diff options
Diffstat (limited to 'net')
47 files changed, 496 insertions, 309 deletions
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index c32d27af0a3f..7b214cffc956 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -23,7 +23,7 @@ #include <linux/errno.h> /* return codes */ #include <linux/kernel.h> #include <linux/slab.h> /* kmalloc(), kfree() */ -#include <linux/mm.h> /* verify_area(), etc. */ +#include <linux/mm.h> #include <linux/string.h> /* inline mem*, str* functions */ #include <linux/init.h> /* __initfunc et al. */ #include <asm/byteorder.h> /* htons(), etc. */ diff --git a/net/atm/common.c b/net/atm/common.c index 6d16be334ea0..e93e838069e8 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -12,7 +12,7 @@ #include <linux/socket.h> /* SOL_SOCKET */ #include <linux/errno.h> /* error codes */ #include <linux/capability.h> -#include <linux/mm.h> /* verify_area */ +#include <linux/mm.h> #include <linux/sched.h> #include <linux/time.h> /* struct timeval */ #include <linux/skbuff.h> @@ -540,7 +540,7 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, error = -EMSGSIZE; goto out; } - /* verify_area is done by net/socket.c */ + eff = (size+3) & ~3; /* align to word boundary */ prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); error = 0; diff --git a/net/core/datagram.c b/net/core/datagram.c index d1bfd279cc1a..fcee054b6f75 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -115,10 +115,10 @@ out_noerr: /** * skb_recv_datagram - Receive a datagram skbuff - * @sk - socket - * @flags - MSG_ flags - * @noblock - blocking operation? - * @err - error code returned + * @sk: socket + * @flags: MSG_ flags + * @noblock: blocking operation? + * @err: error code returned * * Get a datagram skbuff, understands the peeking, nonblocking wakeups * and possible races. This replaces identical code in packet, raw and @@ -201,10 +201,10 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb) /** * skb_copy_datagram_iovec - Copy a datagram to an iovec. - * @skb - buffer to copy - * @offset - offset in the buffer to start copying from - * @iovec - io vector to copy to - * @len - amount of data to copy from buffer to iovec + * @skb: buffer to copy + * @offset: offset in the buffer to start copying from + * @to: io vector to copy to + * @len: amount of data to copy from buffer to iovec * * Note: the iovec is modified during the copy. */ @@ -377,9 +377,9 @@ fault: /** * skb_copy_and_csum_datagram_iovec - Copy and checkum skb to user iovec. - * @skb - skbuff - * @hlen - hardware length - * @iovec - io vector + * @skb: skbuff + * @hlen: hardware length + * @iov: io vector * * Caller _must_ check that skb will fit to this iovec. * @@ -425,9 +425,9 @@ fault: /** * datagram_poll - generic datagram poll - * @file - file struct - * @sock - socket - * @wait - poll table + * @file: file struct + * @sock: socket + * @wait: poll table * * Datagram poll: Again totally generic. This also handles * sequenced packet sockets providing the socket receive queue diff --git a/net/core/dev.c b/net/core/dev.c index 7bd4cd4502c4..f5f005846fe1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3091,7 +3091,7 @@ void free_netdev(struct net_device *dev) void synchronize_net(void) { might_sleep(); - synchronize_kernel(); + synchronize_rcu(); } /** diff --git a/net/core/iovec.c b/net/core/iovec.c index d57ace949ab8..65e4b56fbc77 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -33,7 +33,7 @@ * Verify iovec. The caller must ensure that the iovec is big enough * to hold the message iovec. * - * Save time not doing verify_area. copy_*_user will make this work + * Save time not doing access_ok. copy_*_user will make this work * in any case. */ diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 4859b7446c6f..d43d1201275c 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -16,6 +16,7 @@ #include <linux/netdevice.h> #include <linux/if.h> #include <net/sock.h> +#include <net/pkt_sched.h> #include <linux/rtnetlink.h> #include <linux/jiffies.h> #include <linux/spinlock.h> @@ -74,6 +75,12 @@ void linkwatch_run_queue(void) clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); if (dev->flags & IFF_UP) { + if (netif_carrier_ok(dev)) { + WARN_ON(dev->qdisc_sleeping == &noop_qdisc); + dev_activate(dev); + } else + dev_deactivate(dev); + netdev_state_change(dev); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 0a2f67bbef2e..43bdc521e20d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1953,7 +1953,7 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { - seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs forced_gc_goal_miss\n"); + seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs\n"); return 0; } diff --git a/net/core/netfilter.c b/net/core/netfilter.c index e51cfa46950c..22a8f127c4aa 100644 --- a/net/core/netfilter.c +++ b/net/core/netfilter.c @@ -217,21 +217,10 @@ void nf_debug_ip_local_deliver(struct sk_buff *skb) * NF_IP_RAW_INPUT and NF_IP_PRE_ROUTING. */ if (!skb->dev) { printk("ip_local_deliver: skb->dev is NULL.\n"); - } - else if (strcmp(skb->dev->name, "lo") == 0) { - if (skb->nf_debug != ((1 << NF_IP_LOCAL_OUT) - | (1 << NF_IP_POST_ROUTING) - | (1 << NF_IP_PRE_ROUTING) - | (1 << NF_IP_LOCAL_IN))) { - printk("ip_local_deliver: bad loopback skb: "); - debug_print_hooks_ip(skb->nf_debug); - nf_dump_skb(PF_INET, skb); - } - } - else { + } else { if (skb->nf_debug != ((1<<NF_IP_PRE_ROUTING) | (1<<NF_IP_LOCAL_IN))) { - printk("ip_local_deliver: bad non-lo skb: "); + printk("ip_local_deliver: bad skb: "); debug_print_hooks_ip(skb->nf_debug); nf_dump_skb(PF_INET, skb); } @@ -247,8 +236,6 @@ void nf_debug_ip_loopback_xmit(struct sk_buff *newskb) debug_print_hooks_ip(newskb->nf_debug); nf_dump_skb(PF_INET, newskb); } - /* Clear to avoid confusing input check */ - newskb->nf_debug = 0; } void nf_debug_ip_finish_output2(struct sk_buff *skb) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d8c198e42f90..00caf4b318b2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -86,30 +86,33 @@ struct sock *rtnl; struct rtnetlink_link * rtnetlink_links[NPROTO]; -static const int rtm_min[(RTM_MAX+1-RTM_BASE)/4] = +static const int rtm_min[RTM_NR_FAMILIES] = { - NLMSG_LENGTH(sizeof(struct ifinfomsg)), - NLMSG_LENGTH(sizeof(struct ifaddrmsg)), - NLMSG_LENGTH(sizeof(struct rtmsg)), - NLMSG_LENGTH(sizeof(struct ndmsg)), - NLMSG_LENGTH(sizeof(struct rtmsg)), - NLMSG_LENGTH(sizeof(struct tcmsg)), - NLMSG_LENGTH(sizeof(struct tcmsg)), - NLMSG_LENGTH(sizeof(struct tcmsg)), - NLMSG_LENGTH(sizeof(struct tcamsg)) + [RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)), + [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), + [RTM_FAM(RTM_NEWNEIGH)] = NLMSG_LENGTH(sizeof(struct ndmsg)), + [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), + [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)), + [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)), + [RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)), + [RTM_FAM(RTM_NEWACTION)] = NLMSG_LENGTH(sizeof(struct