linux_dsm_epyc7002/net/core/sock_diag.c

339 lines
7.8 KiB
C
Raw Normal View History

/* License: GPL */
#include <linux/mutex.h>
#include <linux/socket.h>
#include <linux/skbuff.h>
#include <net/netlink.h>
#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/nospec.h>
#include <linux/inet_diag.h>
#include <linux/sock_diag.h>
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 atomic64_t cookie_gen;
u64 sock_gen_cookie(struct sock *sk)
{
while (1) {
u64 res = atomic64_read(&sk->sk_cookie);
if (res)
return res;
res = atomic64_inc_return(&cookie_gen);
atomic64_cmpxchg(&sk->sk_cookie, 0, res);
}
}
int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie)
{
u64 res;
if (cookie[0] == INET_DIAG_NOCOOKIE && cookie[1] == INET_DIAG_NOCOOKIE)
return 0;
res = sock_gen_cookie(sk);
if ((u32)res != cookie[0] || (u32)(res >> 32) != cookie[1])
return -ESTALE;
return 0;
}
EXPORT_SYMBOL_GPL(sock_diag_check_cookie);
void sock_diag_save_cookie(struct sock *sk, __u32 *cookie)
{
u64 res = sock_gen_cookie(sk);
cookie[0] = (u32)res;
cookie[1] = (u32)(res >> 32);
}
EXPORT_SYMBOL_GPL(sock_diag_save_cookie);
int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
{
u32 mem[SK_MEMINFO_VARS];
sk_get_meminfo(sk, mem);
return nla_put(skb, attrtype, sizeof(mem), &mem);
}
EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
struct sk_buff *skb, int attrtype)
{
struct sock_fprog_kern *fprog;
struct sk_filter *filter;
struct nlattr *attr;
unsigned int flen;
int err = 0;
if (!may_report_filterinfo) {
nla_reserve(skb, attrtype, 0);
return 0;
}
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (!filter)
goto out;
net: filter: split 'struct sk_filter' into socket and bpf parts clean up names related to socket filtering and bpf in the following way: - everything that deals with sockets keeps 'sk_*' prefix - everything that is pure BPF is changed to 'bpf_*' prefix split 'struct sk_filter' into struct sk_filter { atomic_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; and struct bpf_prog { u32 jited:1, len:31; struct sock_fprog_kern *orig_prog; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); union { struct sock_filter insns[0]; struct bpf_insn insnsi[0]; struct work_struct work; }; }; so that 'struct bpf_prog' can be used independent of sockets and cleans up 'unattached' bpf use cases split SK_RUN_FILTER macro into: SK_RUN_FILTER to be used with 'struct sk_filter *' and BPF_PROG_RUN to be used with 'struct bpf_prog *' __sk_filter_release(struct sk_filter *) gains __bpf_prog_release(struct bpf_prog *) helper function also perform related renames for the functions that work with 'struct bpf_prog *', since they're on the same lines: sk_filter_size -> bpf_prog_size sk_filter_select_runtime -> bpf_prog_select_runtime sk_filter_free -> bpf_prog_free sk_unattached_filter_create -> bpf_prog_create sk_unattached_filter_destroy -> bpf_prog_destroy sk_store_orig_filter -> bpf_prog_store_orig_filter sk_release_orig_filter -> bpf_release_orig_filter __sk_migrate_filter -> bpf_migrate_filter __sk_prepare_filter -> bpf_prepare_filter API for attaching classic BPF to a socket stays the same: sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *) and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program which is used by sockets, tun, af_packet API for 'unattached' BPF programs becomes: bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *) and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-31 10:34:16 +07:00
fprog = filter->prog->orig_prog;
if (!fprog)
goto out;
flen = bpf_classic_proglen(fprog);
attr = nla_reserve(skb, attrtype, flen);
if (attr == NULL) {
err = -EMSGSIZE;
goto out;
}
memcpy(nla_data(attr), fprog->filter, flen);
out:
rcu_read_unlock();
return err;
}
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_64bit(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);
inet_rcv_compat = fn;
mutex_unlock(&sock_diag_table_mutex);
}
EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat);
void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
{
mutex_lock(&sock_diag_table_mutex);
inet_rcv_compat = NULL;
mutex_unlock(&sock_diag_table_mutex);
}
EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat);
int sock_diag_register(const struct sock_diag_handler *hndl)
{
int err = 0;
if (hndl->family >= AF_MAX)
return -EINVAL;
mutex_lock(&sock_diag_table_mutex);
if (sock_diag_handlers[hndl->family])
err = -EBUSY;
else
sock_diag_handlers[hndl->family] = hndl;
mutex_unlock(&sock_diag_table_mutex);
return err;
}
EXPORT_SYMBOL_GPL(sock_diag_register);
void sock_diag_unregister(const struct sock_diag_handler *hnld)
{
int family = hnld->family;
if (family >= AF_MAX)
return;
mutex_lock(&sock_diag_table_mutex);
BUG_ON(sock_diag_handlers[family] != hnld);
sock_diag_handlers[family] = NULL;
mutex_unlock(&sock_diag_table_mutex);
}
EXPORT_SYMBOL_GPL(sock_diag_unregister);
static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
{
int err;
struct sock_diag_req *req = nlmsg_data(nlh);
const struct sock_diag_handler *hndl;
if (nlmsg_len(nlh) < sizeof(*req))
return -EINVAL;
if (req->sdiag_family >= AF_MAX)
return -EINVAL;
req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX);
if (sock_diag_handlers[req->sdiag_family] == NULL)
sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Phil Sutter <phil@nwl.cc> Acked-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-10 17:57:50 +07:00
sock_load_diag_module(req->sdiag_family, 0);
mutex_lock(&sock_diag_table_mutex);
hndl = sock_diag_handlers[req->sdiag_family];
if (hndl == NULL)
err = -ENOENT;
else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY)
err = hndl->dump(skb, nlh);
else if (nlh->nlmsg_type == SOCK_DESTROY && hndl->destroy)
err = hndl->destroy(skb, nlh);
else
err = -EOPNOTSUPP;
mutex_unlock(&sock_diag_table_mutex);
return err;
}
static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
int ret;
switch (nlh->nlmsg_type) {
case TCPDIAG_GETSOCK:
case DCCPDIAG_GETSOCK:
if (inet_rcv_compat == NULL)
sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Phil Sutter <phil@nwl.cc> Acked-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-10 17:57:50 +07:00
sock_load_diag_module(AF_INET, 0);
mutex_lock(&sock_diag_table_mutex);
if (inet_rcv_compat != NULL)
ret = inet_rcv_compat(skb, nlh);
else
ret = -EOPNOTSUPP;
mutex_unlock(&sock_diag_table_mutex);
return ret;
case SOCK_DIAG_BY_FAMILY:
case SOCK_DESTROY:
return __sock_diag_cmd(skb, nlh);
default:
return -EINVAL;
}
}
static DEFINE_MUTEX(sock_diag_mutex);
static void sock_diag_rcv(struct sk_buff *skb)
{
mutex_lock(&sock_diag_mutex);
netlink_rcv_skb(skb, &sock_diag_rcv_msg);
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])
sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Phil Sutter <phil@nwl.cc> Acked-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-10 17:57:50 +07:00
sock_load_diag_module(AF_INET, 0);
break;
case SKNLGRP_INET6_TCP_DESTROY:
case SKNLGRP_INET6_UDP_DESTROY:
if (!sock_diag_handlers[AF_INET6])
sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Phil Sutter <phil@nwl.cc> Acked-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-10 17:57:50 +07:00
sock_load_diag_module(AF_INET6, 0);
break;
}
return 0;
}
int sock_diag_destroy(struct sock *sk, int err)
{
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (!sk->sk_prot->diag_destroy)
return -EOPNOTSUPP;
return sk->sk_prot->diag_destroy(sk, err);
}
EXPORT_SYMBOL_GPL(sock_diag_destroy);
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);
return net->diag_nlsk == NULL ? -ENOMEM : 0;
}
static void __net_exit diag_net_exit(struct net *net)
{
netlink_kernel_release(net->diag_nlsk);
net->diag_nlsk = NULL;
}
static struct pernet_operations diag_net_ops = {
.init = diag_net_init,
.exit = diag_net_exit,
};
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);
}
device_initcall(sock_diag_init);