xfrm: state: fix out-of-bounds read during lookup

xfrm: state: fix out-of-bounds read during lookup

lookup and resize can run in parallel.

The xfrm_state_hash_generation seqlock ensures a retry, but the hash
functions can observe a hmask value that is too large for the new hlist
array.

rehash does:
  rcu_assign_pointer(net->xfrm.state_bydst, ndst) [..]
  net->xfrm.state_hmask = nhashmask;

While state lookup does:
  h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
  hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {

This is only safe in case the update to state_bydst is larger than
net->xfrm.xfrm_state_hmask (or if the lookup function gets
serialized via state spinlock again).

Fix this by prefetching state_hmask and the associated pointers.
The xfrm_state_hash_generation seqlock retry will ensure that the pointer
and the hmask will be consistent.

The existing helpers, like xfrm_dst_hash(), are now unsafe for RCU side,
add lockdep assertions to document that they are only safe for insert
side.

xfrm_state_lookup_byaddr() uses the spinlock rather than RCU.
AFAICS this is an oversight from back when state lookup was converted to
RCU, this lock should be replaced with RCU in a future patch.

Reported-by: [email protected]
Closes: https://lore.kernel.org/netdev/CACT4Y+azwfrE3uz6A5ZErov5YN2LYBN5KrsymBerT36VU8qzBA@mail.gmail.com/
Diagnosed-by: Dmitry Vyukov <[email protected]>
Fixes: c2f672fc9464 ("xfrm: state lookup can be lockless")
Signed-off-by: Florian Westphal <[email protected]>
Signed-off-by: Steffen Klassert <[email protected]>