Commit bfc17d00 authored by David S. Miller's avatar David S. Miller

Merge branch 'hv_netvsc-notification-and-namespace-fixes'

Stephen Hemminger says:

====================
hv_netvsc: notification and namespace fixes

This set of patches addresses two set of fixes. First it backs out
the common callback model which was merged in net-next without
completing all the review feedback or getting maintainer approval.

Then it fixes the transparent VF management code to handle network
namespaces.
====================
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 01a1a170 c0a41b88
...@@ -2,6 +2,5 @@ config HYPERV_NET ...@@ -2,6 +2,5 @@ config HYPERV_NET
tristate "Microsoft Hyper-V virtual network driver" tristate "Microsoft Hyper-V virtual network driver"
depends on HYPERV depends on HYPERV
select UCS2_STRING select UCS2_STRING
select FAILOVER
help help
Select this option to enable the Hyper-V virtual network driver. Select this option to enable the Hyper-V virtual network driver.
...@@ -901,6 +901,8 @@ struct net_device_context { ...@@ -901,6 +901,8 @@ struct net_device_context {
struct hv_device *device_ctx; struct hv_device *device_ctx;
/* netvsc_device */ /* netvsc_device */
struct netvsc_device __rcu *nvdev; struct netvsc_device __rcu *nvdev;
/* list of netvsc net_devices */
struct list_head list;
/* reconfigure work */ /* reconfigure work */
struct delayed_work dwork; struct delayed_work dwork;
/* last reconfig time */ /* last reconfig time */
...@@ -931,8 +933,6 @@ struct net_device_context { ...@@ -931,8 +933,6 @@ struct net_device_context {
u32 vf_alloc; u32 vf_alloc;
/* Serial number of the VF to team with */ /* Serial number of the VF to team with */
u32 vf_serial; u32 vf_serial;
struct failover *failover;
}; };
/* Per channel data */ /* Per channel data */
......
...@@ -42,7 +42,6 @@ ...@@ -42,7 +42,6 @@
#include <net/pkt_sched.h> #include <net/pkt_sched.h>
#include <net/checksum.h> #include <net/checksum.h>
#include <net/ip6_checksum.h> #include <net/ip6_checksum.h>
#include <net/failover.h>
#include "hyperv_net.h" #include "hyperv_net.h"
...@@ -68,6 +67,8 @@ static int debug = -1; ...@@ -68,6 +67,8 @@ static int debug = -1;
module_param(debug, int, 0444); module_param(debug, int, 0444);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
static LIST_HEAD(netvsc_dev_list);
static void netvsc_change_rx_flags(struct net_device *net, int change) static void netvsc_change_rx_flags(struct net_device *net, int change)
{ {
struct net_device_context *ndev_ctx = netdev_priv(net); struct net_device_context *ndev_ctx = netdev_priv(net);
...@@ -1780,6 +1781,36 @@ static void netvsc_link_change(struct work_struct *w) ...@@ -1780,6 +1781,36 @@ static void netvsc_link_change(struct work_struct *w)
rtnl_unlock(); rtnl_unlock();
} }
static struct net_device *get_netvsc_bymac(const u8 *mac)
{
struct net_device_context *ndev_ctx;
list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
struct net_device *dev = hv_get_drvdata(ndev_ctx->device_ctx);
if (ether_addr_equal(mac, dev->perm_addr))
return dev;
}
return NULL;
}
static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
{
struct net_device_context *net_device_ctx;
struct net_device *dev;
dev = netdev_master_upper_dev_get(vf_netdev);
if (!dev || dev->netdev_ops != &device_ops)
return NULL; /* not a netvsc device */
net_device_ctx = netdev_priv(dev);
if (!rtnl_dereference(net_device_ctx->nvdev))
return NULL; /* device is removed */
return dev;
}
/* Called when VF is injecting data into network stack. /* Called when VF is injecting data into network stack.
* Change the associated network device from VF to netvsc. * Change the associated network device from VF to netvsc.
* note: already called with rcu_read_lock * note: already called with rcu_read_lock
...@@ -1802,6 +1833,46 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb) ...@@ -1802,6 +1833,46 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
return RX_HANDLER_ANOTHER; return RX_HANDLER_ANOTHER;
} }
static int netvsc_vf_join(struct net_device *vf_netdev,
struct net_device *ndev)
{
struct net_device_context *ndev_ctx = netdev_priv(ndev);
int ret;
ret = netdev_rx_handler_register(vf_netdev,
netvsc_vf_handle_frame, ndev);
if (ret != 0) {
netdev_err(vf_netdev,
"can not register netvsc VF receive handler (err = %d)\n",
ret);
goto rx_handler_failed;
}
ret = netdev_master_upper_dev_link(vf_netdev, ndev,
NULL, NULL, NULL);
if (ret != 0) {
netdev_err(vf_netdev,
"can not set master device %s (err = %d)\n",
ndev->name, ret);
goto upper_link_failed;
}
/* set slave flag before open to prevent IPv6 addrconf */
vf_netdev->flags |= IFF_SLAVE;
schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
netdev_info(vf_netdev, "joined to %s\n", ndev->name);
return 0;
upper_link_failed:
netdev_rx_handler_unregister(vf_netdev);
rx_handler_failed:
return ret;