tcamsg)), + [RTM_FAM(RTM_NEWPREFIX)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), + [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), + [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), }; -static const int rta_max[(RTM_MAX+1-RTM_BASE)/4] = +static const int rta_max[RTM_NR_FAMILIES] = { - IFLA_MAX, - IFA_MAX, - RTA_MAX, - NDA_MAX, - RTA_MAX, - TCA_MAX, - TCA_MAX, - TCA_MAX, - TCAA_MAX + [RTM_FAM(RTM_NEWLINK)] = IFLA_MAX, + [RTM_FAM(RTM_NEWADDR)] = IFA_MAX, + [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX, + [RTM_FAM(RTM_NEWNEIGH)] = NDA_MAX, + [RTM_FAM(RTM_NEWRULE)] = RTA_MAX, + [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX, + [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, + [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, + [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, }; void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) @@ -606,27 +609,33 @@ static inline int rtnetlink_rcv_skb(struct sk_buff *skb) /* * rtnetlink input queue processing routine: - * - try to acquire shared lock. If it is failed, defer processing. + * - process as much as there was in the queue upon entry. * - feed skbs to rtnetlink_rcv_skb, until it refuse a message, - * that will occur, when a dump started and/or acquisition of - * exclusive lock failed. + * that will occur, when a dump started. */ static void rtnetlink_rcv(struct sock *sk, int len) { + unsigned int qlen = skb_queue_len(&sk->sk_receive_queue); + do { struct sk_buff *skb; - if (rtnl_shlock_nowait()) - return; + rtnl_lock(); + + if (qlen > skb_queue_len(&sk->sk_receive_queue)) + qlen = skb_queue_len(&sk->sk_receive_queue); - while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { + for (; qlen; qlen--) { + skb = skb_dequeue(&sk->sk_receive_queue); if (rtnetlink_rcv_skb(skb)) { if (skb->len) skb_queue_head(&sk->sk_receive_queue, skb); - else + else { kfree_skb(skb); + qlen--; + } break; } kfree_skb(skb); @@ -635,10 +644,10 @@ static void rtnetlink_rcv(struct sock *sk, int len) up(&rtnl_sem); netdev_run_todo(); - } while (rtnl && rtnl->sk_receive_queue.qlen); + } while (qlen); } -static struct rtnetlink_link link_rtnetlink_table[RTM_MAX-RTM_BASE+1] = +static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = { [RTM_GETLINK - RTM_BASE] = { .dumpit = rtnetlink_dump_ifinfo }, [RTM_SETLINK - RTM_BASE] = { .doit = do_setlink }, diff --git a/net/core/sock.c b/net/core/sock.c index 5c2f72fa1013..98171ddd7e7d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -616,10 +616,10 @@ lenout: /** * sk_alloc - All socket objects are allocated here - * @family - protocol family - * @priority - for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) - * @prot - struct proto associated with this new sock instance - * @zero_it - if we should zero the newly allocated sock + * @family: protocol family + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * @prot: struct proto associated with this new sock instance + * @zero_it: if we should zero the newly allocated sock */ struct sock *sk_alloc(int family, int priority, struct proto *prot, int zero_it) { @@ -970,8 +970,8 @@ static void __release_sock(struct sock *sk) /** * sk_wait_data - wait for data to arrive at sk_receive_queue - * sk - sock to wait on - * timeo - for how long + * @sk: sock to wait on + * @timeo: for how long * * Now socket state including sk->sk_err is changed only under lock, * hence we may omit checks after joining wait queue. diff --git a/net/core/stream.c b/net/core/stream.c index 1e27a57b5a97..ac9edfdf8742 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -21,7 +21,7 @@ /** * sk_stream_write_space - stream socket write_space callback. - * sk - socket + * @sk: socket * * FIXME: write proper description */ @@ -43,8 +43,8 @@ EXPORT_SYMBOL(sk_stream_write_space); /** * sk_stream_wait_connect - Wait for a socket to get into the connected state - * @sk - sock to wait on - * @timeo_p - for how long to wait + * @sk: sock to wait on + * @timeo_p: for how long to wait * * Must be called with the socket locked. */ @@ -79,7 +79,7 @@ EXPORT_SYMBOL(sk_stream_wait_connect); /** * sk_stream_closing - Return 1 if we still have things to send in our buffers. - * @sk - socket to verify + * @sk: socket to verify */ static inline int sk_stream_closing(struct sock *sk) { @@ -107,8 +107,8 @@ EXPORT_SYMBOL(sk_stream_wait_close); /** * sk_stream_wait_memory - Wait for more memory for a socket - * @sk - socket to wait for memory - * @timeo_p - for how long + * @sk: socket to wait for memory + * @timeo_p: for how long */ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) { diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index c2a0346f423b..e6e23eb14428 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1411,21 +1411,22 @@ static struct file_operations dn_dev_seq_fops = { #endif /* CONFIG_PROC_FS */ -static struct rtnetlink_link dnet_rtnetlink_table[RTM_MAX-RTM_BASE+1] = +static struct rtnetlink_link dnet_rtnetlink_table[RTM_NR_MSGTYPES] = { - [4] = { .doit = dn_dev_rtm_newaddr, }, - [5] = { .doit = dn_dev_rtm_deladdr, }, - [6] = { .dumpit = dn_dev_dump_ifaddr, }, - + [RTM_NEWADDR - RTM_BASE] = { .doit = dn_dev_rtm_newaddr, }, + [RTM_DELADDR - RTM_BASE] = { .doit = dn_dev_rtm_deladdr, }, + [RTM_GETADDR - RTM_BASE] = { .dumpit = dn_dev_dump_ifaddr, }, #ifdef CONFIG_DECNET_ROUTER - [8] = { .doit = dn_fib_rtm_newroute, }, - [9] = { .doit = dn_fib_rtm_delroute, }, - [10] = { .doit = dn_cache_getroute, .dumpit = dn_fib_dump, }, - [16] = { .doit = dn_fib_rtm_newrule, }, - [17] = { .doit = dn_fib_rtm_delrule, }, - [18] = { .dumpit = dn_fib_dump_rules, }, + [RTM_NEWROUTE - RTM_BASE] = { .doit = dn_fib_rtm_newroute, }, + [RTM_DELROUTE - RTM_BASE] = { .doit = dn_fib_rtm_delroute, }, + [RTM_GETROUTE - RTM_BASE] = { .doit = dn_cache_getroute, + .dumpit = dn_fib_dump, }, + [RTM_NEWRULE - RTM_BASE] = { .doit = dn_fib_rtm_newrule, }, + [RTM_DELRULE - RTM_BASE] = { .doit = dn_fib_rtm_delrule, }, + [RTM_GETRULE - RTM_BASE] = { .dumpit = dn_fib_dump_rules, }, #else - [10] = { .doit = dn_cache_getroute, .dumpit = dn_cache_dump, }, + [RTM_GETROUTE - RTM_BASE] = { .doit = dn_cache_getroute, + .dumpit = dn_cache_dump, #endif }; diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index f86a6259fd12..284a9998e53d 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -119,8 +119,9 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb) static void dnrmg_receive_user_sk(struct sock *sk, int len) { struct sk_buff *skb; + unsigned int qlen = skb_queue_len(&sk->sk_receive_queue); - while((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { + for (; qlen && (skb = skb_dequeue(&sk->sk_receive_queue)); qlen--) { dnrmg_receive_user_skb(skb); kfree_skb(skb); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index eea7ef010776..abbc6d5c183e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1107,17 +1107,18 @@ static void rtmsg_ifa(int event, struct in_ifaddr* ifa) } } -static struct rtnetlink_link inet_rtnetlink_table[RTM_MAX - RTM_BASE + 1] = { - [4] = { .doit = inet_rtm_newaddr, }, - [5] = { .doit = inet_rtm_deladdr, }, - [6] = { .dumpit = inet_dump_ifaddr, }, - [8] = { .doit = inet_rtm_newroute, }, - [9] = { .doit = inet_rtm_delroute, }, - [10] = { .doit = inet_rtm_getroute, .dumpit = inet_dump_fib, }, +static struct rtnetlink_link inet_rtnetlink_table[RTM_NR_MSGTYPES] = { + [RTM_NEWADDR - RTM_BASE] = { .doit = inet_rtm_newaddr, }, + [RTM_DELADDR - RTM_BASE] = { .doit = inet_rtm_deladdr, }, + [RTM_GETADDR - RTM_BASE] = { .dumpit = inet_dump_ifaddr, }, + [RTM_NEWROUTE - RTM_BASE] = { .doit = inet_rtm_newroute, }, + [RTM_DELROUTE - RTM_BASE] = { .doit = inet_rtm_delroute, }, + [RTM_GETROUTE - RTM_BASE] = { .doit = inet_rtm_getroute, + .dumpit = inet_dump_fib, }, #ifdef CONFIG_IP_MULTIPLE_TABLES - [16] = { .doit = inet_rtm_newrule, }, - [17] = { .doit = inet_rtm_delrule, }, - [18] = { .dumpit = inet_dump_rules, }, + [RTM_NEWRULE - RTM_BASE] = { .doit = inet_rtm_newrule, }, + [RTM_DELRULE - RTM_BASE] = { .doit = inet_rtm_delrule, }, + [RTM_GETRULE - RTM_BASE] = { .dumpit = inet_dump_rules, }, #endif }; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 38f69532a029..24fe3e00b42b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -111,6 +111,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb) #ifdef CONFIG_NETFILTER_DEBUG nf_debug_ip_loopback_xmit(newskb); #endif + nf_reset(newskb); netif_rx(newskb); return 0; } diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c index 2b87c1974be6..721ddbf522b4 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c @@ -819,6 +819,7 @@ static int tcp_error(struct sk_buff *skb, */ /* FIXME: Source route IP option packets --RR */ if (hooknum == NF_IP_PRE_ROUTING + && skb->ip_summed != CHECKSUM_UNNECESSARY && csum_tcpudp_magic(iph->saddr, iph->daddr, tcplen, IPPROTO_TCP, skb->ip_summed == CHECKSUM_HW ? skb->csum : skb_checksum(skb, iph->ihl*4, tcplen, 0))) { diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index 9e40dffc204f..e5746b674413 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -546,20 +546,18 @@ ipq_rcv_skb(struct sk_buff *skb) static void ipq_rcv_sk(struct sock *sk, int len) { - do { - struct sk_buff *skb; + struct sk_buff *skb; + unsigned int qlen; - if (down_trylock(&ipqnl_sem)) - return; + down(&ipqnl_sem); - while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { - ipq_rcv_skb(skb); - kfree_skb(skb); - } + for (qlen = skb_queue_len(&sk->sk_receive_queue); qlen; qlen--) { + skb = skb_dequeue(&sk->sk_receive_queue); + ipq_rcv_skb(skb); + kfree_skb(skb); + } - up(&ipqnl_sem); - - } while (ipqnl && ipqnl->sk_receive_queue.qlen); + up(&ipqnl_sem); } static int diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 01b4a3c814d3..47449ba83eb9 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -103,13 +103,15 @@ static struct nf_hook_ops ipt_ops[] = { .hook = ipt_hook, .pf = PF_INET, .hooknum = NF_IP_PRE_ROUTING, - .priority = NF_IP_PRI_RAW + .priority = NF_IP_PRI_RAW, + .owner = THIS_MODULE, }, { .hook = ipt_hook, .pf = PF_INET, .hooknum = NF_IP_LOCAL_OUT, - .priority = NF_IP_PRI_RAW + .priority = NF_IP_PRI_RAW, + .owner = THIS_MODULE, }, }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bb90a0c3a91e..199311746932 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -397,7 +397,7 @@ static int rt_cpu_seq_show(struct seq_file *seq, void *v) struct rt_cache_stat *st = v; if (v == SEQ_START_TOKEN) { - seq_printf(seq, "entries in_hit in_slow_tot in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"); + seq_printf(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"); return 0; } @@ -2843,7 +2843,7 @@ ctl_table ipv4_route_table[] = { .procname = "flush", .data = &flush_delay, .maxlen = sizeof(int), - .mode = 0644, + .mode = 0200, .proc_handler = &ipv4_sysctl_rtcache_flush, .strategy = &ipv4_sysctl_rtcache_flush_strategy, }, diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 313c1408da33..8faa8948f75c 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -777,8 +777,9 @@ static inline void tcpdiag_rcv_skb(struct sk_buff *skb) static void tcpdiag_rcv(struct sock *sk, int len) { struct sk_buff *skb; + unsigned int qlen = skb_queue_len(&sk->sk_receive_queue); - while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { + while (qlen-- && (skb = skb_dequeue(&sk->sk_receive_queue))) { tcpdiag_rcv_skb(skb); kfree_skb(skb); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3ac6659869c4..dad98e4a5043 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -222,10 +222,13 @@ static int tcp_v4_get_port(struct sock *sk, unsigned short snum) int rover; spin_lock(&tcp_portalloc_lock); - rover = tcp_port_rover; + if (tcp_port_rover < low) + rover = low; + else + rover = tcp_port_rover; do { rover++; - if (rover < low || rover > high) + if (rover > high) rover = low; head = &tcp_bhash[tcp_bhashfn(rover)]; spin_lock(&head->lock); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 7fe2afd2e669..b2b60f3e9cdd 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -8,7 +8,10 @@ * */ +#include <asm/bug.h> +#include <linux/compiler.h> #include <linux/config.h> +#include <linux/inetdevice.h> #include <net/xfrm.h> #include <net/ip.h> @@ -152,6 +155,8 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int x->u.rt.rt_dst = rt0->rt_dst; x->u.rt.rt_gateway = rt->rt_gateway; x->u.rt.rt_spec_dst = rt0->rt_spec_dst; + x->u.rt.idev = rt0->idev; + in_dev_hold(rt0->idev); header_len -= x->u.dst.xfrm->props.header_len; trailer_len -= x->u.dst.xfrm->props.trailer_len; } @@ -243,11 +248,48 @@ static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu) path->ops->update_pmtu(path, mtu); } +static void xfrm4_dst_destroy(struct dst_entry *dst) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + + if (likely(xdst->u.rt.idev)) + in_dev_put(xdst->u.rt.idev); + xfrm_dst_destroy(xdst); +} + +static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, + int unregister) +{ + struct xfrm_dst *xdst; + + if (!unregister) + return; + + xdst = (struct xfrm_dst *)dst; + if (xdst->u.rt.idev->dev == dev) { + struct in_device *loopback_idev = in_dev_get(&loopback_dev); + BUG_ON(!loopback_idev); + + do { + in_dev_put(xdst->u.rt.idev); + xdst->u.rt.idev = loopback_idev; + in_dev_hold(loopback_idev); + xdst = (struct xfrm_dst *)xdst->u.dst.child; + } while (xdst->u.dst.xfrm); + + __in_dev_put(loopback_idev); + } + + xfrm_dst_ifdown(dst, dev); +} + static struct dst_ops xfrm4_dst_ops = { .family = AF_INET, .protocol = __constant_htons(ETH_P_IP), .gc = xfrm4_garbage_collect, .update_pmtu = xfrm4_update_pmtu, + .destroy = xfrm4_dst_destroy, + .ifdown = xfrm4_dst_ifdown, .gc_thresh = 1024, .entry_size = sizeof(struct xfrm_dst), }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 