RDMA/rxe: Flush delayed SKBs while releasing RXE resources

When skb packets are sent out, these skb packets still depends on
the rxe resources, for example, QP, sk, when these packets are
destroyed.

If these rxe resources are released when the skb packets are destroyed,
the call traces will appear.

To avoid skb packets hang too long time in some network devices,
a timestamp is added when these skb packets are created. If these
skb packets hang too long time in network devices, these network
devices can free these skb packets to release rxe resources.

Reported-by: syzbot+8425ccfb599521edb153@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=8425ccfb599521edb153
Tested-by: syzbot+8425ccfb599521edb153@syzkaller.appspotmail.com
Fixes: 1a633bdc8fd9 ("RDMA/rxe: Let destroy qp succeed with stuck packet")
Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Link: https://patch.msgid.link/20250726013104.463570-1-yanjun.zhu@linux.dev
Signed-off-by: Leon Romanovsky <leon@kernel.org>

diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 132a87e52d5c7e9a63ea7eddc10d410eb15c83a4..ac0183a2ff7aa12237aab10b90a1406f67c561c4 100644 (file)
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -345,33 +345,15 @@ int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt,
 
 static void rxe_skb_tx_dtor(struct sk_buff *skb)
 {
-       struct net_device *ndev = skb->dev;
-       struct rxe_dev *rxe;
-       unsigned int qp_index;
-       struct rxe_qp *qp;
+       struct rxe_qp *qp = skb->sk->sk_user_data;
        int skb_out;
 
-       rxe = rxe_get_dev_from_net(ndev);
-       if (!rxe && is_vlan_dev(ndev))
-               rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev));
-       if (WARN_ON(!rxe))
-               return;
-
-       qp_index = (int)(uintptr_t)skb->sk->sk_user_data;
-       if (!qp_index)
-               return;
-
-       qp = rxe_pool_get_index(&rxe->qp_pool, qp_index);
-       if (!qp)
-               goto put_dev;
-
        skb_out = atomic_dec_return(&qp->skb_out);
-       if (qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW)
+       if (unlikely(qp->need_req_skb &&
+               skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW))
                rxe_sched_task(&qp->send_task);
 
        rxe_put(qp);
-put_dev:
-       ib_device_put(&rxe->ib_dev);
        sock_put(skb->sk);
 }
 
@@ -383,6 +365,7 @@ static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt)
        sock_hold(sk);
        skb->sk = sk;
        skb->destructor = rxe_skb_tx_dtor;
+       rxe_get(pkt->qp);
        atomic_inc(&pkt->qp->skb_out);
 
        if (skb->protocol == htons(ETH_P_IP))
@@ -405,6 +388,7 @@ static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt)
        sock_hold(sk);
        skb->sk = sk;
        skb->destructor = rxe_skb_tx_dtor;
+       rxe_get(pkt->qp);
        atomic_inc(&pkt->qp->skb_out);
 
        if (skb->protocol == htons(ETH_P_IP))
@@ -497,6 +481,9 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
                goto out;
        }
 
+       /* Add time stamp to skb. */
+       skb->tstamp = ktime_get();
+
        skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev));
 
        /* FIXME: hold reference to this netdev until life of this skb. */

diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index f2af3e0aef35b55050a9548a75498eaff98cf8f1..95f1c1c2949de7778aeb9bc7890ba945b9ad1b3b 100644 (file)
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -244,7 +244,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
        err = sock_create_kern(&init_net, AF_INET, SOCK_DGRAM, 0, &qp->sk);
        if (err < 0)
                return err;
-       qp->sk->sk->sk_user_data = (void *)(uintptr_t)qp->elem.index;
+       qp->sk->sk->sk_user_data = qp;
 
        /* pick a source UDP port number for this QP based on
         * the source QPN. this spreads traffic for different QPs