Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.37 as permitted sender) client-ip=23.128.96.37;
Message-ID: <8403e613-e51e-4c76-a542-3bdd3050cfa9@linux.ibm.com>
Date:   Wed, 11 Oct 2023 16:33:37 +0200
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v2 net] net/smc: fix smc clc failed issue when netdevice
 not in init_net
Content-Language: en-GB
To:     Albert Huang <huangjie.albert@bytedance.com>,
        Karsten Graul <kgraul@linux.ibm.com>,
        Jan Karcher <jaka@linux.ibm.com>,
        Tony Lu <tonylu@linux.alibaba.com>,
        Wen Gu <guwen@linux.alibaba.com>
Cc:     "D. Wythe" <alibuda@linux.alibaba.com>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>, linux-s390@vger.kernel.org,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org
References: <20231011074851.95280-1-huangjie.albert@bytedance.com>
From:   Wenjia Zhang <wenjia@linux.ibm.com>
In-Reply-To: <20231011074851.95280-1-huangjie.albert@bytedance.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
MIME-Version: 1.0
Precedence: bulk


On 11.10.23 09:48, Albert Huang wrote:
> If the netdevice is within a container and communicates externally
> through network technologies such as VxLAN, we won't be able to find
> routing information in the init_net namespace. To address this issue,
> we need to add a struct net parameter to the smc_ib_find_route function.
> This allow us to locate the routing information within the corresponding
> net namespace, ensuring the correct completion of the SMC CLC interaction.
> 
> Fixes: e5c4744cfb59 ("net/smc: add SMC-Rv2 connection establishment")
> Signed-off-by: Albert Huang <huangjie.albert@bytedance.com>
> ---
>   net/smc/af_smc.c | 3 ++-
>   net/smc/smc_ib.c | 7 ++++---
>   net/smc/smc_ib.h | 2 +-
>   3 files changed, 7 insertions(+), 5 deletions(-)
> 
> diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
> index bacdd971615e..7a874da90c7f 100644
> --- a/net/smc/af_smc.c
> +++ b/net/smc/af_smc.c
> @@ -1201,6 +1201,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
>   		(struct smc_clc_msg_accept_confirm_v2 *)aclc;
>   	struct smc_clc_first_contact_ext *fce =
>   		smc_get_clc_first_contact_ext(clc_v2, false);
> +	struct net *net = sock_net(&smc->sk);
>   	int rc;
>   
>   	if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1)
> @@ -1210,7 +1211,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
>   		memcpy(ini->smcrv2.nexthop_mac, &aclc->r0.lcl.mac, ETH_ALEN);
>   		ini->smcrv2.uses_gateway = false;
>   	} else {
> -		if (smc_ib_find_route(smc->clcsock->sk->sk_rcv_saddr,
> +		if (smc_ib_find_route(net, smc->clcsock->sk->sk_rcv_saddr,
>   				      smc_ib_gid_to_ipv4(aclc->r0.lcl.gid),
>   				      ini->smcrv2.nexthop_mac,
>   				      &ini->smcrv2.uses_gateway))
> diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
> index 9b66d6aeeb1a..89981dbe46c9 100644
> --- a/net/smc/smc_ib.c
> +++ b/net/smc/smc_ib.c
> @@ -193,7 +193,7 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
>   	return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
>   }
>   
> -int smc_ib_find_route(__be32 saddr, __be32 daddr,
> +int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr,
>   		      u8 nexthop_mac[], u8 *uses_gateway)
>   {
>   	struct neighbour *neigh = NULL;
> @@ -205,7 +205,7 @@ int smc_ib_find_route(__be32 saddr, __be32 daddr,
>   
>   	if (daddr == cpu_to_be32(INADDR_NONE))
>   		goto out;
> -	rt = ip_route_output_flow(&init_net, &fl4, NULL);
> +	rt = ip_route_output_flow(net, &fl4, NULL);
>   	if (IS_ERR(rt))
>   		goto out;
>   	if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET)
> @@ -235,6 +235,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev,
>   	if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP &&
>   	    smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) {
>   		struct in_device *in_dev = __in_dev_get_rcu(ndev);
> +		struct net *net = dev_net(ndev);
>   		const struct in_ifaddr *ifa;
>   		bool subnet_match = false;
>   
> @@ -248,7 +249,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev,
>   		}
>   		if (!subnet_match)
>   			goto out;
> -		if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr,
> +		if (smcrv2->daddr && smc_ib_find_route(net, smcrv2->saddr,
>   						       smcrv2->daddr,
>   						       smcrv2->nexthop_mac,
>   						       &smcrv2->uses_gateway))
> diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
> index 4df5f8c8a0a1..ef8ac2b7546d 100644
> --- a/net/smc/smc_ib.h
> +++ b/net/smc/smc_ib.h
> @@ -112,7 +112,7 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk,
>   int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
>   			 unsigned short vlan_id, u8 gid[], u8 *sgid_index,
>   			 struct smc_init_info_smcrv2 *smcrv2);
> -int smc_ib_find_route(__be32 saddr, __be32 daddr,
> +int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr,
>   		      u8 nexthop_mac[], u8 *uses_gateway);
>   bool smc_ib_is_valid_local_systemid(void);
>   int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);

If it works for VXLAN, I'm still wondering why this case doesn't work, 
could you please answer it?
https://lore.kernel.org/netdev/00bbbf48440c1889ecd16a590ebb746b820a4f48.camel@linux.ibm.com/


Thanks,
Wenjia