Re: [PATCH v2] xen-blkback: fix compatibility bug with single page rings

[Dongli Zhang <dongli.zhang@oracle.com>]

On 1/28/21 5:04 AM, Paul Durrant wrote:
> From: Paul Durrant <pdurrant@amazon.com>
> 
> Prior to commit 4a8c31a1c6f5 ("xen/blkback: rework connect_ring() to avoid
> inconsistent xenstore 'ring-page-order' set by malicious blkfront"), the
> behaviour of xen-blkback when connecting to a frontend was:
> 
> - read 'ring-page-order'
> - if not present then expect a single page ring specified by 'ring-ref'
> - else expect a ring specified by 'ring-refX' where X is between 0 and
>   1 << ring-page-order
> 
> This was correct behaviour, but was broken by the afforementioned commit to
> become:
> 
> - read 'ring-page-order'
> - if not present then expect a single page ring (i.e. ring-page-order = 0)
> - expect a ring specified by 'ring-refX' where X is between 0 and
>   1 << ring-page-order
> - if that didn't work then see if there's a single page ring specified by
>   'ring-ref'
> 
> This incorrect behaviour works most of the time but fails when a frontend
> that sets 'ring-page-order' is unloaded and replaced by one that does not
> because, instead of reading 'ring-ref', xen-blkback will read the stale
> 'ring-ref0' left around by the previous frontend will try to map the wrong
> grant reference.
> 
> This patch restores the original behaviour.
> 
> Fixes: 4a8c31a1c6f5 ("xen/blkback: rework connect_ring() to avoid inconsistent xenstore 'ring-page-order' set by malicious blkfront")
> Signed-off-by: Paul Durrant <pdurrant@amazon.com>
> ---
> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> Cc: "Roger Pau Monné" <roger.pau@citrix.com>
> Cc: Jens Axboe <axboe@kernel.dk>
> Cc: Dongli Zhang <dongli.zhang@oracle.com>
> 
> v2:
>  - Remove now-spurious error path special-case when nr_grefs == 1
> ---
>  drivers/block/xen-blkback/common.h |  1 +
>  drivers/block/xen-blkback/xenbus.c | 38 +++++++++++++-----------------
>  2 files changed, 17 insertions(+), 22 deletions(-)
> 
> diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
> index b0c71d3a81a0..524a79f10de6 100644
> --- a/drivers/block/xen-blkback/common.h
> +++ b/drivers/block/xen-blkback/common.h
> @@ -313,6 +313,7 @@ struct xen_blkif {
>  
>  	struct work_struct	free_work;
>  	unsigned int 		nr_ring_pages;
> +	bool                    multi_ref;

Is it really necessary to introduce 'multi_ref' here or we may just re-use
'nr_ring_pages'?

According to blkfront code, 'ring-page-order' is set only when it is not zero,
that is, only when (info->nr_ring_pages > 1).

1819         if (info->nr_ring_pages > 1) {
1820                 err = xenbus_printf(xbt, dev->nodename, "ring-page-order",
"%u",
1821                                     ring_page_order);
1822                 if (err) {
1823                         message = "writing ring-page-order";
1824                         goto abort_transaction;
1825                 }
1826         }

Therefore, can we assume 'ring-page-order' can never be 0? Once we have
'ring-page-order' set, it should be >= 1 and we should read from "ring-ref%u"?

If the specification allows 'ring-page-order' to be zero with "ring-ref%u"
available, we should introduce 'multi_ref'.

Thank you very much!

Dongli Zhang


>  	/* All rings for this device. */
>  	struct xen_blkif_ring	*rings;
>  	unsigned int		nr_rings;
> diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
> index 9860d4842f36..6c5e9373e91c 100644
> --- a/drivers/block/xen-blkback/xenbus.c
> +++ b/drivers/block/xen-blkback/xenbus.c
> @@ -998,14 +998,17 @@ static int read_per_ring_refs(struct xen_blkif_ring *ring, const char *dir)
>  	for (i = 0; i < nr_grefs; i++) {
>  		char ring_ref_name[RINGREF_NAME_LEN];
>  
> -		snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
> +		if (blkif->multi_ref)
> +			snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
> +		else {
> +			WARN_ON(i != 0);
> +			snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref");
> +		}
> +
>  		err = xenbus_scanf(XBT_NIL, dir, ring_ref_name,
>  				   "%u", &ring_ref[i]);
>  
>  		if (err != 1) {
> -			if (nr_grefs == 1)
> -				break;
> -
>  			err = -EINVAL;
>  			xenbus_dev_fatal(dev, err, "reading %s/%s",
>  					 dir, ring_ref_name);
> @@ -1013,18 +1016,6 @@ static int read_per_ring_refs(struct xen_blkif_ring *ring, const char *dir)
>  		}
>  	}
>  
> -	if (err != 1) {
> -		WARN_ON(nr_grefs != 1);
> -
> -		err = xenbus_scanf(XBT_NIL, dir, "ring-ref", "%u",
> -				   &ring_ref[0]);
> -		if (err != 1) {
> -			err = -EINVAL;
> -			xenbus_dev_fatal(dev, err, "reading %s/ring-ref", dir);
> -			return err;
> -		}
> -	}
> -
>  	err = -ENOMEM;
>  	for (i = 0; i < nr_grefs * XEN_BLKIF_REQS_PER_PAGE; i++) {
>  		req = kzalloc(sizeof(*req), GFP_KERNEL);
> @@ -1129,10 +1120,15 @@ static int connect_ring(struct backend_info *be)
>  		 blkif->nr_rings, blkif->blk_protocol, protocol,
>  		 blkif->vbd.feature_gnt_persistent ? "persistent grants" : "");
>  
> -	ring_page_order = xenbus_read_unsigned(dev->otherend,
> -					       "ring-page-order", 0);
> -
> -	if (ring_page_order > xen_blkif_max_ring_order) {
> +	err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-page-order", "%u",
> +			   &ring_page_order);
> +	if (err != 1) {
> +		blkif->nr_ring_pages = 1;
> +		blkif->multi_ref = false;
> +	} else if (ring_page_order <= xen_blkif_max_ring_order) {
> +		blkif->nr_ring_pages = 1 << ring_page_order;
> +		blkif->multi_ref = true;
> +	} else {
>  		err = -EINVAL;
>  		xenbus_dev_fatal(dev, err,
>  				 "requested ring page order %d exceed max:%d",
> @@ -1141,8 +1137,6 @@ static int connect_ring(struct backend_info *be)
>  		return err;
>  	}
>  
> -	blkif->nr_ring_pages = 1 << ring_page_order;
> -
>  	if (blkif->nr_rings == 1)
>  		return read_per_ring_refs(&blkif->rings[0], dev->otherend);
>  	else {
>