@@ -149,13 +149,18 @@ static void __rxe_insert_mcg(struct rxe_mcg *mcg)
tmp = rb_entry(node, struct rxe_mcg, node);
cmp = memcmp(&tmp->mgid, &mcg->mgid, sizeof(mcg->mgid));
- if (cmp > 0)
+ if (cmp > 0) {
link = &(*link)->rb_left;
- else
+ } else if (cmp < 0) {
link = &(*link)->rb_right;
+ } else {
+ /* we must delete the old mcg before adding one */
+ WARN_ON_ONCE(1);
+ return;
+ }
}
- rb_link_node(&mcg->node, node, link);
+ rb_link_node_rcu(&mcg->node, node, link);
rb_insert_color(&mcg->node, tree);
}
@@ -170,15 +175,11 @@ static void __rxe_remove_mcg(struct rxe_mcg *mcg)
rb_erase(&mcg->node, &mcg->rxe->mcg_tree);
}
-/**
- * __rxe_lookup_mcg - lookup mcg in rxe->mcg_tree while holding lock
- * @rxe: rxe device object
- * @mgid: multicast IP address
- *
- * Context: caller must hold rxe->mcg_lock
- * Returns: mcg on success and takes a ref to mcg else NULL
+/*
+ * Lookup mgid in the multicast group red-black tree and try to
+ * get a ref on it. Return mcg on success else NULL.
*/
-static struct rxe_mcg *__rxe_lookup_mcg(struct rxe_dev *rxe,
+struct rxe_mcg *rxe_lookup_mcg(struct rxe_dev *rxe,
union ib_gid *mgid)
{
struct rb_root *tree = &rxe->mcg_tree;
@@ -186,7 +187,8 @@ static struct rxe_mcg *__rxe_lookup_mcg(struct rxe_dev *rxe,
struct rb_node *node;
int cmp;
- node = tree->rb_node;
+ rcu_read_lock();
+ node = rcu_dereference_raw(tree->rb_node);
while (node) {
mcg = rb_entry(node, struct rxe_mcg, node);
@@ -194,35 +196,14 @@ static struct rxe_mcg *__rxe_lookup_mcg(struct rxe_dev *rxe,
cmp = memcmp(&mcg->mgid, mgid, sizeof(*mgid));
if (cmp > 0)
- node = node->rb_left;
+ node = rcu_dereference_raw(node->rb_left);
else if (cmp < 0)
- node = node->rb_right;
+ node = rcu_dereference_raw(node->rb_right);
else
break;
}
-
- if (node) {
- kref_get(&mcg->ref_cnt);
- return mcg;
- }
-
- return NULL;
-}
-
-/**
- * rxe_lookup_mcg - lookup up mcg in red-back tree
- * @rxe: rxe device object
- * @mgid: multicast IP address
- *
- * Returns: mcg if found else NULL
- */
-struct rxe_mcg *rxe_lookup_mcg(struct rxe_dev *rxe, union ib_gid *mgid)
-{
- struct rxe_mcg *mcg;
-
- spin_lock_bh(&rxe->mcg_lock);
- mcg = __rxe_lookup_mcg(rxe, mgid);
- spin_unlock_bh(&rxe->mcg_lock);
+ mcg = (node && kref_get_unless_zero(&mcg->ref_cnt)) ? mcg : NULL;
+ rcu_read_unlock();
return mcg;
}
@@ -290,7 +271,7 @@ static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid)
spin_lock_bh(&rxe->mcg_lock);
/* re-check to see if someone else just added it */
- tmp = __rxe_lookup_mcg(rxe, mgid);
+ tmp = rxe_lookup_mcg(rxe, mgid);
if (tmp) {
spin_unlock_bh(&rxe->mcg_lock);
atomic_dec(&rxe->mcg_num);
@@ -320,7 +301,7 @@ void rxe_cleanup_mcg(struct kref *kref)
{
struct rxe_mcg *mcg = container_of(kref, typeof(*mcg), ref_cnt);
- kfree(mcg);
+ kfree_rcu(mcg, rcu);
}
/**
@@ -345,6 +345,7 @@ struct rxe_mw {
struct rxe_mcg {
struct rb_node node;
+ struct rcu_head rcu;
struct kref ref_cnt;
struct rxe_dev *rxe;
struct list_head qp_list;
Change locking of read side operations of the mcast group red-black tree to use rcu read locking. This will allow changing the mcast lock in the next patch to be a mutex without breaking rxe_recv.c which runs in an atomic state. It is also a better implementation than the current use of a spin-lock per rdma device since receiving mcast packets will be much more common than registering/deregistering mcast groups. Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com> --- drivers/infiniband/sw/rxe/rxe_mcast.c | 59 +++++++++------------------ drivers/infiniband/sw/rxe/rxe_verbs.h | 1 + 2 files changed, 21 insertions(+), 39 deletions(-)