From 4eb41d10c7ab419a1408bed2e63a9c0fdfa38844 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Sat, 3 Oct 2009 19:48:22 +0900 Subject: this_cpu: Use this_cpu operations for SNMP statistics SNMP statistic macros can be signficantly simplified. This will also reduce code size if the arch supports these operations in hardware. Acked-by: Tejun Heo Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/net/snmp.h | 50 ++++++++++++++++++-------------------------------- 1 file changed, 18 insertions(+), 32 deletions(-) (limited to 'include/net') diff --git a/include/net/snmp.h b/include/net/snmp.h index 8c842e06bec..f0d756f2ac9 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -136,45 +136,31 @@ struct linux_xfrm_mib { #define SNMP_STAT_BHPTR(name) (name[0]) #define SNMP_STAT_USRPTR(name) (name[1]) -#define SNMP_INC_STATS_BH(mib, field) \ - (per_cpu_ptr(mib[0], raw_smp_processor_id())->mibs[field]++) -#define SNMP_INC_STATS_USER(mib, field) \ - do { \ - per_cpu_ptr(mib[1], get_cpu())->mibs[field]++; \ - put_cpu(); \ - } while (0) -#define SNMP_INC_STATS(mib, field) \ - do { \ - per_cpu_ptr(mib[!in_softirq()], get_cpu())->mibs[field]++; \ - put_cpu(); \ - } while (0) -#define SNMP_DEC_STATS(mib, field) \ - do { \ - per_cpu_ptr(mib[!in_softirq()], get_cpu())->mibs[field]--; \ - put_cpu(); \ - } while (0) -#define SNMP_ADD_STATS(mib, field, addend) \ - do { \ - per_cpu_ptr(mib[!in_softirq()], get_cpu())->mibs[field] += addend; \ - put_cpu(); \ - } while (0) -#define SNMP_ADD_STATS_BH(mib, field, addend) \ - (per_cpu_ptr(mib[0], raw_smp_processor_id())->mibs[field] += addend) -#define SNMP_ADD_STATS_USER(mib, field, addend) \ - do { \ - per_cpu_ptr(mib[1], get_cpu())->mibs[field] += addend; \ - put_cpu(); \ - } while (0) +#define SNMP_INC_STATS_BH(mib, field) \ + __this_cpu_inc(mib[0]->mibs[field]) +#define SNMP_INC_STATS_USER(mib, field) \ + this_cpu_inc(mib[1]->mibs[field]) +#define SNMP_INC_STATS(mib, field) \ + this_cpu_inc(mib[!in_softirq()]->mibs[field]) +#define SNMP_DEC_STATS(mib, field) \ + this_cpu_dec(mib[!in_softirq()]->mibs[field]) +#define SNMP_ADD_STATS_BH(mib, field, addend) \ + __this_cpu_add(mib[0]->mibs[field], addend) +#define SNMP_ADD_STATS_USER(mib, field, addend) \ + this_cpu_add(mib[1]->mibs[field], addend) #define SNMP_UPD_PO_STATS(mib, basefield, addend) \ do { \ - __typeof__(mib[0]) ptr = per_cpu_ptr(mib[!in_softirq()], get_cpu());\ + __typeof__(mib[0]) ptr; \ + preempt_disable(); \ + ptr = this_cpu_ptr((mib)[!in_softirq()]); \ ptr->mibs[basefield##PKTS]++; \ ptr->mibs[basefield##OCTETS] += addend;\ - put_cpu(); \ + preempt_enable(); \ } while (0) #define SNMP_UPD_PO_STATS_BH(mib, basefield, addend) \ do { \ - __typeof__(mib[0]) ptr = per_cpu_ptr(mib[!in_softirq()], raw_smp_processor_id());\ + __typeof__(mib[0]) ptr = \ + __this_cpu_ptr((mib)[!in_softirq()]); \ ptr->mibs[basefield##PKTS]++; \ ptr->mibs[basefield##OCTETS] += addend;\ } while (0) -- cgit v1.2.3 From 4ea7334b6de818b0123fa4be32af4cb8ac65174c Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Sat, 3 Oct 2009 19:48:22 +0900 Subject: this_cpu: Use this_cpu ops for network statistics Acked-by: Tejun Heo Acked-by: David Miller Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/net/neighbour.h | 7 +------ include/net/netfilter/nf_conntrack.h | 4 ++-- 2 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3817fda82a8..f28403ff764 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -90,12 +90,7 @@ struct neigh_statistics unsigned long unres_discards; /* number of unresolved drops */ }; -#define NEIGH_CACHE_STAT_INC(tbl, field) \ - do { \ - preempt_disable(); \ - (per_cpu_ptr((tbl)->stats, smp_processor_id())->field)++; \ - preempt_enable(); \ - } while (0) +#define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field) struct neighbour { diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index cbdd6284996..dde549779e4 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -295,11 +295,11 @@ extern unsigned int nf_conntrack_htable_size; extern unsigned int nf_conntrack_max; #define NF_CT_STAT_INC(net, count) \ - (per_cpu_ptr((net)->ct.stat, raw_smp_processor_id())->count++) + __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) \ do { \ local_bh_disable(); \ - per_cpu_ptr((net)->ct.stat, raw_smp_processor_id())->count++; \ + __this_cpu_inc((net)->ct.stat->count); \ local_bh_enable(); \ } while (0) -- cgit v1.2.3 From 16c6cf8bb471392fd09b48b7c27e7d83a446b4bc Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sun, 20 Sep 2009 10:35:36 +0000 Subject: ipv4: fib table algorithm performance improvement The FIB algorithim for IPV4 is set at compile time, but kernel goes through the overhead of function call indirection at runtime. Save some cycles by turning the indirect calls to direct calls to either hash or trie code. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/ip_fib.h | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index ef91fe924ba..68fd5ebd094 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -144,18 +144,21 @@ struct fib_table { struct hlist_node tb_hlist; u32 tb_id; int tb_default; - int (*tb_lookup)(struct fib_table *tb, const struct flowi *flp, struct fib_result *res); - int (*tb_insert)(struct fib_table *, struct fib_config *); - int (*tb_delete)(struct fib_table *, struct fib_config *); - int (*tb_dump)(struct fib_table *table, struct sk_buff *skb, - struct netlink_callback *cb); - int (*tb_flush)(struct fib_table *table); - void (*tb_select_default)(struct fib_table *table, - const struct flowi *flp, struct fib_result *res); - unsigned char tb_data[0]; }; +extern int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, + struct fib_result *res); +extern int fib_table_insert(struct fib_table *, struct fib_config *); +extern int fib_table_delete(struct fib_table *, struct fib_config *); +extern int fib_table_dump(struct fib_table *table, struct sk_buff *skb, + struct netlink_callback *cb); +extern int fib_table_flush(struct fib_table *table); +extern void fib_table_select_default(struct fib_table *table, + const struct flowi *flp, + struct fib_result *res); + + #ifndef CONFIG_IP_MULTIPLE_TABLES #define TABLE_LOCAL_INDEX 0 @@ -182,11 +185,11 @@ static inline int fib_lookup(struct net *net, const struct flowi *flp, struct fib_table *table; table = fib_get_table(net, RT_TABLE_LOCAL); - if (!table->tb_lookup(table, flp, res)) + if (!fib_table_lookup(table, flp, res)) return 0; table = fib_get_table(net, RT_TABLE_MAIN); - if (!table->tb_lookup(table, flp, res)) + if (!fib_table_lookup(table, flp, res)) return 0; return -ENETUNREACH; } -- cgit v1.2.3 From 0bfbedb14a8a96c529341bec88991a92b41fac72 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 5 Oct 2009 00:11:22 -0700 Subject: tunnels: Optimize tx path We currently dirty a cache line to update tunnel device stats (tx_packets/tx_bytes). We better use the txq->tx_bytes/tx_packets counters that already are present in cpu cache, in the cache line shared with txq->_xmit_lock This patch extends IPTUNNEL_XMIT() macro to use txq pointer provided by the caller. Also &tunnel->dev->stats can be replaced by &dev->stats Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipip.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/ipip.h b/include/net/ipip.h index 87acf8f3a15..0159221a850 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -42,9 +42,9 @@ struct ip_tunnel_prl_entry ip_select_ident(iph, &rt->u.dst, NULL); \ \ err = ip_local_out(skb); \ - if (net_xmit_eval(err) == 0) { \ - stats->tx_bytes += pkt_len; \ - stats->tx_packets++; \ + if (likely(net_xmit_eval(err) == 0)) { \ + txq->tx_bytes += pkt_len; \ + txq->tx_packets++; \ } else { \ stats->tx_errors++; \ stats->tx_aborted_errors++; \ -- cgit v1.2.3 From bcdce7195e0eab55b37dbd53be53057f38006380 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Oct 2009 17:28:29 -0700 Subject: net: speedup sk_wake_async() An incoming datagram must bring into cpu cache *lot* of cache lines, in particular : (other parts omitted (hash chains, ip route cache...)) On 32bit arches : offsetof(struct sock, sk_rcvbuf) =0x30 (read) offsetof(struct sock, sk_lock) =0x34 (rw) offsetof(struct sock, sk_sleep) =0x50 (read) offsetof(struct sock, sk_rmem_alloc) =0x64 (rw) offsetof(struct sock, sk_receive_queue)=0x74 (rw) offsetof(struct sock, sk_forward_alloc)=0x98 (rw) offsetof(struct sock, sk_callback_lock)=0xcc (rw) offsetof(struct sock, sk_drops) =0xd8 (read if we add dropcount support, rw if frame dropped) offsetof(struct sock, sk_filter) =0xf8 (read) offsetof(struct sock, sk_socket) =0x138 (read) offsetof(struct sock, sk_data_ready) =0x15c (read) We can avoid sk->sk_socket and socket->fasync_list referencing on sockets with no fasync() structures. (socket->fasync_list ptr is probably already in cache because it shares a cache line with socket->wait, ie location pointed by sk->sk_sleep) This avoids one cache line load per incoming packet for common cases (no fasync()) We can leave (or even move in a future patch) sk->sk_socket in a cold location Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 1621935aad5..98398bdec57 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -504,6 +504,7 @@ enum sock_flags { SOCK_TIMESTAMPING_SOFTWARE, /* %SOF_TIMESTAMPING_SOFTWARE */ SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */ SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */ + SOCK_FASYNC, /* fasync() active */ }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) @@ -1396,7 +1397,7 @@ static inline unsigned long sock_wspace(struct sock *sk) static inline void sk_wake_async(struct sock *sk, int how, int band) { - if (sk->sk_socket && sk->sk_socket->fasync_list) + if (sock_flag(sk, SOCK_FASYNC)) sock_wake_async(sk->sk_socket, how, band); } -- cgit v1.2.3 From fa857afcf77da669eb6b7031ec07ad14b912c307 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?YOSHIFUJI=20Hideaki=20/=20=E5=90=89=E8=97=A4=E8=8B=B1?= =?UTF-8?q?=E6=98=8E?= Date: Tue, 22 Sep 2009 23:43:14 +0000 Subject: ipv6 sit: 6rd (IPv6 Rapid Deployment) Support. IPv6 Rapid Deployment (6rd; draft-ietf-softwire-ipv6-6rd) builds upon mechanisms of 6to4 (RFC3056) to enable a service provider to rapidly deploy IPv6 unicast service to IPv4 sites to which it provides customer premise equipment. Like 6to4, it utilizes stateless IPv6 in IPv4 encapsulation in order to transit IPv4-only network infrastructure. Unlike 6to4, a 6rd service provider uses an IPv6 prefix of its own in place of the fixed 6to4 prefix. With this option enabled, the SIT driver offers 6rd functionality by providing additional ioctl API to configure the IPv6 Prefix for in stead of static 2002::/16 for 6to4. Original patch was done by Alexandre Cassen based on old Internet-Draft. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/ipip.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/net') diff --git a/include/net/ipip.h b/include/net/ipip.h index 0159221a850..86f1c8bd040 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -7,6 +7,15 @@ /* Keep error state on tunnel for 30 sec */ #define IPTUNNEL_ERR_TIMEO (30*HZ) +/* 6rd prefix/relay information */ +struct ip_tunnel_6rd_parm +{ + struct in6_addr prefix; + __be32 relay_prefix; + u16 prefixlen; + u16 relay_prefixlen; +}; + struct ip_tunnel { struct ip_tunnel *next; @@ -23,6 +32,10 @@ struct ip_tunnel struct ip_tunnel_parm parms; + /* for SIT */ +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd_parm ip6rd; +#endif struct ip_tunnel_prl_entry *prl; /* potential router list */ unsigned int prl_count; /* # of entries in PRL */ }; -- cgit v1.2.3 From d250a5f90e53f5e150618186230795352d154c88 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Oct 2009 10:32:18 +0000 Subject: pkt_sched: gen_estimator: Dont report fake rate estimators MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Jarek Poplawski a écrit : > > > Hmm... So you made me to do some "real" work here, and guess what?: > there is one serious checkpatch warning! ;-) Plus, this new parameter > should be added to the function description. Otherwise: > Signed-off-by: Jarek Poplawski > > Thanks, > Jarek P. > > PS: I guess full "Don't" would show we really mean it... Okay :) Here is the last round, before the night ! Thanks again [RFC] pkt_sched: gen_estimator: Don't report fake rate estimators We currently send TCA_STATS_RATE_EST elements to netlink users, even if no estimator is running. # tc -s -d qdisc qdisc pfifo_fast 0: dev eth0 root bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 Sent 112833764978 bytes 1495081739 pkt (dropped 0, overlimits 0 requeues 0) rate 0bit 0pps backlog 0b 0p requeues 0 User has no way to tell if the "rate 0bit 0pps" is a real estimation, or a fake one (because no estimator is active) After this patch, tc command output is : $ tc -s -d qdisc qdisc pfifo_fast 0: dev eth0 root bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 Sent 561075 bytes 1196 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 We add a parameter to gnet_stats_copy_rate_est() function so that it can use gen_estimator_active(bstats, r), as suggested by Jarek. This parameter can be NULL if check is not necessary, (htb for example has a mandatory rate estimator) Signed-off-by: Eric Dumazet Signed-off-by: Jarek Poplawski Signed-off-by: David S. Miller --- include/net/gen_stats.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index c1488553e34..eb87a1447ae 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -30,6 +30,7 @@ extern int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, extern int gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b); extern int gnet_stats_copy_rate_est(struct gnet_dump *d, + const struct gnet_stats_basic_packed *b, struct gnet_stats_rate_est *r); extern int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q); -- cgit v1.2.3 From ec1b4cf74c81bfd0fbe5bf62bafc86c45917e72f Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 5 Oct 2009 05:58:39 +0000 Subject: net: mark net_proto_ops as const All usages of structure net_proto_ops should be declared const. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/bluetooth/bluetooth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 718394e2c01..04a6908e38d 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -121,7 +121,7 @@ struct bt_sock_list { rwlock_t lock; }; -int bt_sock_register(int proto, struct net_proto_family *ops); +int bt_sock_register(int proto, const struct net_proto_family *ops); int bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); -- cgit v1.2.3 From 3d23e349d807177eaf519d444677cee86b1a04cf Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 29 Sep 2009 23:27:28 +0200 Subject: wext: refactor Refactor wext to * split out iwpriv handling * split out iwspy handling * split out procfs support * allow cfg80211 to have wireless extensions compat code w/o CONFIG_WIRELESS_EXT After this, drivers need to - select WIRELESS_EXT - for wext support - select WEXT_PRIV - for iwpriv support - select WEXT_SPY - for iwspy support except cfg80211 -- which gets new hooks in wext-core.c and can then get wext handlers without CONFIG_WIRELESS_EXT. Wireless extensions procfs support is auto-selected based on PROC_FS and anything that requires the wext core (i.e. WIRELESS_EXT or CFG80211_WEXT). Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 6 +++++- include/net/iw_handler.h | 14 +++++++------ include/net/net_namespace.h | 2 +- include/net/wext.h | 49 ++++++++++++++++++++++++++++++++------------- 4 files changed, 49 insertions(+), 22 deletions(-) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 3d874c62021..241ea14d6df 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1171,6 +1171,10 @@ struct wiphy { struct net *_net; #endif +#ifdef CONFIG_CFG80211_WEXT + const struct iw_handler_def *wext; +#endif + char priv[0] __attribute__((__aligned__(NETDEV_ALIGN))); }; @@ -1345,7 +1349,7 @@ struct wireless_dev { struct cfg80211_internal_bss *auth_bsses[MAX_AUTH_BSSES]; struct cfg80211_internal_bss *current_bss; /* associated / joined */ -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_CFG80211_WEXT /* wext data */ struct { struct cfg80211_ibss_params ibss; diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index e9054a283fd..d5d337170a5 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -323,18 +323,19 @@ typedef int (*iw_handler)(struct net_device *dev, struct iw_request_info *info, */ struct iw_handler_def { - /* Number of handlers defined (more precisely, index of the - * last defined handler + 1) */ - __u16 num_standard; - __u16 num_private; - /* Number of private arg description */ - __u16 num_private_args; /* Array of handlers for standard ioctls * We will call dev->wireless_handlers->standard[ioctl - SIOCSIWCOMMIT] */ const iw_handler * standard; + /* Number of handlers defined (more precisely, index of the + * last defined handler + 1) */ + __u16 num_standard; +#ifdef CONFIG_WEXT_PRIV + __u16 num_private; + /* Number of private arg description */ + __u16 num_private_args; /* Array of handlers for private ioctls * Will call dev->wireless_handlers->private[ioctl - SIOCIWFIRSTPRIV] */ @@ -344,6 +345,7 @@ struct iw_handler_def * can put it in any order you want and should not leave holes... * We will automatically export that to user space... */ const struct iw_priv_args * private_args; +#endif /* New location of get_wireless_stats, to de-bloat struct net_device. * The old pointer in struct net_device will be gradually phased diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index a1202841aad..699410142bf 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -80,7 +80,7 @@ struct net { #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif -#ifdef CONFIG_WIRELESS_EXT +#ifdef CONFIG_WEXT_CORE struct sk_buff_head wext_nlevents; #endif struct net_generic *gen; diff --git a/include/net/wext.h b/include/net/wext.h index 3f2b94de2cf..4f6e7423174 100644 --- a/include/net/wext.h +++ b/include/net/wext.h @@ -1,29 +1,19 @@ #ifndef __NET_WEXT_H #define __NET_WEXT_H -/* - * wireless extensions interface to the core code - */ +#include struct net; -#ifdef CONFIG_WIRELESS_EXT -extern int wext_proc_init(struct net *net); -extern void wext_proc_exit(struct net *net); +#ifdef CONFIG_WEXT_CORE extern int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cmd, void __user *arg); extern int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, unsigned long arg); + extern struct iw_statistics *get_wireless_stats(struct net_device *dev); +extern int call_commit_handler(struct net_device *dev); #else -static inline int wext_proc_init(struct net *net) -{ - return 0; -} -static inline void wext_proc_exit(struct net *net) -{ - return; -} static inline int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cmd, void __user *arg) { @@ -36,4 +26,35 @@ static inline int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, } #endif +#ifdef CONFIG_WEXT_PROC +extern int wext_proc_init(struct net *net); +extern void wext_proc_exit(struct net *net); +#else +static inline int wext_proc_init(struct net *net) +{ + return 0; +} +static inline void wext_proc_exit(struct net *net) +{ + return; +} +#endif + +#ifdef CONFIG_WEXT_PRIV +int ioctl_private_call(struct net_device *dev, struct iwreq *iwr, + unsigned int cmd, struct iw_request_info *info, + iw_handler handler); +int compat_private_call(struct net_device *dev, struct iwreq *iwr, + unsigned int cmd, struct iw_request_info *info, + iw_handler handler); +int iw_handler_get_private(struct net_device * dev, + struct iw_request_info * info, + union iwreq_data * wrqu, + char * extra); +#else +#define ioctl_private_call NULL +#define compat_private_call NULL +#endif + + #endif /* __NET_WEXT_H */ -- cgit v1.2.3 From dfce95f51fe34fa18c87a7d0bea53594b9bf1b9a Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Thu, 24 Sep 2009 11:02:42 -0700 Subject: cfg80211: add firmware and hardware version to wiphy It's useful to provide firmware and hardware version to user space and have a generic interface to retrieve them. Users can provide the version information in bug reports etc. Add fields for firmware and hardware version to struct wiphy. (Dropped nl80211 bits for now and modified remaining bits in favor of ethtool. -- JWL) Cc: Kalle Valo Signed-off-by: John W. Linville --- include/net/cfg80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 241ea14d6df..6f4862b3ec2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1142,6 +1142,9 @@ struct wiphy { u32 frag_threshold; u32 rts_threshold; + char fw_version[ETHTOOL_BUSINFO_LEN]; + u32 hw_version; + /* If multiple wiphys are registered and you're handed e.g. * a regular netdev with assigned ieee80211_ptr, you won't * know whether it points to a wiphy your driver has registered -- cgit v1.2.3 From f86dcc5aa8c7908f2c287e7a211228df599e3e71 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Oct 2009 00:37:59 +0000 Subject: udp: dynamically size hash tables at boot time UDP_HTABLE_SIZE was initialy defined to 128, which is a bit small for several setups. 4000 active UDP sockets -> 32 sockets per chain in average. An incoming frame has to lookup all sockets to find best match, so long chains hurt latency. Instead of a fixed size hash table that cant be perfect for every needs, let UDP stack choose its table size at boot time like tcp/ip route, using alloc_large_system_hash() helper Add an optional boot parameter, uhash_entries=x so that an admin can force a size between 256 and 65536 if needed, like thash_entries and rhash_entries. dmesg logs two new lines : [ 0.647039] UDP hash table entries: 512 (order: 0, 4096 bytes) [ 0.647099] UDP Lite hash table entries: 512 (order: 0, 4096 bytes) Maximal size on 64bit arches would be 65536 slots, ie 1 MBytes for non debugging spinlocks. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/udp.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/udp.h b/include/net/udp.h index f98abd2ce70..22aa2e7eb1d 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -54,12 +54,19 @@ struct udp_hslot { struct hlist_nulls_head head; spinlock_t lock; } __attribute__((aligned(2 * sizeof(long)))); + struct udp_table { - struct udp_hslot hash[UDP_HTABLE_SIZE]; + struct udp_hslot *hash; + unsigned int mask; + unsigned int log; }; extern struct udp_table udp_table; -extern void udp_table_init(struct udp_table *); - +extern void udp_table_init(struct udp_table *, const char *); +static inline struct udp_hslot *udp_hashslot(struct udp_table *table, + struct net *net, unsigned num) +{ + return &table->hash[udp_hashfn(net, num, table->mask)]; +} /* Note: this must match 'valbool' in sock_setsockopt */ #define UDP_CSUM_NOXMIT 1 -- cgit v1.2.3 From 3b885787ea4112eaa80945999ea0901bf742707f Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Mon, 12 Oct 2009 13:26:31 -0700 Subject: net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 98398bdec57..10669b01eea 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -505,6 +505,7 @@ enum sock_flags { SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */ SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */ SOCK_FASYNC, /* fasync() active */ + SOCK_RXQ_OVFL, }; static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) @@ -1493,6 +1494,8 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) sk->sk_stamp = kt; } +extern void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); + /** * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @msg: outgoing packet -- cgit v1.2.3 From a2e2725541fad72416326798c2d7fa4dafb7d337 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 12 Oct 2009 23:40:10 -0700 Subject: net: Introduce recvmmsg socket syscall MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Meaning receive multiple messages, reducing the number of syscalls and net stack entry/exit operations. Next patches will introduce mechanisms where protocols that want to optimize this operation will provide an unlocked_recvmsg operation. This takes into account comments made by: . Paul Moore: sock_recvmsg is called only for the first datagram, sock_recvmsg_nosec is used for the rest. . Caitlin Bestler: recvmmsg now has a struct timespec timeout, that works in the same fashion as the ppoll one. If the underlying protocol returns a datagram with MSG_OOB set, this will make recvmmsg return right away with as many datagrams (+ the OOB one) it has received so far. . Rémi Denis-Courmont & Steven Whitehouse: If we receive N < vlen datagrams and then recvmsg returns an error, recvmmsg will return the successfully received datagrams, store the error and return it in the next call. This paves the way for a subsequent optimization, sk_prot->unlocked_recvmsg, where we will be able to acquire the lock only at batch start and end, not at every underlying recvmsg call. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/compat.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/net') diff --git a/include/net/compat.h b/include/net/compat.h index 7c3002832d0..9679f05e989 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -18,6 +18,11 @@ struct compat_msghdr { compat_uint_t msg_flags; }; +struct compat_mmsghdr { + struct compat_msghdr msg_hdr; + compat_uint_t msg_len; +}; + struct compat_cmsghdr { compat_size_t cmsg_len; compat_int_t cmsg_level; @@ -35,6 +40,9 @@ extern int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *); extern int verify_compat_iovec(struct msghdr *, struct iovec *, struct sockaddr *, int); extern asmlinkage long compat_sys_sendmsg(int,struct compat_msghdr __user *,unsigned); extern asmlinkage long compat_sys_recvmsg(int,struct compat_msghdr __user *,unsigned); +extern asmlinkage long compat_sys_recvmmsg(int, struct compat_mmsghdr __user *, + unsigned, unsigned, + struct timespec __user *); extern asmlinkage long compat_sys_getsockopt(int, int, int, char __user *, int __user *); extern int put_cmsg_compat(struct msghdr*, int, int, int, void *); -- cgit v1.2.3 From f373b53b5fe67aa4a6f28f921a529cc90f88e79b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 9 Oct 2009 00:16:19 +0000 Subject: tcp: replace ehash_size by ehash_mask Storing the mask (size - 1) instead of the size allows fast path to be a bit faster. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index d522dcf3031..5f11c4a0dac 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -125,7 +125,7 @@ struct inet_hashinfo { */ struct inet_ehash_bucket *ehash; spinlock_t *ehash_locks; - unsigned int ehash_size; + unsigned int ehash_mask; unsigned int ehash_locks_mask; /* Ok, let's try this, I give up, we do need a local binding @@ -158,7 +158,7 @@ static inline struct inet_ehash_bucket *inet_ehash_bucket( struct inet_hashinfo *hashinfo, unsigned int hash) { - return &hashinfo->ehash[hash & (hashinfo->ehash_size - 1)]; + return &hashinfo->ehash[hash & hashinfo->ehash_mask]; } static inline spinlock_t *inet_ehash_lockp( -- cgit v1.2.3 From f14001fcd7bd03983c872810a3b11af4148bae72 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= Date: Wed, 14 Oct 2009 00:48:27 +0000 Subject: Phonet: deliver broadcast packets to broadcast sockets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- include/net/phonet/phonet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index d43f71b5ec0..fdb05fa0346 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -47,6 +47,7 @@ static inline struct pn_sock *pn_sk(struct sock *sk) extern const struct proto_ops phonet_dgram_ops; struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *sa); +void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb); void phonet_get_local_port_range(int *min, int *max); void pn_sock_hash(struct sock *sk); void pn_sock_unhash(struct sock *sk); -- cgit v1.2.3 From 55748ac0468134a89bc55aed6a9691e320caa8a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= Date: Wed, 14 Oct 2009 00:48:28 +0000 Subject: Phonet: routing table backend MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Phonet "universe" only has 64 addresses, so we keep a trivial flat routing table. Signed-off-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- include/net/phonet/pn_dev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h index 44c923c9e21..87b5d8112e1 100644 --- a/include/net/phonet/pn_dev.h +++ b/include/net/phonet/pn_dev.h @@ -47,6 +47,11 @@ u8 phonet_address_get(struct net_device *dev, u8 addr); int phonet_address_lookup(struct net *net, u8 addr); void phonet_address_notify(int event, struct net_device *dev, u8 addr); +int phonet_route_add(struct net_device *dev, u8 daddr); +int phonet_route_del(struct net_device *dev, u8 daddr); +struct net_device *phonet_route_get(struct net *net, u8 daddr); +struct net_device *phonet_route_output(struct net *net, u8 daddr); + #define PN_NO_ADDR 0xff extern const struct file_operations pn_sock_seq_fops; -- cgit v1.2.3 From f062f41d06575744b9eaf725eef8a5d3b5f5b7ca Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= Date: Wed, 14 Oct 2009 00:48:29 +0000 Subject: Phonet: routing table Netlink interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- include/net/phonet/pn_dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h index 87b5d8112e1..afa7defceb1 100644 --- a/include/net/phonet/pn_dev.h +++ b/include/net/phonet/pn_dev.h @@ -49,6 +49,7 @@ void phonet_address_notify(int event, struct net_device *dev, u8 addr); int phonet_route_add(struct net_device *dev, u8 daddr); int phonet_route_del(struct net_device *dev, u8 daddr); +void rtm_phonet_notify(int event, struct net_device *dev, u8 dst); struct net_device *phonet_route_get(struct net *net, u8 daddr); struct net_device *phonet_route_output(struct net *net, u8 daddr); -- cgit v1.2.3 From c720c7e8383aff1cb219bddf474ed89d850336e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 15 Oct 2009 06:30:45 +0000 Subject: inet: rename some inet_sock fields In order to have better cache layouts of struct sock (separate zones for rx/tx paths), we need this preliminary patch. Goal is to transfert fields used at lookup time in the first read-mostly cache line (inside struct sock_common) and move sk_refcnt to a separate cache line (only written by rx path) This patch adds inet_ prefix to daddr, rcv_saddr, dport, num, saddr, sport and id fields. This allows a future patch to define these fields as macros, like sk_refcnt, without name clashes. