Commit eaeb3984 authored by Jason Gunthorpe's avatar Jason Gunthorpe

IB/ipoib: Move init code to ndo_init

Now that we have a proper ndo_uninit, move code that naturally pairs
with the ndo_uninit into ndo_init. This allows the netdev core to natually
handle ordering.

This fixes the situation where register_netdev can fail before calling
ndo_init, in which case it wouldn't call ndo_uninit either.

Also move a bunch of duplicated init code that is shared between child
and parent for clarity. Now the child and parent register functions look
very similar.
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
Signed-off-by: default avatarLeon Romanovsky <leonro@mellanox.com>
parent 7cbee87c
...@@ -508,8 +508,6 @@ void ipoib_ib_dev_down(struct net_device *dev); ...@@ -508,8 +508,6 @@ void ipoib_ib_dev_down(struct net_device *dev);
int ipoib_ib_dev_stop_default(struct net_device *dev); int ipoib_ib_dev_stop_default(struct net_device *dev);
void ipoib_pkey_dev_check_presence(struct net_device *dev); void ipoib_pkey_dev_check_presence(struct net_device *dev);
int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
void ipoib_mcast_join_task(struct work_struct *work); void ipoib_mcast_join_task(struct work_struct *work);
void ipoib_mcast_carrier_on_task(struct work_struct *work); void ipoib_mcast_carrier_on_task(struct work_struct *work);
void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb); void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb);
...@@ -597,7 +595,6 @@ void ipoib_pkey_open(struct ipoib_dev_priv *priv); ...@@ -597,7 +595,6 @@ void ipoib_pkey_open(struct ipoib_dev_priv *priv);
void ipoib_drain_cq(struct net_device *dev); void ipoib_drain_cq(struct net_device *dev);
void ipoib_set_ethtool_ops(struct net_device *dev); void ipoib_set_ethtool_ops(struct net_device *dev);
void ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca);
#define IPOIB_FLAGS_RC 0x80 #define IPOIB_FLAGS_RC 0x80
#define IPOIB_FLAGS_UC 0x40 #define IPOIB_FLAGS_UC 0x40
......
...@@ -1741,13 +1741,11 @@ static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, ...@@ -1741,13 +1741,11 @@ static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr,
return priv->rn_ops->ndo_do_ioctl(dev, ifr, cmd); return priv->rn_ops->ndo_do_ioctl(dev, ifr, cmd);
} }
int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port) static int ipoib_dev_init(struct net_device *dev)
{ {
struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_dev_priv *priv = ipoib_priv(dev);
int ret = -ENOMEM; int ret = -ENOMEM;
priv->ca = ca;
priv->port = port;
priv->qp = NULL; priv->qp = NULL;
/* /*
...@@ -1763,7 +1761,7 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port) ...@@ -1763,7 +1761,7 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
/* create pd, which used both for control and datapath*/ /* create pd, which used both for control and datapath*/
priv->pd = ib_alloc_pd(priv->ca, 0); priv->pd = ib_alloc_pd(priv->ca, 0);
if (IS_ERR(priv->pd)) { if (IS_ERR(priv->pd)) {
pr_warn("%s: failed to allocate PD\n", ca->name); pr_warn("%s: failed to allocate PD\n", priv->ca->name);
goto clean_wq; goto clean_wq;
} }
...@@ -1837,6 +1835,108 @@ static void ipoib_parent_unregister_pre(struct net_device *ndev) ...@@ -1837,6 +1835,108 @@ static void ipoib_parent_unregister_pre(struct net_device *ndev)
flush_workqueue(ipoib_workqueue); flush_workqueue(ipoib_workqueue);
} }
static void ipoib_set_dev_features(struct ipoib_dev_priv *priv)
{
priv->hca_caps = priv->ca->attrs.device_cap_flags;
if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) {
priv->dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
if (priv->hca_caps & IB_DEVICE_UD_TSO)
priv->dev->hw_features |= NETIF_F_TSO;
priv->dev->features |= priv->dev->hw_features;
}
}
static int ipoib_parent_init(struct net_device *ndev)
{
struct ipoib_dev_priv *priv = ipoib_priv(ndev);
struct ib_port_attr attr;
int result;
result = ib_query_port(priv->ca, priv->port, &attr);
if (result) {
pr_warn("%s: ib_query_port %d failed\n", priv->ca->name,
priv->port);
return result;
}
priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey);
if (result) {
pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n",
priv->ca->name, priv->port, result);
return result;
}
result = rdma_query_gid(priv->ca, priv->port, 0, &priv->local_gid);
if (result) {
pr_warn("%s: rdma_query_gid port %d failed (ret = %d)\n",
priv->ca->name, priv->port, result);
return result;
}
memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw,
sizeof(union ib_gid));
SET_NETDEV_DEV(priv->dev, priv->ca->dev.parent);
priv->dev->dev_id = priv->port - 1;
return 0;
}
static void ipoib_child_init(struct net_device *ndev)
{
struct ipoib_dev_priv *priv = ipoib_priv(ndev);
struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
priv->max_ib_mtu = ppriv->max_ib_mtu;
set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags);
memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN);
memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid));
}
static int ipoib_ndo_init(struct net_device *ndev)
{
struct ipoib_dev_priv *priv = ipoib_priv(ndev);
int rc;
if (priv->parent) {
ipoib_child_init(ndev);
} else {
rc = ipoib_parent_init(ndev);
if (rc)
return rc;
}
/* MTU will be reset when mcast join happens */
ndev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
priv->mcast_mtu = priv->admin_mtu = ndev->mtu;
ndev->max_mtu = IPOIB_CM_MTU;
ndev->neigh_priv_len = sizeof(struct ipoib_neigh);
/*
* Set the full membership bit, so that we join the right
* broadcast group, etc.
