提交 eb4cb008 编写于 作者: C Craig Gallek 提交者: David S. Miller

sock_diag: define destruction multicast groups

These groups will contain socket-destruction events for
AF_INET/AF_INET6, IPPROTO_TCP/IPPROTO_UDP.

Near the end of socket destruction, a check for listeners is
performed.  In the presence of a listener, rather than completely
cleanup the socket, a unit of work will be added to a private
work queue which will first broadcast information about the socket
and then finish the cleanup operation.
Signed-off-by: NCraig Gallek <kraig@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
上级 916035dd
master alk-4.19.24 alk-4.19.30 alk-4.19.34 alk-4.19.36 alk-4.19.43 alk-4.19.48 alk-4.19.57 ck-4.19.67 ck-4.19.81 ck-4.19.91 github/fork/deepanshu1422/fix-typo-in-comment github/fork/haosdent/fix-typo linux-next v4.19.91 v4.19.90 v4.19.89 v4.19.88 v4.19.87 v4.19.86 v4.19.85 v4.19.84 v4.19.83 v4.19.82 v4.19.81 v4.19.80 v4.19.79 v4.19.78 v4.19.77 v4.19.76 v4.19.75 v4.19.74 v4.19.73 v4.19.72 v4.19.71 v4.19.70 v4.19.69 v4.19.68 v4.19.67 v4.19.66 v4.19.65 v4.19.64 v4.19.63 v4.19.62 v4.19.61 v4.19.60 v4.19.59 v4.19.58 v4.19.57 v4.19.56 v4.19.55 v4.19.54 v4.19.53 v4.19.52 v4.19.51 v4.19.50 v4.19.49 v4.19.48 v4.19.47 v4.19.46 v4.19.45 v4.19.44 v4.19.43 v4.19.42 v4.19.41 v4.19.40 v4.19.39 v4.19.38 v4.19.37 v4.19.36 v4.19.35 v4.19.34 v4.19.33 v4.19.32 v4.19.31 v4.19.30 v4.19.29 v4.19.28 v4.19.27 v4.19.26 v4.19.25 v4.19.24 v4.19.23 v4.19.22 v4.19.21 v4.19.20 v4.19.19 v4.19.18 v4.19.17 v4.19.16 v4.19.15 v4.19.14 v4.19.13 v4.19.12 v4.19.11 v4.19.10 v4.19.9 v4.19.8 v4.19.7 v4.19.6 v4.19.5 v4.19.4 v4.19.3 v4.19.2 v4.19.1 v4.19 v4.19-rc8 v4.19-rc7 v4.19-rc6 v4.19-rc5 v4.19-rc4 v4.19-rc3 v4.19-rc2 v4.19-rc1 ck-release-21 ck-release-20 ck-release-19.2 ck-release-19.1 ck-release-19 ck-release-18 ck-release-17.2 ck-release-17.1 ck-release-17 ck-release-16 ck-release-15.1 ck-release-15 ck-release-14 ck-release-13.2 ck-release-13 ck-release-12 ck-release-11 ck-release-10 ck-release-9 ck-release-7 alk-release-15 alk-release-14 alk-release-13.2 alk-release-13 alk-release-12 alk-release-11 alk-release-10 alk-release-9 alk-release-7
无相关合并请求
#ifndef __SOCK_DIAG_H__
#define __SOCK_DIAG_H__
#include <linux/netlink.h>
#include <linux/user_namespace.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
struct sk_buff;
......@@ -11,6 +14,7 @@ struct sock;
struct sock_diag_handler {
__u8 family;
int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh);
int (*get_info)(struct sk_buff *skb, struct sock *sk);
};
int sock_diag_register(const struct sock_diag_handler *h);
......@@ -26,4 +30,42 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr);
int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
struct sk_buff *skb, int attrtype);
static inline
enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk)
{
switch (sk->sk_family) {
case AF_INET:
switch (sk->sk_protocol) {
case IPPROTO_TCP:
return SKNLGRP_INET_TCP_DESTROY;
case IPPROTO_UDP:
return SKNLGRP_INET_UDP_DESTROY;
default:
return SKNLGRP_NONE;
}
case AF_INET6:
switch (sk->sk_protocol) {
case IPPROTO_TCP:
return SKNLGRP_INET6_TCP_DESTROY;
case IPPROTO_UDP:
return SKNLGRP_INET6_UDP_DESTROY;
default:
return SKNLGRP_NONE;
}
default:
return SKNLGRP_NONE;
}
}
static inline
bool sock_diag_has_destroy_listeners(const struct sock *sk)
{
const struct net *n = sock_net(sk);
const enum sknetlink_groups group = sock_diag_destroy_group(sk);
return group != SKNLGRP_NONE && n->diag_nlsk &&
netlink_has_listeners(n->diag_nlsk, group);
}
void sock_diag_broadcast_destroy(struct sock *sk);
#endif
......@@ -1518,6 +1518,7 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow)
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot, int kern);
void sk_free(struct sock *sk);
void sk_destruct(struct sock *sk);
struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
......
......@@ -23,4 +23,14 @@ enum {
SK_MEMINFO_VARS,
};
enum sknetlink_groups {
SKNLGRP_NONE,
SKNLGRP_INET_TCP_DESTROY,
SKNLGRP_INET_UDP_DESTROY,
SKNLGRP_INET6_TCP_DESTROY,
SKNLGRP_INET6_UDP_DESTROY,
__SKNLGRP_MAX,
};
#define SKNLGRP_MAX (__SKNLGRP_MAX - 1)
#endif /* _UAPI__SOCK_DIAG_H__ */
......@@ -131,6 +131,7 @@
#include <linux/ipsec.h>
#include <net/cls_cgroup.h>
#include <net/netprio_cgroup.h>
#include <linux/sock_diag.h>
#include <linux/filter.h>
......@@ -1423,7 +1424,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
}
EXPORT_SYMBOL(sk_alloc);
static void __sk_free(struct sock *sk)
void sk_destruct(struct sock *sk)
{
struct sk_filter *filter;
......@@ -1451,6 +1452,14 @@ static void __sk_free(struct sock *sk)
sk_prot_free(sk->sk_prot_creator, sk);
}
static void __sk_free(struct sock *sk)
{
if (unlikely(sock_diag_has_destroy_listeners(sk)))
sock_diag_broadcast_destroy(sk);
else
sk_destruct(sk);
}
void sk_free(struct sock *sk)
{
/*
......
......@@ -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 @@ int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
}
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);
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册