[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAJedcCxAjsahL1MAjHMfZkOWZD5Rnbq-vgFTvUfFU3zXMUWCaQ@mail.gmail.com>
Date: Tue, 14 Feb 2023 10:36:56 +0800
From: Zheng Hacker <hackerzheng666@...il.com>
To: "Michael S. Tsirkin" <mst@...hat.com>
Cc: Zheng Wang <zyytlz.wz@....com>, jasowang@...hat.com,
pbonzini@...hat.com, stefanha@...hat.com, jejb@...ux.ibm.com,
martin.petersen@...cle.com,
virtualization@...ts.linux-foundation.org,
linux-scsi@...r.kernel.org, linux-kernel@...r.kernel.org,
security@...nel.org, alex000young@...il.com
Subject: Re: [PATCH v2] scsi: virtio_scsi: Fix poential NULL pointer
dereference in virtscsi_rescan_hotunplug
Michael S. Tsirkin <mst@...hat.com> 于2023年2月13日周一 20:09写道:
>
> On Thu, Feb 02, 2023 at 02:41:24PM +0800, Zheng Wang wrote:
> > There is no check about the return value of kmalloc in
> > virtscsi_rescan_hotunplug. Add the check to avoid use
> > of null pointer 'inq_result' in case of the failure
> > of kmalloc.
> >
> > Signed-off-by: Zheng Wang <zyytlz.wz@....com>
> > ---
>
> I fixed a typo in subject and tweaked the patch a bit
Thanks for your kindness ^^
>
> > v2:
> > - add kfree to avoid memory leak
> > ---
> > drivers/scsi/virtio_scsi.c | 13 +++++++++++--
> > 1 file changed, 11 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
> > index d07d24c06b54..a66d8815d738 100644
> > --- a/drivers/scsi/virtio_scsi.c
> > +++ b/drivers/scsi/virtio_scsi.c
> > @@ -330,7 +330,7 @@ static void virtscsi_handle_param_change(struct virtio_scsi *vscsi,
> > scsi_device_put(sdev);
> > }
> >
> > -static void virtscsi_rescan_hotunplug(struct virtio_scsi *vscsi)
> > +static int virtscsi_rescan_hotunplug(struct virtio_scsi *vscsi)
> > {
> > struct scsi_device *sdev;
> > struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
> > @@ -338,6 +338,11 @@ static void virtscsi_rescan_hotunplug(struct virtio_scsi *vscsi)
> > int result, inquiry_len, inq_result_len = 256;
> > char *inq_result = kmalloc(inq_result_len, GFP_KERNEL);
> >
> > + if (!inq_result) {
> > + kfree(inq_result);
> > + return -ENOMEM;
> > + }
> > +
> > shost_for_each_device(sdev, shost) {
> > inquiry_len = sdev->inquiry_len ? sdev->inquiry_len : 36;
> >
> > @@ -366,6 +371,7 @@ static void virtscsi_rescan_hotunplug(struct virtio_scsi *vscsi)
> > }
> >
> > kfree(inq_result);
> > + return 0;
> > }
> >
> > static void virtscsi_handle_event(struct work_struct *work)
> > @@ -374,12 +380,15 @@ static void virtscsi_handle_event(struct work_struct *work)
> > container_of(work, struct virtio_scsi_event_node, work);
> > struct virtio_scsi *vscsi = event_node->vscsi;
> > struct virtio_scsi_event *event = &event_node->event;
> > + int ret = 0;
> >
>
> dropped = 0 here
Get it.
>
> > if (event->event &
> > cpu_to_virtio32(vscsi->vdev, VIRTIO_SCSI_T_EVENTS_MISSED)) {
>
> and moved declaration here.
Will do in the next version of patch.
>
> > event->event &= ~cpu_to_virtio32(vscsi->vdev,
> > VIRTIO_SCSI_T_EVENTS_MISSED);
> > - virtscsi_rescan_hotunplug(vscsi);
> > + ret = virtscsi_rescan_hotunplug(vscsi);
> > + if (ret)
> > + return;
> > scsi_scan_host(virtio_scsi_host(vscsi->vdev));
> > }
> >
> > --
> > 2.25.1
> >
> >
>
Powered by blists - more mailing lists