7196ac2f2d16..7744a2592693 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3076,7 +3076,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, netlink_broadcast(rtnl, skb, 0, RTMGRP_IPV6_PREFIX, GFP_ATOMIC); } -static struct rtnetlink_link inet6_rtnetlink_table[RTM_MAX - RTM_BASE + 1] = { +static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = { [RTM_GETLINK - RTM_BASE] = { .dumpit = inet6_dump_ifinfo, }, [RTM_NEWADDR - RTM_BASE] = { .doit = inet6_rtm_newaddr, }, [RTM_DELADDR - RTM_BASE] = { .doit = inet6_rtm_deladdr, }, diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index c54830b89593..750943e2d34e 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -549,20 +549,18 @@ ipq_rcv_skb(struct sk_buff *skb) static void ipq_rcv_sk(struct sock *sk, int len) { - do { - struct sk_buff *skb; + struct sk_buff *skb; + unsigned int qlen; - if (down_trylock(&ipqnl_sem)) - return; + down(&ipqnl_sem); - while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { - ipq_rcv_skb(skb); - kfree_skb(skb); - } + for (qlen = skb_queue_len(&sk->sk_receive_queue); qlen; qlen--) { + skb = skb_dequeue(&sk->sk_receive_queue); + ipq_rcv_skb(skb); + kfree_skb(skb); + } - up(&ipqnl_sem); - - } while (ipqnl && ipqnl->sk_receive_queue.qlen); + up(&ipqnl_sem); } static int diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 1352c1d9bf4d..617645bc5ed6 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -455,11 +455,11 @@ csum_copy_err: static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct raw6_sock *rp) { - struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; int err = 0; int offset; int len; + int total_len; u32 tmp_csum; u16 csum; @@ -470,7 +470,8 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, goto out; offset = rp->offset; - if (offset >= inet->cork.length - 1) { + total_len = inet_sk(sk)->cork.length - (skb->nh.raw - skb->data); + if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); goto out; @@ -514,7 +515,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl, tmp_csum = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst, - inet->cork.length, fl->proto, tmp_csum); + total_len, fl->proto, tmp_csum); if (tmp_csum == 0) tmp_csum = -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 183802902c02..3bf8a0254f81 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2005,7 +2005,7 @@ ctl_table ipv6_route_table[] = { .procname = "flush", .data = &flush_delay, .maxlen = sizeof(int), - .mode = 0644, + .mode = 0200, .proc_handler = &ipv6_sysctl_rtcache_flush }, { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4760c85e19db..0f69e800a0ad 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -139,9 +139,12 @@ static int tcp_v6_get_port(struct sock *sk, unsigned short snum) int rover; spin_lock(&tcp_portalloc_lock); - rover = tcp_port_rover; + if (tcp_port_rover < low) + rover = low; + else + rover = tcp_port_rover; do { rover++; - if ((rover < low) || (rover > high)) + if (rover > high) rover = low; head = &tcp_bhash[tcp_bhashfn(rover)]; spin_lock(&head->lock); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 8a4f37de4d2d..4429b1a1fe5f 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -11,7 +11,11 @@ * */ +#include <asm/bug.h> +#include <linux/compiler.h> #include <linux/config.h> +#include <linux/netdevice.h> +#include <net/addrconf.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/ipv6.h> @@ -166,6 +170,8 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int memcpy(&x->u.rt6.rt6i_gateway, &rt0->rt6i_gateway, sizeof(x->u.rt6.rt6i_gateway)); x->u.rt6.rt6i_dst = rt0->rt6i_dst; x->u.rt6.rt6i_src = rt0->rt6i_src; + x->u.rt6.rt6i_idev = rt0->rt6i_idev; + in6_dev_hold(rt0->rt6i_idev); header_len -= x->u.dst.xfrm->props.header_len; trailer_len -= x->u.dst.xfrm->props.trailer_len; } @@ -251,11 +257,48 @@ static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) path->ops->update_pmtu(path, mtu); } +static void xfrm6_dst_destroy(struct dst_entry *dst) +{ + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + + if (likely(xdst->u.rt6.rt6i_idev)) + in6_dev_put(xdst->u.rt6.rt6i_idev); + xfrm_dst_destroy(xdst); +} + +static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, + int unregister) +{ + struct xfrm_dst *xdst; + + if (!unregister) + return; + + xdst = (struct xfrm_dst *)dst; + if (xdst->u.rt6.rt6i_idev->dev == dev) { + struct inet6_dev *loopback_idev = in6_dev_get(&loopback_dev); + BUG_ON(!loopback_idev); + + do { + in6_dev_put(xdst->u.rt6.rt6i_idev); + xdst->u.rt6.rt6i_idev = loopback_idev; + in6_dev_hold(loopback_idev); + xdst = (struct xfrm_dst *)xdst->u.dst.child; + } while (xdst->u.dst.xfrm); + + __in6_dev_put(loopback_idev); + } + + xfrm_dst_ifdown(dst, dev); +} + static struct dst_ops xfrm6_dst_ops = { .family = AF_INET6, .protocol = __constant_htons(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, + .destroy = xfrm6_dst_destroy, + .ifdown = xfrm6_dst_ifdown, .gc_thresh = 1024, .entry_size = sizeof(struct xfrm_dst), }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 29a5fd231eac..4ee392066148 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -373,7 +373,6 @@ static int netlink_release(struct socket *sock) nlk->cb->done(nlk->cb); netlink_destroy_callback(nlk->cb); nlk->cb = NULL; - __sock_put(sk); } spin_unlock(&nlk->cb_lock); @@ -1099,7 +1098,6 @@ static int netlink_dump(struct sock *sk) spin_unlock(&nlk->cb_lock); netlink_destroy_callback(cb); - __sock_put(sk); return 0; } @@ -1138,7 +1136,6 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, return -EBUSY; } nlk->cb = cb; - sock_hold(sk); spin_unlock(&nlk->cb_lock); netlink_dump(sk); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 9c118baed9dc..b0941186f867 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -185,7 +185,7 @@ config NET_SCH_GRED depends on NET_SCHED help Say Y here if you want to use the Generic Random Early Detection - (RED) packet scheduling algorithm for some of your network devices + (GRED) packet scheduling algorithm for some of your network devices (see the top of <file:net/sched/sch_red.c> for details and references about the algorithm). diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 5e6cc371b39e..cafcb084098d 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -171,10 +171,10 @@ repeat: skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); skb->tc_verd = CLR_TC_MUNGED(skb->tc_verd); } - if (ret != TC_ACT_PIPE) - goto exec_done; if (ret == TC_ACT_REPEAT) goto repeat; /* we need a ttl - JHS */ + if (ret != TC_ACT_PIPE) + goto exec_done; } act = a->next; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 4323a74eea30..07977f8f2679 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1289,6 +1289,7 @@ static int __init pktsched_init(void) subsys_initcall(pktsched_init); +EXPORT_SYMBOL(qdisc_lookup); EXPORT_SYMBOL(qdisc_get_rtab); EXPORT_SYMBOL(qdisc_put_rtab); EXPORT_SYMBOL(register_qdisc); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 8c01e023f02e..87e48a4e1051 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -179,6 +179,7 @@ requeue: netif_schedule(dev); return 1; } + BUG_ON((int) q->q.qlen < 0); return q->q.qlen; } @@ -539,6 +540,10 @@ void dev_activate(struct net_device *dev) write_unlock_bh(&qdisc_tree_lock); } + if (!netif_carrier_ok(dev)) + /* Delay activation until next carrier-on event */ + return; + spin_lock_bh(&dev->queue_lock); rcu_assign_pointer(dev->qdisc, dev->qdisc_sleeping); if (dev->qdisc != &noqueue_qdisc) { diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index a85935e7d53d..558cc087e602 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -717,6 +717,10 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (q->direct_queue.qlen < q->direct_qlen) { __skb_queue_tail(&q->direct_queue, skb); q->direct_pkts++; + } else { + kfree_skb(skb); + sch->qstats.drops++; + return NET_XMIT_DROP; } #ifdef CONFIG_NET_CLS_ACT } else if (!cl) { diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 31c29deb139d..e0c9fbe73b15 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -138,38 +138,77 @@ static long tabledist(unsigned long mu, long sigma, } /* Put skb in the private delayed queue. */ -static int delay_skb(struct Qdisc *sch, struct sk_buff *skb) +static int netem_delay(struct Qdisc *sch, struct sk_buff *skb) { struct netem_sched_data *q = qdisc_priv(sch); - struct netem_skb_cb *cb = (struct netem_skb_cb *)skb->cb; psched_tdiff_t td; psched_time_t now; PSCHED_GET_TIME(now); td = tabledist(q->latency, q->jitter, &q->delay_cor, q->delay_dist); - PSCHED_TADD2(now, td, cb->time_to_send); /* Always queue at tail to keep packets in order */ if (likely(q->delayed.qlen < q->limit)) { + struct netem_skb_cb *cb = (struct netem_skb_cb *)skb->cb; + + PSCHED_TADD2(now, td, cb->time_to_send); + + pr_debug("netem_delay: skb=%p now=%llu tosend=%llu\n", skb, + now, cb->time_to_send); + __skb_queue_tail(&q->delayed, skb); - if (!timer_pending(&q->timer)) { - q->timer.expires = jiffies + PSCHED_US2JIFFIE(td); - add_timer(&q->timer); - } return NET_XMIT_SUCCESS; } + pr_debug("netem_delay: queue over limit %d\n", q->limit); + sch->qstats.overlimits++; kfree_skb(skb); return NET_XMIT_DROP; } +/* + * Move a packet that is ready to send from the delay holding + * list to the underlying qdisc. + */ +static int netem_run(struct Qdisc *sch) +{ + struct netem_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + psched_time_t now; + + PSCHED_GET_TIME(now); + + skb = skb_peek(&q->delayed); + if (skb) { + const struct netem_skb_cb *cb + = (const struct netem_skb_cb *)skb->cb; + long delay + = PSCHED_US2JIFFIE(PSCHED_TDIFF(cb->time_to_send, now)); + pr_debug("netem_run: skb=%p delay=%ld\n", skb, delay); + + /* if more time remaining? */ + if (delay > 0) { + mod_timer(&q->timer, jiffies + delay); + return 1; + } + + __skb_unlink(skb, &q->delayed); + + if (q->qdisc->enqueue(skb, q->qdisc)) { + sch->q.qlen--; + sch->qstats.drops++; + } + } + + return 0; +} + static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); - struct sk_buff *skb2; int ret; - pr_debug("netem_enqueue skb=%p @%lu\n", skb, jiffies); + pr_debug("netem_enqueue skb=%p\n", skb); /* Random packet drop 0 => none, ~0 => all */ if (q->loss && q->loss >= get_crandom(&q->loss_cor)) { @@ -180,11 +219,21 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) } /* Random duplication */ - if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor) - && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - pr_debug("netem_enqueue: dup %p\n", skb2); + if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) { + struct sk_buff *skb2; + + skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2 && netem_delay(sch, skb2) == NET_XMIT_SUCCESS) { + struct Qdisc *qp; + + /* Since one packet can generate two packets in the + * queue, the parent's qlen accounting gets confused, + * so fix it. + */ + qp = qdisc_lookup(sch->dev, TC_H_MAJ(sch->parent)); + if (qp) + qp->q.qlen++; - if (delay_skb(sch, skb2)) { sch->q.qlen++; sch->bstats.bytes += skb2->len; sch->bstats.packets++; @@ -202,7 +251,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = q->qdisc->enqueue(skb, q->qdisc); } else { q->counter = 0; - ret = delay_skb(sch, skb); + ret = netem_delay(sch, skb); + netem_run(sch); } if (likely(ret == NET_XMIT_SUCCESS)) { @@ -212,6 +262,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) } else sch->qstats.drops++; + pr_debug("netem: enqueue ret %d\n", ret); return ret; } @@ -241,56 +292,35 @@ static unsigned int netem_drop(struct Qdisc* sch) return len; } -/* Dequeue packet. - * Move all packets that are ready to send from the delay holding - * list to the underlying qdisc, then just call dequeue - */ static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; + int pending; + + pending = netem_run(sch); skb = q->qdisc->dequeue(q->qdisc); - if (skb) + if (skb) { + pr_debug("netem_dequeue: return skb=%p\n", skb); sch->q.qlen--; + sch->flags &= ~TCQ_F_THROTTLED; + } + else if (pending) { + pr_debug("netem_dequeue: throttling\n"); + sch->flags |= TCQ_F_THROTTLED; + } + return skb; } static void netem_watchdog(unsigned long arg) { struct Qdisc *sch = (struct Qdisc *)arg; - struct netem_sched_data *q = qdisc_priv(sch); - struct net_device *dev = sch->dev; - struct sk_buff *skb; - psched_time_t now; - - pr_debug("netem_watchdog: fired @%lu\n", jiffies); - - spin_lock_bh(&dev->queue_lock); - PSCHED_GET_TIME(now); - - while ((skb = skb_peek(&q->delayed)) != NULL) { - const struct netem_skb_cb *cb - = (const struct netem_skb_cb *)skb->cb; - long delay - = PSCHED_US2JIFFIE(PSCHED_TDIFF(cb->time_to_send, now)); - pr_debug("netem_watchdog: skb %p@%lu %ld\n", - skb, jiffies, delay); - /* if more time remaining? */ - if (delay > 0) { - mod_timer(&q->timer, jiffies + delay); - break; - } - __skb_unlink(skb, &q->delayed); - - if (q->qdisc->enqueue(skb, q->qdisc)) { - sch->q.qlen--; - sch->qstats.drops++; - } - } - qdisc_run(dev); - spin_unlock_bh(&dev->queue_lock); + pr_debug("netem_watchdog qlen=%d\n", sch->q.qlen); + sch->flags &= ~TCQ_F_THROTTLED; + netif_schedule(sch->dev); } static void netem_reset(struct Qdisc *sch) @@ -301,6 +331,7 @@ static void netem_reset(struct Qdisc *sch) skb_queue_purge(&q->delayed); sch->q.qlen = 0; + sch->flags &= ~TCQ_F_THROTTLED; del_timer_sync(&q->timer); } diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 544b75077dbd..334f61773e6d 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -125,6 +125,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, sp->autoclose * HZ; /* Use SCTP specific send buffer space queues. */ + ep->sndbuf_policy = sctp_sndbuf_policy; sk->sk_write_space = sctp_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e42c74e3ec1e..c9d9ea064734 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -496,9 +496,7 @@ static void sctp_v6_inaddr_any(union sctp_addr *addr, unsigned short port) /* Is this a wildcard