1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
From f15c072d6576c5e2b693c22e39ccc9103c952078 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Mon, 5 Nov 2018 10:35:47 +0000
Subject: [PATCH] vhost/vsock: fix use-after-free in network stack callers
commit 834e772c8db0c6a275d75315d90aba4ebbb1e249 upstream.
If the network stack calls .send_pkt()/.cancel_pkt() during .release(),
a struct vhost_vsock use-after-free is possible. This occurs because
.release() does not wait for other CPUs to stop using struct
vhost_vsock.
Switch to an RCU-enabled hashtable (indexed by guest CID) so that
.release() can wait for other CPUs by calling synchronize_rcu(). This
also eliminates vhost_vsock_lock acquisition in the data path so it
could have a positive effect on performance.
This is CVE-2018-14625 "kernel: use-after-free Read in vhost_transport_send_pkt".
CVE: CVE-2018-14625
Upstream-Status: Backport
Cc: stable@vger.kernel.org
Reported-and-tested-by: syzbot+bd391451452fb0b93039@syzkaller.appspotmail.com
Reported-by: syzbot+e3e074963495f92a89ed@syzkaller.appspotmail.com
Reported-by: syzbot+d5a0a170c5069658b141@syzkaller.appspotmail.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andreas Wellving <andreas.wellving@enea.com>
---
drivers/vhost/vsock.c | 57 +++++++++++++++++++++++++------------------
1 file changed, 33 insertions(+), 24 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index c9de9c41aa97..b044a0800805 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -15,6 +15,7 @@
#include <net/sock.h>
#include <linux/virtio_vsock.h>
#include <linux/vhost.h>
+#include <linux/hashtable.h>
#include <net/af_vsock.h>
#include "vhost.h"
@@ -27,14 +28,14 @@ enum {
/* Used to track all the vhost_vsock instances on the system. */
static DEFINE_SPINLOCK(vhost_vsock_lock);
-static LIST_HEAD(vhost_vsock_list);
+static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8);
struct vhost_vsock {
struct vhost_dev dev;
struct vhost_virtqueue vqs[2];
- /* Link to global vhost_vsock_list, protected by vhost_vsock_lock */
- struct list_head list;
+ /* Link to global vhost_vsock_hash, writes use vhost_vsock_lock */
+ struct hlist_node hash;
struct vhost_work send_pkt_work;
spinlock_t send_pkt_list_lock;
@@ -50,11 +51,14 @@ static u32 vhost_transport_get_local_cid(void)
return VHOST_VSOCK_DEFAULT_HOST_CID;
}
-static struct vhost_vsock *__vhost_vsock_get(u32 guest_cid)
+/* Callers that dereference the return value must hold vhost_vsock_lock or the
+ * RCU read lock.
+ */
+static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
{
struct vhost_vsock *vsock;
- list_for_each_entry(vsock, &vhost_vsock_list, list) {
+ hash_for_each_possible_rcu(vhost_vsock_hash, vsock, hash, guest_cid) {
u32 other_cid = vsock->guest_cid;
/* Skip instances that have no CID yet */
@@ -69,17 +73,6 @@ static struct vhost_vsock *__vhost_vsock_get(u32 guest_cid)
return NULL;
}
-static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
-{
- struct vhost_vsock *vsock;
-
- spin_lock_bh(&vhost_vsock_lock);
- vsock = __vhost_vsock_get(guest_cid);
- spin_unlock_bh(&vhost_vsock_lock);
-
- return vsock;
-}
-
static void
vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
struct vhost_virtqueue *vq)
@@ -210,9 +203,12 @@ vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
struct vhost_vsock *vsock;
int len = pkt->len;
+ rcu_read_lock();
+
/* Find the vhost_vsock according to guest context id */
vsock = vhost_vsock_get(le64_to_cpu(pkt->hdr.dst_cid));
if (!vsock) {
+ rcu_read_unlock();
virtio_transport_free_pkt(pkt);
return -ENODEV;
}
@@ -225,6 +221,8 @@ vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
spin_unlock_bh(&vsock->send_pkt_list_lock);
vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
+
+ rcu_read_unlock();
return len;
}
@@ -234,12 +232,15 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
struct vhost_vsock *vsock;
struct virtio_vsock_pkt *pkt, *n;
int cnt = 0;
+ int ret = -ENODEV;
LIST_HEAD(freeme);
+ rcu_read_lock();
+
/* Find the vhost_vsock according to guest context id */
vsock = vhost_vsock_get(vsk->remote_addr.svm_cid);
if (!vsock)
- return -ENODEV;
+ goto out;
spin_lock_bh(&vsock->send_pkt_list_lock);
list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
@@ -265,7 +266,10 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
vhost_poll_queue(&tx_vq->poll);
}
- return 0;
+ ret = 0;
+out:
+ rcu_read_unlock();
+ return ret;
}
static struct virtio_vsock_pkt *
@@ -531,10 +535,6 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
spin_lock_init(&vsock->send_pkt_list_lock);
INIT_LIST_HEAD(&vsock->send_pkt_list);
vhost_work_init(&vsock->send_pkt_work, vhost_transport_send_pkt_work);
-
- spin_lock_bh(&vhost_vsock_lock);
- list_add_tail(&vsock->list, &vhost_vsock_list);
- spin_unlock_bh(&vhost_vsock_lock);
return 0;
out:
@@ -575,9 +575,13 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
struct vhost_vsock *vsock = file->private_data;
spin_lock_bh(&vhost_vsock_lock);
- list_del(&vsock->list);
+ if (vsock->guest_cid)
+ hash_del_rcu(&vsock->hash);
spin_unlock_bh(&vhost_vsock_lock);
+ /* Wait for other CPUs to finish using vsock */
+ synchronize_rcu();
+
/* Iterating over all connections for all CIDs to find orphans is
* inefficient. Room for improvement here. */
vsock_for_each_connected_socket(vhost_vsock_reset_orphans);
@@ -618,12 +622,17 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid)
/* Refuse if CID is already in use */
spin_lock_bh(&vhost_vsock_lock);
- other = __vhost_vsock_get(guest_cid);
+ other = vhost_vsock_get(guest_cid);
if (other && other != vsock) {
spin_unlock_bh(&vhost_vsock_lock);
return -EADDRINUSE;
}
+
+ if (vsock->guest_cid)
+ hash_del_rcu(&vsock->hash);
+
vsock->guest_cid = guest_cid;
+ hash_add_rcu(vhost_vsock_hash, &vsock->hash, guest_cid);
spin_unlock_bh(&vhost_vsock_lock);
return 0;
--
2.19.2
|
