RE: Re: [PATCH RFC] RDMA/core: Store zero GIDs in some cases

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 




> -----Original Message-----
> From: Jason Gunthorpe <jgg@xxxxxxxx>
> Sent: Friday, 28 April 2023 16:04
> To: Chuck Lever III <chuck.lever@xxxxxxxxxx>
> Cc: Chuck Lever <cel@xxxxxxxxxx>; Bernard Metzler <BMT@xxxxxxxxxxxxxx>;
> linux-rdma <linux-rdma@xxxxxxxxxxxxxxx>; Linux NFS Mailing List <linux-
> nfs@xxxxxxxxxxxxxxx>
> Subject: [EXTERNAL] Re: [PATCH RFC] RDMA/core: Store zero GIDs in some
> cases
> 
> On Fri, Apr 28, 2023 at 01:58:53PM +0000, Chuck Lever III wrote:
> >
> >
> > > On Apr 28, 2023, at 9:47 AM, Jason Gunthorpe <jgg@xxxxxxxx> wrote:
> > >
> > > On Fri, Apr 28, 2023 at 01:42:24PM +0000, Chuck Lever III wrote:
> > >>
> > >>
> > >>> On Apr 28, 2023, at 9:39 AM, Jason Gunthorpe <jgg@xxxxxxxx> wrote:
> > >>>
> > >>> On Thu, Apr 27, 2023 at 01:14:43PM -0400, Chuck Lever wrote:
> > >>>> From: Bernard Metzler <bmt@xxxxxxxxxxxxxx>
> > >>>>
> > >>>> Tunnel devices have zero GIDs, so skip the zero GID check when
> > >>>> setting up soft iWARP over a tunnel device.
> > >>>
> > >>> Huh? Why? How does that make any sense?
> > >>
> > >> Read it as a cry for help.
> > >>
> > >> The scenario is attempting to set up a soft iWARP device
> > >> with a slave that is a tunnel device. The set up seems to
> > >> work, but when connecting, the ULP gets an ADDR_ERROR
> > >> because the setup did not add an entry to the GID table.
> > >
> > > Don't assign a 0 IP to the tunnel?
> >
> > That's a little cryptic... can you expand?
> >
> > Right now I have a Tailscale VPN device with assigned IP
> > addresses:
> >
> > 3: tailscale0: <POINTOPOINT,MULTICAST,NOARP,UP,LOWER_UP> mtu 1280
> qdisc fq_codel state UNKNOWN group default qlen 500
> >     link/none      inet 100.64.0.16/32 scope global tailscale0
> >        valid_lft forever preferred_lft forever
> >     inet6 fd7a:115c:a1e0::10/128 scope global         valid_lft
> forever preferred_lft forever
> >     inet6 fe80::725c:1b6d:60ed:fce4/64 scope link stable-privacy
> valid_lft forever preferred_lft forever
> >
> > And after that i/f is UP, I've done this:
> 
> That seems OK..
> 
> >  $ sudo rdma link add siw0 type siw netdev tailscale0
> >
> > With the patch I sent, I can do NFS/RDMA via soft iWARP through
> > the tunnel. I'm not at all claiming that's a good fix, but only
> > that this scenario is supposed to work, but currently doesn't.
> 
> Then there is something wrong in SIW, it should not be reporting 0
> GIDs to the core code for that kind of device.
> 
> I don't remember what iwarp uses for it's guid format .. Maybe it was
> mac adress or something and tunnels don't have a MAC, it should make
> up a dummy GID for the tunnel instead of using 0..
> 
Yes. it is taken from the MAC address and we don't have one
here. I don't remember the iwcm code by heart - maybe any unique
GID makes it and there is no need to have the MAC there.
Unfortunately I cannot look into it deeper
right now since away from my desk a long time, until end of
May. Sorry about that confusion.

Bernard




[Index of Archives]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Photo]     [Yosemite News]     [Yosemite Photos]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux