linux-stable.git/drivers/vhost, branch v4.19.71

vhost: scsi: add weight support

2019-08-04T07:30:55+00:00

commit c1ea02f15ab5efb3e93fc3144d895410bf79fcf2 upstream.

This patch will check the weight and exit the loop if we exceeds the
weight. This is useful for preventing scsi kthread from hogging cpu
which is guest triggerable.

This addresses CVE-2019-3900.

Cc: Paolo Bonzini 
Cc: Stefan Hajnoczi 
Fixes: 057cbf49a1f0 ("tcm_vhost: Initial merge for vhost level target fabric driver")
Signed-off-by: Jason Wang 
Reviewed-by: Stefan Hajnoczi 
Signed-off-by: Michael S. Tsirkin 
Reviewed-by: Stefan Hajnoczi 
[jwang: backport to 4.19]
Signed-off-by: Jack Wang 
Signed-off-by: Greg Kroah-Hartman

vhost: vsock: add weight support

2019-08-04T07:30:55+00:00

commit e79b431fb901ba1106670bcc80b9b617b25def7d upstream.

This patch will check the weight and exit the loop if we exceeds the
weight. This is useful for preventing vsock kthread from hogging cpu
which is guest triggerable. The weight can help to avoid starving the
request from on direction while another direction is being processed.

The value of weight is picked from vhost-net.

This addresses CVE-2019-3900.

Cc: Stefan Hajnoczi 
Fixes: 433fc58e6bf2 ("VSOCK: Introduce vhost_vsock.ko")
Signed-off-by: Jason Wang 
Reviewed-by: Stefan Hajnoczi 
Signed-off-by: Michael S. Tsirkin 
Signed-off-by: Greg Kroah-Hartman

vhost_net: fix possible infinite loop

2019-08-04T07:30:55+00:00

commit e2412c07f8f3040593dfb88207865a3cd58680c0 upstream.

When the rx buffer is too small for a packet, we will discard the vq
descriptor and retry it for the next packet:

while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
					      &busyloop_intr))) {
...
	/* On overrun, truncate and discard */
	if (unlikely(headcount > UIO_MAXIOV)) {
		iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
		err = sock->ops->recvmsg(sock, &msg,
					 1, MSG_DONTWAIT | MSG_TRUNC);
		pr_debug("Discarded rx packet: len %zd\n", sock_len);
		continue;
	}
...
}

This makes it possible to trigger a infinite while..continue loop
through the co-opreation of two VMs like:

1) Malicious VM1 allocate 1 byte rx buffer and try to slow down the
   vhost process as much as possible e.g using indirect descriptors or
   other.
2) Malicious VM2 generate packets to VM1 as fast as possible

Fixing this by checking against weight at the end of RX and TX
loop. This also eliminate other similar cases when:

- userspace is consuming the packets in the meanwhile
- theoretical TOCTOU attack if guest moving avail index back and forth
  to hit the continue after vhost find guest just add new buffers

This addresses CVE-2019-3900.

Fixes: d8316f3991d20 ("vhost: fix total length when packets are too short")
Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server")
Signed-off-by: Jason Wang 
Reviewed-by: Stefan Hajnoczi 
Signed-off-by: Michael S. Tsirkin 
[jwang: backport to 4.19]
Signed-off-by: Jack Wang 
Signed-off-by: Greg Kroah-Hartman

vhost: introduce vhost_exceeds_weight()

2019-08-04T07:30:55+00:00

commit e82b9b0727ff6d665fff2d326162b460dded554d upstream.

We used to have vhost_exceeds_weight() for vhost-net to:

- prevent vhost kthread from hogging the cpu
- balance the time spent between TX and RX

This function could be useful for vsock and scsi as well. So move it
to vhost.c. Device must specify a weight which counts the number of
requests, or it can also specific a byte_weight which counts the
number of bytes that has been processed.

Signed-off-by: Jason Wang 
Reviewed-by: Stefan Hajnoczi 
Signed-off-by: Michael S. Tsirkin 
[jwang: backport to 4.19, fix conflict in net.c]
Signed-off-by: Jack Wang 
Signed-off-by: Greg Kroah-Hartman

vhost_net: disable zerocopy by default

2019-07-26T07:14:08+00:00

[ Upstream commit 098eadce3c622c07b328d0a43dda379b38cf7c5e ]

Vhost_net was known to suffer from HOL[1] issues which is not easy to
fix. Several downstream disable the feature by default. What's more,
the datapath was split and datacopy path got the support of batching
and XDP support recently which makes it faster than zerocopy part for
small packets transmission.

It looks to me that disable zerocopy by default is more
appropriate. It cold be enabled by default again in the future if we
fix the above issues.

[1] https://patchwork.kernel.org/patch/3787671/

Signed-off-by: Jason Wang 
Acked-by: Michael S. Tsirkin 
Signed-off-by: David S. Miller 
Signed-off-by: Sasha Levin

vhost: reject zero size iova range

2019-04-27T07:36:31+00:00

[ Upstream commit 813dbeb656d6c90266f251d8bd2b02d445afa63f ]

We used to accept zero size iova range which will lead a infinite loop
in translate_desc(). Fixing this by failing the request in this case.

Reported-by: syzbot+d21e6e297322a900c128@syzkaller.appspotmail.com
Fixes: 6b1e6cc7 ("vhost: new device IOTLB API")
Signed-off-by: Jason Wang 
Acked-by: Michael S. Tsirkin 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

vhost/vsock: fix vhost vsock cid hashing inconsistent

2019-03-19T12:12:42+00:00

commit 7fbe078c37aba3088359c9256c1a1d0c3e39ee81 upstream.

The vsock core only supports 32bit CID, but the Virtio-vsock spec define
CID (dst_cid and src_cid) as u64 and the upper 32bits is reserved as
zero. This inconsistency causes one bug in vhost vsock driver. The
scenarios is:

  0. A hash table (vhost_vsock_hash) is used to map an CID to a vsock
  object. And hash_min() is used to compute the hash key. hash_min() is
  defined as:
  (sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits)).
  That means the hash algorithm has dependency on the size of macro
  argument 'val'.
  0. In function vhost_vsock_set_cid(), a 64bit CID is passed to
  hash_min() to compute the hash key when inserting a vsock object into
  the hash table.
  0. In function vhost_vsock_get(), a 32bit CID is passed to hash_min()
  to compute the hash key when looking up a vsock for an CID.

Because the different size of the CID, hash_min() returns different hash
key, thus fails to look up the vsock object for an CID.

To fix this bug, we keep CID as u64 in the IOCTLs and virtio message
headers, but explicitly convert u64 to u32 when deal with the hash table
and vsock core.

Fixes: 834e772c8db0 ("vhost/vsock: fix use-after-free in network stack callers")
Link: https://github.com/stefanha/virtio/blob/vsock/trunk/content.tex
Signed-off-by: Zha Bin 
Reviewed-by: Liu Jiang 
Reviewed-by: Stefan Hajnoczi 
Acked-by: Jason Wang 
Signed-off-by: David S. Miller 
Signed-off-by: Shengjing Zhu 
Signed-off-by: Greg Kroah-Hartman

vhost: return EINVAL if iovecs size does not match the message size

2019-02-27T09:08:56+00:00

[ Upstream commit 74ad7419489ddade8044e3c9ab064ad656520306 ]

We've failed to copy and process vhost_iotlb_msg so let userspace at
least know about it. For instance before these patch the code below runs
without any error:

int main()
{
  struct vhost_msg msg;
  struct iovec iov;
  int fd;

  fd = open("/dev/vhost-net", O_RDWR);
  if (fd == -1) {
    perror("open");
    return 1;
  }

  iov.iov_base = &msg;
  iov.iov_len = sizeof(msg)-4;

  if (writev(fd, &iov,1) == -1) {
    perror("writev");
    return 1;
  }

  return 0;
}

Signed-off-by: Pavel Tikhomirov 
Signed-off-by: Michael S. Tsirkin 
Signed-off-by: Sasha Levin

vhost: correctly check the return value of translate_desc() in log_used()

2019-02-23T08:07:25+00:00

[ Upstream commit 816db7663565cd23f74ed3d5c9240522e3fb0dda ]

When fail, translate_desc() returns negative value, otherwise the
number of iovs. So we should fail when the return value is negative
instead of a blindly check against zero.

Detected by CoverityScan, CID# 1442593:  Control flow issues  (DEADCODE)

Fixes: cc5e71075947 ("vhost: log dirty page correctly")
Acked-by: Michael S. Tsirkin 
Reported-by: Stephen Hemminger 
Signed-off-by: Jason Wang 
Signed-off-by: David S. Miller 
Signed-off-by: Sasha Levin

vhost: fix OOB in get_rx_bufs()

2019-02-06T16:30:08+00:00

[ Upstream commit b46a0bf78ad7b150ef5910da83859f7f5a514ffd ]

After batched used ring updating was introduced in commit e2b3b35eb989
("vhost_net: batch used ring update in rx"). We tend to batch heads in
vq->heads for more than one packet. But the quota passed to
get_rx_bufs() was not correctly limited, which can result a OOB write
in vq->heads.

        headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
                    vhost_len, &in, vq_log, &log,
                    likely(mergeable) ? UIO_MAXIOV : 1);

UIO_MAXIOV was still used which is wrong since we could have batched
used in vq->heads, this will cause OOB if the next buffer needs more
than 960 (1024 (UIO_MAXIOV) - 64 (VHOST_NET_BATCH)) heads after we've
batched 64 (VHOST_NET_BATCH) heads:
Acked-by: Stefan Hajnoczi 

=============================================================================
BUG kmalloc-8k (Tainted: G    B            ): Redzone overwritten
-----------------------------------------------------------------------------

INFO: 0x00000000fd93b7a2-0x00000000f0713384. First byte 0xa9 instead of 0xcc
INFO: Allocated in alloc_pd+0x22/0x60 age=3933677 cpu=2 pid=2674
    kmem_cache_alloc_trace+0xbb/0x140
    alloc_pd+0x22/0x60
    gen8_ppgtt_create+0x11d/0x5f0
    i915_ppgtt_create+0x16/0x80
    i915_gem_create_context+0x248/0x390
    i915_gem_context_create_ioctl+0x4b/0xe0
    drm_ioctl_kernel+0xa5/0xf0
    drm_ioctl+0x2ed/0x3a0
    do_vfs_ioctl+0x9f/0x620
    ksys_ioctl+0x6b/0x80
    __x64_sys_ioctl+0x11/0x20
    do_syscall_64+0x43/0xf0
    entry_SYSCALL_64_after_hwframe+0x44/0xa9
INFO: Slab 0x00000000d13e87af objects=3 used=3 fp=0x          (null) flags=0x200000000010201
INFO: Object 0x0000000003278802 @offset=17064 fp=0x00000000e2e6652b

Fixing this by allocating UIO_MAXIOV + VHOST_NET_BATCH iovs for
vhost-net. This is done through set the limitation through
vhost_dev_init(), then set_owner can allocate the number of iov in a
per device manner.

This fixes CVE-2018-16880.

Fixes: e2b3b35eb989 ("vhost_net: batch used ring update in rx")
Signed-off-by: Jason Wang 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman