RDMA/core: Fix ENODEV error for iWARP test over vlan
PATCH 1/1 RDMA/core: Fix ENODEV error for iWARP test over vlan
If traffic is over vlan, cma_validate_port() fails to match net_device ifindex with bound_if_index and results in ENODEV error. As iWARP gid table is static, it contains entry corresponding to only one net device which is either real netdev or vlan netdev for cases like siw attached to a vlan interface.
This patch fixes the issue by assigning bound_if_index with net device index, if real net device obtained from bound if index matches with net device retrieved from gid table
--- drivers/infiniband/core/cma.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-)
drivers/infiniband/core/cma.c +16 -1
@@ -689,7 +689,7 @@ cma_validate_port(struct ib_device *device, u32 port,const struct ib_gid_attr *sgid_attr =ERR_PTR (-ENODEV );int bound_if_index = dev_addr->bound_dev_if;int dev_type = dev_addr->dev_type; -struct net_device *ndev =NULL ; +struct net_device *ndev =NULL , *pdev =NULL ;if (!rdma_dev_access_netns (device, id_priv->id.route.addr.dev_addr.net)) goto out;
@@ -714,6 +714,21 @@ cma_validate_port(struct ib_device *device, u32 port,rcu_read_lock (); ndev =rcu_dereference (sgid_attr->ndev); +if (ndev->ifindex != bound_if_index) { + pdev =dev_get_by_index_rcu (dev_addr->net, bound_if_index); +if (pdev) { +if (is_vlan_dev (pdev)) { + pdev =vlan_dev_real_dev (pdev); +if (ndev->ifindex == pdev->ifindex) + bound_if_index = pdev->ifindex; + } +if (is_vlan_dev (ndev)) { + pdev =vlan_dev_real_dev (ndev); +if (bound_if_index == pdev->ifindex) + bound_if_index = ndev->ifindex; + } + } + }if (!net_eq (dev_net (ndev), dev_addr->net) || ndev->ifindex != bound_if_index) {rdma_put_gid_attr (sgid_attr);
Signature · 1 line
2.39.3
Quoted 22 lines · Anumula Murali Mohan Reddy
If traffic is over vlan,
cma_validate_port()fails to matchnet_deviceifindex withbound_if_indexand results in ENODEV error. As iWARP gid table is static, it contains entry corresponding to only one net device which is either real netdev or vlan netdev for cases like siw attached to a vlan interface.
This patch fixes the issue by assigningbound_if_indexwith net device index, if real net device obtained from bound if index matches with net device retrieved from gid tableFixes f8ef1be816bf ("RDMA/cma: Avoid GID lookups on iWARP devices")Signed-off-by Anumula Murali Mohan Reddy <[email protected]>Signed-off-by Potnuri Bharat Teja <[email protected]>--- drivers/infiniband/core/cma.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-)drivers/infiniband/core/cma.c +0
-0
drivers/infiniband/core/cma.c cma_validate_port(struct ib_device *device, u32 port, · line 692
Quoted 5 lines
drivers/infiniband/core/cma.c +1
-1@@ -689,7 +689,7 @@ cma_validate_port(struct ib_device *device, u32 port,const struct ib_gid_attr *sgid_attr =ERR_PTR (-ENODEV );int bound_if_index = dev_addr->bound_dev_if;int dev_type = dev_addr->dev_type; -struct net_device *ndev =NULL ; +struct net_device *ndev =NULL , *pdev =NULL ;
In the original source code, the local variables lay out in the form of Reverse Christmas Tree. But the new code breaks the rule of Reverse Christmas Tree.
Zhu Yanjun
Quoted 25 lines
drivers/infiniband/core/cma.c +15
-0if (!rdma_dev_access_netns (device, id_priv->id.route.addr.dev_addr.net)) goto out;@@ -714,6 +714,21 @@ cma_validate_port(struct ib_device *device, u32 port,rcu_read_lock (); ndev =rcu_dereference (sgid_attr->ndev); +if (ndev->ifindex != bound_if_index) { + pdev =dev_get_by_index_rcu (dev_addr->net, bound_if_index); +if (pdev) { +if (is_vlan_dev (pdev)) { + pdev =vlan_dev_real_dev (pdev); +if (ndev->ifindex == pdev->ifindex) + bound_if_index = pdev->ifindex; + } +if (is_vlan_dev (ndev)) { + pdev =vlan_dev_real_dev (ndev); +if (bound_if_index == pdev->ifindex) + bound_if_index = ndev->ifindex; + } + } + }if (!net_eq (dev_net (ndev), dev_addr->net) || ndev->ifindex != bound_if_index) {rdma_put_gid_attr (sgid_attr);
Leon Romanovsky
maintainerQuoted 18 lines · Zhu Yanjun
Quoted 17 lines · Anumula Murali Mohan Reddy
If traffic is over vlan,
cma_validate_port()fails to matchnet_deviceifindex withbound_if_indexand results in ENODEV error. As iWARP gid table is static, it contains entry corresponding to only one net device which is either real netdev or vlan netdev for cases like siw attached to a vlan interface.
This patch fixes the issue by assigningbound_if_indexwith net device index, if real net device obtained from bound if index matches with net device retrieved from gid tableFixes f8ef1be816bf ("RDMA/cma: Avoid GID lookups on iWARP devices")Signed-off-by Anumula Murali Mohan Reddy <[email protected]>Signed-off-by Potnuri Bharat Teja <[email protected]>--- drivers/infiniband/core/cma.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-)
Quoted 14 lines
drivers/infiniband/core/cma.c cma_validate_port(struct ib_device *device, u32 port, · line 692
Quoted 10 lines
drivers/infiniband/core/cma.c +1
-1@@ -689,7 +689,7 @@ cma_validate_port(struct ib_device *device, u32 port,const struct ib_gid_attr *sgid_attr =ERR_PTR (-ENODEV );int bound_if_index = dev_addr->bound_dev_if;int dev_type = dev_addr->dev_type; -struct net_device *ndev =NULL ; +struct net_device *ndev =NULL , *pdev =NULL ;In the original source code, the local variables lay out in the form of Reverse Christmas Tree.
But the new code breaks the rule of Reverse Christmas Tree.
There is no such rule outside of netdev world. I suggest to everyone in RDMA to stick to that practice as sometimes we need to send the code to netdev too and it is much easier to keep their coding style from the beginning.
However, for pure RDMA patches, we don't care.
Thanks
Quoted 28 lines
Zhu Yanjun
Quoted 23 lines
drivers/infiniband/core/cma.c +15
-0if (!rdma_dev_access_netns (device, id_priv->id.route.addr.dev_addr.net)) goto out;@@ -714,6 +714,21 @@ cma_validate_port(struct ib_device *device, u32 port,rcu_read_lock (); ndev =rcu_dereference (sgid_attr->ndev); +if (ndev->ifindex != bound_if_index) { + pdev =dev_get_by_index_rcu (dev_addr->net, bound_if_index); +if (pdev) { +if (is_vlan_dev (pdev)) { + pdev =vlan_dev_real_dev (pdev); +if (ndev->ifindex == pdev->ifindex) + bound_if_index = pdev->ifindex; + } +if (is_vlan_dev (ndev)) { + pdev =vlan_dev_real_dev (ndev); +if (bound_if_index == pdev->ifindex) + bound_if_index = ndev->ifindex; + } + } + }if (!net_eq (dev_net (ndev), dev_addr->net) || ndev->ifindex != bound_if_index) {rdma_put_gid_attr (sgid_attr);