| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 9 Jul 2021 11:42:22 +0200
From: Roger Pau Monné <roger.pau@...rix.com>
To: Juergen Gross <jgross@...e.com>
CC: <xen-devel@...ts.xenproject.org>, <linux-block@...r.kernel.org>,
<linux-kernel@...r.kernel.org>,
Boris Ostrovsky <boris.ostrovsky@...cle.com>,
Stefano Stabellini <sstabellini@...nel.org>,
Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
Jens Axboe <axboe@...nel.dk>
Subject: Re: [PATCH v2 3/3] xen/blkfront: don't trust the backend response
data blindly
On Thu, Jul 08, 2021 at 02:43:45PM +0200, Juergen Gross wrote:
> 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).
>
> Signed-off-by: Juergen Gross <jgross@...e.com>
Acked-by: Roger Pau Monné <roger.pau@...rix.com>
> ---
> V2:
> - use READ_ONCE() for reading the producer index
> - check validity of producer index only after memory barrier (Jan Beulich)
> - use virt_rmb() as barrier (Jan Beulich)
> ---
> drivers/block/xen-blkfront.c | 66 ++++++++++++++++++++++++++----------
> 1 file changed, 49 insertions(+), 17 deletions(-)
>
> diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
> index 80701860870a..ecdbb0381b4c 100644
> --- a/drivers/block/xen-blkfront.c
> +++ b/drivers/block/xen-blkfront.c
> @@ -80,6 +80,7 @@ enum blkif_state {
> BLKIF_STATE_DISCONNECTED,
> BLKIF_STATE_CONNECTED,
> BLKIF_STATE_SUSPENDED,
> + BLKIF_STATE_ERROR,
> };
>
> struct grant {
> @@ -89,6 +90,7 @@ struct grant {
> };
>
> enum blk_req_status {
> + REQ_PROCESSING,
> REQ_WAITING,
> REQ_DONE,
> REQ_ERROR,
> @@ -543,7 +545,7 @@ static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo,
>
> 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;
> @@ -572,6 +574,7 @@ static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_inf
>
> /* Copy the request to the ring page. */
> *final_ring_req = *ring_req;
> + rinfo->shadow[id].status = REQ_WAITING;
>
> return 0;
> }
> @@ -847,8 +850,11 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
>
> /* 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 (new_persistent_gnts)
> gnttab_free_grant_references(setup.gref_head);
> @@ -1402,8 +1408,8 @@ static enum blk_req_status blkif_rsp_to_req_status(int rsp)
> 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;
> @@ -1436,7 +1442,7 @@ static bool blkif_completion(unsigned long *id,
> 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 false;
>
> bret->status = blkif_get_final_status(s->status,
> @@ -1555,11 +1561,17 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
>
> 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'. */
Is the READ_ONCE strictly needed? Doesn't the barrier prevent rp from
not being loaded at this point?
> + 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 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
> * 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);
You could also use op_name here, but I guess this could mask the
operation as 'unknown' for any number out of the defined ones.
> + goto err;
> + }
> +
> if (bret.operation != BLKIF_OP_DISCARD) {
> /*
> * We may need to wait for an extra response if the
> @@ -1602,7 +1628,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
> 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));
> blkif_req(req)->error = BLK_STS_NOTSUPP;
> info->feature_discard = 0;
> @@ -1614,13 +1641,13 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
> 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));
> blkif_req(req)->error = BLK_STS_NOTSUPP;
> }
> 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));
> blkif_req(req)->error = BLK_STS_NOTSUPP;
> }
> @@ -1635,8 +1662,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
> 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);
Since you are touching the line, could you use %#x here? It's IMO not
obvious from the context this status will be printed in hex base. Also
bret.status parameter could be split into a newline.
Thanks, Roger.
Powered by blists - more mailing lists