[openib-general] [PATCH]IPOIB: delete neigh from the list before kfree(neigh)

[Roland Dreier]

    Shirley> I did see one race during stress test on SMP, when going
    Shirley> through neigh_list, neigh->ah revisited a freed
    Shirley> memory. After applying this patch the problem was gone. I
    Shirley> need to go through my test to see where is the race.

By the way, do you still have the oops stack trace for this?

The proposed patch I posted for IPoIB did fix one potential problem:
ipoib_neigh_destructor() looked at *to_ipoib_neigh(n) outside of
priv->lock, which could race against other freeing of the neigh.  So
my patch may also fix this problem.

If we apply the patch in this thread, I'd be afraid that we're just
making a race window smaller, since I don't see what it's fixing.

 - R.