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_hashtables.h | 4 ++-- include/net/inet_hashtables.h | 12 ++++++------ include/net/inet_sock.h | 36 ++++++++++++++++++------------------ include/net/inet_timewait_sock.h | 2 +- include/net/ip.h | 12 ++++++------ 5 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include/net') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 22c73a77cd9..92838d3a1ab 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -46,8 +46,8 @@ static inline int inet6_sk_ehashfn(const struct sock *sk) const struct ipv6_pinfo *np = inet6_sk(sk); const struct in6_addr *laddr = &np->rcv_saddr; const struct in6_addr *faddr = &np->daddr; - const __u16 lport = inet->num; - const __be16 fport = inet->dport; + const __u16 lport = inet->inet_num; + const __be16 fport = inet->inet_dport; struct net *net = sock_net(sk); return inet6_ehashfn(net, laddr, lport, faddr, fport); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 5f11c4a0dac..5b698b3b463 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -241,7 +241,7 @@ static inline int inet_lhashfn(struct net *net, const unsigned short num) static inline int inet_sk_listen_hashfn(const struct sock *sk) { - return inet_lhashfn(sock_net(sk), inet_sk(sk)->num); + return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num); } /* Caller must disable local BH processing. */ @@ -301,8 +301,8 @@ typedef __u64 __bitwise __addrpair; #endif /* __BIG_ENDIAN */ #define INET_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) && \ - ((*((__addrpair *)&(inet_sk(__sk)->daddr))) == (__cookie)) && \ - ((*((__portpair *)&(inet_sk(__sk)->dport))) == (__ports)) && \ + ((*((__addrpair *)&(inet_sk(__sk)->inet_daddr))) == (__cookie)) && \ + ((*((__portpair *)&(inet_sk(__sk)->inet_dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) #define INET_TW_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) && \ @@ -313,9 +313,9 @@ typedef __u64 __bitwise __addrpair; #define INET_ADDR_COOKIE(__name, __saddr, __daddr) #define INET_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif) \ (((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) && \ - (inet_sk(__sk)->daddr == (__saddr)) && \ - (inet_sk(__sk)->rcv_saddr == (__daddr)) && \ - ((*((__portpair *)&(inet_sk(__sk)->dport))) == (__ports)) && \ + (inet_sk(__sk)->inet_daddr == (__saddr)) && \ + (inet_sk(__sk)->inet_rcv_saddr == (__daddr)) && \ + ((*((__portpair *)&(inet_sk(__sk)->inet_dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) #define INET_TW_MATCH(__sk, __net, __hash,__cookie, __saddr, __daddr, __ports, __dif) \ (((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) && \ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 47004f35cc7..bd4c53f75ac 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -93,14 +93,14 @@ struct rtable; * * @sk - ancestor class * @pinet6 - pointer to IPv6 control block - * @daddr - Foreign IPv4 addr - * @rcv_saddr - Bound local IPv4 addr - * @dport - Destination port - * @num - Local port - * @saddr - Sending source + * @inet_daddr - Foreign IPv4 addr + * @inet_rcv_saddr - Bound local IPv4 addr + * @inet_dport - Destination port + * @inet_num - Local port + * @inet_saddr - Sending source * @uc_ttl - Unicast TTL - * @sport - Source port - * @id - ID counter for DF pkts + * @inet_sport - Source port + * @inet_id - ID counter for DF pkts * @tos - TOS * @mc_ttl - Multicasting TTL * @is_icsk - is this an inet_connection_sock? @@ -115,16 +115,16 @@ struct inet_sock { struct ipv6_pinfo *pinet6; #endif /* Socket demultiplex comparisons on incoming packets. */ - __be32 daddr; - __be32 rcv_saddr; - __be16 dport; - __u16 num; - __be32 saddr; + __be32 inet_daddr; + __be32 inet_rcv_saddr; + __be16 inet_dport; + __u16 inet_num; + __be32 inet_saddr; __s16 uc_ttl; __u16 cmsg_flags; struct ip_options *opt; - __be16 sport; - __u16 id; + __be16 inet_sport; + __u16 inet_id; __u8 tos; __u8 mc_ttl; __u8 pmtudisc; @@ -190,10 +190,10 @@ static inline unsigned int inet_ehashfn(struct net *net, static inline int inet_sk_ehashfn(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); - const __be32 laddr = inet->rcv_saddr; - const __u16 lport = inet->num; - const __be32 faddr = inet->daddr; - const __be16 fport = inet->dport; + const __be32 laddr = inet->inet_rcv_saddr; + const __u16 lport = inet->inet_num; + const __be32 faddr = inet->inet_daddr; + const __be16 fport = inet->inet_dport; struct net *net = sock_net(sk); return inet_ehashfn(net, laddr, lport, faddr, fport); diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index b63b80fac56..37f3aea074a 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -194,7 +194,7 @@ static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) static inline __be32 inet_rcv_saddr(const struct sock *sk) { return likely(sk->sk_state != TCP_TIME_WAIT) ? - inet_sk(sk)->rcv_saddr : inet_twsk(sk)->tw_rcv_saddr; + inet_sk(sk)->inet_rcv_saddr : inet_twsk(sk)->tw_rcv_saddr; } extern void inet_twsk_put(struct inet_timewait_sock *tw); diff --git a/include/net/ip.h b/include/net/ip.h index 2f47e5482b5..376adf47764 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -240,8 +240,8 @@ static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, str * does not change, they drop every other packet in * a TCP stream using header compression. */ - iph->id = (sk && inet_sk(sk)->daddr) ? - htons(inet_sk(sk)->id++) : 0; + iph->id = (sk && inet_sk(sk)->inet_daddr) ? + htons(inet_sk(sk)->inet_id++) : 0; } else __ip_select_ident(iph, dst, 0); } @@ -249,9 +249,9 @@ static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, str static inline void ip_select_ident_more(struct iphdr *iph, struct dst_entry *dst, struct sock *sk, int more) { if (iph->frag_off & htons(IP_DF)) { - if (sk && inet_sk(sk)->daddr) { - iph->id = htons(inet_sk(sk)->id); - inet_sk(sk)->id += 1 + more; + if (sk && inet_sk(sk)->inet_daddr) { + iph->id = htons(inet_sk(sk)->inet_id); + inet_sk(sk)->inet_id += 1 + more; } else iph->id = 0; } else @@ -317,7 +317,7 @@ static inline void ip_ib_mc_map(__be32 naddr, const unsigned char *broadcast, ch static __inline__ void inet_reset_saddr(struct sock *sk) { - inet_sk(sk)->rcv_saddr = inet_sk(sk)->saddr = 0; + inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0; #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) if (sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); -- cgit v1.2.3 From 49cbf952488e7fa2f1160c80016e09e6c2854b24 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 7 Oct 2009 22:47:16 +0000 Subject: ah: Add struct crypto_ahash to ah_data To support for ahash algorithms, we add a pointer to a crypto_ahash to ah_data. Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller --- include/net/ah.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/ah.h b/include/net/ah.h index ae1c322f424..7ac52214ba0 100644 --- a/include/net/ah.h +++ b/include/net/ah.h @@ -14,6 +14,7 @@ struct ah_data int icv_trunc_len; struct crypto_hash *tfm; + struct crypto_ahash *ahash; }; static inline int ah_mac_digest(struct ah_data *ahp, struct sk_buff *skb, -- cgit v1.2.3 From 2ad9afbf5ca27482aa275de517261d56fd1e7ba0 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 7 Oct 2009 22:49:57 +0000 Subject: ah: Remove obsolete code ah4 and ah6 are converted to ahash now, so we can remove the code for the obsolete hash algorithm. Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller --- include/net/ah.h | 29 +++-------------------------- 1 file changed, 3 insertions(+), 26 deletions(-) (limited to 'include/net') diff --git a/include/net/ah.h b/include/net/ah.h index 7ac52214ba0..7573a7152a7 100644 --- a/include/net/ah.h +++ b/include/net/ah.h @@ -1,44 +1,21 @@ #ifndef _NET_AH_H #define _NET_AH_H -#include -#include +#include /* This is the maximum truncated ICV length that we know of. */ #define MAX_AH_AUTH_LEN 12 +struct crypto_ahash; + struct ah_data { - u8 *work_icv; int icv_full_len; int icv_trunc_len; - struct crypto_hash *tfm; struct crypto_ahash *ahash; }; -static inline int ah_mac_digest(struct ah_data *ahp, struct sk_buff *skb, - u8 *auth_data) -{ - struct hash_desc desc; - int err; - - desc.tfm = ahp->tfm; - desc.flags = 0; - - memset(auth_data, 0, ahp->icv_trunc_len); - err = crypto_hash_init(&desc); - if (unlikely(err)) - goto out; - err = skb_icv_walk(skb, &desc, 0, skb->len, crypto_hash_update); - if (unlikely(err)) - goto out; - err = crypto_hash_final(&desc, ahp->work_icv); - -out: - return err; -} - struct ip_auth_hdr; static inline struct ip_auth_hdr *ip_auth_hdr(const struct sk_buff *skb) -- cgit v1.2.3 From eb2ff967a587a4a784fd2390f38e324a5bec01ec Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 7 Oct 2009 22:50:40 +0000 Subject: xfrm: remove skb_icv_walk The last users of skb_icv_walk are converted to ahash now, so skb_icv_walk is unused and can be removed. Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller --- include/net/xfrm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 223e90a4482..d9c6dbb9271 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1500,9 +1500,6 @@ struct scatterlist; typedef int (icv_update_fn_t)(struct hash_desc *, struct scatterlist *, unsigned int); -extern int skb_icv_walk(const struct sk_buff *skb, struct hash_desc *tfm, - int offset, int len, icv_update_fn_t icv_update); - static inline int xfrm_addr_cmp(xfrm_address_t *a, xfrm_address_t *b, int family) { -- cgit v1.2.3 From c2315b4ea9ac9c3f8caf03c3511d86fabe4a5fcd Mon Sep 17 00:00:00 2001 From: Inaky Perez-Gonzalez Date: Wed, 16 Sep 2009 17:10:55 -0700 Subject: wimax/i2400m: clarify and fix i2400m->{ready,updown} The i2400m driver uses two different bits to distinguish how much the driver is up. i2400m->ready is used to denote that the infrastructure to communicate with the device is up and running. i2400m->updown is used to indicate if 'ready' and the device is up and running, ready to take control and data traffic. However, all this was pretty dirty and not clear, with many open spots where race conditions were present. This commit cleans up the situation by: - documenting the usage of both bits - setting them only in specific, well controlled places (i2400m_dev_start, i2400m_dev_stop) - ensuring the i2400m workqueue can't get in the middle of the setting by flushing it when i2400m->ready is set to zero. This allows the report hook not having to check again for the bit to be set [rx.c:i2400m_report_hook_work()]. - using i2400m->updown to determine if the device is up and running instead of the wimax state in i2400m_dev_reset_handle(). - not loosing missed messages sent by the hardware before i2400m->ready is set. In rx.c, whatever the device sends can be sent to user space over the message pipes as soon as the wimax device is registered, so don't wait for i2400m->ready to be set. Signed-off-by: Inaky Perez-Gonzalez --- include/net/wimax.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/net') diff --git a/include/net/wimax.h b/include/net/wimax.h index 2af7bf839f2..d69c4a7a126 100644 --- a/include/net/wimax.h +++ b/include/net/wimax.h @@ -195,6 +195,12 @@ * defining the `struct nla_policy` for each message, it has to have * an array size of WIMAX_GNL_ATTR_MAX+1. * + * The op_*() function pointers will not be called if the wimax_dev is + * in a state <= %WIMAX_ST_UNINITIALIZED. The exception is: + * + * - op_reset: can be called at any time after wimax_dev_add() has + * been called. + * * THE PIPE INTERFACE: * * This interface is kept intentionally simple. The driver can send -- cgit v1.2.3 From 748879776e3b738d53e64df6dbec7394b829462a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 20 Oct 2009 01:09:17 -0700 Subject: net: Avoid compiler warning for mmsghdr when CONFIG_COMPAT is not selected Reported-by: Stephen Rothwell Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/compat.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/compat.h b/include/net/compat.h index 9679f05e989..3c7d4e38fa1 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -33,7 +33,11 @@ extern int compat_sock_get_timestamp(struct sock *, struct timeval __user *); extern int compat_sock_get_timestampns(struct sock *, struct timespec __user *); #else /* defined(CONFIG_COMPAT) */ -#define compat_msghdr msghdr /* to avoid compiler warnings */ +/* + * To avoid compiler warnings: + */ +#define compat_msghdr msghdr +#define compat_mmsghdr mmsghdr #endif /* defined(CONFIG_COMPAT) */ extern int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *); -- cgit v1.2.3 From e022f0b4a03f4fff9323b509df023b8af635716e Mon Sep 17 00:00:00 2001 From: Krishna Kumar Date: Mon, 19 Oct 2009 23:46:20 +0000 Subject: net: Introduce sk_tx_queue_mapping Introduce sk_tx_queue_mapping; and functions that set, test and get this value. Reset sk_tx_queue_mapping to -1 whenever the dst cache is set/reset, and in socket alloc. Setting txq to -1 and using valid txq=<0 to n-1> allows the tx path to use the value of sk_tx_queue_mapping directly instead of subtracting 1 on every tx. Signed-off-by: Krishna Kumar Signed-off-by: David S. Miller --- include/net/sock.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 1364428f53f..55de3bd719a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -107,6 +107,7 @@ struct net; * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol * @skc_refcnt: reference count + * @skc_tx_queue_mapping: tx queue number for this connection * @skc_hash: hash value used with various protocol lookup tables * @skc_family: network address family * @skc_state: Connection state @@ -128,6 +129,7 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; atomic_t skc_refcnt; + int skc_tx_queue_mapping; unsigned int skc_hash; unsigned short skc_family; @@ -215,6 +217,7 @@ struct sock { #define sk_node __sk_common.skc_node #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt +#define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping #define sk_copy_start __sk_common.skc_hash #define sk_hash __sk_common.skc_hash @@ -1094,8 +1097,29 @@ static inline void sock_put(struct sock *sk) extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested); +static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) +{ + sk->sk_tx_queue_mapping = tx_queue; +} + +static inline void sk_tx_queue_clear(struct sock *sk) +{ + sk->sk_tx_queue_mapping = -1; +} + +static inline int sk_tx_queue_get(const struct sock *sk) +{ + return sk->sk_tx_queue_mapping; +} + +static inline bool sk_tx_queue_recorded(const struct sock *sk) +{ + return (sk && sk->sk_tx_queue_mapping >= 0); +} + static inline void sk_set_socket(struct sock *sk, struct socket *sock) { + sk_tx_queue_clear(sk); sk->sk_socket = sock; } @@ -1152,6 +1176,7 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; + sk_tx_queue_clear(sk); old_dst = sk->sk_dst_cache; sk->sk_dst_cache = dst; dst_release(old_dst); @@ -1170,6 +1195,7 @@ __sk_dst_reset(struct sock *sk) { struct dst_entry *old_dst; + sk_tx_queue_clear(sk); old_dst = sk->sk_dst_cache; sk->sk_dst_cache = NULL; dst_release(old_dst); -- cgit v1.2.3 From ea94ff3b55188df157a8740bdf3976a87563d705 Mon Sep 17 00:00:00 2001 From: Krishna Kumar Date: Mon, 19 Oct 2009 23:46:45 +0000 Subject: net: Fix for dst_negative_advice dst_negative_advice() should check for changed dst and reset sk_tx_queue_mapping accordingly. Pass sock to the callers of dst_negative_advice. (sk_reset_txq is defined just for use by dst_negative_advice. The only way I could find to get around this is to move dst_negative_() from dst.h to dst.c, include sock.h in dst.c, etc) Signed-off-by: Krishna Kumar Signed-off-by: David S. Miller --- include/net/dst.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 5a900ddcf10..720d90653a8 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -222,11 +222,19 @@ static inline void dst_confirm(struct dst_entry *dst) neigh_confirm(dst->neighbour); } -static inline void dst_negative_advice(struct dst_entry **dst_p) +static inline void dst_negative_advice(struct dst_entry **dst_p, + struct sock *sk) { struct dst_entry * dst = *dst_p; - if (dst && dst->ops->negative_advice) + if (dst && dst->ops->negative_advice) { *dst_p = dst->ops->negative_advice(dst); + + if (dst != *dst_p) { + extern void sk_reset_txq(struct sock *sk); + + sk_reset_txq(sk); + } + } } static inline void dst_link_failure(struct sk_buff *skb) -- cgit v1.2.3 From 1c55d62e77fa16cdace417834fc7b8a421a1877f Mon Sep 17 00:00:00 2001 From: jamal Date: Thu, 15 Oct 2009 03:09:18 +0000 Subject: pkt_sched: skbedit add support for setting mark This adds support for setting the skb mark. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/tc_act/tc_skbedit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 6abb3ed3ebf..e103fe02f37 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -26,7 +26,9 @@ struct tcf_skbedit { struct tcf_common common; u32 flags; u32 priority; + u32 mark; u16 queue_mapping; + /* XXX: 16-bit pad here? */ }; #define to_skbedit(pc) \ container_of(pc, struct tcf_skbedit, common) -- cgit v1.2.3 From ef9a9d1183b36fbf3de327f44596533b770c3005 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 23 Oct 2009 17:51:26 +0000 Subject: ipv6 sit: RCU conversion phase I SIT tunnels use one rwlock to protect their prl entries. This first patch adds RCU locking for prl management, with standard call_rcu() calls. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipip.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/ipip.h b/include/net/ipip.h index 86f1c8bd040..b3db2fd6e61 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -45,6 +45,7 @@ struct ip_tunnel_prl_entry struct ip_tunnel_prl_entry *next; __be32 addr; u16 flags; + struct rcu_head rcu_head; }; #define IPTUNNEL_XMIT() do { \ -- cgit v1.2.3 From 7c28bd0b8ec4d128bd7660671d1b626b0abc471f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 24 Oct 2009 06:13:17 -0700 Subject: rtnetlink: speedup rtnl_dump_ifinfo() When handling large number of netdevice, rtnl_dump_ifinfo() is very slow because it has O(N^2) complexity. Instead of scanning one single list, we can use the 256 sub lists of the dev_index hash table. This considerably speedups "ip link" operations Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/net_namespace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 699410142bf..0addd45038a 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -28,6 +28,10 @@ struct ctl_table_header; struct net_generic; struct sock; + +#define NETDEV_HASHBITS 8 +#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) + struct net { atomic_t count; /* To decided when the network * namespace should be freed. -- cgit v1.2.3 From ce470613cdfde70f25419cc52a4816315825f5d9 Mon Sep 17 00:00:00 2001 From: Holger Schurig Date: Tue, 13 Oct 2009 13:28:13 +0200 Subject: cfg80211: no cookies in cfg80211_send_XXX() Get rid of cookies in cfg80211_send_XXX() functions. Signed-off-by: Holger Schurig Signed-off-by: John W. Linville --- include/net/cfg80211.h | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6f4862b3ec2..ff67865de23 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1809,30 +1809,45 @@ void cfg80211_send_assoc_timeout(struct net_device *dev, const u8 *addr); * @dev: network device * @buf: deauthentication frame (header + body) * @len: length of the frame data - * @cookie: cookie from ->deauth if called within that callback, - * %NULL otherwise * * This function is called whenever deauthentication has been processed in * station mode. This includes both received deauthentication frames and * locally generated ones. This function may sleep. */ -void cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len, - void *cookie); +void cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len); + +/** + * __cfg80211_send_deauth - notification of processed deauthentication + * @dev: network device + * @buf: deauthentication frame (header + body) + * @len: length of the frame data + * + * Like cfg80211_send_deauth(), but doesn't take the wdev lock. + */ +void __cfg80211_send_deauth(struct net_device *dev, const u8 *buf, size_t len); /** * cfg80211_send_disassoc - notification of processed disassociation * @dev: network device * @buf: disassociation response frame (header + body) * @len: length of the frame data - * @cookie: cookie from ->disassoc if called within that callback, - * %NULL otherwise * * This function is called whenever disassociation has been processed in * station mode. This includes both received disassociation frames and locally * generated ones. This function may sleep. */ -void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len, - void *cookie); +void cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len); + +/** + * __cfg80211_send_disassoc - notification of processed disassociation + * @dev: network device + * @buf: disassociation response frame (header + body) + * @len: length of the frame data + * + * Like cfg80211_send_disassoc(), but doesn't take the wdev lock. + */ +void __cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, + size_t len); /** * cfg80211_michael_mic_failure - notification of Michael MIC failure (TKIP) -- cgit v1.2.3 From e36e49f7338f0f73cd7f5ba4f5b646a479ab60a8 Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Tue, 13 Oct 2009 20:33:13 +0300 Subject: mac80211: add ieee80211_rx_ni() ieee80211_rx() must be called with bottom halves disabled. To simplify driver development implement ieee80211_rx_ni() which disables BH. This function must be used when in process context. Signed-off-by: Kalle Valo Signed-off-by: John W. Linville --- include/net/mac80211.h | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c75b960c8ac..c42c4a820b8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1665,11 +1665,11 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw); * header if %RX_FLAG_RADIOTAP is set in the @status flags. * * This function may not be called in IRQ context. Calls to this function - * for a single hardware must be synchronized against each other. Calls - * to this function and ieee80211_rx_irqsafe() may not be mixed for a - * single hardware. + * for a single hardware must be synchronized against each other. Calls to + * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be + * mixed for a single hardware. * - * Note that right now, this function must be called with softirqs disabled. + * In process context use instead ieee80211_rx_ni(). * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call @@ -1682,14 +1682,34 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb); * Like ieee80211_rx() but can be called in IRQ context * (internally defers to a tasklet.) * - * Calls to this function and ieee80211_rx() may not be mixed for a - * single hardware. + * Calls to this function, ieee80211_rx() or ieee80211_rx_ni() may not + * be mixed for a single hardware. * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call */ void ieee80211_rx_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb); +/** + * ieee80211_rx_ni - receive frame (in process context) + * + * Like ieee80211_rx() but can be called in process context + * (internally disables bottom halves). + * + * Calls to this function, ieee80211_rx() and ieee80211_rx_irqsafe() may + * not be mixed for a single hardware. + * + * @hw: the hardware this frame came in on + * @skb: the buffer to receive, owned by mac80211 after this call + */ +static inline void ieee80211_rx_ni(struct ieee80211_hw *hw, + struct sk_buff *skb) +{ + local_bh_disable(); + ieee80211_rx(hw, skb); + local_bh_enable(); +} + /** * ieee80211_tx_status - transmit status callback * -- cgit v1.2.3 From 23289a37e2b127dfc4de1313fba15bb4c9f0cd5b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 27 Oct 2009 07:06:36 +0000 Subject: net: add a list_head parameter to dellink() method Adding a list_head parameter to rtnl_link_ops->dellink() methods allow us to queue devices on a list, in order to dismantle them all at once. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index c3aa044d3fc..cd5af1f508f 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -61,7 +61,8 @@ struct rtnl_link_ops { int (*changelink)(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]); - void (*dellink)(struct net_device *dev); + void (*dellink)(struct net_device *dev, + struct list_head *head); size_t (*get_size)(const struct net_device *dev); int (*fill_info)(struct sk_buff *skb, -- cgit v1.2.3 From 022c3f7d82f0f1c68018696f2f027b87b9bb45c2 Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 28 Oct 2009 04:15:22 +0000 Subject: Allow tcp_parse_options to consult dst entry We need tcp_parse_options to be aware of dst_entry to take into account per dst_entry TCP options settings Signed-off-by: Gilad Ben-Yossef Sigend-off-by: Ori Finkelman Sigend-off-by: Yony Amit Signed-off-by: David S. Miller --- include/net/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 03a49c70337..740d09be8e2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -409,7 +409,8 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, extern void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - int estab); + int estab, + struct dst_entry *dst); extern u8 *tcp_parse_md5sig_option(struct tcphdr *th); -- cgit v1.2.3 From 0c3adfb8ec9f85a63556b70f11e0fcf280545951 Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 28 Oct 2009 04:15:23 +0000 Subject: Add dst_feature to query route entry features Adding an accessor to existing dst_entry feautres field and refactor the only supported feature (allfrag) to use it. Signed-off-by: Gilad Ben-Yossef Sigend-off-by: Ori Finkelman Sigend-off-by: Yony Amit Signed-off-by: David S. Miller --- include/net/dst.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 720d90653a8..6377ab2feba 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -111,6 +111,12 @@ dst_metric(const struct dst_entry *dst, int metric) return dst->metrics[metric-1]; } +static inline u32 +dst_feature(const struct dst_entry *dst, u32 feature) +{ + return dst_metric(dst, RTAX_FEATURES) & feature; +} + static inline u32 dst_mtu(const struct dst_entry *dst) { u32 mtu = dst_metric(dst, RTAX_MTU); @@ -136,7 +142,7 @@ static inline void set_dst_metric_rtt(struct dst_entry *dst, int metric, static inline u32 dst_allfrag(const struct dst_entry *dst) { - int ret = dst_metric(dst, RTAX_FEATURES) & RTAX_FEATURE_ALLFRAG; + int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); /* Yes, _exactly_. This is paranoia. */ barrier(); return ret; -- cgit v1.2.3 From 6a86b9c78ebd0397eb953493c68ea9e194e7023c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 28 Oct 2009 09:58:52 +0100 Subject: mac80211: fix radiotap header generation In commit 601ae7f25aea58f208a7f640f6174aac0652403a Author: Bruno Randolf Date: Thu May 8 19:22:43 2008 +0200 mac80211: make rx radiotap header more flexible code was added that tried to align the radiotap header position in memory based on the radiotap header length. Quite obviously, that is completely useless. Instead of trying to do that, use unaligned accesses to generate the radiotap header. To properly do that, we also need to mark struct ieee80211_radiotap_header packed, but that is fine since it's already packed (and it should be marked packed anyway since its a wire format). Cc: Bruno Randolf Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/ieee80211_radiotap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 23c3f3d9777..9d3d86aaccb 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -80,7 +80,7 @@ struct ieee80211_radiotap_header { * Additional extensions are made * by setting bit 31. */ -}; +} __packed; /* Name Data type Units * ---- --------- ----- -- cgit v1.2.3 From 0869aea0eb711982cd2b8bebf41b3c0191c89cde Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 28 Oct 2009 10:03:35 +0100 Subject: mac80211: remove RX_FLAG_RADIOTAP While there may be a case for a driver adding its own bits of radiotap information, none currently does. Also, drivers would have to copy the code to generate the radiotap bits that now mac80211 generates. If some driver in the future needs to add some driver-specific information I'd expect that to be in a radiotap vendor namespace and we can add a different way of passing such data up and having mac80211 include it. Additionally, rename IEEE80211_CONF_RADIOTAP to IEEE80211_CONF_MONITOR since it's still used by b43(legacy) to obtain per-frame timestamps. The purpose of this patch is to simplify the RX code in mac80211 to make it easier to add paged skb support. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c42c4a820b8..2c9d3c719d8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -494,7 +494,6 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_MMIC_ERROR: Michael MIC error was reported on this frame. * Use together with %RX_FLAG_MMIC_STRIPPED. * @RX_FLAG_DECRYPTED: This frame was decrypted in hardware. - * @RX_FLAG_RADIOTAP: This frame starts with a radiotap header. * @RX_FLAG_MMIC_STRIPPED: the Michael MIC is stripped off this frame, * verification has been done by the hardware. * @RX_FLAG_IV_STRIPPED: The IV/ICV are stripped from this frame. @@ -515,7 +514,6 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = 1<<0, RX_FLAG_DECRYPTED = 1<<1, - RX_FLAG_RADIOTAP = 1<<2, RX_FLAG_MMIC_STRIPPED = 1<<3, RX_FLAG_IV_STRIPPED = 1<<4, RX_FLAG_FAILED_FCS_CRC = 1<<5, @@ -565,7 +563,9 @@ struct ieee80211_rx_status { * * Flags to define PHY configuration options * - * @IEEE80211_CONF_RADIOTAP: add radiotap header at receive time (if supported) + * @IEEE80211_CONF_MONITOR: there's a monitor interface present -- use this + * to determine for example whether to calculate timestamps for packets + * or not, do not use instead of filter flags! * @IEEE80211_CONF_PS: Enable 802.11 power save mode (managed mode only) * @IEEE80211_CONF_IDLE: The device is running, but idle; if the flag is set * the driver should be prepared to handle configuration requests but @@ -574,7 +574,7 @@ struct ieee80211_rx_status { * it can also be unset in that case when monitor interfaces are active. */ enum ieee80211_conf_flags { - IEEE80211_CONF_RADIOTAP = (1<<0), + IEEE80211_CONF_MONITOR = (1<<0), IEEE80211_CONF_PS = (1<<1), IEEE80211_CONF_IDLE = (1<<2), }; @@ -584,7 +584,7 @@ enum ieee80211_conf_flags { * enum ieee80211_conf_changed - denotes which configuration changed * * @IEEE80211_CONF_CHANGE_LISTEN_INTERVAL: the listen interval changed - * @IEEE80211_CONF_CHANGE_RADIOTAP: the radiotap flag changed + * @IEEE80211_CONF_CHANGE_MONITOR: the monitor flag changed * @IEEE80211_CONF_CHANGE_PS: the PS flag or dynamic PS timeout changed * @IEEE80211_CONF_CHANGE_POWER: the TX power changed * @IEEE80211_CONF_CHANGE_CHANNEL: the channel/channel_type changed @@ -593,7 +593,7 @@ enum ieee80211_conf_flags { */ enum ieee80211_conf_changed { IEEE80211_CONF_CHANGE_LISTEN_INTERVAL = BIT(2), - IEEE80211_CONF_CHANGE_RADIOTAP = BIT(3), + IEEE80211_CONF_CHANGE_MONITOR = BIT(3), IEEE80211_CONF_CHANGE_PS = BIT(4), IEEE80211_CONF_CHANGE_POWER = BIT(5), IEEE80211_CONF_CHANGE_CHANNEL = BIT(6), @@ -1661,8 +1661,7 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw); * ieee80211_rx - receive frame * * Use this function to hand received frames to mac80211. The receive - * buffer in @skb must start with an IEEE 802.11 header or a radiotap - * header if %RX_FLAG_RADIOTAP is set in the @status flags. + * buffer in @skb must start with an IEEE 802.11 header. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to -- cgit v1.2.3 From eddcbb94f75c3e8944503e9f13c1d29acd0d7052 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 29 Oct 2009 08:30:35 +0100 Subject: mac80211: introduce ieee80211_beacon_get_tim() Compared to ieee80211_beacon_get(), the new function ieee80211_beacon_get_tim() returns information on the location and length of the TIM IE, which some drivers need in order to generate the TIM on the device. The old function, ieee80211_beacon_get(), becomes a small static inline wrapper around the new one to not break all drivers. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 42 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2c9d3c719d8..bd0bbc37a1a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1743,19 +1743,45 @@ void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb); /** - * ieee80211_beacon_get - beacon generation function + * ieee80211_beacon_get_tim - beacon generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * @tim_offset: pointer to variable that will receive the TIM IE offset. + * Set to 0 if invalid (in non-AP modes). + * @tim_length: pointer to variable that will receive the TIM IE length, + * (including the ID and length bytes!). + * Set to 0 if invalid (in non-AP modes). + * + * If the driver implements beaconing modes, it must use this function to + * obtain the beacon frame/template. * * If the beacon frames are generated by the host system (i.e., not in - * hardware/firmware), the low-level driver uses this function to receive - * the next beacon frame from the 802.11 code. The low-level is responsible - * for calling this function before beacon data is needed (e.g., based on - * hardware interrupt). Returned skb is used only once and low-level driver - * is responsible for freeing it. + * hardware/firmware), the driver uses this function to get each beacon + * frame from mac80211 -- it is responsible for calling this function + * before the beacon is needed (e.g. based on hardware interrupt). + * + * If the beacon frames are generated by the device, then the driver + * must use the returned beacon as the template and change the TIM IE + * according to the current DTIM parameters/TIM bitmap. + * + * The driver is responsible for freeing the returned skb. + */ +struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u16 *tim_offset, u16 *tim_length); + +/** + * ieee80211_beacon_get - beacon generation function + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf. + * + * See ieee80211_beacon_get_tim(). */ -struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, - struct ieee80211_vif *vif); +static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + return ieee80211_beacon_get_tim(hw, vif, NULL, NULL); +} /** * ieee80211_rts_get - RTS frame generation function -- cgit v1.2.3 From c27f2fded51948edf40007f4f31350e9e0c6ba23 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 29 Oct 2009 08:41:25 +0100 Subject: mac80211: deprecate qual value This value is unused by mac80211, because it was only be used by wireless extensions, and turned out to not be useful there because the quality value needs to be comparable between scan results and the current value which is impossible when the qual value is calculated taking into account noise, for example. Since it is unused anyway, this patch deprecates it in the hope that drivers will remove their sometimes quite expensive calculations of the value. I'm open to actual uses of the value, but the best way of using it seems to be what the Intel drivers do which should probably be generalised if we have noise values from the hardware. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index bd0bbc37a1a..e12293e60ac 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -552,7 +552,7 @@ struct ieee80211_rx_status { int freq; int signal; int noise; - int qual; + int __deprecated qual; int antenna; int rate_idx; int flag; -- cgit v1.2.3 From fd2c3ef761fbc5e6c27fa7d40b30cda06bfcd7d8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 3 Nov 2009 03:26:03 +0000 Subject: net: cleanup include/net This cleanup patch puts struct/union/enum opening braces, in first line to ease grep games. struct something { becomes : struct something { Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ah.h | 3 +-- include/net/dn_dev.h | 12 ++++------- include/net/dn_fib.h | 3 +-- include/net/dn_nsp.h | 24 ++++++++-------------- include/net/dst.h | 3 +-- include/net/fib_rules.h | 9 +++------ include/net/gen_stats.h | 3 +-- include/net/genetlink.h | 12 ++++------- include/net/if_inet6.h | 24 ++++++++-------------- include/net/inetpeer.h | 3 +-- include/net/ip.h | 15 +++++--------- include/net/ip6_fib.h | 15 +++++--------- include/net/ip6_route.h | 3 +-- include/net/ip_vs.h | 6 ++---- include/net/ipip.h | 9 +++------ include/net/ipv6.h | 12 ++++------- include/net/iw_handler.h | 12 ++++------- include/net/neighbour.h | 18 ++++++----------- include/net/netfilter/nf_conntrack_ecache.h | 3 +-- include/net/netfilter/nf_conntrack_expect.h | 6 ++---- include/net/netfilter/nf_conntrack_extend.h | 6 ++---- include/net/netfilter/nf_conntrack_helper.h | 3 +-- include/net/netfilter/nf_conntrack_l3proto.h | 3 +-- include/net/netfilter/nf_conntrack_l4proto.h | 3 +-- include/net/netfilter/nf_conntrack_tuple.h | 12 ++++------- include/net/netfilter/nf_nat.h | 15 +++++--------- include/net/netfilter/nf_nat_protocol.h | 3 +-- include/net/pkt_cls.h | 24 ++++++++-------------- include/net/pkt_sched.h | 3 +-- include/net/protocol.h | 3 +-- include/net/red.h | 6 ++---- include/net/route.h | 12 ++++------- include/net/sch_generic.h | 30 ++++++++++------------------ include/net/scm.h | 9 +++------ include/net/sctp/sctp.h | 3 +-- include/net/tcp.h | 3 +-- include/net/xfrm.h | 27 +++++++++---------------- 37 files changed, 120 insertions(+), 240 deletions(-) (limited to 'include/net') diff --git a/include/net/ah.h b/include/net/ah.h index 7573a7152a7..f0129f79a31 100644 --- a/include/net/ah.h +++ b/include/net/ah.h @@ -8,8 +8,7 @@ struct crypto_ahash; -struct ah_data -{ +struct ah_data { int icv_full_len; int icv_trunc_len; diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h index cee46821dc5..28966cae3fd 100644 --- a/include/net/dn_dev.h +++ b/include/net/dn_dev.h @@ -97,16 +97,14 @@ struct dn_dev { unsigned long uptime; /* Time device went up in jiffies */ }; -struct dn_short_packet -{ +struct dn_short_packet { __u8 msgflg; __le16 dstnode; __le16 srcnode; __u8 forward; } __attribute__((packed)); -struct dn_long_packet -{ +struct dn_long_packet { __u8 msgflg; __u8 d_area; __u8 d_subarea; @@ -122,8 +120,7 @@ struct dn_long_packet /*------------------------- DRP - Routing messages ---------------------*/ -struct endnode_hello_message -{ +struct endnode_hello_message { __u8 msgflg; __u8 tiver[3]; __u8 id[6]; @@ -138,8 +135,7 @@ struct endnode_hello_message __u8 data[2]; } __attribute__((packed)); -struct rtnode_hello_message -{ +struct rtnode_hello_message { __u8 msgflg; __u8 tiver[3]; __u8 id[6]; diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h index c378be7bf96..52da6c3dd50 100644 --- a/include/net/dn_fib.h +++ b/include/net/dn_fib.h @@ -4,8 +4,7 @@ /* WARNING: The ordering of these elements must match ordering * of RTA_* rtnetlink attribute numbers. */ -struct dn_kern_rta -{ +struct dn_kern_rta { void *rta_dst; void *rta_src; int *rta_iif; diff --git a/include/net/dn_nsp.h b/include/net/dn_nsp.h index 96e816b6974..17d43d2db5e 100644 --- a/include/net/dn_nsp.h +++ b/include/net/dn_nsp.h @@ -70,30 +70,26 @@ extern struct sk_buff *dn_alloc_send_skb(struct sock *sk, size_t *size, int nobl /* Data Messages (data segment/interrupt/link service) */ -struct nsp_data_seg_msg -{ +struct nsp_data_seg_msg { __u8 msgflg; __le16 dstaddr; __le16 srcaddr; } __attribute__((packed)); -struct nsp_data_opt_msg -{ +struct nsp_data_opt_msg { __le16 acknum; __le16 segnum; __le16 lsflgs; } __attribute__((packed)); -struct nsp_data_opt_msg1 -{ +struct nsp_data_opt_msg1 { __le16 acknum; __le16 segnum; } __attribute__((packed)); /* Acknowledgment Message (data/other data) */ -struct nsp_data_ack_msg -{ +struct nsp_data_ack_msg { __u8 msgflg; __le16 dstaddr; __le16 srcaddr; @@ -101,16 +97,14 @@ struct nsp_data_ack_msg } __attribute__((packed)); /* Connect Acknowledgment Message */ -struct nsp_conn_ack_msg -{ +struct nsp_conn_ack_msg { __u8 msgflg; __le16 dstaddr; } __attribute__((packed)); /* Connect Initiate/Retransmit Initiate/Connect Confirm */ -struct nsp_conn_init_msg -{ +struct nsp_conn_init_msg { __u8 msgflg; #define NSP_CI 0x18 /* Connect Initiate */ #define NSP_RCI 0x68 /* Retrans. Conn Init */ @@ -126,8 +120,7 @@ struct nsp_conn_init_msg } __attribute__((packed)); /* Disconnect Initiate/Disconnect Confirm */ -struct nsp_disconn_init_msg -{ +struct nsp_disconn_init_msg { __u8 msgflg; __le16 dstaddr; __le16 srcaddr; @@ -136,8 +129,7 @@ struct nsp_disconn_init_msg -struct srcobj_fmt -{ +struct srcobj_fmt { __u8 format; __u8 task; __le16 grpcode; diff --git a/include/net/dst.h b/include/net/dst.h index 6377ab2feba..39c4a5963e1 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -36,8 +36,7 @@ struct sk_buff; -struct dst_entry -{ +struct dst_entry { struct rcu_head rcu_head; struct dst_entry *child; struct net_device *dev; diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index ca4b2e84007..2cd707b15d5 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -7,8 +7,7 @@ #include #include -struct fib_rule -{ +struct fib_rule { struct list_head list; atomic_t refcnt; int ifindex; @@ -25,15 +24,13 @@ struct fib_rule struct net * fr_net; }; -struct fib_lookup_arg -{ +struct fib_lookup_arg { void *lookup_ptr; void *result; struct fib_rule *rule; }; -struct fib_rules_ops -{ +struct fib_rules_ops { int family; struct list_head list; int rule_size; diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index eb87a1447ae..fa157712e98 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -6,8 +6,7 @@ #include #include -struct gnet_dump -{ +struct gnet_dump { spinlock_t * lock; struct sk_buff * skb; struct nlattr * tail; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 2a1c06874c4..eb551baafc0 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -13,8 +13,7 @@ * @list: list entry for linking * @family: pointer to family, need not be set before registering */ -struct genl_multicast_group -{ +struct genl_multicast_group { struct genl_family *family; /* private */ struct list_head list; /* private */ char name[GENL_NAMSIZ]; @@ -35,8 +34,7 @@ struct genl_multicast_group * @family_list: family list * @mcast_groups: multicast groups list */ -struct genl_family -{ +struct genl_family { unsigned int id; unsigned int hdrsize; char name[GENL_NAMSIZ]; @@ -58,8 +56,7 @@ struct genl_family * @userhdr: user specific header * @attrs: netlink attributes */ -struct genl_info -{ +struct genl_info { u32 snd_seq; u32 snd_pid; struct nlmsghdr * nlhdr; @@ -102,8 +99,7 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) * @done: completion callback for dumps * @ops_list: operations list */ -struct genl_ops -{ +struct genl_ops { u8 cmd; unsigned int flags; const struct nla_policy *policy; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 38b78132019..e9d69d19849 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -32,8 +32,7 @@ #ifdef __KERNEL__ -struct inet6_ifaddr -{ +struct inet6_ifaddr { struct in6_addr addr; __u32 prefix_len; @@ -67,8 +66,7 @@ struct inet6_ifaddr int dead; }; -struct ip6_sf_socklist -{ +struct ip6_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct in6_addr sl_addr[0]; @@ -79,8 +77,7 @@ struct ip6_sf_socklist #define IP6_SFBLOCK 10 /* allocate this many at once */ -struct ipv6_mc_socklist -{ +struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; struct ipv6_mc_socklist *next; @@ -89,8 +86,7 @@ struct ipv6_mc_socklist struct ip6_sf_socklist *sflist; }; -struct ip6_sf_list -{ +struct ip6_sf_list { struct ip6_sf_list *sf_next; struct in6_addr sf_addr; unsigned long sf_count[2]; /* include/exclude counts */ @@ -105,8 +101,7 @@ struct ip6_sf_list #define MAF_NOREPORT 0x08 #define MAF_GSQUERY 0x10 -struct ifmcaddr6 -{ +struct ifmcaddr6 { struct in6_addr mca_addr; struct inet6_dev *idev; struct ifmcaddr6 *next; @@ -126,15 +121,13 @@ struct ifmcaddr6 /* Anycast stuff */ -struct ipv6_ac_socklist -{ +struct ipv6_ac_socklist { struct in6_addr acl_addr; int acl_ifindex; struct ipv6_ac_socklist *acl_next; }; -struct ifacaddr6 -{ +struct ifacaddr6 { struct in6_addr aca_addr; struct inet6_dev *aca_idev; struct rt6_info *aca_rt; @@ -157,8 +150,7 @@ struct ipv6_devstat { DEFINE_SNMP_STAT(struct icmpv6msg_mib, icmpv6msg); }; -struct inet6_dev -{ +struct inet6_dev { struct net_device *dev; struct inet6_ifaddr *addr_list; diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 15e1f8fe4c1..35ad7b93046 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -13,8 +13,7 @@ #include #include -struct inet_peer -{ +struct inet_peer { /* group together avl_left,avl_right,v4daddr to speedup lookups */ struct inet_peer *avl_left, *avl_right; __be32 v4daddr; /* peer's address */ diff --git a/include/net/ip.h b/include/net/ip.h index 376adf47764..e6b9d12d5f6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -33,8 +33,7 @@ struct sock; -struct inet_skb_parm -{ +struct inet_skb_parm { struct ip_options opt; /* Compiled IP options */ unsigned char flags; @@ -50,8 +49,7 @@ static inline unsigned int ip_hdrlen(const struct sk_buff *skb) return ip_hdr(skb)->ihl * 4; } -struct ipcm_cookie -{ +struct ipcm_cookie { __be32 addr; int oif; struct ip_options *opt; @@ -60,8 +58,7 @@ struct ipcm_cookie #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) -struct ip_ra_chain -{ +struct ip_ra_chain { struct ip_ra_chain *next; struct sock *sk; void (*destructor)(struct sock *); @@ -159,8 +156,7 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *arg, unsigned int len); -struct ipv4_config -{ +struct ipv4_config { int log_martians; int no_pmtu_disc; }; @@ -336,8 +332,7 @@ extern int ip_call_ra_chain(struct sk_buff *skb); * Functions provided by ip_fragment.c */ -enum ip_defrag_users -{ +enum ip_defrag_users { IP_DEFRAG_LOCAL_DELIVER, IP_DEFRAG_CALL_RA_CHAIN, IP_DEFRAG_CONNTRACK_IN, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 15b492a9aa7..257808188ad 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -30,8 +30,7 @@ struct rt6_info; -struct fib6_config -{ +struct fib6_config { u32 fc_table; u32 fc_metric; int fc_dst_len; @@ -51,8 +50,7 @@ struct fib6_config struct nl_info fc_nlinfo; }; -struct fib6_node -{ +struct fib6_node { struct fib6_node *parent; struct fib6_node *left; struct fib6_node *right; @@ -78,16 +76,14 @@ struct fib6_node * */ -struct rt6key -{ +struct rt6key { struct in6_addr addr; int plen; }; struct fib6_table; -struct rt6_info -{ +struct rt6_info { union { struct dst_entry dst; } u; @@ -127,8 +123,7 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) return ((struct rt6_info *)dst)->rt6i_idev; } -struct fib6_walker_t -{ +struct fib6_walker_t { struct fib6_walker_t *prev, *next; struct fib6_node *root, *node; struct rt6_info *leaf; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 0e1b8aebaff..4a808de7c0f 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -103,8 +103,7 @@ extern void rt6_pmtu_discovery(struct in6_addr *daddr, struct netlink_callback; -struct rt6_rtnl_dump_arg -{ +struct rt6_rtnl_dump_arg { struct sk_buff *skb; struct netlink_callback *cb; struct net *net; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 98978e73f66..8dc3296b7be 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -251,8 +251,7 @@ struct ip_vs_estimator { u32 outbps; }; -struct ip_vs_stats -{ +struct ip_vs_stats { struct ip_vs_stats_user ustats; /* statistics */ struct ip_vs_estimator est; /* estimator */ @@ -518,8 +517,7 @@ struct ip_vs_scheduler { /* * The application module object (a.k.a. app incarnation) */ -struct ip_vs_app -{ +struct ip_vs_app { struct list_head a_list; /* member in app list */ int type; /* IP_VS_APP_TYPE_xxx */ char *name; /* application module name */ diff --git a/include/net/ipip.h b/include/net/ipip.h index b3db2fd6e61..11e8513d2d0 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -8,16 +8,14 @@ #define IPTUNNEL_ERR_TIMEO (30*HZ) /* 6rd prefix/relay information */ -struct ip_tunnel_6rd_parm -{ +struct ip_tunnel_6rd_parm { struct in6_addr prefix; __be32 relay_prefix; u16 prefixlen; u16 relay_prefixlen; }; -struct ip_tunnel -{ +struct ip_tunnel { struct ip_tunnel *next; struct net_device *dev; @@ -40,8 +38,7 @@ struct ip_tunnel unsigned int prl_count; /* # of entries in PRL */ }; -struct ip_tunnel_prl_entry -{ +struct ip_tunnel_prl_entry { struct ip_tunnel_prl_entry *next; __be32 addr; u16 flags; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 8c31d8a0c1f..92db8617d18 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -160,8 +160,7 @@ extern struct ctl_path net_ipv6_ctl_path[]; #define ICMP6MSGIN_INC_STATS_BH(net, idev, field) \ _DEVINC(net, icmpv6msg, _BH, idev, field) -struct ip6_ra_chain -{ +struct ip6_ra_chain { struct ip6_ra_chain *next; struct sock *sk; int sel; @@ -176,8 +175,7 @@ extern rwlock_t ip6_ra_lock; ancillary data and passed to IPv6. */ -struct ipv6_txoptions -{ +struct ipv6_txoptions { /* Length of this structure */ int tot_len; @@ -194,8 +192,7 @@ struct ipv6_txoptions /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; -struct ip6_flowlabel -{ +struct ip6_flowlabel { struct ip6_flowlabel *next; __be32 label; atomic_t users; @@ -212,8 +209,7 @@ struct ip6_flowlabel #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) #define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) -struct ipv6_fl_socklist -{ +struct ipv6_fl_socklist { struct ipv6_fl_socklist *next; struct ip6_flowlabel *fl; }; diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index d5d337170a5..b2b98f3fa26 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -300,8 +300,7 @@ * This struct is also my long term insurance. I can add new fields here * without breaking the prototype of iw_handler... */ -struct iw_request_info -{ +struct iw_request_info { __u16 cmd; /* Wireless Extension command */ __u16 flags; /* More to come ;-) */ }; @@ -321,8 +320,7 @@ typedef int (*iw_handler)(struct net_device *dev, struct iw_request_info *info, * shared by all driver instances... Same for the members... * This will be linked from net_device in */ -struct iw_handler_def -{ +struct iw_handler_def { /* Array of handlers for standard ioctls * We will call dev->wireless_handlers->standard[ioctl - SIOCSIWCOMMIT] @@ -372,8 +370,7 @@ struct iw_handler_def /* * Describe how a standard IOCTL looks like. */ -struct iw_ioctl_description -{ +struct iw_ioctl_description { __u8 header_type; /* NULL, iw_point or other */ __u8 token_type; /* Future */ __u16 token_size; /* Granularity of payload */ @@ -395,8 +392,7 @@ struct iw_ioctl_description /* * Instance specific spy data, i.e. addresses spied and quality for them. */ -struct iw_spy_data -{ +struct iw_spy_data { /* --- Standard spy support --- */ int spy_number; u_char spy_address[IW_MAX_SPY][ETH_ALEN]; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3817fda82a8..db8e96dd114 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -37,8 +37,7 @@ struct neighbour; -struct neigh_parms -{ +struct neigh_parms { #ifdef CONFIG_NET_NS struct net *net; #endif @@ -70,8 +69,7 @@ struct neigh_parms int locktime; }; -struct neigh_statistics -{ +struct neigh_statistics { unsigned long allocs; /* number of allocated neighs */ unsigned long destroys; /* number of destroyed neighs */ unsigned long hash_grows; /* number of hash resizes */ @@ -97,8 +95,7 @@ struct neigh_statistics preempt_enable(); \ } while (0) -struct neighbour -{ +struct neighbour { struct neighbour *next; struct neigh_table *tbl; struct neigh_parms *parms; @@ -122,8 +119,7 @@ struct neighbour u8 primary_key[0]; }; -struct neigh_ops -{ +struct neigh_ops { int family; void (*solicit)(struct neighbour *, struct sk_buff*); void (*error_report)(struct neighbour *, struct sk_buff*); @@ -133,8 +129,7 @@ struct neigh_ops int (*queue_xmit)(struct sk_buff*); }; -struct pneigh_entry -{ +struct pneigh_entry { struct pneigh_entry *next; #ifdef CONFIG_NET_NS struct net *net; @@ -149,8 +144,7 @@ struct pneigh_entry */ -struct neigh_table -{ +struct neigh_table { struct neigh_table *next; int family; int entry_size; diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 4f20d58e2ab..475facc3051 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -13,8 +13,7 @@ #include /* Connection tracking event types */ -enum ip_conntrack_events -{ +enum ip_conntrack_events { IPCT_NEW = 0, /* new conntrack */ IPCT_RELATED = 1, /* related conntrack */ IPCT_DESTROY = 2, /* destroyed conntrack */ diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index a9652806d0d..9a2b9cb5227 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -9,8 +9,7 @@ extern unsigned int nf_ct_expect_hsize; extern unsigned int nf_ct_expect_max; -struct nf_conntrack_expect -{ +struct nf_conntrack_expect { /* Conntrack expectation list member */ struct hlist_node lnode; @@ -64,8 +63,7 @@ static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp) #endif } -struct nf_conntrack_expect_policy -{ +struct nf_conntrack_expect_policy { unsigned int max_expected; unsigned int timeout; }; diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 7f8fc5d123c..e192dc17c58 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -3,8 +3,7 @@ #include -enum nf_ct_ext_id -{ +enum nf_ct_ext_id { NF_CT_EXT_HELPER, NF_CT_EXT_NAT, NF_CT_EXT_ACCT, @@ -65,8 +64,7 @@ __nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); #define NF_CT_EXT_F_PREALLOC 0x0001 -struct nf_ct_ext_type -{ +struct nf_ct_ext_type { /* Destroys relationships (can be NULL). */ void (*destroy)(struct nf_conn *ct); /* Called when realloacted (can be NULL). diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 1b706800092..d015de92e03 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -16,8 +16,7 @@ struct module; #define NF_CT_HELPER_NAME_LEN 16 -struct nf_conntrack_helper -{ +struct nf_conntrack_helper { struct hlist_node hnode; /* Internal use. */ const char *name; /* name of the module */ diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index 9f99d36d5de..a7547611e8f 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -16,8 +16,7 @@ #include #include -struct nf_conntrack_l3proto -{ +struct nf_conntrack_l3proto { /* L3 Protocol Family number. ex) PF_INET */ u_int16_t l3proto; diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 3767fb41e54..ca6dcf3445a 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -15,8 +15,7 @@ struct seq_file; -struct nf_conntrack_l4proto -{ +struct nf_conntrack_l4proto { /* L3 Protocol number. */ u_int16_t l3proto; diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index 2628c154d40..4ee44c84a30 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -26,8 +26,7 @@ /* The protocol-specific manipulable parts of the tuple: always in network order! */ -union nf_conntrack_man_proto -{ +union nf_conntrack_man_proto { /* Add other protocols here. */ __be16 all; @@ -52,8 +51,7 @@ union nf_conntrack_man_proto }; /* The manipulable part of the tuple. */ -struct nf_conntrack_man -{ +struct nf_conntrack_man { union nf_inet_addr u3; union nf_conntrack_man_proto u; /* Layer 3 protocol */ @@ -61,8 +59,7 @@ struct nf_conntrack_man }; /* This contains the information to distinguish a connection. */ -struct nf_conntrack_tuple -{ +struct nf_conntrack_tuple { struct nf_conntrack_man src; /* These are the parts of the tuple which are fixed. */ @@ -100,8 +97,7 @@ struct nf_conntrack_tuple } dst; }; -struct nf_conntrack_tuple_mask -{ +struct nf_conntrack_tuple_mask { struct { union nf_inet_addr u3; union nf_conntrack_man_proto u; diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index 8df0b7f7fc6..f5f09f032a9 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -5,8 +5,7 @@ #define NF_NAT_MAPPING_TYPE_MAX_NAMELEN 16 -enum nf_nat_manip_type -{ +enum nf_nat_manip_type { IP_NAT_MANIP_SRC, IP_NAT_MANIP_DST }; @@ -30,8 +29,7 @@ struct nf_nat_seq { }; /* Single range specification. */ -struct nf_nat_range -{ +struct nf_nat_range { /* Set to OR of flags above. */ unsigned int flags; @@ -43,8 +41,7 @@ struct nf_nat_range }; /* For backwards compat: don't use in modern code. */ -struct nf_nat_multi_range_compat -{ +struct nf_nat_multi_range_compat { unsigned int rangesize; /* Must be 1. */ /* hangs off end. */ @@ -57,8 +54,7 @@ struct nf_nat_multi_range_compat #include /* per conntrack: nat application helper private data */ -union nf_conntrack_nat_help -{ +union nf_conntrack_nat_help { /* insert nat helper private data here */ struct nf_nat_pptp nat_pptp_info; }; @@ -66,8 +62,7 @@ union nf_conntrack_nat_help struct nf_conn; /* The structure embedded in the conntrack structure. */ -struct nf_conn_nat -{ +struct nf_conn_nat { struct hlist_node bysource; struct nf_nat_seq seq[IP_CT_DIR_MAX]; struct nf_conn *ct; diff --git a/include/net/netfilter/nf_nat_protocol.h b/include/net/netfilter/nf_nat_protocol.h index f3662c4394e..c398017ccfa 100644 --- a/include/net/netfilter/nf_nat_protocol.h +++ b/include/net/netfilter/nf_nat_protocol.h @@ -6,8 +6,7 @@ struct nf_nat_range; -struct nf_nat_protocol -{ +struct nf_nat_protocol { /* Protocol number. */ unsigned int protonum; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index d1ca3144464..3dd210d073c 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -7,8 +7,7 @@ /* Basic packet classifier frontend definitions. */ -struct tcf_walker -{ +struct tcf_walker { int stop; int skip; int count; @@ -61,8 +60,7 @@ tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r) tp->q->ops->cl_ops->unbind_tcf(tp->q, cl); } -struct tcf_exts -{ +struct tcf_exts { #ifdef CONFIG_NET_CLS_ACT struct tc_action *action; #endif @@ -71,8 +69,7 @@ struct tcf_exts /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. */ -struct tcf_ext_map -{ +struct tcf_ext_map { int action; int police; }; @@ -143,8 +140,7 @@ extern int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts, /** * struct tcf_pkt_info - packet information */ -struct tcf_pkt_info -{ +struct tcf_pkt_info { unsigned char * ptr; int nexthdr; }; @@ -162,8 +158,7 @@ struct tcf_ematch_ops; * @datalen: length of the ematch specific configuration data * @data: ematch specific data */ -struct tcf_ematch -{ +struct tcf_ematch { struct tcf_ematch_ops * ops; unsigned long data; unsigned int datalen; @@ -211,8 +206,7 @@ static inline int tcf_em_early_end(struct tcf_ematch *em, int result) * @hdr: ematch tree header supplied by userspace * @matches: array of ematches */ -struct tcf_ematch_tree -{ +struct tcf_ematch_tree { struct tcf_ematch_tree_hdr hdr; struct tcf_ematch * matches; @@ -230,8 +224,7 @@ struct tcf_ematch_tree * @owner: owner, must be set to THIS_MODULE * @link: link to previous/next ematch module (internal use) */ -struct tcf_ematch_ops -{ +struct tcf_ematch_ops { int kind; int datalen; int (*change)(struct tcf_proto *, void *, @@ -302,8 +295,7 @@ static inline int tcf_em_tree_match(struct sk_buff *skb, #else /* CONFIG_NET_EMATCH */ -struct tcf_ematch_tree -{ +struct tcf_ematch_tree { }; #define tcf_em_tree_validate(tp, tb, t) ((void)(t), 0) diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f911ec7598e..2d567265363 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -5,8 +5,7 @@ #include #include -struct qdisc_walker -{ +struct qdisc_walker { int stop; int skip; int count; diff --git a/include/net/protocol.h b/include/net/protocol.h index 60249e51b66..89932d45da5 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -47,8 +47,7 @@ struct net_protocol { }; #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) -struct inet6_protocol -{ +struct inet6_protocol { int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, diff --git a/include/net/red.h b/include/net/red.h index 3cf31d466a8..995108e54d9 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -90,8 +90,7 @@ #define RED_STAB_SIZE 256 #define RED_STAB_MASK (RED_STAB_SIZE - 1) -struct red_stats -{ +struct red_stats { u32 prob_drop; /* Early probability drops */ u32 prob_mark; /* Early probability marks */ u32 forced_drop; /* Forced drops, qavg > max_thresh */ @@ -101,8 +100,7 @@ struct red_stats u32 backlog; }; -struct red_parms -{ +struct red_parms { /* Parameters */ u32 qth_min; /* Min avg length threshold: A scaled */ u32 qth_max; /* Max avg length threshold: A scaled */ diff --git a/include/net/route.h b/include/net/route.h index 40f6346ef49..cfb4c071a13 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -49,10 +49,8 @@ struct fib_nh; struct inet_peer; -struct rtable -{ - union - { +struct rtable { + union { struct dst_entry dst; } u; @@ -77,16 +75,14 @@ struct rtable struct inet_peer *peer; /* long-living peer info */ }; -struct ip_rt_acct -{ +struct ip_rt_acct { __u32 o_bytes; __u32 o_packets; __u32 i_bytes; __u32 i_packets; }; -struct rt_cache_stat -{ +struct rt_cache_stat { unsigned int in_hit; unsigned int in_slow_tot; unsigned int in_slow_mc; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c33180dd42b..dad558bc06f 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -15,16 +15,14 @@ struct qdisc_walker; struct tcf_walker; struct module; -struct qdisc_rate_table -{ +struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; struct qdisc_rate_table *next; int refcnt; }; -enum qdisc_state_t -{ +enum qdisc_state_t { __QDISC_STATE_RUNNING, __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, @@ -37,8 +35,7 @@ struct qdisc_size_table { u16 data[]; }; -struct Qdisc -{ +struct Qdisc { int (*enqueue)(struct sk_buff *skb, struct Qdisc *dev); struct sk_buff * (*dequeue)(struct Qdisc *dev); unsigned flags; @@ -78,8 +75,7 @@ struct Qdisc struct gnet_stats_queue qstats; }; -struct Qdisc_class_ops -{ +struct Qdisc_class_ops { /* Child qdisc manipulation */ struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *); int (*graft)(struct Qdisc *, unsigned long cl, @@ -108,8 +104,7 @@ struct Qdisc_class_ops struct gnet_dump *); }; -struct Qdisc_ops -{ +struct Qdisc_ops { struct Qdisc_ops *next; const struct Qdisc_class_ops *cl_ops; char id[IFNAMSIZ]; @@ -133,14 +128,12 @@ struct Qdisc_ops }; -struct tcf_result -{ +struct tcf_result { unsigned long class; u32 classid; }; -struct tcf_proto_ops -{ +struct tcf_proto_ops { struct tcf_proto_ops *next; char kind[IFNAMSIZ]; @@ -164,8 +157,7 @@ struct tcf_proto_ops struct module *owner; }; -struct tcf_proto -{ +struct tcf_proto { /* Fast access part */ struct tcf_proto *next; void *root; @@ -261,14 +253,12 @@ extern struct Qdisc_ops noop_qdisc_ops; extern struct Qdisc_ops pfifo_fast_ops; extern struct Qdisc_ops mq_qdisc_ops; -struct Qdisc_class_common -{ +struct Qdisc_class_common { u32 classid; struct hlist_node hnode; }; -struct Qdisc_class_hash -{ +struct Qdisc_class_hash { struct hlist_head *hash; unsigned int hashsize; unsigned int hashmask; diff --git a/include/net/scm.h b/include/net/scm.h index cf48c800e92..8360e47aa7e 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -12,15 +12,13 @@ */ #define SCM_MAX_FD 255 -struct scm_fp_list -{ +struct scm_fp_list { struct list_head list; int count; struct file *fp[SCM_MAX_FD]; }; -struct scm_cookie -{ +struct scm_cookie { struct ucred creds; /* Skb credentials */ struct scm_fp_list *fp; /* Passed files */ #ifdef CONFIG_SECURITY_NETWORK @@ -88,8 +86,7 @@ static inline void scm_passec(struct socket *sock, struct msghdr *msg, struct sc static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm, int flags) { - if (!msg->msg_control) - { + if (!msg->msg_control) { if (test_bit(SOCK_PASSCRED, &sock->flags) || scm->fp) msg->msg_flags |= MSG_CTRUNC; scm_destroy(scm); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 8a6d5297de1..78740ec57d5 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -227,8 +227,7 @@ DECLARE_SNMP_STAT(struct sctp_mib, sctp_statistics); #endif /* !TEST_FRAME */ /* sctp mib definitions */ -enum -{ +enum { SCTP_MIB_NUM = 0, SCTP_MIB_CURRESTAB, /* CurrEstab */ SCTP_MIB_ACTIVEESTABS, /* ActiveEstabs */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 740d09be8e2..bf20f88fd03 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -359,8 +359,7 @@ TCP_ECN_create_request(struct request_sock *req, struct tcphdr *th) inet_rsk(req)->ecn_ok = 1; } -enum tcp_tw_status -{ +enum tcp_tw_status { TCP_TW_SUCCESS = 0, TCP_TW_RST = 1, TCP_TW_ACK = 2, diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d9c6dbb9271..7f38ef50995 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -121,8 +121,7 @@ struct xfrm_state_walk { }; /* Full description of state of transformer. */ -struct xfrm_state -{ +struct xfrm_state { #ifdef CONFIG_NET_NS struct net *xs_net; #endif @@ -237,8 +236,7 @@ enum { }; /* callback structure passed from either netlink or pfkey */ -struct km_event -{ +struct km_event { union { u32 hard; u32 proto; @@ -313,8 +311,7 @@ extern int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo); extern void xfrm_state_delete_tunnel(struct xfrm_state *x); -struct xfrm_type -{ +struct xfrm_type { char *description; struct module *owner; __u8 proto; @@ -420,8 +417,7 @@ static inline struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipp return x->inner_mode_iaf; } -struct xfrm_tmpl -{ +struct xfrm_tmpl { /* id in template is interpreted as: * daddr - destination of tunnel, may be zero for transport mode. * spi - zero to acquire spi. Not zero if spi is static, then @@ -468,8 +464,7 @@ struct xfrm_policy_walk { u32 seq; }; -struct xfrm_policy -{ +struct xfrm_policy { #ifdef CONFIG_NET_NS struct net *xp_net; #endif @@ -538,8 +533,7 @@ struct xfrm_migrate { /* default seq threshold size */ #define XFRM_AE_SEQT_SIZE 2 -struct xfrm_mgr -{ +struct xfrm_mgr { struct list_head list; char *id; int (*notify)(struct xfrm_state *x, struct km_event *c); @@ -626,8 +620,7 @@ struct xfrm_spi_skb_cb { #define XFRM_SPI_SKB_CB(__skb) ((struct xfrm_spi_skb_cb *)&((__skb)->cb[0])) /* Audit Information */ -struct xfrm_audit -{ +struct xfrm_audit { u32 secid; uid_t loginuid; u32 sessionid; @@ -871,8 +864,7 @@ static inline int xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ct * bundles differing by session id. All the bundles grow from a parent * policy rule. */ -struct xfrm_dst -{ +struct xfrm_dst { union { struct dst_entry dst; struct rtable rt; @@ -907,8 +899,7 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) extern void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); -struct sec_path -{ +struct sec_path { atomic_t refcnt; int len; struct xfrm_state *xvec[XFRM_MAX_DEPTH]; -- cgit v1.2.3 From 5ed176e1c425f9bd1af161d66d348f6116a04fc6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 4 Nov 2009 14:42:28 +0100 Subject: mac80211: make ieee80211_find_sta per virtual interface Since we have a TODO item to make all station management dependent on virtual interfaces, I figured I'd start with pushing such a change to drivers before more drivers start using the ieee80211_find_sta() API with a hw pointer and cause us grief later on. For now continue exporting the old API in form of ieee80211_find_sta_by_hw(), but discourage its use strongly. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e12293e60ac..7f035d779db 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2106,15 +2106,36 @@ void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_hw *hw, const u8 *ra, /** * ieee80211_find_sta - find a station * - * @hw: pointer as obtained from ieee80211_alloc_hw() + * @vif: virtual interface to look for station on * @addr: station's address * * This function must be called under RCU lock and the * resulting pointer is only valid under RCU lock as well. */ -struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_hw *hw, +struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif, const u8 *addr); +/** + * ieee80211_find_sta_by_hw - find a station on hardware + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @addr: station's address + * + * This function must be called under RCU lock and the + * resulting pointer is only valid under RCU lock as well. + * + * NOTE: This function should not be used! When mac80211 is converted + * internally to properly keep track of stations on multiple + * virtual interfaces, it will not always know which station to + * return here since a single address might be used by multiple + * logical stations (e.g. consider a station connecting to another + * BSSID on the same AP hardware without disconnecting first). + * + * DO NOT USE THIS FUNCTION. + */ +struct ieee80211_sta *ieee80211_find_sta_by_hw(struct ieee80211_hw *hw, + const u8 *addr); + /** * ieee80211_beacon_loss - inform hardware does not receive beacons * -- cgit v1.2.3 From 6a2a2d6bf8581216e08be15fcb563cfd6c430e1e Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 4 Nov 2009 23:23:10 -0800 Subject: tcp: Use defaults when no route options are available Trying to parse the option of a SYN packet that we have no route entry for should just use global wide defaults for route entry options. Signed-off-by: Gilad Ben-Yossef Tested-by: Valdis.Kletnieks@vt.edu Signed-off-by: David S. Miller --- include/net/dst.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 39c4a5963e1..387cb3cfde7 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -113,7 +113,7 @@ dst_metric(const struct dst_entry *dst, int metric) static inline u32 dst_feature(const struct dst_entry *dst, u32 feature) { - return dst_metric(dst, RTAX_FEATURES) & feature; + return (dst ? dst_metric(dst, RTAX_FEATURES) & feature : 0); } static inline u32 dst_mtu(const struct dst_entry *dst) -- cgit v1.2.3 From 13f18aa05f5abe135f47b6417537ae2b2fedc18c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 5 Nov 2009 20:44:37 -0800 Subject: net: drop capability from protocol definitions struct can_proto had a capability field which wasn't ever used. It is dropped entirely. struct inet_protosw had a capability field which can be more clearly expressed in the code by just checking if sock->type = SOCK_RAW. Signed-off-by: Eric Paris Acked-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/protocol.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/net') diff --git a/include/net/protocol.h b/include/net/protocol.h index 89932d45da5..f1effdd3c26 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -82,10 +82,6 @@ struct inet_protosw { struct proto *prot; const struct proto_ops *ops; - int capability; /* Which (if any) capability do - * we need to use this socket - * interface? - */ char no_check; /* checksum on rcv/xmit/none? */ unsigned char flags; /* See INET_PROTOSW_* below. */ }; -- cgit v1.2.3 From f9dd09c7f7199685601d75882447a6598be8a3e0 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 6 Nov 2009 00:43:42 -0800 Subject: netfilter: nf_nat: fix NAT issue in 2.6.30.4+ Vitezslav Samel discovered that since 2.6.30.4+ active FTP can not work over NAT. The "cause" of the problem was a fix of unacknowledged data detection with NAT (commit a3a9f79e361e864f0e9d75ebe2a0cb43d17c4272). However, actually, that fix uncovered a long standing bug in TCP conntrack: when NAT was enabled, we simply updated the max of the right edge of the segments we have seen (td_end), by the offset NAT produced with changing IP/port in the data. However, we did not update the other parameter (td_maxend) which is affected by the NAT offset. Thus that could drift away from the correct value and thus resulted breaking active FTP. The patch below fixes the issue by *not* updating the conntrack parameters from NAT, but instead taking into account the NAT offsets in conntrack in a consistent way. (Updating from NAT would be more harder and expensive because it'd need to re-calculate parameters we already calculated in conntrack.) Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/netfilter/nf_conntrack.h | 8 +++----- include/net/netfilter/nf_nat_helper.h | 4 ++++ 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index cbdd6284996..5cf7270e3ff 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -255,11 +255,9 @@ static inline bool nf_ct_kill(struct nf_conn *ct) } /* These are for NAT. Icky. */ -/* Update TCP window tracking data when NAT mangles the packet */ -extern void nf_conntrack_tcp_update(const struct sk_buff *skb, - unsigned int dataoff, - struct nf_conn *ct, int dir, - s16 offset); +extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq); /* Fake conntrack entry for untracked connections */ extern struct nf_conn nf_conntrack_untracked; diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index 237a961f40e..4222220920a 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -32,4 +32,8 @@ extern int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, * to port ct->master->saved_proto. */ extern void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *this); + +extern s16 nf_nat_get_offset(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq); #endif -- cgit v1.2.3 From 69d9ab96f983720b7794e91437bd9c5f83bae9f7 Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Mon, 14 Sep 2009 18:11:03 +0400 Subject: wpan-phy: add a helper to put the wpan_phy device Signed-off-by: Dmitry Eremin-Solenikov --- include/net/wpan-phy.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/net') diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h index 547b1e271ac..5e803a0e4e7 100644 --- a/include/net/wpan-phy.h +++ b/include/net/wpan-phy.h @@ -56,6 +56,12 @@ static inline void *wpan_phy_priv(struct wpan_phy *phy) } struct wpan_phy *wpan_phy_find(const char *str); + +static inline void wpan_phy_put(struct wpan_phy *phy) +{ + put_device(&phy->dev); +} + static inline const char *wpan_phy_name(struct wpan_phy *phy) { return dev_name(&phy->dev); -- cgit v1.2.3 From 1c889f4db6b2f8f8429e62011ba622642faba019 Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Tue, 15 Sep 2009 16:57:04 +0400 Subject: wpan-phy: add wpan-phy iteration functions Add API to iterate over the wpan-phy instances. Signed-off-by: Dmitry Eremin-Solenikov --- include/net/wpan-phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h index 5e803a0e4e7..3367dd95cf8 100644 --- a/include/net/wpan-phy.h +++ b/include/net/wpan-phy.h @@ -48,6 +48,8 @@ struct wpan_phy *wpan_phy_alloc(size_t priv_size); int wpan_phy_register(struct device *parent, struct wpan_phy *phy); void wpan_phy_unregister(struct wpan_phy *phy); void wpan_phy_free(struct wpan_phy *phy); +/* Same semantics as for class_for_each_device */ +int wpan_phy_for_each(int (*fn)(struct wpan_phy *phy, void *data), void *data); static inline void *wpan_phy_priv(struct wpan_phy *phy) { -- cgit v1.2.3 From a0b4a738e0e03f5e0d6ca366560f9a48e5adf83a Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Tue, 22 Sep 2009 15:26:48 +0400 Subject: wpan-phy: allow specifying a per-page channel mask IEEE 802.15.4-2006 defines channel pages that hold channels (max 32 pages, 27 channels per page). Allow the driver to specify supported channels on pages, other than the first one. Signed-off-by: Dmitry Eremin-Solenikov --- include/net/wpan-phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h index 3367dd95cf8..7b7fc581e67 100644 --- a/include/net/wpan-phy.h +++ b/include/net/wpan-phy.h @@ -34,7 +34,7 @@ struct wpan_phy { */ u8 current_channel; u8 current_page; - u32 channels_supported; + u32 channels_supported[32]; u8 transmit_power; u8 cca_mode; -- cgit v1.2.3 From e9cf356c0c6b975fda84b15a5abdd1db88d74f84 Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Mon, 28 Sep 2009 19:01:20 +0400 Subject: wpan-phy: follow usual patter of devices registration Follow the usual pattern of devices registration by adding new function (wpan_phy_set_dev) that sets child->parent relationship and removing parent argument from wpan_phy_register call. Signed-off-by: Dmitry Eremin-Solenikov --- include/net/wpan-phy.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h index 7b7fc581e67..f63537c1736 100644 --- a/include/net/wpan-phy.h +++ b/include/net/wpan-phy.h @@ -45,7 +45,11 @@ struct wpan_phy { }; struct wpan_phy *wpan_phy_alloc(size_t priv_size); -int wpan_phy_register(struct device *parent, struct wpan_phy *phy); +static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev) +{ + phy->dev.parent = dev; +} +int wpan_phy_register(struct wpan_phy *phy); void wpan_phy_unregister(struct wpan_phy *phy); void wpan_phy_free(struct wpan_phy *phy); /* Same semantics as for class_for_each_device */ -- cgit v1.2.3 From a9966b580a3e9d7cf820b5360b574f439d813ef4 Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Fri, 2 Oct 2009 19:05:00 +0400 Subject: ieee802154: constify struct net_device in some operations Some of ieee802154 operations really shouldn't change passed net_device. Constify passed argument. Signed-off-by: Dmitry Eremin-Solenikov --- include/net/ieee802154_netdev.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 5dc6a61952d..d23fb5a94c9 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -98,14 +98,14 @@ struct ieee802154_mlme_ops { * FIXME: these should become the part of PIB/MIB interface. * However we still don't have IB interface of any kind */ - u16 (*get_pan_id)(struct net_device *dev); - u16 (*get_short_addr)(struct net_device *dev); - u8 (*get_dsn)(struct net_device *dev); - u8 (*get_bsn)(struct net_device *dev); + u16 (*get_pan_id)(const struct net_device *dev); + u16 (*get_short_addr)(const struct net_device *dev); + u8 (*get_dsn)(const struct net_device *dev); + u8 (*get_bsn)(const struct net_device *dev); }; static inline struct ieee802154_mlme_ops *ieee802154_mlme_ops( - struct net_device *dev) + const struct net_device *dev) { return dev->ml_priv; } -- cgit v1.2.3 From 42723448b8bacf60c96812196d7725d8d605d0c4 Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Wed, 4 Nov 2009 17:53:23 +0300 Subject: ieee802154: add an mlme_ops call to retrieve PHY object ops->get_phy should increment reference to wpan-phy. As we return the external structure, we should do refcounting correctly. Signed-off-by: Dmitry Eremin-Solenikov --- include/net/ieee802154_netdev.h | 6 ++++++ include/net/wpan-phy.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/net') diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index d23fb5a94c9..57430555487 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -74,8 +74,12 @@ static inline int mac_cb_type(struct sk_buff *skb) #define IEEE802154_MAC_SCAN_PASSIVE 2 #define IEEE802154_MAC_SCAN_ORPHAN 3 +struct wpan_phy; /* * This should be located at net_device->ml_priv + * + * get_phy should increment the reference counting on returned phy. + * Use wpan_wpy_put to put that reference. */ struct ieee802154_mlme_ops { int (*assoc_req)(struct net_device *dev, @@ -94,6 +98,8 @@ struct ieee802154_mlme_ops { int (*scan_req)(struct net_device *dev, u8 type, u32 channels, u8 page, u8 duration); + struct wpan_phy *(*get_phy)(const struct net_device *dev); + /* * FIXME: these should become the part of PIB/MIB interface. * However we still don't have IB interface of any kind diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h index f63537c1736..a65e98509fb 100644 --- a/include/net/wpan-phy.h +++ b/include/net/wpan-phy.h @@ -44,6 +44,8 @@ struct wpan_phy { char priv[0] __attribute__((__aligned__(NETDEV_ALIGN))); }; +#define to_phy(_dev) container_of(_dev, struct wpan_phy, dev) + struct wpan_phy *wpan_phy_alloc(size_t priv_size); static inline void wpan_phy_set_dev(struct wpan_phy *phy, struct device *dev) { -- cgit v1.2.3 From bb1cafb8fc414d6dbe933f888df6540c2ef02101 Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Thu, 5 Nov 2009 16:56:23 +0300 Subject: ieee802154: add support for creation/removal of logic interfaces Add support for two more NL802154 commands: ADD_IFACE and DEL_IFACE, thus allowing creation and removal of logic WPAN interfaces on the top of wpan-phy. Signed-off-by: Dmitry Eremin-Solenikov --- include/net/wpan-phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h index a65e98509fb..85926231c07 100644 --- a/include/net/wpan-phy.h +++ b/include/net/wpan-phy.h @@ -41,6 +41,10 @@ struct wpan_phy { struct device dev; int idx; + struct net_device *(*add_iface)(struct wpan_phy *phy, + const char *name); + void (*del_iface)(struct wpan_phy *phy, struct net_device *dev); + char priv[0] __attribute__((__aligned__(NETDEV_ALIGN))); }; -- cgit v1.2.3 From af81858172cc0f3da81946aab919c26e4b364efc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 6 Nov 2009 11:35:50 +0100 Subject: mac80211: async station powersave handling Some devices require that all frames to a station are flushed when that station goes into powersave mode before being able to send frames to that station again when it wakes up or polls -- all in order to avoid reordering and too many or too few frames being sent to the station when it polls. Normally, this is the case unless the station goes to sleep and wakes up very quickly again. But in that case, frames for it may be pending on the hardware queues, and thus races could happen in the case of multiple hardware queues used for QoS/WMM. Normally this isn't a problem, but with the iwlwifi mechanism we need to make sure the race doesn't happen. This makes mac80211 able to cope with the race with driver help by a new WLAN_STA_PS_DRIVER per-station flag that can be controlled by the driver and tells mac80211 whether it can transmit frames or not. This flag must be set according to very specific rules outlined in the documentation for the function that controls it. When we buffer new frames for the station, we normally set the TIM bit right away, but while the driver has blocked transmission to that sta we need to avoid that as well since we cannot respond to the station if it wakes up due to the TIM bit. Once the driver unblocks, we can set the TIM bit. Similarly, when the station just wakes up, we need to wait until all other frames are flushed before we can transmit frames to that station, so the same applies here, we need to wait for the driver to give the OK. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7f035d779db..2c10eac637d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2136,6 +2136,38 @@ struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif, struct ieee80211_sta *ieee80211_find_sta_by_hw(struct ieee80211_hw *hw, const u8 *addr); +/** + * ieee80211_sta_block_awake - block station from waking up + * @hw: the hardware + * @pubsta: the station + * @block: whether to block or unblock + * + * Some devices require that all frames that are on the queues + * for a specific station that went to sleep are flushed before + * a poll response or frames after the station woke up can be + * delivered to that it. Note that such frames must be rejected + * by the driver as filtered, with the appropriate status flag. + * + * This function allows implementing this mode in a race-free + * manner. + * + * To do this, a driver must keep track of the number of frames + * still enqueued for a specific station. If this number is not + * zero when the station goes to sleep, the driver must call + * this function to force mac80211 to consider the station to + * be asleep regardless of the station's actual state. Once the + * number of outstanding frames reaches zero, the driver must + * call this function again to unblock the station. That will + * cause mac80211 to be able to send ps-poll responses, and if + * the station queried in the meantime then frames will also + * be sent out as a result of this. Additionally, the driver + * will be notified that the station woke up some time after + * it is unblocked, regardless of whether the station actually + * woke up while blocked or not. + */ +void ieee80211_sta_block_awake(struct ieee80211_hw *hw, + struct ieee80211_sta *pubsta, bool block); + /** * ieee80211_beacon_loss - inform hardware does not receive beacons * -- cgit v1.2.3 From 81adee47dfb608df3ad0b91d230fb3cef75f0060 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 8 Nov 2009 00:53:51 -0800 Subject: net: Support specifying the network namespace upon device creation. There is no good reason to not support userspace specifying the network namespace during device creation, and it makes it easier to create a network device and pass it to a child network namespace with a well known name. We have to be careful to ensure that the target network namespace for the new device exists through the life of the call. To keep that logic clear I have factored out the network namespace grabbing logic into rtnl_link_get_net. In addtion we need to continue to pass the source network namespace to the rtnl_link_ops.newlink method so that we can find the base device source network namespace. Signed-off-by: Eric W. Biederman Acked-by: Eric Dumazet --- include/net/rtnetlink.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index cd5af1f508f..48d3efcb088 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -55,7 +55,8 @@ struct rtnl_link_ops { int (*validate)(struct nlattr *tb[], struct nlattr *data[]); - int (*newlink)(struct net_device *dev, + int (*newlink)(struct net *src_net, + struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]); int (*changelink)(struct net_device *dev, @@ -83,8 +84,9 @@ extern void rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops); extern int rtnl_link_register(struct rtnl_link_ops *ops); extern void rtnl_link_unregister(struct rtnl_link_ops *ops); -extern struct net_device *rtnl_create_link(struct net *net, char *ifname, - const struct rtnl_link_ops *ops, struct nlattr *tb[]); +extern struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); +extern struct net_device *rtnl_create_link(struct net *src_net, struct net *net, + char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]); extern const struct nla_policy ifla_policy[IFLA_MAX+1]; #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) -- cgit v1.2.3 From fdcc8aa953a1123a289791dd192090651036d593 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 8 Nov 2009 10:17:05 +0000 Subject: udp: add a counter into udp_hslot Adds a counter in udp_hslot to keep an accurate count of sockets present in chain. This will permit to upcoming UDP lookup algo to chose the shortest chain when secondary hash is added. