aboutsummaryrefslogtreecommitdiff
path: root/net/xfrm
diff options
context:
space:
mode:
authorVarad Gautam2021-05-28 18:04:06 +0200
committerSteffen Klassert2021-06-01 07:48:46 +0200
commitd7b0408934c749f546b01f2b33d07421a49b6f3e (patch)
tree5faac6b37125d3432fb772e9806b7c20b85cc0d1 /net/xfrm
parentb515d2637276a3810d6595e10ab02c13bfd0b63a (diff)
xfrm: policy: Read seqcount outside of rcu-read side in xfrm_policy_lookup_bytype
xfrm_policy_lookup_bytype loops on seqcount mutex xfrm_policy_hash_generation within an RCU read side critical section. Although ill advised, this is fine if the loop is bounded. xfrm_policy_hash_generation wraps mutex hash_resize_mutex, which is used to serialize writers (xfrm_hash_resize, xfrm_hash_rebuild). This is fine too. On PREEMPT_RT=y, the read_seqcount_begin call within xfrm_policy_lookup_bytype emits a mutex lock/unlock for hash_resize_mutex. Mutex locking is fine, since RCU read side critical sections are allowed to sleep with PREEMPT_RT. xfrm_hash_resize can, however, block on synchronize_rcu while holding hash_resize_mutex. This leads to the following situation on PREEMPT_RT, where the writer is blocked on RCU grace period expiry, while the reader is blocked on a lock held by the writer: Thead 1 (xfrm_hash_resize) Thread 2 (xfrm_policy_lookup_bytype) rcu_read_lock(); mutex_lock(&hash_resize_mutex); read_seqcount_begin(&xfrm_policy_hash_generation); mutex_lock(&hash_resize_mutex); // block xfrm_bydst_resize(); synchronize_rcu(); // block <RCU stalls in xfrm_policy_lookup_bytype> Move the read_seqcount_begin call outside of the RCU read side critical section, and do an rcu_read_unlock/retry if we got stale data within the critical section. On non-PREEMPT_RT, this shortens the time spent within RCU read side critical section in case the seqcount needs a retry, and avoids unbounded looping. Fixes: 77cc278f7b20 ("xfrm: policy: Use sequence counters with associated lock") Signed-off-by: Varad Gautam <varad.gautam@suse.com> Cc: linux-rt-users <linux-rt-users@vger.kernel.org> Cc: netdev@vger.kernel.org Cc: stable@vger.kernel.org # v4.9 Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Florian Westphal <fw@strlen.de> Cc: "Ahmed S. Darwish" <a.darwish@linutronix.de> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Acked-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Diffstat (limited to 'net/xfrm')
-rw-r--r--net/xfrm/xfrm_policy.c21
1 files changed, 14 insertions, 7 deletions
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b74f28cabe24..8c56e3e59c3c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2092,12 +2092,15 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
if (unlikely(!daddr || !saddr))
return NULL;
- rcu_read_lock();
retry:
- do {
- sequence = read_seqcount_begin(&xfrm_policy_hash_generation);
- chain = policy_hash_direct(net, daddr, saddr, family, dir);
- } while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence));
+ sequence = read_seqcount_begin(&xfrm_policy_hash_generation);
+ rcu_read_lock();
+
+ chain = policy_hash_direct(net, daddr, saddr, family, dir);
+ if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) {
+ rcu_read_unlock();
+ goto retry;
+ }
ret = NULL;
hlist_for_each_entry_rcu(pol, chain, bydst) {
@@ -2128,11 +2131,15 @@ 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(&xfrm_policy_hash_generation, sequence)) {
+ rcu_read_unlock();
goto retry;
+ }
- if (ret && !xfrm_pol_hold_rcu(ret))
+ if (ret && !xfrm_pol_hold_rcu(ret)) {
+ rcu_read_unlock();
goto retry;
+ }
fail:
rcu_read_unlock();