linux/net/netlink/diag.c
Kuniyuki Iwashima 43a6b3b4c7 netlink: Add __sock_i_ino() for __netlink_diag_dump().
[ Upstream commit 25a9c8a443 ]

syzbot reported a warning in __local_bh_enable_ip(). [0]

Commit 8d61f926d4 ("netlink: fix potential deadlock in
netlink_set_err()") converted read_lock(&nl_table_lock) to
read_lock_irqsave() in __netlink_diag_dump() to prevent a deadlock.

However, __netlink_diag_dump() calls sock_i_ino() that uses
read_lock_bh() and read_unlock_bh().  If CONFIG_TRACE_IRQFLAGS=y,
read_unlock_bh() finally enables IRQ even though it should stay
disabled until the following read_unlock_irqrestore().

Using read_lock() in sock_i_ino() would trigger a lockdep splat
in another place that was fixed in commit f064af1e50 ("net: fix
a lockdep splat"), so let's add __sock_i_ino() that would be safe
to use under BH disabled.

[0]:
WARNING: CPU: 0 PID: 5012 at kernel/softirq.c:376 __local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376
Modules linked in:
CPU: 0 PID: 5012 Comm: syz-executor487 Not tainted 6.4.0-rc7-syzkaller-00202-g6f68fc395f49 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023
RIP: 0010:__local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376
Code: 45 bf 01 00 00 00 e8 91 5b 0a 00 e8 3c 15 3d 00 fb 65 8b 05 ec e9 b5 7e 85 c0 74 58 5b 5d c3 65 8b 05 b2 b6 b4 7e 85 c0 75 a2 <0f> 0b eb 9e e8 89 15 3d 00 eb 9f 48 89 ef e8 6f 49 18 00 eb a8 0f
RSP: 0018:ffffc90003a1f3d0 EFLAGS: 00010046
RAX: 0000000000000000 RBX: 0000000000000201 RCX: 1ffffffff1cf5996
RDX: 0000000000000000 RSI: 0000000000000201 RDI: ffffffff8805c6f3
RBP: ffffffff8805c6f3 R08: 0000000000000001 R09: ffff8880152b03a3
R10: ffffed1002a56074 R11: 0000000000000005 R12: 00000000000073e4
R13: dffffc0000000000 R14: 0000000000000002 R15: 0000000000000000
FS:  0000555556726300(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000045ad50 CR3: 000000007c646000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 sock_i_ino+0x83/0xa0 net/core/sock.c:2559
 __netlink_diag_dump+0x45c/0x790 net/netlink/diag.c:171
 netlink_diag_dump+0xd6/0x230 net/netlink/diag.c:207
 netlink_dump+0x570/0xc50 net/netlink/af_netlink.c:2269
 __netlink_dump_start+0x64b/0x910 net/netlink/af_netlink.c:2374
 netlink_dump_start include/linux/netlink.h:329 [inline]
 netlink_diag_handler_dump+0x1ae/0x250 net/netlink/diag.c:238
 __sock_diag_cmd net/core/sock_diag.c:238 [inline]
 sock_diag_rcv_msg+0x31e/0x440 net/core/sock_diag.c:269
 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2547
 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:280
 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline]
 netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1365
 netlink_sendmsg+0x925/0xe30 net/netlink/af_netlink.c:1914
 sock_sendmsg_nosec net/socket.c:724 [inline]
 sock_sendmsg+0xde/0x190 net/socket.c:747
 ____sys_sendmsg+0x71c/0x900 net/socket.c:2503
 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2557
 __sys_sendmsg+0xf7/0x1c0 net/socket.c:2586
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7f5303aaabb9
Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffc7506e548 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5303aaabb9
RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003
RBP: 00007f5303a6ed60 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007f5303a6edf0
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 </TASK>

Fixes: 8d61f926d4 ("netlink: fix potential deadlock in netlink_set_err()")
Reported-by: syzbot+5da61cf6a9bc1902d422@syzkaller.appspotmail.com
Link: https://syzkaller.appspot.com/bug?extid=5da61cf6a9bc1902d422
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230626164313.52528-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2023-08-11 11:45:07 +02:00

