfilter: xtables: idletimer target implementation This patch implements an idletimer Xtables target that can be used to identify when interfaces have been idle for a certain period of time. Timers are identified by labels and are created when a rule is set with a new label. The rules also take a timeout value (in seconds) as an option. If more than one rule uses the same timer label, the timer will be restarted whenever any of the rules get a hit. One entry for each timer is created in sysfs. This attribute contains the timer remaining for the timer to expire. The attributes are located under the xt_idletimer class: /sys/class/xt_idletimer/timers/