From mboxrd@z Thu Jan 1 00:00:00 1970 From: Zhu Yanjun Subject: [PATCH 1/1] IB/rxe: remove unnecessary skb_clone in xmit Date: Fri, 5 Jan 2018 03:19:51 -0500 Message-ID: <1515140391-24752-1-git-send-email-yanjun.zhu@oracle.com> Return-path: Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, jgg-uk2M96/98Pc@public.gmane.org, dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org, monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org, junxiao.bi-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org, yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org, Haakon.Bugge-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org List-Id: linux-rdma@vger.kernel.org In xmit, there is a skb_clone. This function copies the struct sk_buff. And some parameters are changed to the new skb. Then the new skb is sent while the old skb is freed. While the function skb_clone is removed, the parameter changes are made on the old skb, then the old skb is sent. It can also work well. The following tests are made. server client --------- --------- |1.1.1.1|<----rxe-channel--->|1.1.1.2| --------- --------- On server: rping -s -a 1.1.1.1 -v -C 1000 -S 512 On client: rping -c -a 1.1.1.1 -v -C 1000 -S 512 The kernel config CONFIG_DEBUG_KMEMLEAK is enabled on both server and client. This test runs for several hours. There is no memory leak and the whole system can work well. CC: Srinivas Eeda CC: Joe Jin CC: Junxiao Bi Signed-off-by: Zhu Yanjun --- drivers/infiniband/sw/rxe/rxe_net.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 59dee10..5fc6bb5 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -452,31 +452,26 @@ static void rxe_skb_tx_dtor(struct sk_buff *skb) int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb) { - struct sk_buff *nskb; struct rxe_av *av; int err; av = rxe_get_av(pkt); - nskb = skb_clone(skb, GFP_ATOMIC); - if (!nskb) - return -ENOMEM; - - nskb->destructor = rxe_skb_tx_dtor; - nskb->sk = pkt->qp->sk->sk; + skb->destructor = rxe_skb_tx_dtor; + skb->sk = pkt->qp->sk->sk; rxe_add_ref(pkt->qp); atomic_inc(&pkt->qp->skb_out); if (av->network_type == RDMA_NETWORK_IPV4) { - err = ip_local_out(dev_net(skb_dst(skb)->dev), nskb->sk, nskb); + err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } else if (av->network_type == RDMA_NETWORK_IPV6) { - err = ip6_local_out(dev_net(skb_dst(skb)->dev), nskb->sk, nskb); + err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } else { pr_err("Unknown layer 3 protocol: %d\n", av->network_type); atomic_dec(&pkt->qp->skb_out); rxe_drop_ref(pkt->qp); - kfree_skb(nskb); + kfree_skb(skb); return -EINVAL; } @@ -485,7 +480,6 @@ int rxe_send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct sk_buff *skb) return -EAGAIN; } - kfree_skb(skb); return 0; } -- 2.7.4 -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html