*/
priv->pkey |= 0x8000;
ndev->broadcast[8] = priv->pkey >> 8;
ndev->broadcast[9] = priv->pkey & 0xff;
set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
ipoib_set_dev_features(priv);
rc = ipoib_dev_init(ndev);
if (rc) {
pr_warn("%s: failed to initialize device: %s port %d (ret = %d)\n",
priv->ca->name, priv->dev->name, priv->port, rc);
}
return 0;
}
static void ipoib_ndo_uninit(struct net_device *dev) static void ipoib_ndo_uninit(struct net_device *dev)
{ {
struct ipoib_dev_priv *priv = ipoib_priv(dev), *cpriv, *tcpriv; struct ipoib_dev_priv *priv = ipoib_priv(dev), *cpriv, *tcpriv;
...@@ -1909,6 +2009,7 @@ static const struct header_ops ipoib_header_ops = { ...@@ -1909,6 +2009,7 @@ static const struct header_ops ipoib_header_ops = {
}; };
static const struct net_device_ops ipoib_netdev_ops_pf = { static const struct net_device_ops ipoib_netdev_ops_pf = {
.ndo_init = ipoib_ndo_init,
.ndo_uninit = ipoib_ndo_uninit, .ndo_uninit = ipoib_ndo_uninit,
.ndo_open = ipoib_open, .ndo_open = ipoib_open,
.ndo_stop = ipoib_stop, .ndo_stop = ipoib_stop,
...@@ -1928,6 +2029,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = { ...@@ -1928,6 +2029,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = {
}; };
static const struct net_device_ops ipoib_netdev_ops_vf = { static const struct net_device_ops ipoib_netdev_ops_vf = {
.ndo_init = ipoib_ndo_init,
.ndo_uninit = ipoib_ndo_uninit, .ndo_uninit = ipoib_ndo_uninit,
.ndo_open = ipoib_open, .ndo_open = ipoib_open,
.ndo_stop = ipoib_stop, .ndo_stop = ipoib_stop,
...@@ -2054,6 +2156,9 @@ struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port, ...@@ -2054,6 +2156,9 @@ struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port,
if (!priv) if (!priv)
return NULL; return NULL;
priv->ca = hca;
priv->port = port;
dev = ipoib_get_netdev(hca, port, name); dev = ipoib_get_netdev(hca, port, name);
if (!dev) if (!dev)
goto free_priv; goto free_priv;
...@@ -2201,12 +2306,6 @@ static ssize_t create_child(struct device *dev, ...@@ -2201,12 +2306,6 @@ static ssize_t create_child(struct device *dev,
if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000) if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000)
return -EINVAL; return -EINVAL;
/*
* Set the full membership bit, so that we join the right
* broadcast group, etc.
*/
pkey |= 0x8000;
ret = ipoib_vlan_add(to_net_dev(dev), pkey); ret = ipoib_vlan_add(to_net_dev(dev), pkey);
return ret ? ret : count; return ret ? ret : count;
...@@ -2238,86 +2337,17 @@ int ipoib_add_pkey_attr(struct net_device *dev) ...@@ -2238,86 +2337,17 @@ int ipoib_add_pkey_attr(struct net_device *dev)
return device_create_file(&dev->dev, &dev_attr_pkey); return device_create_file(&dev->dev, &dev_attr_pkey);
} }
void ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca)
{
priv->hca_caps = hca->attrs.device_cap_flags;
if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) {
priv->dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
if (priv->hca_caps & IB_DEVICE_UD_TSO)
priv->dev->hw_features |= NETIF_F_TSO;
priv->dev->features |= priv->dev->hw_features;
}
}
static struct net_device *ipoib_add_port(const char *format, static struct net_device *ipoib_add_port(const char *format,
struct ib_device *hca, u8 port) struct ib_device *hca, u8 port)
{ {
struct ipoib_dev_priv *priv; struct ipoib_dev_priv *priv;
struct ib_port_attr attr;
struct rdma_netdev *rn; struct rdma_netdev *rn;
int result = -ENOMEM; int result;
priv = ipoib_intf_alloc(hca, port, format); priv = ipoib_intf_alloc(hca, port, format);
if (!priv) { if (!priv) {
pr_warn("%s, %d: ipoib_intf_alloc failed\n", hca->name, port); pr_warn("%s, %d: ipoib_intf_alloc failed\n", hca->name, port);
goto alloc_mem_failed; return ERR_PTR(-ENOMEM);
}
SET_NETDEV_DEV(priv->dev, hca->dev.parent);
priv->dev->dev_id = port - 1;
result = ib_query_port(hca, port, &attr);
if (result) {
pr_warn("%s: ib_query_port %d failed\n", hca->name, port);
goto device_init_failed;
}
priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
/* MTU will be reset when mcast join happens */
priv->dev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
priv->mcast_mtu = priv->admin_mtu = priv->dev->mtu;
priv->dev->max_mtu = IPOIB_CM_MTU;
priv->dev->neigh_priv_len = sizeof(struct ipoib_neigh);
result = ib_query_pkey(hca, port, 0, &priv->pkey);
if (result) {
pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n",
hca->name, port, result);
goto device_init_failed;
}
ipoib_set_dev_features(priv, hca);
/*
* Set the full membership bit, so that we join the right
* broadcast group, etc.