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/udp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/net') diff --git a/include/net/udp.h b/include/net/udp.h index 22aa2e7eb1d..9167281e47d 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -50,8 +50,16 @@ struct udp_skb_cb { }; #define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb)) +/** + * struct udp_hslot - UDP hash slot + * + * @head: head of list of sockets + * @count: number of sockets in 'head' list + * @lock: spinlock protecting changes to head/count + */ struct udp_hslot { struct hlist_nulls_head head; + int count; spinlock_t lock; } __attribute__((aligned(2 * sizeof(long)))); -- cgit v1.2.3 From d4cada4ae1c012815f95fa507eb86a0ae9d607d7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 8 Nov 2009 10:17:30 +0000 Subject: udp: split sk_hash into two u16 hashes Union sk_hash with two u16 hashes for udp (no extra memory taken) One 16 bits hash on (local port) value (the previous udp 'hash') One 16 bits hash on (local address, local port) values, initialized but not yet used. This second hash is using jenkin hash for better distribution. Because the 'port' is xored later, a partial hash is performed on local address + net_hash_mix(net) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 55de3bd719a..827366b6268 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -109,6 +109,7 @@ struct net; * @skc_refcnt: reference count * @skc_tx_queue_mapping: tx queue number for this connection * @skc_hash: hash value used with various protocol lookup tables + * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting @@ -131,7 +132,10 @@ struct sock_common { atomic_t skc_refcnt; int skc_tx_queue_mapping; - unsigned int skc_hash; + union { + unsigned int skc_hash; + __u16 skc_u16hashes[2]; + }; unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse; -- cgit v1.2.3 From 512615b6b843ff3ff5ad583f34c39b3f302f5f26 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 8 Nov 2009 10:17:58 +0000 Subject: udp: secondary hash on (local port, local address) Extends udp_table to contain a secondary hash table. socket anchor for this second hash is free, because UDP doesnt use skc_bind_node : We define an union to hold both skc_bind_node & a new hlist_nulls_node udp_portaddr_node udp_lib_get_port() inserts sockets into second hash chain (additional cost of one atomic op) udp_lib_unhash() deletes socket from second hash chain (additional cost of one atomic op) Note : No spinlock lockdep annotation is needed, because lock for the secondary hash chain is always get after lock for primary hash chain. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 8 ++++++-- include/net/udp.h | 22 ++++++++++++++++++++-- 2 files changed, 26 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 827366b6268..3f1a4804bb3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -105,7 +105,7 @@ struct net; /** * struct sock_common - minimal network layer representation of sockets * @skc_node: main hash linkage for various protocol lookup tables - * @skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol + * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_refcnt: reference count * @skc_tx_queue_mapping: tx queue number for this connection * @skc_hash: hash value used with various protocol lookup tables @@ -115,6 +115,7 @@ struct net; * @skc_reuse: %SO_REUSEADDR setting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables + * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket * @@ -140,7 +141,10 @@ struct sock_common { volatile unsigned char skc_state; unsigned char skc_reuse; int skc_bound_dev_if; - struct hlist_node skc_bind_node; + union { + struct hlist_node skc_bind_node; + struct hlist_nulls_node skc_portaddr_node; + }; struct proto *skc_prot; #ifdef CONFIG_NET_NS struct net *skc_net; diff --git a/include/net/udp.h b/include/net/udp.h index 9167281e47d..af41850f742 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -63,10 +63,19 @@ struct udp_hslot { spinlock_t lock; } __attribute__((aligned(2 * sizeof(long)))); +/** + * struct udp_table - UDP table + * + * @hash: hash table, sockets are hashed on (local port) + * @hash2: hash table, sockets are hashed on (local port, local address) + * @mask: number of slots in hash tables, minus 1 + * @log: log2(number of slots in hash table) + */ struct udp_table { struct udp_hslot *hash; - unsigned int mask; - unsigned int log; + struct udp_hslot *hash2; + unsigned int mask; + unsigned int log; }; extern struct udp_table udp_table; extern void udp_table_init(struct udp_table *, const char *); @@ -75,6 +84,15 @@ static inline struct udp_hslot *udp_hashslot(struct udp_table *table, { return &table->hash[udp_hashfn(net, num, table->mask)]; } +/* + * For secondary hash, net_hash_mix() is performed before calling + * udp_hashslot2(), this explains difference with udp_hashslot() + */ +static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, + unsigned int hash) +{ + return &table->hash2[hash & table->mask]; +} /* Note: this must match 'valbool' in sock_setsockopt */ #define UDP_CSUM_NOXMIT 1 -- cgit v1.2.3 From 9e0d57fd6dad37d72a3ca6db00ca8c76f2215454 Mon Sep 17 00:00:00 2001 From: Yury Polyanskiy Date: Sun, 8 Nov 2009 20:58:41 -0800 Subject: xfrm: SAD entries do not expire correctly after suspend-resume This fixes the following bug in the current implementation of net/xfrm: SAD entries timeouts do not count the time spent by the machine in the suspended state. This leads to the connectivity problems because after resuming local machine thinks that the SAD entry is still valid, while it has already been expired on the remote server. The cause of this is very simple: the timeouts in the net/xfrm are bound to the old mod_timer() timers. This patch reassigns them to the CLOCK_REALTIME hrtimer. I have been using this version of the patch for a few months on my machines without any problems. Also run a few stress tests w/o any issues. This version of the patch uses tasklet_hrtimer by Peter Zijlstra (commit 9ba5f0). This patch is against 2.6.31.4. Please CC me. Signed-off-by: Yury Polyanskiy Signed-off-by: David S. Miller --- include/net/xfrm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 7f38ef50995..93d184b91a8 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -19,6 +19,9 @@ #include #include #include + +#include + #ifdef CONFIG_XFRM_STATISTICS #include #endif @@ -198,7 +201,7 @@ struct xfrm_state { struct xfrm_stats stats; struct xfrm_lifetime_cur curlft; - struct timer_list timer; + struct tasklet_hrtimer mtimer; /* Last used time */ unsigned long lastused; -- cgit v1.2.3 From 6b0d07ba152893b40f1014a9db8da5aa564aa00e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= Date: Mon, 9 Nov 2009 02:17:01 +0000 Subject: Phonet: put sockets in a hash table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- include/net/phonet/phonet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index fdb05fa0346..7b114079a51 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -46,6 +46,7 @@ static inline struct pn_sock *pn_sk(struct sock *sk) extern const struct proto_ops phonet_dgram_ops; +void pn_sock_init(void); struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *sa); void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb); void phonet_get_local_port_range(int *min, int *max); -- cgit v1.2.3 From 30fff9231fad757c061285e347b33c5149c2c2e4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 Nov 2009 05:26:33 +0000 Subject: udp: bind() optimisation UDP bind() can be O(N^2) in some pathological cases. Thanks to secondary hash tables, we can make it O(N) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/udp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/udp.h b/include/net/udp.h index af41850f742..5348d80b25b 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -158,7 +158,8 @@ static inline void udp_lib_close(struct sock *sk, long timeout) } extern int udp_lib_get_port(struct sock *sk, unsigned short snum, - int (*)(const struct sock*,const struct sock*)); + int (*)(const struct sock *,const struct sock *), + unsigned int hash2_nulladdr); /* net/ipv4/udp.c */ extern int udp_get_port(struct sock *sk, unsigned short snum, -- cgit v1.2.3 From 8b787643ca0a5130c647109d77fe512f89cfa611 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 10 Nov 2009 18:53:10 +0100 Subject: nl80211: add a parameter for using 4-address frames on virtual interfaces Signed-off-by: Felix Fietkau Signed-off-by: John W. Linville --- include/net/cfg80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ff67865de23..1ee41e4a92e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -206,10 +206,12 @@ struct ieee80211_supported_band { * struct vif_params - describes virtual interface parameters * @mesh_id: mesh ID to use * @mesh_id_len: length of the mesh ID + * @use_4addr: use 4-address frames */ struct vif_params { u8 *mesh_id; int mesh_id_len; + int use_4addr; }; /** -- cgit v1.2.3 From f8572d8f2a2ba75408b97dc24ef47c83671795d7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 5 Nov 2009 13:32:03 -0800 Subject: sysctl net: Remove unused binary sysctl code Now that sys_sysctl is a compatiblity wrapper around /proc/sys all sysctl strategy routines, and all ctl_name and strategy entries in the sysctl tables are unused, and can be revmoed. In addition neigh_sysctl_register has been modified to no longer take a strategy argument and it's callers have been modified not to pass one. Cc: "David Miller" Cc: Hideaki YOSHIFUJI Cc: netdev@vger.kernel.org Signed-off-by: Eric W. Biederman --- include/net/dn_dev.h | 1 - include/net/neighbour.h | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h index cee46821dc5..3f781a4cafb 100644 --- a/include/net/dn_dev.h +++ b/include/net/dn_dev.h @@ -75,7 +75,6 @@ struct dn_dev_parms { unsigned long t3; /* Default value of t3 */ int priority; /* Priority to be a router */ char *name; /* Name for sysctl */ - int ctl_name; /* Index for sysctl */ int (*up)(struct net_device *); void (*down)(struct net_device *); void (*timer3)(struct net_device *, struct dn_ifaddr *ifa); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3817fda82a8..da99fdd63cf 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -264,8 +264,7 @@ extern int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, int p_id, int pdev_id, char *p_name, - proc_handler *proc_handler, - ctl_handler *strategy); + proc_handler *proc_handler); extern void neigh_sysctl_unregister(struct neigh_parms *p); static inline void __neigh_parms_put(struct neigh_parms *parms) -- cgit v1.2.3 From d19b3bf6384e66ac6e11a61ee31ed2cfe149f4d8 Mon Sep 17 00:00:00 2001 From: Rui Paulo Date: Mon, 9 Nov 2009 23:46:55 +0000 Subject: mac80211: replace "destination" with "target" to follow the spec Resulting object files have the same MD5 as before. Signed-off-by: Rui Paulo Signed-off-by: Javier Cardona Reviewed-by: Andrey Yurovsky Tested-by: Brian Cavagnolo Signed-off-by: John W. Linville --- include/net/cfg80211.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1ee41e4a92e..7d0ae9c1828 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -420,7 +420,7 @@ enum monitor_flags { * in during get_station() or dump_station(). * * MPATH_INFO_FRAME_QLEN: @frame_qlen filled - * MPATH_INFO_DSN: @dsn filled + * MPATH_INFO_SN: @sn filled * MPATH_INFO_METRIC: @metric filled * MPATH_INFO_EXPTIME: @exptime filled * MPATH_INFO_DISCOVERY_TIMEOUT: @discovery_timeout filled @@ -429,7 +429,7 @@ enum monitor_flags { */ enum mpath_info_flags { MPATH_INFO_FRAME_QLEN = BIT(0), - MPATH_INFO_DSN = BIT(1), + MPATH_INFO_SN = BIT(1), MPATH_INFO_METRIC = BIT(2), MPATH_INFO_EXPTIME = BIT(3), MPATH_INFO_DISCOVERY_TIMEOUT = BIT(4), @@ -444,7 +444,7 @@ enum mpath_info_flags { * * @filled: bitfield of flags from &enum mpath_info_flags * @frame_qlen: number of queued frames for this destination - * @dsn: destination sequence number + * @sn: target sequence number * @metric: metric (cost) of this mesh path * @exptime: expiration time for the mesh path from now, in msecs * @flags: mesh path flags @@ -458,7 +458,7 @@ enum mpath_info_flags { struct mpath_info { u32 filled; u32 frame_qlen; - u32 dsn; + u32 sn; u32 metric; u32 exptime; u32 discovery_timeout; -- cgit v1.2.3 From 63c5723bc3af8d4e86984dd4ff0c78218de418d0 Mon Sep 17 00:00:00 2001 From: Rui Paulo Date: Mon, 9 Nov 2009 23:46:57 +0000 Subject: mac80211: add nl80211/cfg80211 handling of the new mesh root mode option. Signed-off-by: Rui Paulo Signed-off-by: Javier Cardona Reviewed-by: Andrey Yurovsky Tested-by: Brian Cavagnolo Signed-off-by: John W. Linville --- include/net/cfg80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7d0ae9c1828..0e4c51fc63e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -508,6 +508,7 @@ struct mesh_config { u32 dot11MeshHWMPactivePathTimeout; u16 dot11MeshHWMPpreqMinInterval; u16 dot11MeshHWMPnetDiameterTraversalTime; + u8 dot11MeshHWMPRootMode; }; /** -- cgit v1.2.3 From 61fa713c751683da915fa0c1aa502be85822c357 Mon Sep 17 00:00:00 2001 From: Holger Schurig Date: Wed, 11 Nov 2009 12:25:40 +0100 Subject: cfg80211: return channel noise via survey API This patch implements the NL80211_CMD_GET_SURVEY command and an get_survey() ops that a driver can implement. The goal of this command is to allow a drivers to report channel survey data (e.g. channel noise, channel occupation). For now, only the mechanism to report back channel noise has been implemented. In future, there will either be a survey-trigger command --- or the existing scan-trigger command will be enhanced. This will allow user-space to request survey for arbitrary channels. Note: any driver that cannot report channel noise should not report any value at all, e.g. made-up -92 dBm. Signed-off-by: Holger Schurig Signed-off-by: John W. Linville --- include/net/cfg80211.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0e4c51fc63e..21710fc17ea 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -234,6 +234,35 @@ struct key_params { u32 cipher; }; +/** + * enum survey_info_flags - survey information flags + * + * Used by the driver to indicate which info in &struct survey_info + * it has filled in during the get_survey(). + */ +enum survey_info_flags { + SURVEY_INFO_NOISE_DBM = 1<<0, +}; + +/** + * 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 + * + * This structure can later be expanded with things like + * channel duty cycle etc. + */ +struct survey_info { + struct ieee80211_channel *channel; + u32 filled; + s8 noise; +}; + /** * struct beacon_parameters - beacon parameters * @@ -944,6 +973,8 @@ struct cfg80211_bitrate_mask { * @rfkill_poll: polls the hw rfkill line, use cfg80211 reporting * functions to adjust rfkill hw state * + * @dump_survey: get site survey information. + * * @testmode_cmd: run a test mode command */ struct cfg80211_ops { @@ -1063,6 +1094,9 @@ struct cfg80211_ops { const u8 *peer, const struct cfg80211_bitrate_mask *mask); + int (*dump_survey)(struct wiphy *wiphy, struct net_device *netdev, + int idx, struct survey_info *info); + /* some temporary stuff to finish wext */ int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); -- cgit v1.2.3 From 409b95aff3583c05ac7a9247fa3d8c9aa7f9cae3 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Tue, 10 Nov 2009 08:57:34 +0000 Subject: sctp: Set source addresses on the association before adding transports Recent commit 8da645e101a8c20c6073efda3c7cc74eec01b87f sctp: Get rid of an extra routing lookup when adding a transport introduced a regression in the connection setup. The behavior was different between IPv4 and IPv6. IPv4 case ended up working because the route lookup routing returned a NULL route, which triggered another route lookup later in the output patch that succeeded. In the IPv6 case, a valid route was returned for first call, but we could not find a valid source address at the time since the source addresses were not set on the association yet. Thus resulted in a hung connection. The solution is to set the source addresses on the association prior to adding peers. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 6e5f0e0c796..cd2e18778f8 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1980,7 +1980,7 @@ void sctp_assoc_set_primary(struct sctp_association *, void sctp_assoc_del_nonprimary_peers(struct sctp_association *, struct sctp_transport *); int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *, - gfp_t); + sctp_scope_t, gfp_t); int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *, struct sctp_cookie*, gfp_t gfp); -- cgit v1.2.3 From bee7ca9ec03a26676ea2b1c28dc4039348eff3e1 Mon Sep 17 00:00:00 2001 From: William Allen Simpson Date: Tue, 10 Nov 2009 09:51:18 +0000 Subject: net: TCP_MSS_DEFAULT, TCP_MSS_DESIRED Define two symbols needed in both kernel and user space. Remove old (somewhat incorrect) kernel variant that wasn't used in most cases. Default should apply to both RMSS and SMSS (RFC2581). Replace numeric constants with defined symbols. Stand-alone patch, originally developed for TCPCT. Signed-off-by: William.Allen.Simpson@gmail.com Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index bf20f88fd03..325bfcf5c93 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -62,9 +62,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS 88U -/* Minimal RCV_MSS. */ -#define TCP_MIN_RCVMSS 536U - /* The least MTU to use for probing */ #define TCP_BASE_MSS 512 -- cgit v1.2.3 From 5256f2ef3a40d784b8369035bff3f4dc637a9801 Mon Sep 17 00:00:00 2001 From: Lucian Adrian Grijincu Date: Thu, 12 Nov 2009 05:07:26 +0000 Subject: inet: fix inet_bind_bucket_for_each The first "node" is supposed to be the cursor used in the for_each. The second "node" is ment literally and should not be macro expanded: it's the name of the hlist_node field from the inet_bind_bucket. This currently works because when inet_bind_bucket_for_each is called it's argument is still "node". Signed-off-by: Lucian Adrian Grijincu Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 5b698b3b463..41cbddd25b7 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -92,8 +92,8 @@ static inline struct net *ib_net(struct inet_bind_bucket *ib) return read_pnet(&ib->ib_net); } -#define inet_bind_bucket_for_each(tb, node, head) \ - hlist_for_each_entry(tb, node, head, node) +#define inet_bind_bucket_for_each(tb, pos, head) \ + hlist_for_each_entry(tb, pos, head, node) struct inet_bind_hashbucket { spinlock_t lock; -- cgit v1.2.3 From 2c1409a0a2b88585ec0c03f1de0aafa178c56313 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Nov 2009 09:33:09 +0000 Subject: inetpeer: Optimize inet_getid() While investigating for network latencies, I found inet_getid() was a contention point for some workloads, as inet_peer_idlock is shared by all inet_getid() users regardless of peers. One way to fix this is to make ip_id_count an atomic_t instead of __u16, and use atomic_add_return(). In order to keep sizeof(struct inet_peer) = 64 on 64bit arches tcp_ts_stamp is also converted to __u32 instead of "unsigned long". Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inetpeer.h | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 35ad7b93046..87b1df0d4d8 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -17,15 +17,15 @@ struct inet_peer { /* group together avl_left,avl_right,v4daddr to speedup lookups */ struct inet_peer *avl_left, *avl_right; __be32 v4daddr; /* peer's address */ - __u16 avl_height; - __u16 ip_id_count; /* IP ID for the next packet */ + __u32 avl_height; struct list_head unused; __u32 dtime; /* the time of last use of not * referenced entries */ atomic_t refcnt; atomic_t rid; /* Frag reception counter */ + atomic_t ip_id_count; /* IP ID for the next packet */ __u32 tcp_ts; - unsigned long tcp_ts_stamp; + __u32 tcp_ts_stamp; }; void inet_initpeers(void) __init; @@ -36,17 +36,11 @@ struct inet_peer *inet_getpeer(__be32 daddr, int create); /* can be called from BH context or outside */ extern void inet_putpeer(struct inet_peer *p); -extern spinlock_t inet_peer_idlock; /* can be called with or without local BH being disabled */ static inline __u16 inet_getid(struct inet_peer *p, int more) { - __u16 id; - - spin_lock_bh(&inet_peer_idlock); - id = p->ip_id_count; - p->ip_id_count += 1 + more; - spin_unlock_bh(&inet_peer_idlock); - return id; + more++; + return atomic_add_return(more, &p->ip_id_count) - more; } #endif /* _NET_INETPEER_H */ -- cgit v1.2.3 From eeb74a9d45f781ec6f47b9e0a75a6a427b53f165 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= Date: Wed, 18 Nov 2009 10:08:26 -0800 Subject: Phonet: convert devices list to RCU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- include/net/phonet/pn_dev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h index afa7defceb1..d7b989ca3d6 100644 --- a/include/net/phonet/pn_dev.h +++ b/include/net/phonet/pn_dev.h @@ -25,7 +25,7 @@ struct phonet_device_list { struct list_head list; - spinlock_t lock; + struct mutex lock; }; struct phonet_device_list *phonet_device_list(struct net *net); -- cgit v1.2.3 From 599bf6a4d64d8399e99514e0e1ef02e97e43238f Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Sun, 15 Nov 2009 23:07:30 +0100 Subject: mac80211: add the total ampdu length to tx info Signed-off-by: Felix Fietkau Signed-off-by: John W. Linville --- include/net/mac80211.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2c10eac637d..3b3defbe6fc 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -390,10 +390,12 @@ struct ieee80211_tx_rate { * @control: union for control data * @status: union for status data * @driver_data: array of driver_data pointers - * @ampdu_ack_len: number of aggregated frames. + * @ampdu_ack_len: number of acked aggregated frames. * relevant only if IEEE80211_TX_STATUS_AMPDU was set. * @ampdu_ack_map: block ack bit map for the aggregation. * relevant only if IEEE80211_TX_STATUS_AMPDU was set. + * @ampdu_len: number of aggregated frames. + * relevant only if IEEE80211_TX_STATUS_AMPDU was set. * @ack_signal: signal strength of the ACK frame */ struct ieee80211_tx_info { @@ -428,7 +430,8 @@ struct ieee80211_tx_info { u8 ampdu_ack_len; u64 ampdu_ack_map; int ack_signal; - /* 8 bytes free */ + u8 ampdu_len; + /* 7 bytes free */ } status; struct { struct ieee80211_tx_rate driver_rates[ -- cgit v1.2.3 From c951ad3550ab40071bb0f222ba6125845769c08a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 16 Nov 2009 12:00:38 +0100 Subject: mac80211: convert aggregation to operate on vifs/stas The entire aggregation code currently operates on the hw pointer and station addresses, but that needs to change to make stations purely per-vif; As one step preparing for that make the aggregation code callable with the station, or by the combination of virtual interface and station address. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 3b3defbe6fc..4af0ffb98aa 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1508,6 +1508,7 @@ struct ieee80211_ops { void (*reset_tsf)(struct ieee80211_hw *hw); int (*tx_last_beacon)(struct ieee80211_hw *hw); int (*ampdu_action)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn); @@ -2029,8 +2030,7 @@ void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, /** * ieee80211_start_tx_ba_session - Start a tx Block Ack session. - * @hw: pointer as obtained from ieee80211_alloc_hw(). - * @ra: receiver address of the BA session recipient + * @sta: the station for which to start a BA session * @tid: the TID to BA on. * * Return: success if addBA request was sent, failure otherwise @@ -2039,22 +2039,22 @@ void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, * the need to start aggregation on a certain RA/TID, the session level * will be managed by the mac80211. */ -int ieee80211_start_tx_ba_session(struct ieee80211_hw *hw, u8 *ra, u16 tid); +int ieee80211_start_tx_ba_session(struct ieee80211_sta *sta, u16 tid); /** * ieee80211_start_tx_ba_cb - low level driver ready to aggregate. - * @hw: pointer as obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf * @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_hw *hw, u8 *ra, u16 tid); +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. - * @hw: pointer as obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf * @ra: receiver address of the BA session recipient. * @tid: the TID to BA on. * @@ -2062,13 +2062,12 @@ void ieee80211_start_tx_ba_cb(struct ieee80211_hw *hw, u8 *ra, u16 tid); * finished with preparations for the BA session. * This version of the function is IRQ-safe. */ -void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_hw *hw, const u8 *ra, +void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid); /** * ieee80211_stop_tx_ba_session - Stop a Block Ack session. - * @hw: pointer as obtained from ieee80211_alloc_hw(). - * @ra: receiver address of the BA session recipient + * @sta: the station whose BA session to stop * @tid: the TID to stop BA. * @initiator: if indicates initiator DELBA frame will be sent. * @@ -2078,24 +2077,23 @@ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_hw *hw, const u8 *ra, * 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_hw *hw, - u8 *ra, u16 tid, +int ieee80211_stop_tx_ba_session(struct ieee80211_sta *sta, u16 tid, enum ieee80211_back_parties initiator); /** * ieee80211_stop_tx_ba_cb - low level driver ready to stop aggregate. - * @hw: pointer as obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf * @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_hw *hw, u8 *ra, u8 tid); +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. - * @hw: pointer as obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from &struct ieee80211_if_init_conf * @ra: receiver address of the BA session recipient. * @tid: the desired TID to BA on. * @@ -2103,7 +2101,7 @@ void ieee80211_stop_tx_ba_cb(struct ieee80211_hw *hw, u8 *ra, u8 tid); * finished with preparations for the BA session tear down. * This version of the function is IRQ-safe. */ -void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_hw *hw, const u8 *ra, +void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid); /** -- cgit v1.2.3 From af65cd96dd4ea8ea5adc6ee850e61a407cd1067a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 17 Nov 2009 18:18:36 +0100 Subject: mac80211: make software rate control optional Some devices implement the entire rate control in firmware in some way, like wl1271 or like iwlwifi which does some things in software but not a lot. Therefore generic software rate control is rather useless for them and just adds avoidable overhead to the transmit path. It's fairly simple to let drivers indicate that they do not need rate control, but they need to fulfil a number of conditions that we encode in WARN_ONs. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 4af0ffb98aa..f34f4ca7016 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -855,6 +855,19 @@ enum ieee80211_tkip_key_type { * any particular flags. There are some exceptions to this rule, * however, so you are advised to review these flags carefully. * + * @IEEE80211_HW_HAS_RATE_CONTROL: + * The hardware or firmware includes rate control, and cannot be + * controlled by the stack. As such, no rate control algorithm + * should be instantiated, and the TX rate reported to userspace + * will be taken from the TX status instead of the rate control + * algorithm. + * Note that this requires that the driver implement a number of + * callbacks so it has the correct information, it needs to have + * the @set_rts_threshold callback and must look at the BSS config + * @use_cts_prot for G/N protection, @use_short_slot for slot + * timing in 2.4 GHz and @use_short_preamble for preambles for + * CCK frames. + * * @IEEE80211_HW_RX_INCLUDES_FCS: * Indicates that received frames passed to the stack include * the FCS at the end. @@ -913,6 +926,7 @@ enum ieee80211_tkip_key_type { * avoid waking up cpu. */ enum ieee80211_hw_flags { + IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, IEEE80211_HW_RX_INCLUDES_FCS = 1<<1, IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING = 1<<2, IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE = 1<<3, -- cgit v1.2.3 From 5be83de54c16944dea9c16c6a5a53c1fa75ed304 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 19 Nov 2009 00:56:28 +0100 Subject: cfg80211: convert bools into flags We've accumulated a number of options for wiphys which make more sense as flags as we keep adding more. Convert the existing ones. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 62 ++++++++++++++++++++++++++++---------------------- 1 file changed, 35 insertions(+), 27 deletions(-) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 21710fc17ea..eca36abca8f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1108,27 +1108,45 @@ struct cfg80211_ops { */ /** - * struct wiphy - wireless hardware description - * @idx: the wiphy index assigned to this item - * @class_dev: the class device representing /sys/class/ieee80211/ - * @custom_regulatory: tells us the driver for this device + * enum wiphy_flags - wiphy capability flags + * + * @WIPHY_FLAG_CUSTOM_REGULATORY: tells us the driver for this device * has its own custom regulatory domain and cannot identify the * ISO / IEC 3166 alpha2 it belongs to. When this is enabled * we will disregard the first regulatory hint (when the * initiator is %REGDOM_SET_BY_CORE). - * @strict_regulatory: tells us the driver for this device will ignore - * regulatory domain settings until it gets its own regulatory domain - * via its regulatory_hint(). After its gets its own regulatory domain - * it will only allow further regulatory domain settings to further - * enhance compliance. For example if channel 13 and 14 are disabled - * by this regulatory domain no user regulatory domain can enable these - * channels at a later time. This can be used for devices which do not - * have calibration information gauranteed for frequencies or settings - * outside of its regulatory domain. - * @disable_beacon_hints: enable this if your driver needs to ensure that - * passive scan flags and beaconing flags may not be lifted by cfg80211 - * due to regulatory beacon hints. For more information on beacon + * @WIPHY_FLAG_STRICT_REGULATORY: tells us the driver for this device will + * ignore regulatory domain settings until it gets its own regulatory + * domain via its regulatory_hint(). After its gets its own regulatory + * domain it will only allow further regulatory domain settings to + * further enhance compliance. For example if channel 13 and 14 are + * disabled by this regulatory domain no user regulatory domain can + * enable these channels at a later time. This can be used for devices + * which do not have calibration information gauranteed for frequencies + * or settings outside of its regulatory domain. + * @WIPHY_FLAG_DISABLE_BEACON_HINTS: enable this if your driver needs to ensure + * that passive scan flags and beaconing flags may not be lifted by + * cfg80211 due to regulatory beacon hints. For more information on beacon * hints read the documenation for regulatory_hint_found_beacon() + * @WIPHY_FLAG_NETNS_OK: if not set, do not allow changing the netns of this + * wiphy at all + * @WIPHY_FLAG_PS_ON_BY_DEFAULT: if set to true, powersave will be enabled + * by default -- this flag will be set depending on the kernel's default + * on wiphy_new(), but can be changed by the driver if it has a good + * reason to override the default + */ +enum wiphy_flags { + WIPHY_FLAG_CUSTOM_REGULATORY = BIT(0), + WIPHY_FLAG_STRICT_REGULATORY = BIT(1), + WIPHY_FLAG_DISABLE_BEACON_HINTS = BIT(2), + WIPHY_FLAG_NETNS_OK = BIT(3), + WIPHY_FLAG_PS_ON_BY_DEFAULT = BIT(4), +}; + +/** + * 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 @@ -1143,11 +1161,6 @@ struct cfg80211_ops { * -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 - * @netnsok: if set to false, do not allow changing the netns of this - * wiphy at all - * @ps_default: default for powersave, will be set depending on the - * kernel's default on wiphy_new(), but can be changed by the - * driver if it has a good reason to override the default */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -1158,12 +1171,7 @@ struct wiphy { /* Supported interface modes, OR together BIT(NL80211_IFTYPE_...) */ u16 interface_modes; - bool custom_regulatory; - bool strict_regulatory; - bool disable_beacon_hints; - - bool netnsok; - bool ps_default; + u32 flags; enum cfg80211_signal_type signal_type; -- cgit v1.2.3 From 9bc383de37090ba7ca3ff32a12c9d809dc5867f0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 19 Nov 2009 11:55:19 +0100 Subject: cfg80211: introduce capability for 4addr mode It's very likely that not many devices will support four-address mode in station or AP mode so introduce capability bits for both modes, set them in mac80211 and check them when userspace tries to use the mode. Also, keep track of 4addr in cfg80211 (wireless_dev) and not in mac80211 any more. mac80211 can also be improved for the VLAN case by not looking at the 4addr flag but maintaining the station pointer for it correctly. However, keep track of use_4addr for station mode in mac80211 to avoid all the derefs. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index eca36abca8f..d1e05aeb0c0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1134,6 +1134,9 @@ struct cfg80211_ops { * by default -- this flag will be set depending on the kernel's default * on wiphy_new(), but can be changed by the driver if it has a good * reason to override the default + * @WIPHY_FLAG_4ADDR_AP: supports 4addr mode even on AP (with a single station + * on a VLAN interface) + * @WIPHY_FLAG_4ADDR_STATION: supports 4addr mode even as a station */ enum wiphy_flags { WIPHY_FLAG_CUSTOM_REGULATORY = BIT(0), @@ -1141,6 +1144,8 @@ enum wiphy_flags { WIPHY_FLAG_DISABLE_BEACON_HINTS = BIT(2), WIPHY_FLAG_NETNS_OK = BIT(3), WIPHY_FLAG_PS_ON_BY_DEFAULT = BIT(4), + WIPHY_FLAG_4ADDR_AP = BIT(5), + WIPHY_FLAG_4ADDR_STATION = BIT(6), }; /** @@ -1366,6 +1371,10 @@ struct cfg80211_cached_keys; * @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 */ struct wireless_dev { struct wiphy *wiphy; @@ -1379,6 +1388,8 @@ struct wireless_dev { struct work_struct cleanup_work; + bool use_4addr; + /* currently used for IBSS and SME - might be rearranged later */ u8 ssid[IEEE80211_MAX_SSID_LEN]; u8 ssid_len; -- cgit v1.2.3 From 7351c6bd482712e5e3ec9dffc547de0e0863efb0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 19 Nov 2009 01:08:30 +0100 Subject: mac80211: request TX status where needed Right now all frames mac80211 hands to the driver have the IEEE80211_TX_CTL_REQ_TX_STATUS flag set to request TX status. This isn't really necessary, only the injected frames need TX status (the latter for hostapd) so move setting this flag. The rate control algorithms also need TX status, but they don't require it. Also, rt2x00 uses that bit for its own purposes and seems to require it being set for all frames, but that can be fixed in rt2x00. This doesn't really change anything for any drivers but in the future drivers using hw-rate control may opt to not report TX status for frames that don't have the IEEE80211_TX_CTL_REQ_TX_STATUS flag set. Signed-off-by: Johannes Berg Acked-by: Ivo van Doorn [rt2x00 bits] Signed-off-by: John W. Linville --- include/net/mac80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f34f4ca7016..3754ea405c8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -219,7 +219,7 @@ struct ieee80211_bss_conf { * * These flags are used with the @flags member of &ieee80211_tx_info. * - * @IEEE80211_TX_CTL_REQ_TX_STATUS: request TX status callback for this frame. + * @IEEE80211_TX_CTL_REQ_TX_STATUS: require TX status callback for this frame. * @IEEE80211_TX_CTL_ASSIGN_SEQ: The driver has to assign a sequence * number to this frame, taking care of not overwriting the fragment * number and increasing the sequence number only when the -- cgit v1.2.3 From a58ce43f2fb17b728395ff530f019ca53c80145f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 19 Nov 2009 12:45:42 +0100 Subject: mac80211: avoid spurious deauth frames/messages With WEXT, it happens frequently that the SME requests an authentication but then deauthenticates right away because some new parameters came along. Every time this happens we print a deauth message and send a deauth frame, but both of that is rather confusing. Avoid it by aborting the authentication process silently, and telling cfg80211 about that. The patch looks larger than it really is: __cfg80211_auth_remove() is split out from cfg80211_send_auth_timeout(), there's no new code except __cfg80211_auth_canceled() (a one-liner) and the mac80211 bits (7 new lines of code). Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d1e05aeb0c0..a6492e9bca9 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1838,6 +1838,18 @@ void cfg80211_send_rx_auth(struct net_device *dev, const u8 *buf, size_t len); */ void cfg80211_send_auth_timeout(struct net_device *dev, const u8 *addr); +/** + * __cfg80211_auth_canceled - notify cfg80211 that authentication was canceled + * @dev: network device + * @addr: The MAC address of the device with which the authentication timed out + * + * When a pending authentication had no action yet, the driver may decide + * to not send a deauth frame, but in that case must calls this function + * to tell cfg80211 about this decision. It is only valid to call this + * function within the deauth() callback. + */ +void __cfg80211_auth_canceled(struct net_device *dev, const u8 *addr); + /** * cfg80211_send_rx_assoc - notification of processed association * @dev: network device -- cgit v1.2.3 From 8964be4a9a5ca8cab1219bb046db2f6d1936227c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Nov 2009 15:35:04 -0800 Subject: net: rename skb->iif to skb->skb_iif To help grep games, rename iif to skb_iif Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 3dd210d073c..dd3031aed9d 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -343,9 +343,9 @@ tcf_match_indev(struct sk_buff *skb, char *indev) struct net_device *dev; if (indev[0]) { - if (!skb->iif) + if (!skb->skb_iif) return 0; - dev = __dev_get_by_index(dev_net(skb->dev), skb->iif); + dev = __dev_get_by_index(dev_net(skb->dev), skb->skb_iif); if (!dev || strcmp(indev, dev->name)) return 0; } -- cgit v1.2.3 From b93d6471748de2ce02cc24774b774deb306a57a8 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 23 Nov 2009 15:53:56 -0500 Subject: sctp: implement the sender side for SACK-IMMEDIATELY extension This patch implement the sender side for SACK-IMMEDIATELY extension. Section 4.1. Sender Side Considerations Whenever the sender of a DATA chunk can benefit from the corresponding SACK chunk being sent back without delay, the sender MAY set the I-bit in the DATA chunk header. Reasons for setting the I-bit include o The sender is in the SHUTDOWN-PENDING state. o The application requests to set the I-bit of the last DATA chunk of a user message when providing the user message to the SCTP implementation. Signed-off-by: Wei Yongjun Signed-off-by: Vlad Yasevich --- include/net/sctp/user.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h index be2334aaf52..50b2431405f 100644 --- a/include/net/sctp/user.h +++ b/include/net/sctp/user.h @@ -206,6 +206,7 @@ enum sctp_sinfo_flags { SCTP_UNORDERED = 1, /* Send/receive message unordered. */ SCTP_ADDR_OVER = 2, /* Override the primary destination. */ SCTP_ABORT=4, /* Send an ABORT message to the peer. */ + SCTP_SACK_IMMEDIATELY = 8, /* SACK should be sent without delay */ SCTP_EOF=MSG_FIN, /* Initiate graceful shutdown process. */ }; -- cgit v1.2.3 From 6383cfb3ed3c5c0bea06da0099c219ef4237ecf5 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 23 Nov 2009 15:53:56 -0500 Subject: sctp: Fix malformed "Invalid Stream Identifier" error The "Invalid Stream Identifier" error has a 16 bit reserved field at the end, thus making the parameter length be 8 bytes. We've never supplied that reserved field making wireshark tag the packet as malformed. Reported-by: Chris Dischino Signed-off-by: Vlad Yasevich --- include/net/sctp/sm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index c1dd8936583..851c813adb3 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -243,7 +243,8 @@ struct sctp_chunk *sctp_make_op_error(const struct sctp_association *, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, - size_t paylen); + size_t paylen, + size_t reserve_tail); struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *, union sctp_addr *, -- cgit v1.2.3 From 90f2f5318b3a5b0898fef0fec9b91376c7de7a2c Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 23 Nov 2009 15:53:57 -0500 Subject: sctp: Update SWS avaoidance receiver side algorithm We currently send window update SACKs every time we free up 1 PMTU worth of data. That a lot more SACKs then necessary. Instead, we'll now send back the actuall window every time we send a sack, and do window-update SACKs when a fraction of the receive buffer has been opened. The fraction is controlled with a sysctl. Signed-off-by: Vlad Yasevich --- include/net/sctp/constants.h | 4 ++++ include/net/sctp/structs.h | 6 ++++++ 2 files changed, 10 insertions(+) (limited to 'include/net') diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 58f714a3b67..63908840eef 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -308,6 +308,10 @@ enum { SCTP_MAX_GABS = 16 }; #define SCTP_DEFAULT_MINWINDOW 1500 /* default minimum rwnd size */ #define SCTP_DEFAULT_MAXWINDOW 65535 /* default rwnd size */ +#define SCTP_DEFAULT_RWND_SHIFT 4 /* by default, update on 1/16 of + * rcvbuf, which is 1/8 of initial + * window + */ #define SCTP_DEFAULT_MAXSEGMENT 1500 /* MTU size, this is the limit * to which we will raise the P-MTU. */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index cd2e18778f8..90876b65777 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -231,6 +231,11 @@ extern struct sctp_globals { /* Flag to indicate whether computing and verifying checksum * is disabled. */ int checksum_disable; + + /* Threshold for rwnd update SACKS. Receive buffer shifted this many + * bits is an indicator of when to send and window update SACK. + */ + int rwnd_update_shift; } sctp_globals; #define sctp_rto_initial (sctp_globals.rto_initial) @@ -267,6 +272,7 @@ extern struct sctp_globals { #define sctp_prsctp_enable (sctp_globals.prsctp_enable) #define sctp_auth_enable (sctp_globals.auth_enable) #define sctp_checksum_disable (sctp_globals.checksum_disable) +#define sctp_rwnd_upd_shift (sctp_globals.rwnd_update_shift) /* SCTP Socket type: UDP or TCP style. */ typedef enum { -- cgit v1.2.3 From a242b41dedfe0fd51ab1c906daa703c09b196744 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Mon, 23 Nov 2009 15:53:58 -0500 Subject: sctp: remove deprecated SCTP_GET_*_OLD stuffs SCTP_GET_*_OLD stuffs are schedlued to be removed. Cc: Vlad Yasevich Signed-off-by: WANG Cong Signed-off-by: Vlad Yasevich --- include/net/sctp/user.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h index 50b2431405f..fceab4d2413 100644 --- a/include/net/sctp/user.h +++ b/include/net/sctp/user.h @@ -131,14 +131,6 @@ enum sctp_optname { #define SCTP_SOCKOPT_BINDX_REM SCTP_SOCKOPT_BINDX_REM SCTP_SOCKOPT_PEELOFF, /* peel off association. */ #define SCTP_SOCKOPT_PEELOFF SCTP_SOCKOPT_PEELOFF - SCTP_GET_PEER_ADDRS_NUM_OLD, /* Get number of peer addresss. */ -#define SCTP_GET_PEER_ADDRS_NUM_OLD SCTP_GET_PEER_ADDRS_NUM_OLD - SCTP_GET_PEER_ADDRS_OLD, /* Get all peer addresss. */ -#define SCTP_GET_PEER_ADDRS_OLD SCTP_GET_PEER_ADDRS_OLD - SCTP_GET_LOCAL_ADDRS_NUM_OLD, /* Get number of local addresss. */ -#define SCTP_GET_LOCAL_ADDRS_NUM_OLD SCTP_GET_LOCAL_ADDRS_NUM_OLD - SCTP_GET_LOCAL_ADDRS_OLD, /* Get all local addresss. */ -#define SCTP_GET_LOCAL_ADDRS_OLD SCTP_GET_LOCAL_ADDRS_OLD SCTP_SOCKOPT_CONNECTX_OLD, /* CONNECTX old requests. */ #define SCTP_SOCKOPT_CONNECTX_OLD SCTP_SOCKOPT_CONNECTX_OLD SCTP_GET_PEER_ADDRS, /* Get all peer addresss. */ -- cgit v1.2.3 From 245cba7e55929dc2b10b7d915bfba0168eeeed17 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 23 Nov 2009 15:53:58 -0500 Subject: sctp: Remove useless last_time_used variable The transport last_time_used variable is rather useless. It was only used when determining if CWND needs to be updated due to idle transport. However, idle transport detection was based on a Heartbeat timer and last_time_used was not incremented when sending Heartbeats. As a result the check for cwnd reduction was always true. We can get rid of the variable and just base our cwnd manipulation on the HB timer (like the code comment sais). We also have to call into the cwnd manipulation function regardless of whether HBs are enabled or not. That way we will detect idle transports if the user has disabled Heartbeats. Signed-off-by: Vlad Yasevich --- include/net/sctp/structs.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 90876b65777..ac794a6823e 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -950,12 +950,6 @@ struct sctp_transport { /* Source address. */ union sctp_addr saddr; - /* When was the last time(in jiffies) that a data packet was sent on - * this transport? This is used to adjust the cwnd when the transport - * becomes inactive. - */ - unsigned long last_time_used; - /* Heartbeat interval: The endpoint sends out a Heartbeat chunk to * the destination address every heartbeat interval. */ -- cgit v1.2.3 From a5b03ad2143c5bc9ae76533e8321fe66258b4f35 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 23 Nov 2009 15:53:59 -0500 Subject: sctp: Turn the enum socket options into defines Recent attempt to remove deprecated socket options demonstrated that removing options from the enum space will have severe binary compatibility issues. The reason is that it changes the subsequent enum space and causes option values to be redefined. To solve this, and to get rid of the ugly double statements for every option, we simply convert to the #define scheme. Signed-off-by: Vlad Yasevich --- include/net/sctp/user.h | 125 +++++++++++++++++------------------------------- 1 file changed, 43 insertions(+), 82 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h index fceab4d2413..2b2769c5ca9 100644 --- a/include/net/sctp/user.h +++ b/include/net/sctp/user.h @@ -60,88 +60,49 @@ typedef __s32 sctp_assoc_t; /* The following symbols come from the Sockets API Extensions for * SCTP . */ -enum sctp_optname { - SCTP_RTOINFO, -#define SCTP_RTOINFO SCTP_RTOINFO - SCTP_ASSOCINFO, -#define SCTP_ASSOCINFO SCTP_ASSOCINFO - SCTP_INITMSG, -#define SCTP_INITMSG SCTP_INITMSG - SCTP_NODELAY, /* Get/set nodelay option. */ -#define SCTP_NODELAY SCTP_NODELAY - SCTP_AUTOCLOSE, -#define SCTP_AUTOCLOSE SCTP_AUTOCLOSE - SCTP_SET_PEER_PRIMARY_ADDR, -#define SCTP_SET_PEER_PRIMARY_ADDR SCTP_SET_PEER_PRIMARY_ADDR - SCTP_PRIMARY_ADDR, -#define SCTP_PRIMARY_ADDR SCTP_PRIMARY_ADDR - SCTP_ADAPTATION_LAYER, -#define SCTP_ADAPTATION_LAYER SCTP_ADAPTATION_LAYER - SCTP_DISABLE_FRAGMENTS, -#define SCTP_DISABLE_FRAGMENTS SCTP_DISABLE_FRAGMENTS - SCTP_PEER_ADDR_PARAMS, -#define SCTP_PEER_ADDR_PARAMS SCTP_PEER_ADDR_PARAMS - SCTP_DEFAULT_SEND_PARAM, -#define SCTP_DEFAULT_SEND_PARAM SCTP_DEFAULT_SEND_PARAM - SCTP_EVENTS, -#define SCTP_EVENTS SCTP_EVENTS - SCTP_I_WANT_MAPPED_V4_ADDR, /* Turn on/off mapped v4 addresses */ -#define SCTP_I_WANT_MAPPED_V4_ADDR SCTP_I_WANT_MAPPED_V4_ADDR - SCTP_MAXSEG, /* Get/set maximum fragment. */ -#define SCTP_MAXSEG SCTP_MAXSEG - SCTP_STATUS, -#define SCTP_STATUS SCTP_STATUS - SCTP_GET_PEER_ADDR_INFO, -#define SCTP_GET_PEER_ADDR_INFO SCTP_GET_PEER_ADDR_INFO - SCTP_DELAYED_ACK, -#define SCTP_DELAYED_ACK_TIME SCTP_DELAYED_ACK -#define SCTP_DELAYED_ACK SCTP_DELAYED_ACK - SCTP_CONTEXT, /* Receive Context */ -#define SCTP_CONTEXT SCTP_CONTEXT - SCTP_FRAGMENT_INTERLEAVE, -#define SCTP_FRAGMENT_INTERLEAVE SCTP_FRAGMENT_INTERLEAVE - SCTP_PARTIAL_DELIVERY_POINT, /* Set/Get partial delivery point */ -#define SCTP_PARTIAL_DELIVERY_POINT SCTP_PARTIAL_DELIVERY_POINT - SCTP_MAX_BURST, /* Set/Get max burst */ -#define SCTP_MAX_BURST SCTP_MAX_BURST - SCTP_AUTH_CHUNK, /* Set only: add a chunk type to authenticat */ -#define SCTP_AUTH_CHUNK SCTP_AUTH_CHUNK - SCTP_HMAC_IDENT, -#define SCTP_HMAC_IDENT SCTP_HMAC_IDENT - SCTP_AUTH_KEY, -#define SCTP_AUTH_KEY SCTP_AUTH_KEY - SCTP_AUTH_ACTIVE_KEY, -#define SCTP_AUTH_ACTIVE_KEY SCTP_AUTH_ACTIVE_KEY - SCTP_AUTH_DELETE_KEY, -#define SCTP_AUTH_DELETE_KEY SCTP_AUTH_DELETE_KEY - SCTP_PEER_AUTH_CHUNKS, /* Read only */ -#define SCTP_PEER_AUTH_CHUNKS SCTP_PEER_AUTH_CHUNKS - SCTP_LOCAL_AUTH_CHUNKS, /* Read only */ -#define SCTP_LOCAL_AUTH_CHUNKS SCTP_LOCAL_AUTH_CHUNKS - SCTP_GET_ASSOC_NUMBER, /* Read only */ -#define SCTP_GET_ASSOC_NUMBER SCTP_GET_ASSOC_NUMBER - - - /* Internal Socket Options. Some of the sctp library functions are - * implemented using these socket options. - */ - SCTP_SOCKOPT_BINDX_ADD = 100,/* BINDX requests for adding addresses. */ -#define SCTP_SOCKOPT_BINDX_ADD SCTP_SOCKOPT_BINDX_ADD - SCTP_SOCKOPT_BINDX_REM, /* BINDX requests for removing addresses. */ -#define SCTP_SOCKOPT_BINDX_REM SCTP_SOCKOPT_BINDX_REM - SCTP_SOCKOPT_PEELOFF, /* peel off association. */ -#define SCTP_SOCKOPT_PEELOFF SCTP_SOCKOPT_PEELOFF - SCTP_SOCKOPT_CONNECTX_OLD, /* CONNECTX old requests. */ -#define SCTP_SOCKOPT_CONNECTX_OLD SCTP_SOCKOPT_CONNECTX_OLD - SCTP_GET_PEER_ADDRS, /* Get all peer addresss. */ -#define SCTP_GET_PEER_ADDRS SCTP_GET_PEER_ADDRS - SCTP_GET_LOCAL_ADDRS, /* Get all local addresss. */ -#define SCTP_GET_LOCAL_ADDRS SCTP_GET_LOCAL_ADDRS - SCTP_SOCKOPT_CONNECTX, /* CONNECTX requests. */ -#define SCTP_SOCKOPT_CONNECTX SCTP_SOCKOPT_CONNECTX - SCTP_SOCKOPT_CONNECTX3, /* CONNECTX requests. (new implementation) */ -#define SCTP_SOCKOPT_CONNECTX3 SCTP_SOCKOPT_CONNECTX3 -}; +#define SCTP_RTOINFO 0 +#define SCTP_ASSOCINFO 1 +#define SCTP_INITMSG 2 +#define SCTP_NODELAY 3 /* Get/set nodelay option. */ +#define SCTP_AUTOCLOSE 4 +#define SCTP_SET_PEER_PRIMARY_ADDR 5 +#define SCTP_PRIMARY_ADDR 6 +#define SCTP_ADAPTATION_LAYER 7 +#define SCTP_DISABLE_FRAGMENTS 8 +#define SCTP_PEER_ADDR_PARAMS 9 +#define SCTP_DEFAULT_SEND_PARAM 10 +#define SCTP_EVENTS 11 +#define SCTP_I_WANT_MAPPED_V4_ADDR 12 /* Turn on/off mapped v4 addresses */ +#define SCTP_MAXSEG 13 /* Get/set maximum fragment. */ +#define SCTP_STATUS 14 +#define SCTP_GET_PEER_ADDR_INFO 15 +#define SCTP_DELAYED_ACK_TIME 16 +#define SCTP_DELAYED_ACK SCTP_DELAYED_ACK_TIME +#define SCTP_CONTEXT 17 +#define SCTP_FRAGMENT_INTERLEAVE 18 +#define SCTP_PARTIAL_DELIVERY_POINT 19 /* Set/Get partial delivery point */ +#define SCTP_MAX_BURST 20 /* Set/Get max burst */ +#define SCTP_AUTH_CHUNK 21 /* Set only: add a chunk type to authenticate */ +#define SCTP_HMAC_IDENT 22 +#define SCTP_AUTH_KEY 23 +#define SCTP_AUTH_ACTIVE_KEY 24 +#define SCTP_AUTH_DELETE_KEY 25 +#define SCTP_PEER_AUTH_CHUNKS 26 /* Read only */ +#define SCTP_LOCAL_AUTH_CHUNKS 27 /* Read only */ +#define SCTP_GET_ASSOC_NUMBER 28 /* Read only */ + +/* Internal Socket Options. Some of the sctp library functions are + * implemented using these socket options. + */ +#define SCTP_SOCKOPT_BINDX_ADD 100 /* BINDX requests for adding addrs */ +#define SCTP_SOCKOPT_BINDX_REM 101 /* BINDX requests for removing addrs. */ +#define SCTP_SOCKOPT_PEELOFF 102 /* peel off association. */ +/* Options 104-106 are deprecated and removed. Do not use this space */ +#define SCTP_SOCKOPT_CONNECTX_OLD 107 /* CONNECTX old requests. */ +#define SCTP_GET_PEER_ADDRS 108 /* Get all peer addresss. */ +#define SCTP_GET_LOCAL_ADDRS 109 /* Get all local addresss. */ +#define SCTP_SOCKOPT_CONNECTX 110 /* CONNECTX requests. */ +#define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */ /* * 5.2.1 SCTP Initiation Structure (SCTP_INIT) -- cgit v1.2.3 From 46d5a808558181e03a4760d2188cc9879445738a Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 23 Nov 2009 15:54:00 -0500 Subject: sctp: Update max.burst implementation Current implementation of max.burst ends up limiting new data during cwnd decay period. The decay is happening becuase the connection is idle and we are allowed to fill the congestion window. The point of max.burst is to limit micro-bursts in response to large acks. This still happens, as max.burst is still applied to each transmit opportunity. It will also apply if a very large send is made (greater then allowed by burst). Tested-by: Florian Niederbacher Signed-off-by: Vlad Yasevich --- include/net/sctp/structs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index ac794a6823e..bc3f8d879c5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -942,6 +942,8 @@ struct sctp_transport { /* Data that has been sent, but not acknowledged. */ __u32 flight_size; + __u32 burst_limited; /* Holds old cwnd when max.burst is applied */ + /* TSN marking the fast recovery exit point */ __u32 fast_recovery_exit; @@ -1070,6 +1072,8 @@ void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); void sctp_transport_raise_cwnd(struct sctp_transport *, __u32, __u32); void sctp_transport_lower_cwnd(struct sctp_transport *, sctp_lower_cwnd_t); +void sctp_transport_burst_limited(struct sctp_transport *); +void sctp_transport_burst_reset(struct sctp_transport *); unsigned long sctp_transport_timeout(struct sctp_transport *); void sctp_transport_reset(struct sctp_transport *); void sctp_transport_update_pmtu(struct sctp_transport *, u32); -- cgit v1.2.3 From 4447bb33f09444920a8f1d89e1540137429351b6 Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Wed, 25 Nov 2009 00:29:52 +0000 Subject: xfrm: Store aalg in xfrm_state with a user specified truncation length Adding a xfrm_state requires an authentication algorithm specified either as xfrm_algo or as xfrm_algo_auth with a specific truncation length. For compatibility, both attributes are dumped to userspace, and we also accept both attributes, but prefer the new syntax. If no truncation length is specified, or the authentication algorithm is specified using xfrm_algo, the truncation length from the algorithm description in the kernel is used. Signed-off-by: Martin Willi Signed-off-by: David S. Miller --- include/net/xfrm.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 93d184b91a8..6d85861ab99 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -162,7 +162,7 @@ struct xfrm_state { struct xfrm_lifetime_cfg lft; /* Data for transformer */ - struct xfrm_algo *aalg; + struct xfrm_algo_auth *aalg; struct xfrm_algo *ealg; struct xfrm_algo *calg; struct xfrm_algo_aead *aead; @@ -1532,12 +1532,22 @@ static inline int xfrm_alg_len(struct xfrm_algo *alg) return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } +static inline int xfrm_alg_auth_len(struct xfrm_algo_auth *alg) +{ + return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); +} + #ifdef CONFIG_XFRM_MIGRATE static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig) { return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL); } +static inline struct xfrm_algo_auth *xfrm_algo_auth_clone(struct xfrm_algo_auth *orig) +{ + return kmemdup(orig, xfrm_alg_auth_len(orig), GFP_KERNEL); +} + static inline void xfrm_states_put(struct xfrm_state **states, int n) { int i; -- cgit v1.2.3 From 8c0c709eea5cbab97fb464cd68b06f24acc58ee1 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 25 Nov 2009 17:46:15 +0100 Subject: mac80211: move cmntr flag out of rx flags The RX flags should soon be used only for flags that cannot change within an a-MPDU, so move the cooked monitor flag into the RX status flags. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 3754ea405c8..1d75b960da0 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -513,6 +513,9 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_HT: HT MCS was used and rate_idx is MCS index * @RX_FLAG_40MHZ: HT40 (40 MHz) was used * @RX_FLAG_SHORT_GI: Short guard interval was used + * @RX_FLAG_INTERNAL_CMTR: set internally after frame was reported + * on cooked monitor to avoid double-reporting it for multiple + * virtual interfaces */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = 1<<0, @@ -526,6 +529,7 @@ enum mac80211_rx_flags { RX_FLAG_HT = 1<<9, RX_FLAG_40MHZ = 1<<10, RX_FLAG_SHORT_GI = 1<<11, + RX_FLAG_INTERNAL_CMTR = 1<<12, }; /** -- cgit v1.2.3 From 67fbb16be69d138a3b6645ec5395b487cb915c58 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Tue, 24 Nov 2009 23:59:15 +0100 Subject: nl80211: PMKSA caching support This is an interface to set, delete and flush PMKIDs through nl80211. Main users would be fullmac devices which firmwares are capable of generating the RSN IEs for the re-association requests, e.g. iwmc3200wifi. Signed-off-by: Samuel Ortiz Signed-off-by: John W. Linville --- include/net/cfg80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a6492e9bca9..0884b9a0f77 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -871,6 +871,19 @@ struct cfg80211_bitrate_mask { u32 fixed; /* fixed bitrate, 0 == not fixed */ u32 maxrate; /* in kbps, 0 == no limit */ }; +/** + * struct cfg80211_pmksa - PMK Security Association + * + * This structure is passed to the set/del_pmksa() method for PMKSA + * caching. + * + * @bssid: The AP's BSSID. + * @pmkid: The PMK material itself. + */ +struct cfg80211_pmksa { + u8 *bssid; + u8 *pmkid; +}; /** * struct cfg80211_ops - backend description for wireless configuration @@ -976,6 +989,13 @@ struct cfg80211_bitrate_mask { * @dump_survey: get site survey information. * * @testmode_cmd: run a test mode command + * + * @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. + * @del_pmksa: Delete a cached PMKID. + * @flush_pmksa: Flush all cached PMKIDs. + * */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy); @@ -1097,6 +1117,12 @@ struct cfg80211_ops { int (*dump_survey)(struct wiphy *wiphy, struct net_device *netdev, int idx, struct survey_info *info); + int (*set_pmksa)(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_pmksa *pmksa); + int (*del_pmksa)(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_pmksa *pmksa); + int (*flush_pmksa)(struct wiphy *wiphy, struct net_device *netdev); + /* some temporary stuff to finish wext */ int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); @@ -1195,6 +1221,8 @@ struct wiphy { char fw_version[ETHTOOL_BUSINFO_LEN]; u32 hw_version; + u8 max_num_pmkids; + /* If multiple wiphys are registered and you're handed e.g. * a regular netdev with assigned ieee80211_ptr, you won't * know whether it points to a wiphy your driver has registered -- cgit v1.2.3 From 5fdd4baef6195a1f2960e901c8877e2105f832ca Mon Sep 17 00:00:00 2001 From: Andrei Pelinescu-Onciul Date: Sun, 29 Nov 2009 00:14:02 -0800 Subject: sctp: on T3_RTX retransmit all the in-flight chunks When retransmitting due to T3 timeout, retransmit all the in-flight chunks for the corresponding transport/path, including chunks sent less then 1 rto ago. This is the correct behaviour according to rfc4960 section 6.3.3 E3 and "Note: Any DATA chunks that were sent to the address for which the T3-rtx timer expired but did not fit in one MTU (rule E3 above) should be marked for retransmission and sent as soon as cwnd allows (normally, when a SACK arrives). ". This fixes problems when more then one path is present and the T3 retransmission of the first chunk that timeouts stops the T3 timer for the initial active path, leaving all the other in-flight chunks waiting forever or until a new chunk is transmitted on the same path and timeouts (and this will happen only if the cwnd allows sending new chunks, but since cwnd was dropped to MTU by the timeout => it will wait until the first heartbeat). Example: 10 packets in flight, sent at 0.1 s intervals on the primary path. The primary path is down and the first packet timeouts. The first packet is retransmitted on another path, the T3 timer for the primary path is stopped and cwnd is set to MTU. All the other 9 in-flight packets will not be retransmitted (unless more new packets are sent on the primary path which depend on cwnd allowing it, and even in this case the 9 packets will be retransmitted only after a new packet timeouts which even in the best case would be more then RTO). This commit reverts d0ce92910bc04e107b2f3f2048f07e94f570035d and also removes the now unused transport->last_rto, introduced in b6157d8e03e1e780660a328f7183bcbfa4a93a19. p.s The problem is not only when multiple paths are there. It can happen in a single homed environment. If the application stops sending data, it possible to have a hung association. Signed-off-by: Andrei Pelinescu-Onciul Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index cd2e18778f8..0a474568b00 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -893,7 +893,6 @@ struct sctp_transport { */ /* RTO : The current retransmission timeout value. */ unsigned long rto; - unsigned long last_rto; __u32 rtt; /* This is the most recent RTT. */ -- cgit v1.2.3 From 2f5517aefcfbdd7fdf0f03b13d292a10d445887f Mon Sep 17 00:00:00 2001 From: andrew hendry Date: Tue, 24 Nov 2009 15:15:26 +0000 Subject: X25: Move SYSCTL ifdefs into header Moves the CONFIG_SYSCTL ifdefs in x25_init into header. Signed-off-by: Andrew Hendry Acked-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/x25.