net: xfrm: fix a race condition during allocing spi

we found that the following race condition exists in
xfrm_alloc_userspi flow:

user thread                                    state_hash_work thread
----                                           ----
xfrm_alloc_userspi()
 __find_acq_core()
   /*alloc new xfrm_state:x*/
   xfrm_state_alloc()
   /*schedule state_hash_work thread*/
   xfrm_hash_grow_check()   	               xfrm_hash_resize()
 xfrm_alloc_spi                                  /*hold lock*/
      x->id.spi = htonl(spi)                     spin_lock_bh(&net->xfrm.xfrm_state_lock)
      /*waiting lock release*/                     xfrm_hash_transfer()
      spin_lock_bh(&net->xfrm.xfrm_state_lock)      /*add x into hlist:net->xfrm.state_byspi*/
	                                                hlist_add_head_rcu(&x->byspi)
                                                 spin_unlock_bh(&net->xfrm.xfrm_state_lock)

    /*add x into hlist:net->xfrm.state_byspi 2 times*/
    hlist_add_head_rcu(&x->byspi)

1. a new state x is alloced in xfrm_state_alloc() and added into the bydst hlist
in  __find_acq_core() on the LHS;
2. on the RHS, state_hash_work thread travels the old bydst and tranfers every xfrm_state
(include x) into the new bydst hlist and new byspi hlist;
3. user thread on the LHS gets the lock and adds x into the new byspi hlist again.

So the same xfrm_state (x) is added into the same list_hash
(net->xfrm.state_byspi) 2 times that makes the list_hash become
an inifite loop.

To fix the race, x->id.spi = htonl(spi) in the xfrm_alloc_spi() is moved
to the back of spin_lock_bh, sothat state_hash_work thread no longer add x
which id.spi is zero into the hash_list.

Fixes: f034b5d4efdf ("[XFRM]: Dynamic xfrm_state hash table sizing.")
Signed-off-by: zhuoliang zhang <zhuoliang.zhang@mediatek.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index efc89a9..ee6ac32 100644 (file)
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2004,6 +2004,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
        int err = -ENOENT;
        __be32 minspi = htonl(low);
        __be32 maxspi = htonl(high);
+       __be32 newspi = 0;
        u32 mark = x->mark.v & x->mark.m;
 
        spin_lock_bh(&x->lock);
@@ -2022,21 +2023,22 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
                        xfrm_state_put(x0);
                        goto unlock;
                }
-               x->id.spi = minspi;
+               newspi = minspi;
        } else {
                u32 spi = 0;
                for (h = 0; h < high-low+1; h++) {
                        spi = low + prandom_u32()%(high-low+1);
                        x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
                        if (x0 == NULL) {
-                               x->id.spi = htonl(spi);
+                               newspi = htonl(spi);
                                break;
                        }
                        xfrm_state_put(x0);
                }
        }
-       if (x->id.spi) {
+       if (newspi) {
                spin_lock_bh(&net->xfrm.xfrm_state_lock);
+               x->id.spi = newspi;
                h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
                hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
                spin_unlock_bh(&net->xfrm.xfrm_state_lock);