*/
priv->pkey |= 0x8000;
priv->dev->broadcast[8] = priv->pkey >> 8;
priv->dev->broadcast[9] = priv->pkey & 0xff;
result = rdma_query_gid(hca, port, 0, &priv->local_gid);
if (result) {
pr_warn("%s: rdma_query_gid port %d failed (ret = %d)\n",
hca->name, port, result);
goto device_init_failed;
}
memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw,
sizeof(union ib_gid));
set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
result = ipoib_dev_init(priv->dev, hca, port);
if (result) {
pr_warn("%s: failed to initialize port %d (ret = %d)\n",
hca->name, port, result);
goto device_init_failed;
} }
INIT_IB_EVENT_HANDLER(&priv->event_handler, INIT_IB_EVENT_HANDLER(&priv->event_handler,
...@@ -2358,7 +2388,6 @@ static struct net_device *ipoib_add_port(const char *format, ...@@ -2358,7 +2388,6 @@ static struct net_device *ipoib_add_port(const char *format,
rn->free_rdma_netdev(priv->dev); rn->free_rdma_netdev(priv->dev);
kfree(priv); kfree(priv);
alloc_mem_failed:
return ERR_PTR(result); return ERR_PTR(result);
} }
......
...@@ -125,12 +125,6 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, ...@@ -125,12 +125,6 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
if (child_pkey == 0 || child_pkey == 0x8000) if (child_pkey == 0 || child_pkey == 0x8000)
return -EINVAL; return -EINVAL;
/*
* Set the full membership bit, so that we join the right
* broadcast group, etc.
*/
child_pkey |= 0x8000;
err = __ipoib_vlan_add(ppriv, ipoib_priv(dev), err = __ipoib_vlan_add(ppriv, ipoib_priv(dev),
child_pkey, IPOIB_RTNL_CHILD); child_pkey, IPOIB_RTNL_CHILD);
......
...@@ -55,35 +55,14 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, ...@@ -55,35 +55,14 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
{ {
int result; int result;
priv->max_ib_mtu = ppriv->max_ib_mtu;
/* MTU will be reset when mcast join happens */
priv->dev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
priv->mcast_mtu = priv->admin_mtu = priv->dev->mtu;
priv->parent = ppriv->dev; priv->parent = ppriv->dev;
set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags);
ipoib_set_dev_features(priv, ppriv->ca);
priv->pkey = pkey; priv->pkey = pkey;
priv->child_type = type;
memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN);
memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid));
set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
priv->dev->broadcast[8] = pkey >> 8;
priv->dev->broadcast[9] = pkey & 0xff;
result = ipoib_dev_init(priv->dev, ppriv->ca, ppriv->port);
if (result < 0) {
ipoib_warn(ppriv, "failed to initialize subinterface: "
"device %s, port %d",
ppriv->ca->name, ppriv->port);
goto err;
}
result = register_netdevice(priv->dev); result = register_netdevice(priv->dev);
if (result) { if (result) {
ipoib_warn(priv, "failed to initialize; error %i", result); ipoib_warn(priv, "failed to initialize; error %i", result);
goto err; return result;
} }
/* RTNL childs don't need proprietary sysfs entries */ /* RTNL childs don't need proprietary sysfs entries */
...@@ -99,17 +78,13 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, ...@@ -99,17 +78,13 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
goto sysfs_failed; goto sysfs_failed;
} }
priv->child_type = type;
list_add_tail(&priv->list, &ppriv->child_intfs); list_add_tail(&priv->list, &ppriv->child_intfs);
return 0; return 0;
sysfs_failed: sysfs_failed:
result = -ENOMEM;
unregister_netdevice(priv->dev); unregister_netdevice(priv->dev);
return -ENOMEM;
err:
return result;
} }
int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment