Re: [Nbd] [PATCH] nbd: Zero from and len fields in NBD_CMD_DISCONNECT.
On Sun, May 18, 2014 at 10:11:13AM +0100, Hani Benhabiles wrote:
> On Fri, May 16, 2014 at 10:56:33PM -0400, Paul Clements wrote:
> > Agreed. But better yet, the request structure should just be zeroed when
> > it's allocated.
> >
>
> It is already initialized in __nbd_ioctl() with the blk_rq_init() call which
> sets the __sector value to -1 (which is 0xfffffffffffffe00 after the left shifts.)
>
> This is the only (non-ugly / non-intrusive) way to do it afaict.
>
Ping!
Anything blocking this patch ?
Thanks.
> > --
> > Paul
> >
> >
> > On Fri, May 16, 2014 at 7:43 PM, Hani Benhabiles <kroosec@...17...> wrote:
> >
> > > Len field is already set to zero, but not the from field which is sent as
> > > 0xfffffffffffffe00. This makes no sense, and may cause confuse server
> > > implementations doing sanity checks (qemu-nbd is an example.)
> > >
> > > Signed-off-by: Hani Benhabiles <hani@...1598...>
> > > ---
> > > drivers/block/nbd.c | 2 +-
> > > 1 file changed, 1 insertion(+), 1 deletion(-)
> > >
> > > diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
> > > index 3a70ea2..657bdac 100644
> > > --- a/drivers/block/nbd.c
> > > +++ b/drivers/block/nbd.c
> > > @@ -246,7 +246,7 @@ static int nbd_send_req(struct nbd_device *nbd, struct
> > > request *req)
> > > request.magic = htonl(NBD_REQUEST_MAGIC);
> > > request.type = htonl(nbd_cmd(req));
> > >
> > > - if (nbd_cmd(req) == NBD_CMD_FLUSH) {
> > > + if (nbd_cmd(req) == NBD_CMD_FLUSH || nbd_cmd(req) == NBD_CMD_DISC)
> > > {
> > > /* Other values are reserved for FLUSH requests. */
> > > request.from = 0;
> > > request.len = 0;
> > > --
> > > 1.8.3.2
> > >
> > >
Reply to: