The xen-9p disconnect path has two issues:
1. It frees the Xen9pfsRing structures while in-flight PDUs may still
reference them via pdu->tag to index rings[]. This causes a UAF
in xen_9pfs_push_and_notify() when worker threads resume after
completing filesystem operations.
2. It never calls v9fs_device_unrealize_common(), which means server
state (struct LocalData, mountfd, FIDs) is never cleaned up on
disconnect, causing a resource leak on every guest-initiated
disconnect.
Fix both by draining in-flight PDUs via v9fs_reset() before tearing
down rings, and calling v9fs_device_unrealize_common() to clean up
server state.
Additionally, explicit calls of xen_9pfs_disconnect() in the error
paths of xen_9pfs_pdu_vmarshal() and xen_9pfs_pdu_vunmarshal() must
be deferred (via aio_bh_schedule_oneshot()), because
xen_9pfs_pdu_v(un)marshal() are running within a coroutine context
which makes them unsafe [1] for calling v9fs_reset() directly, as
the latter e.g. has a loop like:
while (!QLIST_EMPTY(&s->active_list)) {
aio_poll(qemu_get_aio_context(), true);
}
which would a) never terminate (as the coroutine is on the
active_list) and b) aio_poll() is marked as no_coroutine_fn.
[1] https://lore.kernel.org/qemu-devel/3351181.5fSG56mABF@weasel/
And finally, add an idempotent guard to xen_9pfs_disconnect(),
just for the case.
Fixes: b37eeb0201 ("xen/9pfs: introduce Xen 9pfs backend")
Signed-off-by: Christian Schoenebeck <[email protected]>
---
hw/9pfs/xen-9p-backend.c | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)
diff --git a/hw/9pfs/xen-9p-backend.c b/hw/9pfs/xen-9p-backend.c
index 24c90d97ec..edb65a7afc 100644
--- a/hw/9pfs/xen-9p-backend.c
+++ b/hw/9pfs/xen-9p-backend.c
@@ -68,6 +68,11 @@ typedef struct Xen9pfsDev {
static void xen_9pfs_disconnect(struct XenLegacyDevice *xendev);
+static void xen_9pfs_disconnect_bh(void *opaque)
+{
+ xen_9pfs_disconnect(opaque);
+}
+
static void xen_9pfs_in_sg(Xen9pfsRing *ring,
struct iovec *in_sg,
int *num,
@@ -150,7 +155,8 @@ static ssize_t xen_9pfs_pdu_vmarshal(V9fsPDU *pdu,
"Failed to encode VirtFS reply type %d\n",
pdu->id + 1);
xen_be_set_state(&xen_9pfs->xendev, XenbusStateClosing);
- xen_9pfs_disconnect(&xen_9pfs->xendev);
+ aio_bh_schedule_oneshot(qemu_get_aio_context(),
+ xen_9pfs_disconnect_bh, &xen_9pfs->xendev);
}
return ret;
}
@@ -173,7 +179,8 @@ static ssize_t xen_9pfs_pdu_vunmarshal(V9fsPDU *pdu,
xen_pv_printf(&xen_9pfs->xendev, 0,
"Failed to decode VirtFS request type %d\n", pdu->id);
xen_be_set_state(&xen_9pfs->xendev, XenbusStateClosing);
- xen_9pfs_disconnect(&xen_9pfs->xendev);
+ aio_bh_schedule_oneshot(qemu_get_aio_context(),
+ xen_9pfs_disconnect_bh, &xen_9pfs->xendev);
}
return ret;
}
@@ -368,10 +375,18 @@ static void xen_9pfs_evtchn_event(void *opaque)
static void xen_9pfs_disconnect(struct XenLegacyDevice *xendev)
{
Xen9pfsDev *xen_9pdev = container_of(xendev, Xen9pfsDev, xendev);
+ V9fsState *s = &xen_9pdev->state;
int i;
+ if (!xen_9pdev->rings) {
+ return;
+ }
+
trace_xen_9pfs_disconnect(xendev->name);
+ v9fs_reset(s);
+ v9fs_device_unrealize_common(s);
+
for (i = 0; i < xen_9pdev->num_rings; i++) {
if (xen_9pdev->rings[i].evtchndev != NULL) {
qemu_set_fd_handler(qemu_xen_evtchn_fd(xen_9pdev->rings[i].evtchndev),
--
2.47.3