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/net') diff --git a/include/net/x25.h b/include/net/x25.h index 2cda0401156..9baa07dc7d1 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -287,8 +287,14 @@ extern unsigned long x25_display_timer(struct sock *); extern void x25_check_rbuf(struct sock *); /* sysctl_net_x25.c */ +#ifdef CONFIG_SYSCTL extern void x25_register_sysctl(void); extern void x25_unregister_sysctl(void); +#else +static inline void x25_register_sysctl(void) {}; +static inline void x25_unregister_sysctl(void) {}; +#endif /* CONFIG_SYSCTL */ + struct x25_skb_cb { unsigned flags; }; -- cgit v1.2.3 From 827d42c9ac91ddd728e4f4a31fefb906ef2ceff7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 22 Nov 2009 12:28:41 +0100 Subject: mac80211: fix spurious delBA handling Lennert Buytenhek noticed that delBA handling in mac80211 was broken and has remotely triggerable problems, some of which are due to some code shuffling I did that ended up changing the order in which things were done -- this was commit d75636ef9c1af224f1097941879d5a8db7cd04e5 Author: Johannes Berg Date: Tue Feb 10 21:25:53 2009 +0100 mac80211: RX aggregation: clean up stop session and other parts were already present in the original commit d92684e66091c0f0101819619b315b4bb8b5bcc5 Author: Ron Rindjunsky Date: Mon Jan 28 14:07:22 2008 +0200 mac80211: A-MPDU Tx add delBA from recipient support The first problem is that I moved a BUG_ON before various checks -- thereby making it possible to hit. As the comment indicates, the BUG_ON can be removed since the ampdu_action callback must already exist when the state is != IDLE. The second problem isn't easily exploitable but there's a race condition due to unconditionally setting the state to OPERATIONAL when a delBA frame is received, even when no aggregation session was ever initiated. All the drivers accept stopping the session even then, but that opens a race window where crashes could happen before the driver accepts it. Right now, a WARN_ON may happen with non-HT drivers, while the race opens only for HT drivers. For this case, there are two things necessary to fix it: 1) don't process spurious delBA frames, and be more careful about the session state; don't drop the lock 2) HT drivers need to be prepared to handle a session stop even before the session was really started -- this is true for all drivers (that support aggregation) but iwlwifi which can be fixed easily. The other HT drivers (ath9k and ar9170) are behaving properly already. Reported-by: Lennert Buytenhek Cc: stable@kernel.org Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c75b960c8ac..998c30fc898 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1283,6 +1283,12 @@ enum ieee80211_filter_flags { * * These flags are used with the ampdu_action() callback in * &struct ieee80211_ops to indicate which action is needed. + * + * 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 + * might receive the addBA frame and send a delBA right away! + * * @IEEE80211_AMPDU_RX_START: start Rx aggregation * @IEEE80211_AMPDU_RX_STOP: stop Rx aggregation * @IEEE80211_AMPDU_TX_START: start Tx aggregation -- cgit v1.2.3 From a5ee155136b4a8f4ab0e4c9c064b661da475e298 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 29 Nov 2009 15:45:58 +0000 Subject: net: NETDEV_UNREGISTER_PERNET -> NETDEV_UNREGISTER_BATCH The motivation for an additional notifier in batched netdevice notification (rt_do_flush) only needs to be called once per batch not once per namespace. For further batching improvements I need a guarantee that the netdevices are unregistered in order allowing me to unregister an all of the network devices in a network namespace at the same time with the guarantee that the loopback device is really and truly unregistered last. Additionally it appears that we moved the route cache flush after the final synchronize_net, which seems wrong and there was no explanation. So I have restored the original location of the final synchronize_net. Cc: Octavian Purdila Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/route.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/route.h b/include/net/route.h index cfb4c071a13..bce6dd68d27 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -108,6 +108,7 @@ extern int ip_rt_init(void); extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw, __be32 src, struct net_device *dev); extern void rt_cache_flush(struct net *net, int how); +extern void rt_cache_flush_batch(void); extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp); extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp); extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags); -- cgit v1.2.3 From 2b035b39970740722598f7a9d548835f9bdd730f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 29 Nov 2009 22:25:27 +0000 Subject: net: Batch network namespace destruction. It is fairly common to kill several network namespaces at once. Either because they are nested one inside the other or because they are cooperating in multiple machine networking experiments. As the network stack control logic does not parallelize easily batch up multiple network namespaces existing together. To get the full benefit of batching the virtual network devices to be removed must be all removed in one batch. For that purpose I have added a loop after the last network device operations have run that batches up all remaining network devices and deletes them. An extra benefit is that the reorganization slightly shrinks the size of the per network namespace data structures replaceing a work_struct with a list_head. In a trivial test with 4K namespaces this change reduced the cost of a destroying 4K namespaces from 7+ minutes (at 12% cpu) to 44 seconds (at 60% cpu). The bulk of that 44s was spent in inet_twsk_purge. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/net_namespace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 0addd45038a..d69b4796030 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -42,7 +42,7 @@ struct net { */ #endif struct list_head list; /* list of network namespaces */ - struct work_struct work; /* work struct for freeing */ + struct list_head cleanup_list; /* namespaces on death row */ struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; -- cgit v1.2.3 From f875bae065334907796da12523f9df85c89f5712 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 29 Nov 2009 22:25:28 +0000 Subject: net: Automatically allocate per namespace data. To get the full benefit of batched network namespace cleanup netowrk device deletion needs to be performed by the generic code. When using register_pernet_gen_device and freeing the data in exit_net it is impossible to delay allocation until after exit_net has called as the device uninit methods are no longer safe. To correct this, and to simplify working with per network namespace data I have moved allocation and deletion of per network namespace data into the network namespace core. The core now frees the data only after all of the network namespace exit routines have run. Now it is only required to set the new fields .id and .size in the pernet_operations structure if you want network namespace data to be managed for you automatically. This makes the current register_pernet_gen_device and register_pernet_gen_subsys routines unnecessary. For the moment I have left them as compatibility wrappers in net_namespace.h They will be removed once all of the users have been updated. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/net_namespace.h | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index d69b4796030..080774b9dbf 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -236,6 +236,8 @@ struct pernet_operations { struct list_head list; int (*init)(struct net *net); void (*exit)(struct net *net); + int *id; + size_t size; }; /* @@ -259,12 +261,30 @@ struct pernet_operations { */ extern int register_pernet_subsys(struct pernet_operations *); extern void unregister_pernet_subsys(struct pernet_operations *); -extern int register_pernet_gen_subsys(int *id, struct pernet_operations *); -extern void unregister_pernet_gen_subsys(int id, struct pernet_operations *); extern int register_pernet_device(struct pernet_operations *); extern void unregister_pernet_device(struct pernet_operations *); -extern int register_pernet_gen_device(int *id, struct pernet_operations *); -extern void unregister_pernet_gen_device(int id, struct pernet_operations *); + +static inline int register_pernet_gen_subsys(int *id, struct pernet_operations *ops) +{ + ops->id = id; + return register_pernet_subsys(ops); +} + +static inline void unregister_pernet_gen_subsys(int id, struct pernet_operations *ops) +{ + return unregister_pernet_subsys(ops); +} + +static inline int register_pernet_gen_device(int *id, struct pernet_operations *ops) +{ + ops->id = id; + return register_pernet_device(ops); +} + +static inline void unregister_pernet_gen_device(int id, struct pernet_operations *ops) +{ + return unregister_pernet_device(ops); +} struct ctl_path; struct ctl_table; -- cgit v1.2.3 From 65c0cfafce9575319fb6f70080fbe226e5617e3b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 29 Nov 2009 15:46:17 +0000 Subject: net: remove [un]register_pernet_gen_... and update the docs. No that all of the callers have been updated to set fields in struct pernet_operations, and simplified to let the network namespace core handle the allocation and freeing of the storage for them, remove the surpurpflous methods and update the docs to the new style. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/net_namespace.h | 22 ---------------------- include/net/netns/generic.h | 8 +++++--- 2 files changed, 5 insertions(+), 25 deletions(-) (limited to 'include/net') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 080774b9dbf..24a8c5591f6 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -264,28 +264,6 @@ extern void unregister_pernet_subsys(struct pernet_operations *); extern int register_pernet_device(struct pernet_operations *); extern void unregister_pernet_device(struct pernet_operations *); -static inline int register_pernet_gen_subsys(int *id, struct pernet_operations *ops) -{ - ops->id = id; - return register_pernet_subsys(ops); -} - -static inline void unregister_pernet_gen_subsys(int id, struct pernet_operations *ops) -{ - return unregister_pernet_subsys(ops); -} - -static inline int register_pernet_gen_device(int *id, struct pernet_operations *ops) -{ - ops->id = id; - return register_pernet_device(ops); -} - -static inline void unregister_pernet_gen_device(int id, struct pernet_operations *ops) -{ - return unregister_pernet_device(ops); -} - struct ctl_path; struct ctl_table; struct ctl_table_header; diff --git a/include/net/netns/generic.h b/include/net/netns/generic.h index 0c04fd2a700..ff4982ab84b 100644 --- a/include/net/netns/generic.h +++ b/include/net/netns/generic.h @@ -12,9 +12,11 @@ * stuff on the struct net without explicit struct net modification * * The rules are simple: - * 1. register the ops with register_pernet_gen_device to get the id - * of your private pointer; - * 2. call net_assign_generic() to put the private data on the struct + * 1. set pernet_operations->id. After register_pernet_device you + * will have the id of your private pointer. + * 2. Either set pernet_operations->size (to have the code allocate and + * free a private structure pointed to from struct net ) or + * call net_assign_generic() to put the private data on the struct * net (most preferably this should be done in the ->init callback * of the ops registered); * 3. do not change this pointer while the net is alive; -- cgit v1.2.3 From e6b4d11367519bc71729c09d05a126b133c755be Mon Sep 17 00:00:00 2001 From: William Allen Simpson Date: Wed, 2 Dec 2009 18:07:39 +0000 Subject: TCPCT part 1a: add request_values parameter for sending SYNACK Add optional function parameters associated with sending SYNACK. These parameters are not needed after sending SYNACK, and are not used for retransmission. Avoids extending struct tcp_request_sock, and avoids allocating kernel memory. Also affects DCCP as it uses common struct request_sock_ops, but this parameter is currently reserved for future use. Signed-off-by: William.Allen.Simpson@gmail.com Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 8 +++++++- include/net/tcp.h | 3 ++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index c7190846e12..c9b50ebd9ce 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -27,13 +27,19 @@ struct sk_buff; struct dst_entry; struct proto; +/* empty to "strongly type" an otherwise void parameter. + */ +struct request_values { +}; + struct request_sock_ops { int family; int obj_size; struct kmem_cache *slab; char *slab_name; int (*rtx_syn_ack)(struct sock *sk, - struct request_sock *req); + struct request_sock *req, + struct request_values *rvp); void (*send_ack)(struct sock *sk, struct sk_buff *skb, struct request_sock *req); void (*send_reset)(struct sock *sk, diff --git a/include/net/tcp.h b/include/net/tcp.h index 325bfcf5c93..ec183fda05d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -440,7 +440,8 @@ extern int tcp_connect(struct sock *sk); extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct request_sock *req); + struct request_sock *req, + struct request_values *rvp); extern int tcp_disconnect(struct sock *sk, int flags); -- cgit v1.2.3 From da5c78c82629a167794436e4306b4cf1faddea90 Mon Sep 17 00:00:00 2001 From: William Allen Simpson Date: Wed, 2 Dec 2009 18:12:09 +0000 Subject: TCPCT part 1b: generate Responder Cookie secret Define (missing) hash message size for SHA1. Define hashing size constants specific to TCP cookies. Add new function: tcp_cookie_generator(). Maintain global secret values for tcp_cookie_generator(). This is a significantly revised implementation of earlier (15-year-old) Photuris [RFC-2522] code for the KA9Q cooperative multitasking platform. Linux RCU technique appears to be well-suited to this application, though neither of the circular queue items are freed. These functions will also be used in subsequent patches that implement additional features. Signed-off-by: William.Allen.Simpson@gmail.com Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index ec183fda05d..4a99a8e3912 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1478,6 +1478,14 @@ struct tcp_request_sock_ops { #endif }; +/* Using SHA1 for now, define some constants. + */ +#define COOKIE_DIGEST_WORDS (SHA_DIGEST_WORDS) +#define COOKIE_MESSAGE_WORDS (SHA_MESSAGE_BYTES / 4) +#define COOKIE_WORKSPACE_WORDS (COOKIE_DIGEST_WORDS + COOKIE_MESSAGE_WORDS) + +extern int tcp_cookie_generator(u32 *bakery); + extern void tcp_v4_init(void); extern void tcp_init(void); -- cgit v1.2.3 From 519855c508b9a17878c0977a3cdefc09b59b30df Mon Sep 17 00:00:00 2001 From: William Allen Simpson Date: Wed, 2 Dec 2009 18:14:19 +0000 Subject: TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Define sysctl (tcp_cookie_size) to turn on and off the cookie option default globally, instead of a compiled configuration option. Define per socket option (TCP_COOKIE_TRANSACTIONS) for setting constant data values, retrieving variable cookie values, and other facilities. Move inline tcp_clear_options() unchanged from net/tcp.h to linux/tcp.h, near its corresponding struct tcp_options_received (prior to changes). This is a straightforward re-implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 These functions will also be used in subsequent patches that implement additional features. Requires: net: TCP_MSS_DEFAULT, TCP_MSS_DESIRED Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller --- include/net/tcp.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 4a99a8e3912..738b65f01e2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -234,6 +234,7 @@ extern int sysctl_tcp_base_mss; extern int sysctl_tcp_workaround_signed_windows; extern int sysctl_tcp_slow_start_after_idle; extern int sysctl_tcp_max_ssthresh; +extern int sysctl_tcp_cookie_size; extern atomic_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; @@ -340,11 +341,6 @@ static inline void tcp_dec_quickack_mode(struct sock *sk, extern void tcp_enter_quickack_mode(struct sock *sk); -static inline void tcp_clear_options(struct tcp_options_received *rx_opt) -{ - rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0; -} - #define TCP_ECN_OK 1 #define TCP_ECN_QUEUE_CWR 2 #define TCP_ECN_DEMAND_CWR 4 -- cgit v1.2.3 From 435cf559f02ea3a3159eb316f97dc88bdebe9432 Mon Sep 17 00:00:00 2001 From: William Allen Simpson Date: Wed, 2 Dec 2009 18:17:05 +0000 Subject: TCPCT part 1d: define TCP cookie option, extend existing struct's Data structures are carefully composed to require minimal additions. For example, the struct tcp_options_received cookie_plus variable fits between existing 16-bit and 8-bit variables, requiring no additional space (taking alignment into consideration). There are no additions to tcp_request_sock, and only 1 pointer in tcp_sock. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 The principle difference is using a TCP option to carry the cookie nonce, instead of a user configured offset in the data. This is more flexible and less subject to user configuration error. Such a cookie option has been suggested for many years, and is also useful without SYN data, allowing several related concepts to use the same extension option. "Re: SYN floods (was: does history repeat itself?)", September 9, 1996. http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html "Re: what a new TCP header might look like", May 12, 1998. ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail These functions will also be used in subsequent patches that implement additional features. Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller --- include/net/tcp.h | 83 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 738b65f01e2..f9abd9becab 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -164,6 +165,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ +#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */ /* * TCP option lengths @@ -174,6 +176,10 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 +#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */ +#define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */ +#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN) +#define TCPOLEN_COOKIE_MAX (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MAX) /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 @@ -1482,6 +1488,83 @@ struct tcp_request_sock_ops { extern int tcp_cookie_generator(u32 *bakery); +/** + * struct tcp_cookie_values - each socket needs extra space for the + * cookies, together with (optional) space for any SYN data. + * + * A tcp_sock contains a pointer to the current value, and this is + * cloned to the tcp_timewait_sock. + * + * @cookie_pair: variable data from the option exchange. + * + * @cookie_desired: user specified tcpct_cookie_desired. Zero + * indicates default (sysctl_tcp_cookie_size). + * After cookie sent, remembers size of cookie. + * Range 0, TCP_COOKIE_MIN to TCP_COOKIE_MAX. + * + * @s_data_desired: user specified tcpct_s_data_desired. When the + * constant payload is specified (@s_data_constant), + * holds its length instead. + * Range 0 to TCP_MSS_DESIRED. + * + * @s_data_payload: constant data that is to be included in the + * payload of SYN or SYNACK segments when the + * cookie option is present. + */ +struct tcp_cookie_values { + struct kref kref; + u8 cookie_pair[TCP_COOKIE_PAIR_SIZE]; + u8 cookie_pair_size; + u8 cookie_desired; + u16 s_data_desired:11, + s_data_constant:1, + s_data_in:1, + s_data_out:1, + s_data_unused:2; + u8 s_data_payload[0]; +}; + +static inline void tcp_cookie_values_release(struct kref *kref) +{ + kfree(container_of(kref, struct tcp_cookie_values, kref)); +} + +/* The length of constant payload data. Note that s_data_desired is + * overloaded, depending on s_data_constant: either the length of constant + * data (returned here) or the limit on variable data. + */ +static inline int tcp_s_data_size(const struct tcp_sock *tp) +{ + return (tp->cookie_values != NULL && tp->cookie_values->s_data_constant) + ? tp->cookie_values->s_data_desired + : 0; +} + +/** + * struct tcp_extend_values - tcp_ipv?.c to tcp_output.c workspace. + * + * As tcp_request_sock has already been extended in other places, the + * only remaining method is to pass stack values along as function + * parameters. These parameters are not needed after sending SYNACK. + * + * @cookie_bakery: cryptographic secret and message workspace. + * + * @cookie_plus: bytes in authenticator/cookie option, copied from + * struct tcp_options_received (above). + */ +struct tcp_extend_values { + struct request_values rv; + u32 cookie_bakery[COOKIE_WORKSPACE_WORDS]; + u8 cookie_plus:6, + cookie_out_never:1, + cookie_in_always:1; +}; + +static inline struct tcp_extend_values *tcp_xv(struct request_values *rvp) +{ + return (struct tcp_extend_values *)rvp; +} + extern void tcp_v4_init(void); extern void tcp_init(void); -- cgit v1.2.3 From 4957faade11b3a278c3b3cade3411ddc20afa791 Mon Sep 17 00:00:00 2001 From: William Allen Simpson Date: Wed, 2 Dec 2009 18:25:27 +0000 Subject: TCPCT part 1g: Responder Cookie => Initiator Parse incoming TCP_COOKIE option(s). Calculate TCP_COOKIE option. Send optional data. This is a significantly revised implementation of an earlier (year-old) patch that no longer applies cleanly, with permission of the original author (Adam Langley): http://thread.gmane.org/gmane.linux.network/102586 Requires: TCPCT part 1a: add request_values parameter for sending SYNACK TCPCT part 1b: generate Responder Cookie secret TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS TCPCT part 1d: define TCP cookie option, extend existing struct's TCPCT part 1e: implement socket option TCP_COOKIE_TRANSACTIONS TCPCT part 1f: Initiator Cookie => Responder Signed-off-by: William.Allen.Simpson@gmail.com Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index f9abd9becab..28b04ff8c96 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -407,6 +407,7 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, extern void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, + u8 **hvpp, int estab, struct dst_entry *dst); -- cgit v1.2.3 From 8818a9d884e3a589899be3303958fff182e98e55 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Wed, 2 Dec 2009 22:24:02 -0800 Subject: tcp: clear hints to avoid a stale one (nfs only affected?) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Eric Dumazet mentioned in a context of another problem: "Well, it seems NFS reuses its socket, so maybe we miss some cleaning as spotted in this old patch" I've not check under which conditions that actually happens but if true, we need to make sure we don't accidently leave stale hints behind when the write queue had to be purged (whether reusing with NFS can actually happen if purging took place is something I'm not sure of). ...At least it compiles. Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 28b04ff8c96..e2d2ca2509b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1229,6 +1229,7 @@ static inline void tcp_write_queue_purge(struct sock *sk) while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) sk_wmem_free_skb(sk, skb); sk_mem_reclaim(sk); + tcp_clear_all_retrans_hints(tcp_sk(sk)); } static inline struct sk_buff *tcp_write_queue_head(struct sock *sk) -- cgit v1.2.3 From 76bca88012e1d27de794f32cc551d6314d38b6d9 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Wed, 18 Nov 2009 00:40:39 +0100 Subject: Bluetooth: Turn hci_recv_frame into an exported function For future simplification it is important that the hci_recv_frame function is no longer an inline function. So move it into the module itself and export it. Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 23 +---------------------- 1 file changed, 1 insertion(+), 22 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7b640aeddb6..8460f228308 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -437,28 +437,7 @@ int hci_inquiry(void __user *arg); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); -/* Receive frame from HCI drivers */ -static inline int hci_recv_frame(struct sk_buff *skb) -{ - struct hci_dev *hdev = (struct hci_dev *) skb->dev; - if (!hdev || (!test_bit(HCI_UP, &hdev->flags) - && !test_bit(HCI_INIT, &hdev->flags))) { - kfree_skb(skb); - return -ENXIO; - } - - /* Incomming skb */ - bt_cb(skb)->incoming = 1; - - /* Time stamp */ - __net_timestamp(skb); - - /* Queue frame for rx task */ - skb_queue_tail(&hdev->rx_q, skb); - hci_sched_rx(hdev); - return 0; -} - +int hci_recv_frame(struct sk_buff *skb); int hci_recv_fragment(struct hci_dev *hdev, int type, void *data, int count); int hci_register_sysfs(struct hci_dev *hdev); -- cgit v1.2.3 From c78ae283145d3a8799b2fb01650166a66af3bff8 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Wed, 18 Nov 2009 01:02:54 +0100 Subject: Bluetooth: Unobfuscate tasklet_schedule usage The tasklet schedule function helpers are just an obfuscation. So remove them and call the schedule functions directly. Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8460f228308..7b86094a894 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -367,22 +367,6 @@ static inline void hci_conn_put(struct hci_conn *conn) } } -/* ----- HCI tasks ----- */ -static inline void hci_sched_cmd(struct hci_dev *hdev) -{ - tasklet_schedule(&hdev->cmd_task); -} - -static inline void hci_sched_rx(struct hci_dev *hdev) -{ - tasklet_schedule(&hdev->rx_task); -} - -static inline void hci_sched_tx(struct hci_dev *hdev) -{ - tasklet_schedule(&hdev->tx_task); -} - /* ----- HCI Devices ----- */ static inline void __hci_dev_put(struct hci_dev *d) { -- cgit v1.2.3 From 9f121a5a80b4417c6db5a35e26d2e79c29c3fc0d Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 3 Oct 2009 02:34:38 -0300 Subject: Bluetooth: Fix sending ReqSeq on I-frames As specified by ERTM spec an ERTM channel can acknowledge received I-frames(the data frames) by sending an I-frame with the proper ReqSeq value (i.e. ReqSeq is set to BufferSeq). Until now we aren't setting the ReqSeq value on I-frame control bits. That way we can save sending S-frames(Supervise frames) only to acknowledge receipt of I-frames. It is very helpful to the full-duplex channel. ReqSeq is the packet sequence number sent in an acknowledgement frame to acknowledge receipt of frames up to (ReqSeq - 1). BufferSeq controls the receiver buffer, it is used to delay acknowledgement of new frames to not cause buffer overflow. BufferSeq value is not increased until frames are pulled by reassembly function. Signed-off-by: Gustavo F. Padovan Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 9516f4b4a3c..327eb57dab5 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -324,7 +324,6 @@ struct l2cap_pinfo { __u8 next_tx_seq; __u8 expected_ack_seq; - __u8 req_seq; __u8 expected_tx_seq; __u8 buffer_seq; __u8 buffer_seq_srej; -- cgit v1.2.3 From 4ec10d9720ef78cd81d8bcc30a3238665744569f Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 3 Oct 2009 02:34:39 -0300 Subject: Bluetooth: Implement RejActioned flag RejActioned is used to prevent retransmission when a entity is on the WAIT_F state, i.e., waiting for a frame with F-bit set due local busy condition or a expired retransmission timer. (When these two events raise they send a frame with the Poll bit set and enters in the WAIT_F state to wait for a frame with the Final bit set.) The local entity doesn't send I-frames(the data frames) until the receipt of a frame with F-bit set. When that happens it also set RejActioned to false. RejActioned is a mandatory feature of ERTM spec. Signed-off-by: Gustavo F. Padovan Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 327eb57dab5..17a689f27a6 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -374,6 +374,7 @@ struct l2cap_pinfo { #define L2CAP_CONN_SEND_PBIT 0x10 #define L2CAP_CONN_REMOTE_BUSY 0x20 #define L2CAP_CONN_LOCAL_BUSY 0x40 +#define L2CAP_CONN_REJ_ACT 0x80 #define __mod_retrans_timer() mod_timer(&l2cap_pi(sk)->retrans_timer, \ jiffies + msecs_to_jiffies(L2CAP_DEFAULT_RETRANS_TO)); -- cgit v1.2.3 From d285834001df372f81045bb41092e54943e93c84 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 3 Dec 2009 01:25:53 +0000 Subject: net 01/05: fib_rules: rearrange struct fib_rule commit b8952893d5d86f69c4e499d191b98c6658f64b0f Author: Patrick McHardy Date: Thu Dec 3 12:05:22 2009 +0100 net: fib_rules: rearrange struct fib_rule The ifname member is only used to resolve interface names and is not needed during rule lookups. The target and ctarget members however are used during rule lookups and are currently located in a second cacheline. Move ifname further to the end to make sure both target and ctarget are located in the same cacheline as other members used during rule lookups. The layout on 64 bit changes from: struct fib_rule { ... u32 table; /* 56 4 */ u8 action; /* 60 1 */ /* XXX 3 bytes hole, try to pack */ /* --- cacheline 1 boundary (64 bytes) --- */ u32 target; /* 64 4 */ /* XXX 4 bytes hole, try to pack */ struct fib_rule * ctarget; /* 72 8 */ struct rcu_head rcu; /* 80 16 */ struct net * fr_net; /* 96 8 */ }; to: struct fib_rule { ... u32 table; /* 40 4 */ u8 action; /* 44 1 */ /* XXX 3 bytes hole, try to pack */ u32 target; /* 48 4 */ /* XXX 4 bytes hole, try to pack */ struct fib_rule * ctarget; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ char ifname[16]; /* 64 16 */ struct rcu_head rcu; /* 80 16 */ struct net * fr_net; /* 96 8 */ }; Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/fib_rules.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 2cd707b15d5..22fb323cd85 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -11,7 +11,6 @@ struct fib_rule { struct list_head list; atomic_t refcnt; int ifindex; - char ifname[IFNAMSIZ]; u32 mark; u32 mark_mask; u32 pref; @@ -20,6 +19,7 @@ struct fib_rule { u8 action; u32 target; struct fib_rule * ctarget; + char ifname[IFNAMSIZ]; struct rcu_head rcu; struct net * fr_net; }; -- cgit v1.2.3 From 491deb24bf5bf7124141287aaf02c3219783ceab Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 3 Dec 2009 01:25:54 +0000 Subject: net 02/05: fib_rules: rename ifindex/ifname/FRA_IFNAME to iifindex/iifname/FRA_IIFNAME commit 229e77eec406ad68662f18e49fda8b5d366768c5 Author: Patrick McHardy Date: Thu Dec 3 12:05:23 2009 +0100 net: fib_rules: rename ifindex/ifname/FRA_IFNAME to iifindex/iifname/FRA_IIFNAME The next patch will add oif classification, rename interface related members and attributes to reflect that they're used for iif classification. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/fib_rules.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 22fb323cd85..62bebcb2a51 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -10,7 +10,7 @@ struct fib_rule { struct list_head list; atomic_t refcnt; - int ifindex; + int iifindex; u32 mark; u32 mark_mask; u32 pref; @@ -19,7 +19,7 @@ struct fib_rule { u8 action; u32 target; struct fib_rule * ctarget; - char ifname[IFNAMSIZ]; + char iifname[IFNAMSIZ]; struct rcu_head rcu; struct net * fr_net; }; @@ -67,7 +67,7 @@ struct fib_rules_ops { }; #define FRA_GENERIC_POLICY \ - [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ + [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_PRIORITY] = { .type = NLA_U32 }, \ [FRA_FWMARK] = { .type = NLA_U32 }, \ [FRA_FWMASK] = { .type = NLA_U32 }, \ -- cgit v1.2.3 From 1b038a5e60c7812f19818e8a5df96d029e49c38f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 3 Dec 2009 01:25:56 +0000 Subject: net 03/05: fib_rules: add oif classification commit 68144d350f4f6c348659c825cde6a82b34c27a91 Author: Patrick McHardy Date: Thu Dec 3 12:05:25 2009 +0100 net: fib_rules: add oif classification Support routing table lookup based on the flow's oif. This is useful to classify packets originating from sockets bound to interfaces differently. The route cache already includes the oif and needs no changes. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/fib_rules.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 62bebcb2a51..d4e875a58f8 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -11,6 +11,7 @@ struct fib_rule { struct list_head list; atomic_t refcnt; int iifindex; + int oifindex; u32 mark; u32 mark_mask; u32 pref; @@ -20,6 +21,7 @@ struct fib_rule { u32 target; struct fib_rule * ctarget; char iifname[IFNAMSIZ]; + char oifname[IFNAMSIZ]; struct rcu_head rcu; struct net * fr_net; }; @@ -68,6 +70,7 @@ struct fib_rules_ops { #define FRA_GENERIC_POLICY \ [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ + [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_PRIORITY] = { .type = NLA_U32 }, \ [FRA_FWMARK] = { .type = NLA_U32 }, \ [FRA_FWMASK] = { .type = NLA_U32 }, \ -- cgit v1.2.3 From 72ad937abd0a43b7cf2c557ba1f2ec75e608c516 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 3 Dec 2009 02:29:03 +0000 Subject: net: Add support for batching network namespace cleanups - Add exit_list to struct net to support building lists of network namespaces to cleanup. - Add exit_batch to pernet_operations to allow running operations only once during a network namespace exit. Instead of once per network namespace. - Factor opt ops_exit_list and ops_exit_free so the logic with cleanup up a network namespace does not need to be duplicated. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/net_namespace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 24a8c5591f6..f307e133d14 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -43,6 +43,7 @@ struct net { #endif struct list_head list; /* list of network namespaces */ struct list_head cleanup_list; /* namespaces on death row */ + struct list_head exit_list; /* Use only net_mutex */ struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; @@ -236,6 +237,7 @@ struct pernet_operations { struct list_head list; int (*init)(struct net *net); void (*exit)(struct net *net); + void (*exit_batch)(struct list_head *net_exit_list); int *id; size_t size; }; -- cgit v1.2.3 From d79d792ef9f99cca463b6619a93e860d1c833a6e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 3 Dec 2009 02:29:05 +0000 Subject: net: Allow xfrm_user_net_exit to batch efficiently. xfrm.nlsk is provided by the xfrm_user module and is access via rcu from other parts of the xfrm code. Add xfrm.nlsk_stash a copy of xfrm.nlsk that will never be set to NULL. This allows the synchronize_net and netlink_kernel_release to be deferred until a whole batch of xfrm.nlsk sockets have been set to NULL. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/netns/xfrm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 1ba912749ca..56f8e5585df 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -43,6 +43,7 @@ struct netns_xfrm { struct work_struct policy_hash_work; struct sock *nlsk; + struct sock *nlsk_stash; u32 sysctl_aevent_etime; u32 sysctl_aevent_rseqth; -- cgit v1.2.3 From e9c5158ac26affd5d8ce006521bdfb7148090e18 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 3 Dec 2009 12:22:55 -0800 Subject: net: Allow fib_rule_unregister to batch Refactor the code so fib_rules_register always takes a template instead of the actual fib_rules_ops structure that will be used. This is required for network namespace support so 2 out of the 3 callers already do this, it allows the error handling to be made common, and it allows fib_rules_unregister to free the template for hte caller. Modify fib_rules_unregister to use call_rcu instead of syncrhonize_rcu to allw multiple namespaces to be cleaned up in the same rcu grace period. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/fib_rules.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index d4e875a58f8..c07ac9650eb 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -66,6 +66,7 @@ struct fib_rules_ops { struct list_head rules_list; struct module *owner; struct net *fro_net; + struct rcu_head rcu; }; #define FRA_GENERIC_POLICY \ @@ -102,7 +103,7 @@ static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) return frh->table; } -extern int fib_rules_register(struct fib_rules_ops *); +extern struct fib_rules_ops *fib_rules_register(struct fib_rules_ops *, struct net *); extern void fib_rules_unregister(struct fib_rules_ops *); extern void fib_rules_cleanup_ops(struct fib_rules_ops *); -- cgit v1.2.3 From b099ce2602d806deb41caaa578731848995cdb2a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 3 Dec 2009 02:29:09 +0000 Subject: net: Batch inet_twsk_purge This function walks the whole hashtable so there is no point in passing it a network namespace. Instead I purge all timewait sockets from dead network namespaces that I find. If the namespace is one of the once I am trying to purge I am guaranteed no new timewait sockets can be formed so this will get them all. If the namespace is one I am not acting for it might form a few more but I will call inet_twsk_purge again and shortly to get rid of them. In any even if the network namespace is dead timewait sockets are useless. Move the calls of inet_twsk_purge into batch_exit routines so that if I am killing a bunch of namespaces at once I will just call inet_twsk_purge once and save a lot of redundant unnecessary work. My simple 4k network namespace exit test the cleanup time dropped from roughly 8.2s to 1.6s. While the time spent running inet_twsk_purge fell to about 2ms. 1ms for ipv4 and 1ms for ipv6. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 773b10fa38e..4fd007f34dd 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -212,14 +212,14 @@ extern void inet_twsk_schedule(struct inet_timewait_sock *tw, extern void inet_twsk_deschedule(struct inet_timewait_sock *tw, struct inet_timewait_death_row *twdr); -extern void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo, +extern void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family); static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { #ifdef CONFIG_NET_NS - return twsk->tw_net; + return rcu_dereference(twsk->tw_net); #else return &init_net; #endif @@ -229,7 +229,7 @@ static inline void twsk_net_set(struct inet_timewait_sock *twsk, struct net *net) { #ifdef CONFIG_NET_NS - twsk->tw_net = net; + rcu_assign_pointer(twsk->tw_net, net); #endif } #endif /* _INET_TIMEWAIT_SOCK_ */ -- cgit v1.2.3 From 13475a30b66cdb9250a34052c19ac98847373030 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 2 Dec 2009 22:31:19 +0000 Subject: tcp: connect() race with timewait reuse Its currently possible that several threads issuing a connect() find the same timewait socket and try to reuse it, leading to list corruptions. Condition for bug is that these threads bound their socket on same address/port of to-be-find timewait socket, and connected to same target. (SO_REUSEADDR needed) To fix this problem, we could unhash timewait socket while holding ehash lock, to make sure lookups/changes will be serialized. Only first thread finds the timewait socket, other ones find the established socket and return an EADDRNOTAVAIL error. This second version takes into account Evgeniy's review and makes sure inet_twsk_put() is called outside of locked sections. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 4fd007f34dd..b801ade2295 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -199,6 +199,8 @@ static inline __be32 inet_rcv_saddr(const struct sock *sk) extern void inet_twsk_put(struct inet_timewait_sock *tw); +extern int inet_twsk_unhash(struct inet_timewait_sock *tw); + extern struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int state); -- cgit v1.2.3 From af901ca181d92aac3a7dc265144a9081a86d8f39 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Goddard=20Rosa?= Date: Sat, 14 Nov 2009 13:09:05 -0200 Subject: tree-wide: fix assorted typos all over the place MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit That is "success", "unknown", "through", "performance", "[re|un]mapping" , "access", "default", "reasonable", "[con]currently", "temperature" , "channel", "[un]used", "application", "example","hierarchy", "therefore" , "[over|under]flow", "contiguous", "threshold", "enough" and others. Signed-off-by: André Goddard Rosa Signed-off-by: Jiri Kosina --- include/net/sctp/structs.h | 2 +- include/net/tcp.h | 2 +- include/net/wimax.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 6e5f0e0c796..ca4789e4f1e 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -988,7 +988,7 @@ struct sctp_transport { int init_sent_count; /* state : The current state of this destination, - * : i.e. SCTP_ACTIVE, SCTP_INACTIVE, SCTP_UNKOWN. + * : i.e. SCTP_ACTIVE, SCTP_INACTIVE, SCTP_UNKNOWN. */ int state; diff --git a/include/net/tcp.h b/include/net/tcp.h index 03a49c70337..1827e7f217d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1260,7 +1260,7 @@ static inline struct sk_buff *tcp_write_queue_prev(struct sock *sk, struct sk_bu skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) /* This function calculates a "timeout" which is equivalent to the timeout of a - * TCP connection after "boundary" unsucessful, exponentially backed-off + * TCP connection after "boundary" unsuccessful, exponentially backed-off * retransmissions with an initial RTO of TCP_RTO_MIN. */ static inline bool retransmits_timed_out(const struct sock *sk, diff --git a/include/net/wimax.h b/include/net/wimax.h index 2af7bf839f2..3b07f6aad10 100644 --- a/include/net/wimax.h +++ b/include/net/wimax.h @@ -79,7 +79,7 @@ * drivers have to only report state changes due to external * conditions. * - * All API operations are 'atomic', serialized thorough a mutex in the + * All API operations are 'atomic', serialized through a mutex in the * `struct wimax_dev`. * * EXPORTING TO USER SPACE THROUGH GENERIC NETLINK -- cgit v1.2.3 From 9327f7053e3993c125944fdb137a0618319ef2a0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Dec 2009 03:46:54 +0000 Subject: tcp: Fix a connect() race with timewait sockets First patch changes __inet_hash_nolisten() and __inet6_hash() to get a timewait parameter to be able to unhash it from ehash at same time the new socket is inserted in hash. This makes sure timewait socket wont be found by a concurrent writer in __inet_check_established() Reported-by: kapil dakhane Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_hashtables.h | 2 +- include/net/inet_hashtables.h | 8 +++++--- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 92838d3a1ab..e46674d5dae 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -53,7 +53,7 @@ static inline int inet6_sk_ehashfn(const struct sock *sk) return inet6_ehashfn(net, laddr, lport, faddr, fport); } -extern void __inet6_hash(struct sock *sk); +extern int __inet6_hash(struct sock *sk, struct inet_timewait_sock *twp); /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 41cbddd25b7..74358d1b3f4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -251,7 +251,7 @@ extern void inet_put_port(struct sock *sk); void inet_hashinfo_init(struct inet_hashinfo *h); -extern void __inet_hash_nolisten(struct sock *sk); +extern int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw); extern void inet_hash(struct sock *sk); extern void inet_unhash(struct sock *sk); @@ -391,10 +391,12 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, } extern int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, + u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **), - void (*hash)(struct sock *sk)); + int (*hash)(struct sock *sk, struct inet_timewait_sock *twp)); + extern int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); #endif /* _INET_HASHTABLES_H */ -- cgit v1.2.3 From 3cdaedae635b17ce23c738ce7d364b442310cdec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Dec 2009 03:47:42 +0000 Subject: tcp: Fix a connect() race with timewait sockets When we find a timewait connection in __inet_hash_connect() and reuse it for a new connection request, we have a race window, releasing bind list lock and reacquiring it in __inet_twsk_kill() to remove timewait socket from list. Another thread might find the timewait socket we already chose, leading to list corruption and crashes. Fix is to remove timewait socket from bind list before releasing the bind lock. Note: This problem happens if sysctl_tcp_tw_reuse is set. Reported-by: kapil dakhane Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index b801ade2295..79f67eae8a7 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -201,6 +201,9 @@ extern void inet_twsk_put(struct inet_timewait_sock *tw); extern int inet_twsk_unhash(struct inet_timewait_sock *tw); +extern int inet_twsk_bind_unhash(struct inet_timewait_sock *tw, + struct inet_hashinfo *hashinfo); + extern struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int state); -- cgit v1.2.3 From 07f29bc5bbae4e53e982ab956fed7207990a7786 Mon Sep 17 00:00:00 2001 From: Damian Lukowski Date: Mon, 7 Dec 2009 06:06:15 +0000 Subject: tcp: Stalling connections: Fix timeout calculation routine MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes a problem in the TCP connection timeout calculation. Currently, timeout decisions are made on the basis of the current tcp_time_stamp and retrans_stamp, which is usually set at the first retransmission. However, if the retransmission fails in tcp_retransmit_skb(), retrans_stamp is not updated and remains zero. This leads to wrong decisions in retransmits_timed_out() if tcp_time_stamp is larger than the specified timeout, which is very likely. In this case, the TCP connection dies after the first attempted (and unsuccessful) retransmission. With this patch, tcp_skb_cb->when is used instead, when retrans_stamp is not available. This bug has been introduced together with retransmits_timed_out() in 2.6.32, as the number of retransmissions has been used for timeout decisions before. The corresponding commit was 6fa12c85031485dff38ce550c24f10da23b0adaa (Revert Backoff [v3]: Calculate TCP's connection close threshold as a time value.). Thanks to Ilpo Järvinen for code suggestions and Frederic Leroy for testing. Reported-by: Frederic Leroy Signed-off-by: Damian Lukowski Acked-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index e2d2ca2509b..e54bd85d9d4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1265,14 +1265,20 @@ static inline struct sk_buff *tcp_write_queue_prev(struct sock *sk, struct sk_bu * TCP connection after "boundary" unsucessful, exponentially backed-off * retransmissions with an initial RTO of TCP_RTO_MIN. */ -static inline bool retransmits_timed_out(const struct sock *sk, +static inline bool retransmits_timed_out(struct sock *sk, unsigned int boundary) { unsigned int timeout, linear_backoff_thresh; + unsigned int start_ts; if (!inet_csk(sk)->icsk_retransmits) return false; + if (unlikely(!tcp_sk(sk)->retrans_stamp)) + start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when; + else + start_ts = tcp_sk(sk)->retrans_stamp; + linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN); if (boundary <= linear_backoff_thresh) @@ -1281,7 +1287,7 @@ static inline bool retransmits_timed_out(const struct sock *sk, timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; - return (tcp_time_stamp - tcp_sk(sk)->retrans_stamp) >= timeout; + return (tcp_time_stamp - start_ts) >= timeout; } static inline struct sk_buff *tcp_send_head(struct sock *sk) -- cgit v1.2.3 From 2f7de5710a4d394920405febc2a9937c69e16dda Mon Sep 17 00:00:00 2001 From: Damian Lukowski Date: Mon, 7 Dec 2009 06:06:16 +0000 Subject: tcp: Stalling connections: Move timeout calculation routine MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch moves retransmits_timed_out() from include/net/tcp.h to tcp_timer.c, where it is used. Reported-by: Frederic Leroy Signed-off-by: Damian Lukowski Acked-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 28 ---------------------------- 1 file changed, 28 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index e54bd85d9d4..0248c181a92 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1261,34 +1261,6 @@ static inline struct sk_buff *tcp_write_queue_prev(struct sock *sk, struct sk_bu #define tcp_for_write_queue_from_safe(skb, tmp, sk) \ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) -/* This function calculates a "timeout" which is equivalent to the timeout of a - * TCP connection after "boundary" unsucessful, exponentially backed-off - * retransmissions with an initial RTO of TCP_RTO_MIN. - */ -static inline bool retransmits_timed_out(struct sock *sk, - unsigned int boundary) -{ - unsigned int timeout, linear_backoff_thresh; - unsigned int start_ts; - - if (!inet_csk(sk)->icsk_retransmits) - return false; - - if (unlikely(!tcp_sk(sk)->retrans_stamp)) - start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when; - else - start_ts = tcp_sk(sk)->retrans_stamp; - - linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN); - - if (boundary <= linear_backoff_thresh) - timeout = ((2 << boundary) - 1) * TCP_RTO_MIN; - else - timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN + - (boundary - linear_backoff_thresh) * TCP_RTO_MAX; - - return (tcp_time_stamp - start_ts) >= timeout; -} static inline struct sk_buff *tcp_send_head(struct sock *sk) { -- cgit v1.2.3 From 60c2ffd3d2cf12008747d920ae118df119006003 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 9 Dec 2009 20:58:16 +0000 Subject: net: fix compat_sys_recvmmsg parameter type compat_sys_recvmmsg has a compat_timespec parameter and not a timespec parameter. This way we also get rid of an odd cast. Cc: Arnaldo Carvalho de Melo Signed-off-by: Heiko Carstens Acked-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/net/compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/compat.h b/include/net/compat.h index 3c7d4e38fa1..28d5428ec6a 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -46,7 +46,7 @@ extern asmlinkage long compat_sys_sendmsg(int,struct compat_msghdr __user *,unsi extern asmlinkage long compat_sys_recvmsg(int,struct compat_msghdr __user *,unsigned); extern asmlinkage long compat_sys_recvmmsg(int, struct compat_mmsghdr __user *, unsigned, unsigned, - struct timespec __user *); + struct compat_timespec __user *); extern asmlinkage long compat_sys_getsockopt(int, int, int, char __user *, int __user *); extern int put_cmsg_compat(struct msghdr*, int, int, int, void *); -- cgit v1.2.3 From 0b5ccb2ee250136dd7385b1c7da28417d0d4d32d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 15 Dec 2009 16:59:18 +0100 Subject: ipv6: reassembly: use seperate reassembly queues for conntrack and local delivery Currently the same reassembly queue might be used for packets reassembled by conntrack in different positions in the stack (PREROUTING/LOCAL_OUT), as well as local delivery. This can cause "packet jumps" when the fragment completing a reassembled packet is queued from a different position in the stack than the previous ones. Add a "user" identifier to the reassembly queue key to seperate the queues of each caller, similar to what we do for IPv4. Signed-off-by: Patrick McHardy --- include/net/ipv6.h | 7 +++++++ include/net/netfilter/ipv6/nf_conntrack_ipv6.h | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 92db8617d18..d6916035bce 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -350,8 +350,15 @@ static inline int ipv6_prefix_equal(const struct in6_addr *a1, struct inet_frag_queue; +enum ip6_defrag_users { + IP6_DEFRAG_LOCAL_DELIVER, + IP6_DEFRAG_CONNTRACK_IN, + IP6_DEFRAG_CONNTRACK_OUT, +}; + struct ip6_create_arg { __be32 id; + u32 user; struct in6_addr *src; struct in6_addr *dst; }; diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h index abc55ad75c2..1ee717eb5b0 100644 --- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h +++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h @@ -9,7 +9,7 @@ extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6; extern int nf_ct_frag6_init(void); extern void nf_ct_frag6_cleanup(void); -extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb); +extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user); extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, struct net_device *in, struct net_device *out, -- cgit v1.2.3 From 8fa9ff6849bb86c59cc2ea9faadf3cb2d5223497 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 15 Dec 2009 16:59:59 +0100 Subject: netfilter: fix crashes in bridge netfilter caused by fragment jumps When fragments from bridge netfilter are passed to IPv4 or IPv6 conntrack and a reassembly queue with the same fragment key already exists from reassembling a similar packet received on a different device (f.i. with multicasted fragments), the reassembled packet might continue on a different codepath than where the head fragment originated. This can cause crashes in bridge netfilter when a fragment received on a non-bridge device (and thus with skb->nf_bridge == NULL) continues through the bridge netfilter code. Add a new reassembly identifier for packets originating from bridge netfilter and use it to put those packets in insolated queues. Fixes http://bugzilla.kernel.org/show_bug.cgi?id=14805 Reported-and-Tested-by: Chong Qiao Signed-off-by: Patrick McHardy --- include/net/ip.h | 1 + include/net/ipv6.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/ip.h b/include/net/ip.h index e6b9d12d5f6..85108cfbb1a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -337,6 +337,7 @@ enum ip_defrag_users { IP_DEFRAG_CALL_RA_CHAIN, IP_DEFRAG_CONNTRACK_IN, IP_DEFRAG_CONNTRACK_OUT, + IP_DEFRAG_CONNTRACK_BRIDGE_IN, IP_DEFRAG_VS_IN, IP_DEFRAG_VS_OUT, IP_DEFRAG_VS_FWD diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d6916035bce..ccab5946c83 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -354,6 +354,7 @@ enum ip6_defrag_users { IP6_DEFRAG_LOCAL_DELIVER, IP6_DEFRAG_CONNTRACK_IN, IP6_DEFRAG_CONNTRACK_OUT, + IP6_DEFRAG_CONNTRACK_BRIDGE_IN, }; struct ip6_create_arg { -- cgit v1.2.3 From bb5b7c11263dbbe78253cd05945a6bf8f55add8e Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 15 Dec 2009 20:56:42 -0800 Subject: tcp: Revert per-route SACK/DSACK/TIMESTAMP changes. It creates a regression, triggering badness for SYN_RECV sockets, for example: [19148.022102] Badness at net/ipv4/inet_connection_sock.c:293 [19148.022570] NIP: c02a0914 LR: c02a0904 CTR: 00000000 [19148.023035] REGS: eeecbd30 TRAP: 0700 Not tainted (2.6.32) [19148.023496] MSR: 00029032 CR: 24002442 XER: 00000000 [19148.024012] TASK = eee9a820[1756] 'privoxy' THREAD: eeeca000 This is likely caused by the change in the 'estab' parameter passed to tcp_parse_options() when invoked by the functions in net/ipv4/tcp_minisocks.c But even if that is fixed, the ->conn_request() changes made in this patch series is fundamentally wrong. They try to use the listening socket's 'dst' to probe the route settings. The listening socket doesn't even have a route, and you can't get the right route (the child request one) until much later after we setup all of the state, and it must be done by hand. This stuff really isn't ready, so the best thing to do is a full revert. This reverts the following commits: f55017a93f1a74d50244b1254b9a2bd7ac9bbf7d 022c3f7d82f0f1c68018696f2f027b87b9bb45c2 1aba721eba1d84a2defce45b950272cee1e6c72a cda42ebd67ee5fdf09d7057b5a4584d36fe8a335 345cda2fd695534be5a4494f1b59da9daed33663 dc343475ed062e13fc260acccaab91d7d80fd5b2 05eaade2782fb0c90d3034fd7a7d5a16266182bb 6a2a2d6bf8581216e08be15fcb563cfd6c430e1e Signed-off-by: David S. Miller --- include/net/dst.h | 2 +- include/net/tcp.h | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 387cb3cfde7..39c4a5963e1 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -113,7 +113,7 @@ dst_metric(const struct dst_entry *dst, int metric) static inline u32 dst_feature(const struct dst_entry *dst, u32 feature) { - return (dst ? dst_metric(dst, RTAX_FEATURES) & feature : 0); + return dst_metric(dst, RTAX_FEATURES) & feature; } static inline u32 dst_mtu(const struct dst_entry *dst) diff --git a/include/net/tcp.h b/include/net/tcp.h index 1b6f7d348ce..34f5cc24d90 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -408,8 +408,7 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, extern void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, u8 **hvpp, - int estab, - struct dst_entry *dst); + int estab); extern u8 *tcp_parse_md5sig_option(struct tcphdr *th); -- cgit v1.2.3