address? */ static int sctp_v6_is_any(const union sctp_addr *addr) { - int type; - type = ipv6_addr_type((struct in6_addr *)&addr->v6.sin6_addr); - return IPV6_ADDR_ANY == type; + return ipv6_addr_any(&addr->v6.sin6_addr); } /* Should this be available for binding? */ diff --git a/net/sctp/output.c b/net/sctp/output.c index 9013f64f5219..84b5b370b09d 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -313,12 +313,12 @@ int sctp_packet_transmit(struct sctp_packet *packet) sk = chunk->skb->sk; /* Allocate the new skb. */ - nskb = dev_alloc_skb(packet->size); + nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) goto nomem; /* Make sure the outbound skb has enough header room reserved. */ - skb_reserve(nskb, packet->overhead); + skb_reserve(nskb, packet->overhead + LL_MAX_HEADER); /* Set the owning socket so that we know where to get the * destination IP address. diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index b9813cf3d91c..2e1f9c3556f5 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1043,6 +1043,9 @@ SCTP_STATIC __init int sctp_init(void) sctp_max_retrans_path = 5; sctp_max_retrans_init = 8; + /* Sendbuffer growth - do per-socket accounting */ + sctp_sndbuf_policy = 0; + /* HB.interval - 30 seconds */ sctp_hb_interval = 30 * HZ; @@ -1159,8 +1162,6 @@ SCTP_STATIC __init int sctp_init(void) status = 0; out: return status; -err_add_protocol: - proto_unregister(&sctp_prot); err_ctl_sock_init: sctp_v6_exit(); err_v6_init: @@ -1188,6 +1189,8 @@ err_bucket_cachep: inet_del_protocol(&sctp_protocol, IPPROTO_SCTP); inet_unregister_protosw(&sctp_seqpacket_protosw); inet_unregister_protosw(&sctp_stream_protosw); +err_add_protocol: + proto_unregister(&sctp_prot); goto out; } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 1db12cc18cf7..33ac8bf47b0e 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -710,7 +710,9 @@ struct sctp_chunk *sctp_make_shutdown_complete( struct sctp_chunk *retval; __u8 flags = 0; - /* Maybe set the T-bit if we have no association. */ + /* Set the T-bit if we have no association (vtag will be + * reflected) + */ flags |= asoc ? 0 : SCTP_CHUNK_FLAG_T; retval = sctp_make_chunk(asoc, SCTP_CID_SHUTDOWN_COMPLETE, flags, 0); @@ -732,7 +734,7 @@ struct sctp_chunk *sctp_make_shutdown_complete( } /* Create an ABORT. Note that we set the T bit if we have no - * association. + * association, except when responding to an INIT (sctpimpguide 2.41). */ struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, const struct sctp_chunk *chunk, @@ -741,8 +743,16 @@ struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, struct sctp_chunk *retval; __u8 flags = 0; - /* Maybe set the T-bit if we have no association. */ - flags |= asoc ? 0 : SCTP_CHUNK_FLAG_T; + /* Set the T-bit if we have no association and 'chunk' is not + * an INIT (vtag will be reflected). + */ + if (!asoc) { + if (chunk && chunk->chunk_hdr && + chunk->chunk_hdr->type == SCTP_CID_INIT) + flags = 0; + else + flags = SCTP_CHUNK_FLAG_T; + } retval = sctp_make_chunk(asoc, SCTP_CID_ABORT, flags, hint); @@ -2744,7 +2754,6 @@ struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc, hint = (nstreams + 1) * sizeof(__u32); - /* Maybe set the T-bit if we have no association. */ retval = sctp_make_chunk(asoc, SCTP_CID_FWD_TSN, 0, hint); if (!retval) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 278c56a2d076..8e01b8f09ac2 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -126,15 +126,18 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk, * should stop the T2-shutdown timer and remove all knowledge of the * association (and thus the association enters the CLOSED state). * - * Verification Tag: 8.5.1(C) + * Verification Tag: 8.5.1(C), sctpimpguide 2.41. * C) Rules for packet carrying SHUTDOWN COMPLETE: * ... - * - The receiver of a SHUTDOWN COMPLETE shall accept the packet if the - * Verification Tag field of the packet matches its own tag OR it is - * set to its peer's tag and the T bit is set in the Chunk Flags. - * Otherwise, the receiver MUST silently discard the packet and take - * no further action. An endpoint MUST ignore the SHUTDOWN COMPLETE if - * it is not in the SHUTDOWN-ACK-SENT state. + * - The receiver of a SHUTDOWN COMPLETE shall accept the packet + * if the Verification Tag field of the packet matches its own tag and + * the T bit is not set + * OR + * it is set to its peer's tag and the T bit is set in the Chunk + * Flags. + * Otherwise, the receiver MUST silently discard the packet + * and take no further action. An endpoint MUST ignore the + * SHUTDOWN COMPLETE if it is not in the SHUTDOWN-ACK-SENT state. * * Inputs * (endpoint, asoc, chunk) @@ -2858,16 +2861,16 @@ sctp_disposition_t sctp_sf_eat_sack_6_2(const struct sctp_endpoint *ep, /* * Generate an ABORT in response to a packet. * - * Section: 8.4 Handle "Out of the blue" Packets + * Section: 8.4 Handle "Out of the blue" Packets, sctpimpguide 2.41 * - * 8) The receiver should respond to the sender of the OOTB packet - * with an ABORT. When sending the ABORT, the receiver of the - * OOTB packet MUST fill in the Verification Tag field of the - * outbound packet with the value found in the Verification Tag - * field of the OOTB packet and set the T-bit in the Chunk Flags - * to indicate that no TCB was found. After sending this ABORT, - * the receiver of the OOTB packet shall discard the OOTB packet - * and take no further action. + * 8) The receiver should respond to the sender of the OOTB packet with + * an ABORT. When sending the ABORT, the receiver of the OOTB packet + * MUST fill in the Verification Tag field of the outbound packet + * with the value found in the Verification Tag field of the OOTB + * packet and set the T-bit in the Chunk Flags to indicate that the + * Verification Tag is reflected. After sending this ABORT, the + * receiver of the OOTB packet shall discard the OOTB packet and take + * no further action. * * Verification Tag: * @@ -2895,6 +2898,10 @@ sctp_disposition_t sctp_sf_tabort_8_4_8(const struct sctp_endpoint *ep, return SCTP_DISPOSITION_NOMEM; } + /* Reflect vtag if T-Bit is set */ + if (sctp_test_T_bit(abort)) + packet->vtag = ntohl(chunk->sctp_hdr->vtag); + /* Set the skb to the belonging sock for accounting. */ abort->skb->sk = ep->base.sk; @@ -3026,22 +3033,24 @@ nomem: } /* - * RFC 2960, 8.4 - Handle "Out of the blue" Packets + * RFC 2960, 8.4 - Handle "Out of the blue" Packets, sctpimpguide 2.41. + * * 5) If the packet contains a SHUTDOWN ACK chunk, the receiver should * respond to the sender of the OOTB packet with a SHUTDOWN COMPLETE. * When sending the SHUTDOWN COMPLETE, the receiver of the OOTB * packet must fill in the Verification Tag field of the outbound * packet with the Verification Tag received in the SHUTDOWN ACK and - * set the T-bit in the Chunk Flags to indicate that no TCB was - * found. Otherwise, + * set the T-bit in the Chunk Flags to indicate that the Verification + * Tag is reflected. * * 8) The receiver should respond to the sender of the OOTB packet with * an ABORT. When sending the ABORT, the receiver of the OOTB packet * MUST fill in the Verification Tag field of the outbound packet * with the value found in the Verification Tag field of the OOTB - * packet and set the T-bit in the Chunk Flags to indicate that no - * TCB was found. After sending this ABORT, the receiver of the OOTB - * packet shall discard the OOTB packet and take no further action. + * packet and set the T-bit in the Chunk Flags to indicate that the + * Verification Tag is reflected. After sending this ABORT, the + * receiver of the OOTB packet shall discard the OOTB packet and take + * no further action. */ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep, const struct sctp_association *asoc, @@ -3090,13 +3099,15 @@ sctp_disposition_t sctp_sf_ootb(const struct sctp_endpoint *ep, /* * Handle an "Out of the blue" SHUTDOWN ACK. * - * Section: 8.4 5) + * Section: 8.4 5, sctpimpguide 2.41. + * * 5) If the packet contains a SHUTDOWN ACK chunk, the receiver should - * respond to the sender of the OOTB packet with a SHUTDOWN COMPLETE. - * When sending the SHUTDOWN COMPLETE, the receiver of the OOTB packet - * must fill in the Verification Tag field of the outbound packet with - * the Verification Tag received in the SHUTDOWN ACK and set the - * T-bit in the Chunk Flags to indicate that no TCB was found. + * respond to the sender of the OOTB packet with a SHUTDOWN COMPLETE. + * When sending the SHUTDOWN COMPLETE, the receiver of the OOTB + * packet must fill in the Verification Tag field of the outbound + * packet with the Verification Tag received in the SHUTDOWN ACK and + * set the T-bit in the Chunk Flags to indicate that the Verification + * Tag is reflected. * * Inputs * (endpoint, asoc, type, arg, commands) @@ -3128,6 +3139,10 @@ static sctp_disposition_t sctp_sf_shut_8_4_5(const struct sctp_endpoint *ep, return SCTP_DISPOSITION_NOMEM; } + /* Reflect vtag if T-Bit is set */ + if (sctp_test_T_bit(shut)) + packet->vtag = ntohl(chunk->sctp_hdr->vtag); + /* Set the skb to the belonging sock for accounting. */ shut->skb->sk = ep->base.sk; @@ -3591,7 +3606,6 @@ sctp_disposition_t sctp_sf_discard_chunk(const struct sctp_endpoint *ep, * * 2) If the OOTB packet contains an ABORT chunk, the receiver MUST * silently discard the OOTB packet and take no further action. - * Otherwise, * * Verification Tag: No verification necessary * @@ -4961,6 +4975,11 @@ static struct sctp_packet *sctp_abort_pkt_new(const struct sctp_endpoint *ep, sctp_ootb_pkt_free(packet); return NULL; } + + /* Reflect vtag if T-Bit is set */ + if (sctp_test_T_bit(abort)) + packet->vtag = ntohl(chunk->sctp_hdr->vtag); + /* Add specified error causes, i.e., payload, to the * end of the chunk. */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e8c210182571..0b338eca6dc0 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -115,9 +115,17 @@ static inline int sctp_wspace(struct sctp_association *asoc) struct sock *sk = asoc->base.sk; int amt = 0; - amt = sk->sk_sndbuf - asoc->sndbuf_used; + if (asoc->ep->sndbuf_policy) { + /* make sure that no association uses more than sk_sndbuf */ + amt = sk->sk_sndbuf - asoc->sndbuf_used; + } else { + /* do socket level accounting */ + amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + } + if (amt < 0) amt = 0; + return amt; } @@ -138,12 +146,21 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) /* The sndbuf space is tracked per association. */ sctp_association_hold(asoc); + skb_set_owner_w(chunk->skb, sk); + chunk->skb->destructor = sctp_wfree; /* Save the chunk pointer in skb for sctp_wfree to use later. */ *((struct sctp_chunk **)(chunk->skb->cb)) = chunk; - asoc->sndbuf_used += SCTP_DATA_SNDSIZE(chunk); - sk->sk_wmem_queued += SCTP_DATA_SNDSIZE(chunk); + asoc->sndbuf_used += SCTP_DATA_SNDSIZE(chunk) + + sizeof(struct sk_buff) + + sizeof(struct sctp_chunk); + + sk->sk_wmem_queued += SCTP_DATA_SNDSIZE(chunk) + + sizeof(struct sk_buff) + + sizeof(struct sctp_chunk); + + atomic_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); } /* Verify that this is a valid address. */ @@ -3473,7 +3490,7 @@ static int sctp_getsockopt_associnfo(struct sock *sk, int len, return -EINVAL; /* Values correspoinding to the specific association */ - if (assocparams.sasoc_assoc_id != 0) { + if (asoc) { assocparams.sasoc_asocmaxrxt = asoc->max_retrans; assocparams.sasoc_peer_rwnd = asoc->peer.rwnd; assocparams.sasoc_local_rwnd = asoc->a_rwnd; @@ -4422,8 +4439,17 @@ static void sctp_wfree(struct sk_buff *skb) chunk = *((struct sctp_chunk **)(skb->cb)); asoc = chunk->asoc; sk = asoc->base.sk; - asoc->sndbuf_used -= SCTP_DATA_SNDSIZE(chunk); - sk->sk_wmem_queued -= SCTP_DATA_SNDSIZE(chunk); + asoc->sndbuf_used -= SCTP_DATA_SNDSIZE(chunk) + + sizeof(struct sk_buff) + + sizeof(struct sctp_chunk); + + sk->sk_wmem_queued -= SCTP_DATA_SNDSIZE(chunk) + + sizeof(struct sk_buff) + + sizeof(struct sctp_chunk); + + atomic_sub(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); + + sock_wfree(skb); __sctp_write_space(asoc); sctp_association_put(asoc); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 89fa20c73a5c..7fc31849312b 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -110,6 +110,14 @@ static ctl_table sctp_table[] = { .proc_handler = &proc_dointvec }, { + .ctl_name = NET_SCTP_SNDBUF_POLICY, + .procname = "sndbuf_policy", + .data = &sctp_sndbuf_policy, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec + }, + { .ctl_name = NET_SCTP_PATH_MAX_RETRANS, .procname = "path_max_retrans", .data = &sctp_max_retrans_path, diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 4484931018eb..67b9f035ba86 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -46,9 +46,9 @@ xdr_decode_netobj(u32 *p, struct xdr_netobj *obj) /** * xdr_encode_opaque_fixed - Encode fixed length opaque data - * @p - pointer to current position in XDR buffer. - * @ptr - pointer to data to encode (or NULL) - * @nbytes - size of data. + * @p: pointer to current position in XDR buffer. + * @ptr: pointer to data to encode (or NULL) + * @nbytes: size of data. * * Copy the array of data of length nbytes at ptr to the XDR buffer * at position p, then align to the next 32-bit boundary by padding @@ -76,9 +76,9 @@ EXPORT_SYMBOL(xdr_encode_opaque_fixed); /** * xdr_encode_opaque - Encode variable length opaque data - * @p - pointer to current position in XDR buffer. - * @ptr - pointer to data to encode (or NULL) - * @nbytes - size of data. + * @p: pointer to current position in XDR buffer. + * @ptr: pointer to data to encode (or NULL) + * @nbytes: size of data. * * Returns the updated current XDR buffer position */ diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index 956c17f6c548..d6844ac226f5 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -48,8 +48,8 