tree 124648c522fb7a4bd32322eb62850837377505c6
parent 92f04221379ae5e35f6474c2afed2eb02d552df3
author Hanna Czenczek <hreitz@redhat.com> 1689947385 +0200
committer Michael S. Tsirkin <mst@redhat.com> 1691093209 -0400

virtio: Fix packed virtqueue used_idx mask

virtio_queue_packed_set_last_avail_idx() is used by vhost devices to set
the internal queue indices to what has been reported by the vhost
back-end through GET_VRING_BASE.  For packed virtqueues, this
32-bit value is expected to contain both the device's internal avail and
used indices, as well as their respective wrap counters.

To get the used index, we shift the 32-bit value right by 16, and then
apply a mask of 0x7ffff.  That seems to be a typo, because it should be
0x7fff; first of all, the virtio specification says that the maximum
queue size for packed virt queues is 2^15, so the indices cannot exceed
2^15 - 1 anyway, making 0x7fff the correct mask.  Second, the mask
clearly is wrong from context, too, given that (A) `idx & 0x70000` must
be 0 at this point (`idx` is 32 bit and was shifted to the right by 16
already), (B) `idx & 0x8000` is the used_wrap_counter, so should not be
part of the used index, and (C) `vq->used_idx` is a `uint16_t`, so
cannot fit the 0x70000 part of the mask anyway.

This most likely never produced any guest-visible bugs, though, because
for a vhost device, qemu will probably not evaluate the used index
outside of virtio_queue_packed_get_last_avail_idx(), where we
reconstruct the 32-bit value from avail and used indices and their wrap
counters again.  There, it does not matter whether the highest bit of
the used_idx is the used index wrap counter, because we put the wrap
counter exactly in that position anyway.

Signed-off-by: Hanna Czenczek <hreitz@redhat.com>
Message-Id: <20230721134945.26967-1-hreitz@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: German Maglione <gmaglione@redhat.com>