diff options
author | Frederic Weisbecker <frederic@kernel.org> | 2021-06-28 15:34:28 +0200 |
---|---|---|
committer | Steffen Klassert <steffen.klassert@secunet.com> | 2021-07-02 09:27:55 +0200 |
commit | 2580d3f40022642452dd8422bfb8c22e54cf84bb (patch) | |
tree | 0c10c26a6d4bb8f398b40de983894a02bd13f7f1 /net/xfrm | |
parent | eaf228263921cd15962654b539d916380a0f076e (diff) | |
download | linux-2580d3f40022642452dd8422bfb8c22e54cf84bb.tar.bz2 |
xfrm: Fix RCU vs hash_resize_mutex lock inversion
xfrm_bydst_resize() calls synchronize_rcu() while holding
hash_resize_mutex. But then on PREEMPT_RT configurations,
xfrm_policy_lookup_bytype() may acquire that mutex while running in an
RCU read side critical section. This results in a deadlock.
In fact the scope of hash_resize_mutex is way beyond the purpose of
xfrm_policy_lookup_bytype() to just fetch a coherent and stable policy
for a given destination/direction, along with other details.
The lower level net->xfrm.xfrm_policy_lock, which among other things
protects per destination/direction references to policy entries, is
enough to serialize and benefit from priority inheritance against the
write side. As a bonus, it makes it officially a per network namespace
synchronization business where a policy table resize on namespace A
shouldn't block a policy lookup on namespace B.
Fixes: 77cc278f7b20 (xfrm: policy: Use sequence counters with associated lock)
Cc: stable@vger.kernel.org
Cc: Ahmed S. Darwish <a.darwish@linutronix.de>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Varad Gautam <varad.gautam@suse.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Diffstat (limited to 'net/xfrm')
-rw-r--r-- | net/xfrm/xfrm_policy.c | 17 |
1 files changed, 8 insertions, 9 deletions
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ce500f847b99..46a6d15b66d6 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -155,7 +155,6 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; static struct kmem_cache *xfrm_dst_cache __ro_after_init; -static __read_mostly seqcount_mutex_t xfrm_policy_hash_generation; static struct rhashtable xfrm_policy_inexact_table; static const struct rhashtable_params xfrm_pol_inexact_params; @@ -585,7 +584,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); - write_seqcount_begin(&xfrm_policy_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)); @@ -596,7 +595,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst); net->xfrm.policy_bydst[dir].hmask = nhashmask; - write_seqcount_end(&xfrm_policy_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); synchronize_rcu(); @@ -1245,7 +1244,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); - write_seqcount_begin(&xfrm_policy_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. @@ -1354,7 +1353,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) out_unlock: __xfrm_policy_inexact_flush(net); - write_seqcount_end(&xfrm_policy_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); @@ -2095,9 +2094,9 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, rcu_read_lock(); retry: do { - sequence = read_seqcount_begin(&xfrm_policy_hash_generation); + sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); chain = policy_hash_direct(net, daddr, saddr, family, dir); - } while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)); + } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)); ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { @@ -2128,7 +2127,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } skip_inexact: - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) + if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)) goto retry; if (ret && !xfrm_pol_hold_rcu(ret)) @@ -4084,6 +4083,7 @@ static int __net_init xfrm_net_init(struct net *net) /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); spin_lock_init(&net->xfrm.xfrm_policy_lock); + seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); rv = xfrm_statistics_init(net); @@ -4128,7 +4128,6 @@ void __init xfrm_init(void) { register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); - seqcount_mutex_init(&xfrm_policy_hash_generation, &hash_resize_mutex); xfrm_input_init(); #ifdef CONFIG_XFRM_ESPINTCP |