Linux Virtualization - Oct 2013 - [PATCH] vhost/scsi: Fix incorrect usage of get_user_pages_fast write parameter

From: Nicholas Bellinger <nab at linux-iscsi.org>

This patch addresses a long-standing bug where the get_user_pages_fast()
write parameter used for setting the underlying page table entry permission
bits was incorrectly set to write=1 for data_direction=DMA_TO_DEVICE, and
passed into get_user_pages_fast() via vhost_scsi_map_iov_to_sgl().

However, this parameter is intended to signal WRITEs to pinned userspace
PTEs for the virtio-scsi DMA_FROM_DEVICE -> READ payload case, and *not*
for the virtio-scsi DMA_TO_DEVICE -> WRITE payload case.

This bug would manifest itself as random process segmentation faults on
KVM host after repeated vhost starts + stops and/or with lots of vhost
endpoints + LUNs.

Cc: Stefan Hajnoczi <stefanha at redhat.com>
Cc: Michael S. Tsirkin <mst at redhat.com>
Cc: Asias He <asias at redhat.com>
Cc: <stable at vger.kernel.org> # 3.6+
Signed-off-by: Nicholas Bellinger <nab at linux-iscsi.org>
---
 drivers/vhost/scsi.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index ce5221f..e663921 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1056,7 +1056,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct
vhost_virtqueue *vq)
 		if (data_direction != DMA_NONE) {
 			ret = vhost_scsi_map_iov_to_sgl(cmd,
 					&vq->iov[data_first], data_num,
-					data_direction == DMA_TO_DEVICE);
+					data_direction == DMA_FROM_DEVICE);
 			if (unlikely(ret)) {
 				vq_err(vq, "Failed to map iov to sgl\n");
 				goto err_free;
-- 
1.7.2.5

On Fri, Oct 25, 2013 at 06:07:16PM +0000, Nicholas A. Bellinger
wrote:
> From: Nicholas Bellinger <nab at linux-iscsi.org>
> 
> This patch addresses a long-standing bug where the get_user_pages_fast()
> write parameter used for setting the underlying page table entry permission
> bits was incorrectly set to write=1 for data_direction=DMA_TO_DEVICE, and
> passed into get_user_pages_fast() via vhost_scsi_map_iov_to_sgl().
> 
> However, this parameter is intended to signal WRITEs to pinned userspace
> PTEs for the virtio-scsi DMA_FROM_DEVICE -> READ payload case, and *not*
> for the virtio-scsi DMA_TO_DEVICE -> WRITE payload case.
> 
> This bug would manifest itself as random process segmentation faults on
> KVM host after repeated vhost starts + stops and/or with lots of vhost
> endpoints + LUNs.
> 
> Cc: Stefan Hajnoczi <stefanha at redhat.com>
> Cc: Michael S. Tsirkin <mst at redhat.com>
> Cc: Asias He <asias at redhat.com>
> Cc: <stable at vger.kernel.org> # 3.6+
> Signed-off-by: Nicholas Bellinger <nab at linux-iscsi.org>
Reviewed-by: Asias He <asias at redhat.com>
> ---
>  drivers/vhost/scsi.c |    2 +-
>  1 files changed, 1 insertions(+), 1 deletions(-)
> 
> diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
> index ce5221f..e663921 100644
> --- a/drivers/vhost/scsi.c
> +++ b/drivers/vhost/scsi.c
> @@ -1056,7 +1056,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct
vhost_virtqueue *vq)
>  		if (data_direction != DMA_NONE) {
>  			ret = vhost_scsi_map_iov_to_sgl(cmd,
>  					&vq->iov[data_first], data_num,
> -					data_direction == DMA_TO_DEVICE);
> +					data_direction == DMA_FROM_DEVICE);
>  			if (unlikely(ret)) {
>  				vq_err(vq, "Failed to map iov to sgl\n");
>  				goto err_free;
> -- 
> 1.7.2.5
> 
-- 
Asias

On Fri, Oct 25, 2013 at 06:07:16PM +0000, Nicholas A. Bellinger
wrote:
> From: Nicholas Bellinger <nab at linux-iscsi.org>
> 
> This patch addresses a long-standing bug where the get_user_pages_fast()
> write parameter used for setting the underlying page table entry permission
> bits was incorrectly set to write=1 for data_direction=DMA_TO_DEVICE, and
> passed into get_user_pages_fast() via vhost_scsi_map_iov_to_sgl().
> 
> However, this parameter is intended to signal WRITEs to pinned userspace
> PTEs for the virtio-scsi DMA_FROM_DEVICE -> READ payload case, and *not*
> for the virtio-scsi DMA_TO_DEVICE -> WRITE payload case.
> 
> This bug would manifest itself as random process segmentation faults on
> KVM host after repeated vhost starts + stops and/or with lots of vhost
> endpoints + LUNs.
> 
> Cc: Stefan Hajnoczi <stefanha at redhat.com>
> Cc: Michael S. Tsirkin <mst at redhat.com>
> Cc: Asias He <asias at redhat.com>
> Cc: <stable at vger.kernel.org> # 3.6+
> Signed-off-by: Nicholas Bellinger <nab at linux-iscsi.org>
Acked-by: Michael S. Tsirkin <mst at redhat.com>
> ---
>  drivers/vhost/scsi.c |    2 +-
>  1 files changed, 1 insertions(+), 1 deletions(-)
> 
> diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
> index ce5221f..e663921 100644
> --- a/drivers/vhost/scsi.c
> +++ b/drivers/vhost/scsi.c
> @@ -1056,7 +1056,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct
vhost_virtqueue *vq)
>  		if (data_direction != DMA_NONE) {
>  			ret = vhost_scsi_map_iov_to_sgl(cmd,
>  					&vq->iov[data_first], data_num,
> -					data_direction == DMA_TO_DEVICE);
> +					data_direction == DMA_FROM_DEVICE);
>  			if (unlikely(ret)) {
>  				vq_err(vq, "Failed to map iov to sgl\n");
>  				goto err_free;
> -- 
> 1.7.2.5