This code in vhost_scsi_make_tpg() is confusing because we limit "tpgt" to UINT_MAX but the data type of "tpg->tport_tpgt" and that is a u16. I looked at the context and it turns out that in vhost_scsi_set_endpoint(), "tpg->tport_tpgt" is used as an offset into the vs_tpg[] array which has VHOST_SCSI_MAX_TARGET (256) elements so anything higher than 255 then it is invalid. I have made that the limit now. In vhost_scsi_send_evt() we mask away values higher than 255, but now that the limit has changed, we don't need the mask. Signed-off-by: Dan Carpenter <dan.carpenter at oracle.com> --- Compile tested only. diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 3e265ef..4339222 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1278,7 +1278,7 @@ vhost_scsi_send_evt(struct vhost_scsi *vs, * lun[4-7] need to be zero according to virtio-scsi spec. */ evt->event.lun[0] = 0x01; - evt->event.lun[1] = tpg->tport_tpgt & 0xFF; + evt->event.lun[1] = tpg->tport_tpgt; if (lun->unpacked_lun >= 256) evt->event.lun[2] = lun->unpacked_lun >> 8 | 0x40 ; evt->event.lun[3] = lun->unpacked_lun & 0xFF; @@ -2149,12 +2149,12 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, struct vhost_scsi_tport, tport_wwn); struct vhost_scsi_tpg *tpg; - unsigned long tpgt; + u16 tpgt; int ret; if (strstr(name, "tpgt_") != name) return ERR_PTR(-EINVAL); - if (kstrtoul(name + 5, 10, &tpgt) || tpgt > UINT_MAX) + if (kstrtou16(name + 5, 10, &tpgt) || tpgt >= VHOST_SCSI_MAX_TARGET) return ERR_PTR(-EINVAL); tpg = kzalloc(sizeof(struct vhost_scsi_tpg), GFP_KERNEL);
Nicholas A. Bellinger
2015-Feb-06 18:48 UTC
[patch] vhost/scsi: potential memory corruption
On Thu, 2015-02-05 at 10:37 +0300, Dan Carpenter wrote:> This code in vhost_scsi_make_tpg() is confusing because we limit "tpgt" > to UINT_MAX but the data type of "tpg->tport_tpgt" and that is a u16. > > I looked at the context and it turns out that in > vhost_scsi_set_endpoint(), "tpg->tport_tpgt" is used as an offset into > the vs_tpg[] array which has VHOST_SCSI_MAX_TARGET (256) elements so > anything higher than 255 then it is invalid. I have made that the limit > now. > > In vhost_scsi_send_evt() we mask away values higher than 255, but now > that the limit has changed, we don't need the mask. > > Signed-off-by: Dan Carpenter <dan.carpenter at oracle.com> > --- > Compile tested only. > > diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c > index 3e265ef..4339222 100644 > --- a/drivers/vhost/scsi.c > +++ b/drivers/vhost/scsi.c > @@ -1278,7 +1278,7 @@ vhost_scsi_send_evt(struct vhost_scsi *vs, > * lun[4-7] need to be zero according to virtio-scsi spec. > */ > evt->event.lun[0] = 0x01; > - evt->event.lun[1] = tpg->tport_tpgt & 0xFF; > + evt->event.lun[1] = tpg->tport_tpgt; > if (lun->unpacked_lun >= 256) > evt->event.lun[2] = lun->unpacked_lun >> 8 | 0x40 ; > evt->event.lun[3] = lun->unpacked_lun & 0xFF; > @@ -2149,12 +2149,12 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, > struct vhost_scsi_tport, tport_wwn); > > struct vhost_scsi_tpg *tpg; > - unsigned long tpgt; > + u16 tpgt; > int ret; > > if (strstr(name, "tpgt_") != name) > return ERR_PTR(-EINVAL); > - if (kstrtoul(name + 5, 10, &tpgt) || tpgt > UINT_MAX) > + if (kstrtou16(name + 5, 10, &tpgt) || tpgt >= VHOST_SCSI_MAX_TARGET) > return ERR_PTR(-EINVAL); > > tpg = kzalloc(sizeof(struct vhost_scsi_tpg), GFP_KERNEL);Nice catch Dan. Applied to target-pending/for-next. --nab
Apparently Analagous Threads
- [patch] vhost/scsi: potential memory corruption
- [PATCH 1/2] vhost/scsi: Improve a size determination in four functions
- [PATCH 0/2] vhost/scsi: Adjustments for five function implementations
- [PATCH 0/2] vhost/scsi: Adjustments for five function implementations
- [PATCH v2 0/7] vhost-scsi: Fix crashes and management op hangs