linux-kernel - Re: [PATCH net-next] net/smc: add support for netdevice in containers.

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: <20230927034209.GE92403@linux.alibaba.com>
Date:   Wed, 27 Sep 2023 11:42:09 +0800
From:   Dust Li <dust.li@...ux.alibaba.com>
To:     Albert Huang <huangjie.albert@...edance.com>,
        Karsten Graul <kgraul@...ux.ibm.com>,
        Wenjia Zhang <wenjia@...ux.ibm.com>,
        Jan Karcher <jaka@...ux.ibm.com>
Cc:     "D. Wythe" <alibuda@...ux.alibaba.com>,
        Tony Lu <tonylu@...ux.alibaba.com>,
        Wen Gu <guwen@...ux.alibaba.com>,
        "David S. Miller" <davem@...emloft.net>,
        Eric Dumazet <edumazet@...gle.com>,
        Jakub Kicinski <kuba@...nel.org>,
        Paolo Abeni <pabeni@...hat.com>, linux-s390@...r.kernel.org,
        netdev@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH net-next] net/smc: add support for netdevice in
 containers.

On Mon, Sep 25, 2023 at 10:35:45AM +0800, Albert Huang wrote:
>If the netdevice is within a container and communicates externally
>through network technologies like VXLAN, we won't be able to find
>routing information in the init_net namespace. To address this issue,

Thanks for your founding !

I think this is a more generic problem, but not just related to VXLAN ?
If we use SMC-R v2 and the netdevice is in a net namespace which is not
init_net, we should always fail, right ? If so, I'd prefer this to be a bugfix.

Best regards,
Dust

>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.
>
>Signed-off-by: Albert Huang <huangjie.albert@...edance.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);
>-- 
>2.37.1 (Apple Git-137.1)