netdev - [PATCH for-next v6 4/7] RDMA/rxe: Let rxe_lookup_mcg use rcu_read

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20231207192907.10113-5-rpearsonhpe@gmail.com>
Date: Thu,  7 Dec 2023 13:29:05 -0600
From: Bob Pearson <rpearsonhpe@...il.com>
To: jgg@...dia.com,
	yanjun.zhu@...ux.dev,
	linux-rdma@...r.kernel.org,
	netdev@...r.kernel.org,
	dsahern@...nel.org,
	rain.1986.08.12@...il.com
Cc: Bob Pearson <rpearsonhpe@...il.com>
Subject: [PATCH for-next v6 4/7] RDMA/rxe: Let rxe_lookup_mcg use rcu_read_lock

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@...il.com>
---
 drivers/infiniband/sw/rxe/rxe_mcast.c | 59 +++++++++------------------
 drivers/infiniband/sw/rxe/rxe_verbs.h |  1 +
 2 files changed, 21 insertions(+), 39 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c
index 5236761892dd..315e7615e6a7 100644
--- a/drivers/infiniband/sw/rxe/rxe_mcast.c
+++ b/drivers/infiniband/sw/rxe/rxe_mcast.c
@@ -151,13 +151,18 @@ 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);
 }
 
@@ -172,15 +177,11 @@ 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;
@@ -188,7 +189,8 @@ 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);
@@ -196,35 +198,14 @@ 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;
 }
@@ -292,7 +273,7 @@ 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);
@@ -322,7 +303,7 @@ void rxe_cleanup_mcg(struct kref *kref)
 {
 	struct rxe_mcg *mcg = container_of(kref, typeof(*mcg), ref_cnt);
 
-	kfree(mcg);
+	kfree_rcu(mcg, rcu);
 }
 
 /**
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 7be9e6232dd9..8058e5039322 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -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;
-- 
2.40.1