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> /* support for loadable modules */ -#include <linux/slab.h> /* kmalloc(), kfree() */ -#include <linux/mm.h> /* verify_area(), etc. */ +#include <linux/slab.h> /* kmalloc(), kfree() */ +#include <linux/mm.h> #include <linux/string.h> /* inline mem*, str* functions */ #include <asm/byteorder.h> /* htons(), etc. */ diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 80828078733d..55ed979db144 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1028,30 +1028,15 @@ static int stale_bundle(struct dst_entry *dst) return !xfrm_bundle_ok((struct xfrm_dst *)dst, NULL, AF_UNSPEC); } -static void xfrm_dst_destroy(struct dst_entry *dst) +void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { - struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - - dst_release(xdst->route); - - if (!dst->xfrm) - return; - xfrm_state_put(dst->xfrm); - dst->xfrm = NULL; -} - -static void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int unregister) -{ - if (!unregister) - return; - while ((dst = dst->child) && dst->xfrm && dst->dev == dev) { dst->dev = &loopback_dev; dev_hold(&loopback_dev); dev_put(dev); } } +EXPORT_SYMBOL(xfrm_dst_ifdown); static void xfrm_link_failure(struct sk_buff *skb) { @@ -1262,10 +1247,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) dst_ops->kmem_cachep = xfrm_dst_cache; if (likely(dst_ops->check == NULL)) dst_ops->check = xfrm_dst_check; - if (likely(dst_ops->destroy == NULL)) - dst_ops->destroy = xfrm_dst_destroy; - if (likely(dst_ops->ifdown == NULL)) - dst_ops->ifdown = xfrm_dst_ifdown; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) @@ -1297,8 +1278,6 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo) xfrm_policy_afinfo[afinfo->family] = NULL; dst_ops->kmem_cachep = NULL; dst_ops->check = NULL; - dst_ops->destroy = NULL; - dst_ops->ifdown = NULL; dst_ops->negative_advice = NULL; dst_ops->link_failure = NULL; dst_ops->get_mss = NULL; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 63661b0fd736..5ddda2c98af9 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -855,47 +855,44 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **x return 0; } -static const int xfrm_msg_min[(XFRM_MSG_MAX + 1 - XFRM_MSG_BASE)] = { - NLMSG_LENGTH(sizeof(struct xfrm_usersa_info)), /* NEW SA */ - NLMSG_LENGTH(sizeof(struct xfrm_usersa_id)), /* DEL SA */ - NLMSG_LENGTH(sizeof(struct xfrm_usersa_id)), /* GET SA */ - NLMSG_LENGTH(sizeof(struct xfrm_userpolicy_info)),/* NEW POLICY */ - NLMSG_LENGTH(sizeof(struct xfrm_userpolicy_id)), /* DEL POLICY */ - NLMSG_LENGTH(sizeof(struct xfrm_userpolicy_id)), /* GET POLICY */ - NLMSG_LENGTH(sizeof(struct xfrm_userspi_info)), /* ALLOC SPI */ - NLMSG_LENGTH(sizeof(struct xfrm_user_acquire)), /* ACQUIRE */ - NLMSG_LENGTH(sizeof(struct xfrm_user_expire)), /* EXPIRE */ - NLMSG_LENGTH(sizeof(struct xfrm_userpolicy_info)),/* UPD POLICY */ - NLMSG_LENGTH(sizeof(struct xfrm_usersa_info)), /* UPD SA */ - NLMSG_LENGTH(sizeof(struct xfrm_user_polexpire)), /* POLEXPIRE */ - NLMSG_LENGTH(sizeof(struct xfrm_usersa_flush)), /* FLUSH SA */ - NLMSG_LENGTH(0), /* FLUSH POLICY */ +#define XMSGSIZE(type) NLMSG_LENGTH(sizeof(struct type)) + +static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { + [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info), + [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), + [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), + [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info), + [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), + [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), + [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userspi_info), + [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_acquire), + [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_expire), + [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info), + [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info), + [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_polexpire), + [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush), + [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = NLMSG_LENGTH(0), }; +#undef XMSGSIZE + static struct xfrm_link { int (*doit)(struct sk_buff *, struct nlmsghdr *, void **); int (*dump)(struct sk_buff *, struct netlink_callback *); -} xfrm_dispatch[] = { - { .doit = xfrm_add_sa, }, - { .doit = xfrm_del_sa, }, - { - .doit = xfrm_get_sa, - .dump = xfrm_dump_sa, - }, - { .doit = xfrm_add_policy }, - { .doit = xfrm_get_policy }, - { - .doit = xfrm_get_policy, - .dump = xfrm_dump_policy, - }, - { .doit = xfrm_alloc_userspi }, - {}, - {}, - { .doit = xfrm_add_policy }, - { .doit = xfrm_add_sa, }, - {}, - { .doit = xfrm_flush_sa }, - { .doit = xfrm_flush_policy }, +} xfrm_dispatch[XFRM_NR_MSGTYPES] = { + [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = { .doit = xfrm_add_sa }, + [XFRM_MSG_DELSA - XFRM_MSG_BASE] = { .doit = xfrm_del_sa }, + [XFRM_MSG_GETSA - XFRM_MSG_BASE] = { .doit = xfrm_get_sa, + .dump = xfrm_dump_sa }, + [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_add_policy }, + [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy }, + [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy, + .dump = xfrm_dump_policy }, + [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = { .doit = xfrm_alloc_userspi }, + [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_add_policy }, + [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = { .doit = xfrm_add_sa }, + [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = { .doit = xfrm_flush_sa }, + [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_flush_policy }, }; static int xfrm_done(struct netlink_callback *cb) @@ -931,7 +928,9 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *err return -1; } - if ((type == 2 || type == 5) && (nlh->nlmsg_flags & NLM_F_DUMP)) { + if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || + type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) && + (nlh->nlmsg_flags & NLM_F_DUMP)) { u32 rlen; if (link->dump == NULL) @@ -1009,18 +1008,26 @@ static int xfrm_user_rcv_skb(struct sk_buff *skb) static void xfrm_netlink_rcv(struct sock *sk, int len) { + unsigned int qlen = skb_queue_len(&sk->sk_receive_queue); + do { struct sk_buff *skb; down(&xfrm_cfg_sem); - while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { + if (qlen > skb_queue_len(&sk->sk_receive_queue)) + qlen = skb_queue_len(&sk->sk_receive_queue); + + for (; qlen; qlen--) { + skb = skb_dequeue(&sk->sk_receive_queue); if (xfrm_user_rcv_skb(skb)) { if (skb->len) skb_queue_head(&sk->sk_receive_queue, skb); - else + else { kfree_skb(skb); + qlen--; + } break; } kfree_skb(skb); @@ -1028,7 +1035,7 @@ static void xfrm_netlink_rcv(struct sock *sk, int len) up(&xfrm_cfg_sem); - } while (xfrm_nl && xfrm_nl->sk_receive_queue.qlen); + } while (qlen); } static int build_expire(struct sk_buff *skb, struct xfrm_state *x, int hard) |