summaryrefslogtreecommitdiffstats
path: root/net/core/sock_diag.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-06-24 16:49:49 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-06-24 16:49:49 -0700
commite0456717e483bb8a9431b80a5bdc99a928b9b003 (patch)
tree5eb5add2bafd1f20326d70f5cb3b711d00a40b10 /net/core/sock_diag.c
parent98ec21a01896751b673b6c731ca8881daa8b2c6d (diff)
parent1ea2d020ba477cb7011a7174e8501a9e04a325d4 (diff)
downloadlinux-e0456717e483bb8a9431b80a5bdc99a928b9b003.tar.bz2
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) Add TX fast path in mac80211, from Johannes Berg. 2) Add TSO/GRO support to ibmveth, from Thomas Falcon 3) Move away from cached routes in ipv6, just like ipv4, from Martin KaFai Lau. 4) Lots of new rhashtable tests, from Thomas Graf. 5) Run ingress qdisc lockless, from Alexei Starovoitov. 6) Allow servers to fetch TCP packet headers for SYN packets of new connections, for fingerprinting. From Eric Dumazet. 7) Add mode parameter to pktgen, for testing receive. From Alexei Starovoitov. 8) Cache access optimizations via simplifications of build_skb(), from Alexander Duyck. 9) Move page frag allocator under mm/, also from Alexander. 10) Add xmit_more support to hv_netvsc, from KY Srinivasan. 11) Add a counter guard in case we try to perform endless reclassify loops in the packet scheduler. 12) Extern flow dissector to be programmable and use it in new "Flower" classifier. From Jiri Pirko. 13) AF_PACKET fanout rollover fixes, performance improvements, and new statistics. From Willem de Bruijn. 14) Add netdev driver for GENEVE tunnels, from John W Linville. 15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso. 16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet. 17) Add an ECN retry fallback for the initial TCP handshake, from Daniel Borkmann. 18) Add tail call support to BPF, from Alexei Starovoitov. 19) Add several pktgen helper scripts, from Jesper Dangaard Brouer. 20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa. 21) Favor even port numbers for allocation to connect() requests, and odd port numbers for bind(0), in an effort to help avoid ip_local_port_range exhaustion. From Eric Dumazet. 22) Add Cavium ThunderX driver, from Sunil Goutham. 23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata, from Alexei Starovoitov. 24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai. 25) Double TCP Small Queues default to 256K to accomodate situations like the XEN driver and wireless aggregation. From Wei Liu. 26) Add more entropy inputs to flow dissector, from Tom Herbert. 27) Add CDG congestion control algorithm to TCP, from Kenneth Klette Jonassen. 28) Convert ipset over to RCU locking, from Jozsef Kadlecsik. 29) Track and act upon link status of ipv4 route nexthops, from Andy Gospodarek. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits) bridge: vlan: flush the dynamically learned entries on port vlan delete bridge: multicast: add a comment to br_port_state_selection about blocking state net: inet_diag: export IPV6_V6ONLY sockopt stmmac: troubleshoot unexpected bits in des0 & des1 net: ipv4 sysctl option to ignore routes when nexthop link is down net: track link-status of ipv4 nexthops net: switchdev: ignore unsupported bridge flags net: Cavium: Fix MAC address setting in shutdown state drivers: net: xgene: fix for ACPI support without ACPI ip: report the original address of ICMP messages net/mlx5e: Prefetch skb data on RX net/mlx5e: Pop cq outside mlx5e_get_cqe net/mlx5e: Remove mlx5e_cq.sqrq back-pointer net/mlx5e: Remove extra spaces net/mlx5e: Avoid TX CQE generation if more xmit packets expected net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq() net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device ...
