From: Wei Wang <wei...@google.com>
If rwlock is replaced with rcu and spinlock, it is possible that the
reader thread will see fn->leaf as NULL in the following scenarios:
1. fib6_add() is in progress and we have already inserted a new node but
not yet inserted the route.
2. fib6_del_route() is in progress and we have already set fn->leaf to
NULL but not yet freed the node because of rcu grace period.
This patch makes sure all the reader threads check fn->leaf first before
using it. And together with later patch to grab rcu_read_lock() and
rcu_dereference() fn->leaf, it makes sure reader threads are safe when
accessing fn->leaf.
Signed-off-by: Wei Wang <wei...@google.com>
Signed-off-by: Martin KaFai Lau <ka...@fb.com>
Signed-off-by: Eric Dumazet <eduma...@google.com>
---
net/ipv6/ip6_fib.c | 23 ++++++++++++++++++-----
net/ipv6/route.c | 20 ++++++++++++--------
2 files changed, 30 insertions(+), 13 deletions(-)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index f604b311cc3e..cf6137e81408 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1279,10 +1279,13 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node
*root,
while (fn) {
if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) {
+ struct rt6_info *leaf = fn->leaf;
struct rt6key *key;
- key = (struct rt6key *) ((u8 *) fn->leaf +
- args->offset);
+ if (!leaf)
+ goto backtrack;
+
+ key = (struct rt6key *) ((u8 *)leaf + args->offset);
if (ipv6_prefix_equal(&key->addr, args->addr,
key->plen)) {
#ifdef CONFIG_IPV6_SUBTREES
@@ -1299,9 +1302,7 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node
*root,
return fn;
}
}
-#ifdef CONFIG_IPV6_SUBTREES
backtrack:
-#endif
if (fn->fn_flags & RTN_ROOT)
break;
@@ -1358,7 +1359,18 @@ static struct fib6_node *fib6_locate_1(struct fib6_node
*root,
struct fib6_node *fn, *prev = NULL;
for (fn = root; fn ; ) {
- struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset);
+ struct rt6_info *leaf = fn->leaf;
+ struct rt6key *key;
+
+ /* This node is being deleted */
+ if (!leaf) {
+ if (plen <= fn->fn_bit)
+ goto out;
+ else
+ goto next;
+ }
+
+ key = (struct rt6key *)((u8 *)leaf + offset);
/*
* Prefix match
@@ -1372,6 +1384,7 @@ static struct fib6_node *fib6_locate_1(struct fib6_node
*root,
prev = fn;
+next:
/*
* We have more bits to go
*/
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index aeb349aea429..05dc450af441 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -712,6 +712,7 @@ static struct rt6_info *find_match(struct rt6_info *rt, int
oif, int strict,
}
static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
+ struct rt6_info *leaf,
struct rt6_info *rr_head,
u32 metric, int oif, int strict,
bool *do_rr)
@@ -730,7 +731,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
match = find_match(rt, oif, strict, &mpri, match, do_rr);
}
- for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) {
+ for (rt = leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) {
if (rt->rt6i_metric != metric) {
cont = rt;
break;
@@ -748,17 +749,21 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
return match;
}
-static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
+static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
+ int oif, int strict)
{
+ struct rt6_info *leaf = fn->leaf;
struct rt6_info *match, *rt0;
- struct net *net;
bool do_rr = false;
+ if (!leaf)
+ return net->ipv6.ip6_null_entry;
+
rt0 = fn->rr_ptr;
if (!rt0)
- fn->rr_ptr = rt0 = fn->leaf;
+ fn->rr_ptr = rt0 = leaf;
- match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict,
+ match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict,
&do_rr);
if (do_rr) {
@@ -766,13 +771,12 @@ static struct rt6_info *rt6_select(struct fib6_node *fn,
int oif, int strict)
/* no entries matched; do round-robin */
if (!next || next->rt6i_metric != rt0->rt6i_metric)
- next = fn->leaf;
+ next = leaf;
if (next != rt0)
fn->rr_ptr = next;
}
- net = dev_net(rt0->dst.dev);
return match ? match : net->ipv6.ip6_null_entry;
}
@@ -1623,7 +1627,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct
fib6_table *table,
oif = 0;
redo_rt6_select:
- rt = rt6_select(fn, oif, strict);
+ rt = rt6_select(net, fn, oif, strict);
if (rt->rt6i_nsiblings)
rt = rt6_multipath_select(rt, fl6, oif, strict);
if (rt == net->ipv6.ip6_null_entry) {
--
2.14.2.920.gcf0c67979c-goog
