diff options
author | Alexander Duyck <alexander.h.duyck@redhat.com> | 2015-03-10 14:39:34 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2015-03-10 18:36:56 -0400 |
commit | ddb4b9a1328ea89733133e86cf1972d23891abfc (patch) | |
tree | 39e6b01f93a37c97fa6721ff7fa0976cd44a0555 /net/tipc/bearer.c | |
parent | 416377ea392823e8ea1f8a10477e7d08a9bb715e (diff) | |
download | linux-stable-ddb4b9a1328ea89733133e86cf1972d23891abfc.tar.gz linux-stable-ddb4b9a1328ea89733133e86cf1972d23891abfc.tar.bz2 linux-stable-ddb4b9a1328ea89733133e86cf1972d23891abfc.zip |
fib_trie: Address possible NULL pointer dereference in resize
If the inflate call failed it would return NULL. As a result tp would be
set to NULL and cause use to trigger a NULL pointer dereference in
should_halve if the inflate failed on the first attempt.
In order to prevent this we should decrement max_work before we actually
attempt to inflate as this will force us to exit before attempting to halve
a node we should have inflated. In order to keep things symmetric between
inflate and halve I went ahead and also moved the decrement of max_work for
the halve case as well so we take care of that before we actually attempt
to halve the tnode.
Fixes: 88bae714 ("fib_trie: Add key vector to root, return parent key_vector in resize")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/tipc/bearer.c')
0 files changed, 0 insertions, 0 deletions