xen/blkfront: don't trust the backend response data blindly
commit b94e4b147fd1992ad450e1fea1fdaa3738753373 upstream.
Today blkfront will trust the backend to send only sane response data.
In order to avoid privilege escalations or crashes in case of malicious
backends verify the data to be within expected limits. Especially make
sure that the response always references an outstanding request.
Introduce a new state of the ring BLKIF_STATE_ERROR which will be
switched to in case an inconsistency is being detected. Recovering from
this state is possible only via removing and adding the virtual device
again (e.g. via a suspend/resume cycle).
Make all warning messages issued due to valid error responses rate
limited in order to avoid message floods being triggered by a malicious
backend.
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Link: https://lore.kernel.org/r/20210730103854.12681-4-jgross@suse.com
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index d477d04..df58e7d 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -78,6 +78,7 @@
BLKIF_STATE_DISCONNECTED,
BLKIF_STATE_CONNECTED,
BLKIF_STATE_SUSPENDED,
+ BLKIF_STATE_ERROR,
};
struct grant {
@@ -87,6 +88,7 @@
};
enum blk_req_status {
+ REQ_PROCESSING,
REQ_WAITING,
REQ_DONE,
REQ_ERROR,
@@ -529,7 +531,7 @@
id = get_id_from_freelist(rinfo);
rinfo->shadow[id].request = req;
- rinfo->shadow[id].status = REQ_WAITING;
+ rinfo->shadow[id].status = REQ_PROCESSING;
rinfo->shadow[id].associated_id = NO_ASSOCIATED_ID;
rinfo->shadow[id].req.u.rw.id = id;
@@ -558,6 +560,7 @@
/* Copy the request to the ring page. */
*final_ring_req = *ring_req;
+ rinfo->shadow[id].status = REQ_WAITING;
return 0;
}
@@ -830,8 +833,11 @@
/* Copy request(s) to the ring page. */
*final_ring_req = *ring_req;
- if (unlikely(require_extra_req))
+ rinfo->shadow[id].status = REQ_WAITING;
+ if (unlikely(require_extra_req)) {
*final_extra_ring_req = *extra_ring_req;
+ rinfo->shadow[extra_id].status = REQ_WAITING;
+ }
if (max_grefs > 0)
gnttab_free_grant_references(setup.gref_head);
@@ -1401,8 +1407,8 @@
static int blkif_get_final_status(enum blk_req_status s1,
enum blk_req_status s2)
{
- BUG_ON(s1 == REQ_WAITING);
- BUG_ON(s2 == REQ_WAITING);
+ BUG_ON(s1 < REQ_DONE);
+ BUG_ON(s2 < REQ_DONE);
if (s1 == REQ_ERROR || s2 == REQ_ERROR)
return BLKIF_RSP_ERROR;
@@ -1435,7 +1441,7 @@
s->status = blkif_rsp_to_req_status(bret->status);
/* Wait the second response if not yet here. */
- if (s2->status == REQ_WAITING)
+ if (s2->status < REQ_DONE)
return 0;
bret->status = blkif_get_final_status(s->status,
@@ -1555,11 +1561,17 @@
spin_lock_irqsave(&rinfo->ring_lock, flags);
again:
- rp = rinfo->ring.sring->rsp_prod;
- rmb(); /* Ensure we see queued responses up to 'rp'. */
+ rp = READ_ONCE(rinfo->ring.sring->rsp_prod);
+ virt_rmb(); /* Ensure we see queued responses up to 'rp'. */
+ if (RING_RESPONSE_PROD_OVERFLOW(&rinfo->ring, rp)) {
+ pr_alert("%s: illegal number of responses %u\n",
+ info->gd->disk_name, rp - rinfo->ring.rsp_cons);
+ goto err;
+ }
for (i = rinfo->ring.rsp_cons; i != rp; i++) {
unsigned long id;
+ unsigned int op;
RING_COPY_RESPONSE(&rinfo->ring, i, &bret);
id = bret.id;
@@ -1570,14 +1582,28 @@
* look in get_id_from_freelist.
*/
if (id >= BLK_RING_SIZE(info)) {
- WARN(1, "%s: response to %s has incorrect id (%ld)\n",
- info->gd->disk_name, op_name(bret.operation), id);
- /* We can't safely get the 'struct request' as
- * the id is busted. */
- continue;
+ pr_alert("%s: response has incorrect id (%ld)\n",
+ info->gd->disk_name, id);
+ goto err;
}
+ if (rinfo->shadow[id].status != REQ_WAITING) {
+ pr_alert("%s: response references no pending request\n",
+ info->gd->disk_name);
+ goto err;
+ }
+
+ rinfo->shadow[id].status = REQ_PROCESSING;
req = rinfo->shadow[id].request;
+ op = rinfo->shadow[id].req.operation;
+ if (op == BLKIF_OP_INDIRECT)
+ op = rinfo->shadow[id].req.u.indirect.indirect_op;
+ if (bret.operation != op) {
+ pr_alert("%s: response has wrong operation (%u instead of %u)\n",
+ info->gd->disk_name, bret.operation, op);
+ goto err;
+ }
+
if (bret.operation != BLKIF_OP_DISCARD) {
/*
* We may need to wait for an extra response if the
@@ -1598,7 +1624,8 @@
case BLKIF_OP_DISCARD:
if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
struct request_queue *rq = info->rq;
- printk(KERN_WARNING "blkfront: %s: %s op failed\n",
+
+ pr_warn_ratelimited("blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret.operation));
error = -EOPNOTSUPP;
info->feature_discard = 0;
@@ -1611,13 +1638,13 @@
case BLKIF_OP_FLUSH_DISKCACHE:
case BLKIF_OP_WRITE_BARRIER:
if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
- printk(KERN_WARNING "blkfront: %s: %s op failed\n",
+ pr_warn_ratelimited("blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret.operation));
error = -EOPNOTSUPP;
}
if (unlikely(bret.status == BLKIF_RSP_ERROR &&
rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
- printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
+ pr_warn_ratelimited("blkfront: %s: empty %s op failed\n",
info->gd->disk_name, op_name(bret.operation));
error = -EOPNOTSUPP;
}
@@ -1632,8 +1659,9 @@
case BLKIF_OP_READ:
case BLKIF_OP_WRITE:
if (unlikely(bret.status != BLKIF_RSP_OKAY))
- dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
- "request: %x\n", bret.status);
+ dev_dbg_ratelimited(&info->xbdev->dev,
+ "Bad return from blkdev data request: %#x\n",
+ bret.status);
blk_mq_complete_request(req, error);
break;
@@ -1657,6 +1685,14 @@
spin_unlock_irqrestore(&rinfo->ring_lock, flags);
return IRQ_HANDLED;
+
+ err:
+ info->connected = BLKIF_STATE_ERROR;
+
+ spin_unlock_irqrestore(&rinfo->ring_lock, flags);
+
+ pr_alert("%s disabled for further use\n", info->gd->disk_name);
+ return IRQ_HANDLED;
}