xfrm: state: add sequence count to detect hash resizes

Once xfrm_state_find is lockless we have to cope with a concurrent
resize opertion.

We use a sequence counter to block in case a resize is in progress
and to detect if we might have missed a state that got moved to
a new hash table.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 8e373876924f7dd3669f91ff17b6dc6bd8c24e01..ac4037cf6a29aa0bd5e6d9b1253da0c7f13d9dcc 100644 (file)
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -36,6 +36,7 @@
  */
 
 static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
+static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation);
 
 static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x)
 {
@@ -127,6 +128,7 @@ static void xfrm_hash_resize(struct work_struct *work)
        }
 
        spin_lock_bh(&net->xfrm.xfrm_state_lock);
+       write_seqcount_begin(&xfrm_state_hash_generation);
 
        nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
        for (i = net->xfrm.state_hmask; i >= 0; i--)
@@ -143,6 +145,7 @@ static void xfrm_hash_resize(struct work_struct *work)
        net->xfrm.state_byspi = nspi;
        net->xfrm.state_hmask = nhashmask;
 
+       write_seqcount_end(&xfrm_state_hash_generation);
        spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
        osize = (ohashmask + 1) * sizeof(struct hlist_head);
@@ -787,10 +790,13 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
        struct xfrm_state *best = NULL;
        u32 mark = pol->mark.v & pol->mark.m;
        unsigned short encap_family = tmpl->encap_family;
+       unsigned int sequence;
        struct km_event c;
 
        to_put = NULL;
 
+       sequence = read_seqcount_begin(&xfrm_state_hash_generation);
+
        spin_lock_bh(&net->xfrm.xfrm_state_lock);
        h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
        hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
@@ -894,6 +900,15 @@ out:
        spin_unlock_bh(&net->xfrm.xfrm_state_lock);
        if (to_put)
                xfrm_state_put(to_put);
+
+       if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) {
+               *err = -EAGAIN;
+               if (x) {
+                       xfrm_state_put(x);
+                       x = NULL;
+               }
+       }
+
        return x;
 }