Diffstat (limited to 'net/core/sock_diag.c')
-rw-r--r--net/core/sock_diag.c85
1 files changed, 85 insertions, 0 deletions
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 74dddf84adcd..d79866c5f8bc 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -5,6 +5,9 @@
#include <net/net_namespace.h>
#include <linux/module.h>
#include <net/sock.h>
+#include <linux/kernel.h>
+#include <linux/tcp.h>
+#include <linux/workqueue.h>
#include <linux/inet_diag.h>
#include <linux/sock_diag.h>
@@ -12,6 +15,7 @@
static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
static DEFINE_MUTEX(sock_diag_table_mutex);
+static struct workqueue_struct *broadcast_wq;
static u64 sock_gen_cookie(struct sock *sk)
{
@@ -101,6 +105,62 @@ out:
}
EXPORT_SYMBOL(sock_diag_put_filterinfo);
+struct broadcast_sk {
+ struct sock *sk;
+ struct work_struct work;
+};
+
+static size_t sock_diag_nlmsg_size(void)
+{
+ return NLMSG_ALIGN(sizeof(struct inet_diag_msg)
+ + nla_total_size(sizeof(u8)) /* INET_DIAG_PROTOCOL */
+ + nla_total_size(sizeof(struct tcp_info))); /* INET_DIAG_INFO */
+}
+
+static void sock_diag_broadcast_destroy_work(struct work_struct *work)
+{
+ struct broadcast_sk *bsk =
+ container_of(work, struct broadcast_sk, work);
+ struct sock *sk = bsk->sk;
+ const struct sock_diag_handler *hndl;
+ struct sk_buff *skb;
+ const enum sknetlink_groups group = sock_diag_destroy_group(sk);
+ int err = -1;
+
+ WARN_ON(group == SKNLGRP_NONE);
+
+ skb = nlmsg_new(sock_diag_nlmsg_size(), GFP_KERNEL);
+ if (!skb)
+ goto out;
+
+ mutex_lock(&sock_diag_table_mutex);
+ hndl = sock_diag_handlers[sk->sk_family];
+ if (hndl && hndl->get_info)
+ err = hndl->get_info(skb, sk);
+ mutex_unlock(&sock_diag_table_mutex);
+
+ if (!err)
+ nlmsg_multicast(sock_net(sk)->diag_nlsk, skb, 0, group,
+ GFP_KERNEL);
+ else
+ kfree_skb(skb);
+out:
+ sk_destruct(sk);
+ kfree(bsk);
+}
+
+void sock_diag_broadcast_destroy(struct sock *sk)
+{
+ /* Note, this function is often called from an interrupt context. */
+ struct broadcast_sk *bsk =
+ kmalloc(sizeof(struct broadcast_sk), GFP_ATOMIC);
+ if (!bsk)
+ return sk_destruct(sk);
+ bsk->sk = sk;
+ INIT_WORK(&bsk->work, sock_diag_broadcast_destroy_work);
+ queue_work(broadcast_wq, &bsk->work);
+}
+
void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
{
mutex_lock(&sock_diag_table_mutex);
@@ -211,10 +271,32 @@ static void sock_diag_rcv(struct sk_buff *skb)
mutex_unlock(&sock_diag_mutex);
}
+static int sock_diag_bind(struct net *net, int group)
+{
+ switch (group) {
+ case SKNLGRP_INET_TCP_DESTROY:
+ case SKNLGRP_INET_UDP_DESTROY:
+ if (!sock_diag_handlers[AF_INET])
+ request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+ NETLINK_SOCK_DIAG, AF_INET);
+ break;
+ case SKNLGRP_INET6_TCP_DESTROY:
+ case SKNLGRP_INET6_UDP_DESTROY:
+ if (!sock_diag_handlers[AF_INET6])
+ request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+ NETLINK_SOCK_DIAG, AF_INET);
+ break;
+ }
+ return 0;
+}
+
static int __net_init diag_net_init(struct net *net)
{
struct netlink_kernel_cfg cfg = {
+ .groups = SKNLGRP_MAX,
.input = sock_diag_rcv,
+ .bind = sock_diag_bind,
+ .flags = NL_CFG_F_NONROOT_RECV,
};
net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg);
@@ -234,12 +316,15 @@ static struct pernet_operations diag_net_ops = {
static int __init sock_diag_init(void)
{
+ broadcast_wq = alloc_workqueue("sock_diag_events", 0, 0);
+ BUG_ON(!broadcast_wq);
return register_pernet_subsys(&diag_net_ops);
}
static void __exit sock_diag_exit(void)
{
unregister_pernet_subsys(&diag_net_ops);
+ destroy_workqueue(broadcast_wq);
}
module_init(sock_diag_init);