[ofa-general] Re: re [NET]: Fix neighbour destructor handling
Michael S. Tsirkin
mst at dev.mellanox.co.il
Tue Apr 10 07:08:34 PDT 2007
Quoting Or Gerlitz <ogerlitz at voltaire.com>:
Subject: re [NET]: Fix neighbour destructor handling
Hi Michael,
I just came across this patch, can you educate me a little what is the
implication (what problem it came to solve, if there is such) on ipoib?
thanks!
Or.
> From: Alexey Kuznetsov <kuznet at ms2.inr.ac.ru>
> Date: Sat, 24 Mar 2007 19:52:16 +0000 (-0700)
> Subject: [NET]: Fix neighbour destructor handling.
> X-Git-Tag: v2.6.21-rc6~114^2~14
> X-Git-Url: http://git.kernel.org/?p=linux%2Fkernel%2Fgit%2Ftorvalds%2Flinux-2.6.git;a=commitdiff_plain;h=ecbb416939da77c0d107409976499724baddce7b
>
> [NET]: Fix neighbour destructor handling.
>
> ->neigh_destructor() is killed (not used), replaced with
> ->neigh_cleanup(), which is called when neighbor entry goes to dead
> state. At this point everything is still valid: neigh->dev,
> neigh->parms etc.
>
> The device should guarantee that dead neighbor entries (neigh->dead !=
> 0) do not get private part initialized, otherwise nobody will cleanup
> it.
>
> I think this is enough for ipoib which is the only user of this thing.
> Initialization private part of neighbor entries happens in ipib
> start_xmit routine, which is not reached when device is down. But it
> would be better to add explicit test for neigh->dead in any case.
>
> Signed-off-by: David S. Miller <davem at davemloft.net>
Or,
you should find this in lkml or openfabrics archives.
Look for my message titled "dst_ifdown breaks infiniband"
and follow the discussion.
--
MST
More information about the general
mailing list