261 lines
5.4 KiB
C

#include <linux/module.h>
#include <net/sock.h>
#include <linux/netlink.h>
#include <linux/sock_diag.h>
#include <linux/netlink_diag.h>
#include <linux/rhashtable.h>
#include "af_netlink.h"
static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (nlk->groups == NULL)
return 0;
return nla_put(nlskb, NETLINK_DIAG_GROUPS, NLGRPSZ(nlk->ngroups),
nlk->groups);
}
static int sk_diag_put_flags(struct sock *sk, struct sk_buff *skb)
{
struct netlink_sock *nlk = nlk_sk(sk);
u32 flags = 0;
if (nlk->cb_running)
flags |= NDIAG_FLAG_CB_RUNNING;
if (nlk->flags & NETLINK_F_RECV_PKTINFO)
flags |= NDIAG_FLAG_PKTINFO;
if (nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR)
flags |= NDIAG_FLAG_BROADCAST_ERROR;
if (nlk->flags & NETLINK_F_RECV_NO_ENOBUFS)
flags |= NDIAG_FLAG_NO_ENOBUFS;
if (nlk->flags & NETLINK_F_LISTEN_ALL_NSID)
flags |= NDIAG_FLAG_LISTEN_ALL_NSID;
if (nlk->flags & NETLINK_F_CAP_ACK)
flags |= NDIAG_FLAG_CAP_ACK;
return nla_put_u32(skb, NETLINK_DIAG_FLAGS, flags);
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
struct netlink_diag_req *req,
u32 portid, u32 seq, u32 flags, int sk_ino)
{
struct nlmsghdr *nlh;
struct netlink_diag_msg *rep;
struct netlink_sock *nlk = nlk_sk(sk);
nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep),
flags);
if (!nlh)
return -EMSGSIZE;
rep = nlmsg_data(nlh);
rep->ndiag_family = AF_NETLINK;
rep->ndiag_type = sk->sk_type;
rep->ndiag_protocol = sk->sk_protocol;
rep->ndiag_state = sk->sk_state;
rep->ndiag_ino = sk_ino;
rep->ndiag_portid = nlk->portid;
rep->ndiag_dst_portid = nlk->dst_portid;
rep->ndiag_dst_group = nlk->dst_group;
sock_diag_save_cookie(sk, rep->ndiag_cookie);
if ((req->ndiag_show & NDIAG_SHOW_GROUPS) &&
sk_diag_dump_groups(sk, skb))
goto out_nlmsg_trim;
if ((req->ndiag_show & NDIAG_SHOW_MEMINFO) &&
sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
goto out_nlmsg_trim;
if ((req->ndiag_show & NDIAG_SHOW_FLAGS) &&
sk_diag_put_flags(sk, skb))
goto out_nlmsg_trim;
nlmsg_end(skb, nlh);
return 0;
out_nlmsg_trim:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
int protocol, int s_num)
{
struct rhashtable_iter *hti = (void *)cb->args[2];
struct netlink_table *tbl = &nl_table[protocol];
struct net *net = sock_net(skb->sk);
struct netlink_diag_req *req;
struct netlink_sock *nlsk;
unsigned long flags;
struct sock *sk;
int num = 2;
int ret = 0;
req = nlmsg_data(cb->nlh);
if (s_num > 1)
goto mc_list;
num--;
if (!hti) {
hti = kmalloc(sizeof(*hti), GFP_KERNEL);
if (!hti)
return -ENOMEM;
cb->args[2] = (long)hti;
}
if (!s_num)
rhashtable_walk_enter(&tbl->hash, hti);
rhashtable_walk_start(hti);
while ((nlsk = rhashtable_walk_next(hti))) {
if (IS_ERR(nlsk)) {
ret = PTR_ERR(nlsk);
if (ret == -EAGAIN) {
ret = 0;
continue;
}
break;
}
sk = (struct sock *)nlsk;
if (!net_eq(sock_net(sk), net))
continue;
if (sk_diag_fill(sk, skb, req,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NLM_F_MULTI,
sock_i_ino(sk)) < 0) {
ret = 1;
break;
}
}
rhashtable_walk_stop(hti);
if (ret)
goto done;
rhashtable_walk_exit(hti);
num++;
mc_list:
read_lock_irqsave(&nl_table_lock, flags);
sk_for_each_bound(sk, &tbl->mc_list) {
if (sk_hashed(sk))
continue;
if (!net_eq(sock_net(sk), net))
continue;
if (num < s_num) {
num++;
continue;
}
if (sk_diag_fill(sk, skb, req,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NLM_F_MULTI,
__sock_i_ino(sk)) < 0) {
ret = 1;
break;
}
num++;
}
read_unlock_irqrestore(&nl_table_lock, flags);
done:
cb->args[0] = num;
return ret;
}
static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct netlink_diag_req *req;
int s_num = cb->args[0];
int err = 0;
req = nlmsg_data(cb->nlh);
if (req->sdiag_protocol == NDIAG_PROTO_ALL) {
int i;
for (i = cb->args[1]; i < MAX_LINKS; i++) {
err = __netlink_diag_dump(skb, cb, i, s_num);
if (err)
break;
s_num = 0;
}
cb->args[1] = i;
} else {
if (req->sdiag_protocol >= MAX_LINKS)
return -ENOENT;
err = __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num);
}
return err < 0 ? err : skb->len;
}
static int netlink_diag_dump_done(struct netlink_callback *cb)
{
struct rhashtable_iter *hti = (void *)cb->args[2];
if (cb->args[0] == 1)
rhashtable_walk_exit(hti);
kfree(hti);
return 0;
}
static int netlink_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
{
int hdrlen = sizeof(struct netlink_diag_req);
struct net *net = sock_net(skb->sk);
if (nlmsg_len(h) < hdrlen)
return -EINVAL;
if (h->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = netlink_diag_dump,
.done = netlink_diag_dump_done,
};
return netlink_dump_start(net->diag_nlsk, skb, h, &c);
} else
return -EOPNOTSUPP;
}
static const struct sock_diag_handler netlink_diag_handler = {
.family = AF_NETLINK,
.dump = netlink_diag_handler_dump,
};
static int __init netlink_diag_init(void)
{
return sock_diag_register(&netlink_diag_handler);
}
static void __exit netlink_diag_exit(void)
{
sock_diag_unregister(&netlink_diag_handler);
}
module_init(netlink_diag_init);
module_exit(netlink_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 16 /* AF_NETLINK */);