}
static void __netvsc_vf_setup(struct net_device *ndev, static void __netvsc_vf_setup(struct net_device *ndev,
struct net_device *vf_netdev) struct net_device *vf_netdev)
{ {
...@@ -1852,95 +1923,104 @@ static void netvsc_vf_setup(struct work_struct *w) ...@@ -1852,95 +1923,104 @@ static void netvsc_vf_setup(struct work_struct *w)
rtnl_unlock(); rtnl_unlock();
} }
static int netvsc_pre_register_vf(struct net_device *vf_netdev, static int netvsc_register_vf(struct net_device *vf_netdev)
struct net_device *ndev)
{ {
struct net_device *ndev;
struct net_device_context *net_device_ctx; struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev; struct netvsc_device *netvsc_dev;
int ret;
if (vf_netdev->addr_len != ETH_ALEN)
return NOTIFY_DONE;
/*
* We will use the MAC address to locate the synthetic interface to
* associate with the VF interface. If we don't find a matching
* synthetic interface, move on.
*/
ndev = get_netvsc_bymac(vf_netdev->perm_addr);
if (!ndev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev); net_device_ctx = netdev_priv(ndev);
netvsc_dev = rtnl_dereference(net_device_ctx->nvdev); netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev)) if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
return -ENODEV; return NOTIFY_DONE;
return 0;
}
static int netvsc_register_vf(struct net_device *vf_netdev, /* if syntihetic interface is a different namespace,
struct net_device *ndev) * then move the VF to that namespace; join will be
{ * done again in that context.
struct net_device_context *ndev_ctx = netdev_priv(ndev); */
if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) {
/* set slave flag before open to prevent IPv6 addrconf */ ret = dev_change_net_namespace(vf_netdev,
vf_netdev->flags |= IFF_SLAVE; dev_net(ndev), "eth%d");
if (ret)
schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); netdev_err(vf_netdev,
"could not move to same namespace as %s: %d\n",
ndev->name, ret);
else
netdev_info(vf_netdev,
"VF moved to namespace with: %s\n",
ndev->name);
return NOTIFY_DONE;
}
call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
netdev_info(vf_netdev, "joined to %s\n", ndev->name); if (netvsc_vf_join(vf_netdev, ndev) != 0)
return NOTIFY_DONE;
dev_hold(vf_netdev); dev_hold(vf_netdev);
rcu_assign_pointer(ndev_ctx->vf_netdev, vf_netdev); rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev);
return NOTIFY_OK;
return 0;
} }
/* VF up/down change detected, schedule to change data path */ /* VF up/down change detected, schedule to change data path */
static int netvsc_vf_changed(struct net_device *vf_netdev, static int netvsc_vf_changed(struct net_device *vf_netdev)
struct net_device *ndev)
{ {
struct net_device_context *net_device_ctx; struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev; struct netvsc_device *netvsc_dev;
struct net_device *ndev;
bool vf_is_up = netif_running(vf_netdev); bool vf_is_up = netif_running(vf_netdev);
ndev = get_netvsc_byref(vf_netdev);
if (!ndev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev); net_device_ctx = netdev_priv(ndev);
netvsc_dev = rtnl_dereference(net_device_ctx->nvdev); netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
if (!netvsc_dev) if (!netvsc_dev)
return -ENODEV; return NOTIFY_DONE;
netvsc_switch_datapath(ndev, vf_is_up); netvsc_switch_datapath(ndev, vf_is_up);
netdev_info(ndev, "Data path switched %s VF: %s\n", netdev_info(ndev, "Data path switched %s VF: %s\n",
vf_is_up ? "to" : "from", vf_netdev->name); vf_is_up ? "to" : "from", vf_netdev->name);
return 0; return NOTIFY_OK;
} }
static int netvsc_pre_unregister_vf(struct net_device *vf_netdev, static int netvsc_unregister_vf(struct net_device *vf_netdev)
struct net_device *ndev)
{ {
struct net_device *ndev;
struct net_device_context *net_device_ctx; struct net_device_context *net_device_ctx;
net_device_ctx = netdev_priv(ndev); ndev = get_netvsc_byref(vf_netdev);
cancel_delayed_work_sync(&net_device_ctx->vf_takeover); if (!ndev)
return NOTIFY_DONE;
return 0;
}
static int netvsc_unregister_vf(struct net_device *vf_netdev,
struct net_device *ndev)
{
struct net_device_context *net_device_ctx;
net_device_ctx = netdev_priv(ndev); net_device_ctx = netdev_priv(ndev);
cancel_delayed_work_sync(&net_device_ctx->vf_takeover);
netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name); netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
netdev_rx_handler_unregister(vf_netdev);
netdev_upper_dev_unlink(vf_netdev, ndev);
RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL); RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
dev_put(vf_netdev); dev_put(vf_netdev);
return 0; return NOTIFY_OK;
} }
static struct failover_ops netvsc_failover_ops = {
.slave_pre_register = netvsc_pre_register_vf,
.slave_register = netvsc_register_vf,
.slave_pre_unregister = netvsc_pre_unregister_vf,
.slave_unregister = netvsc_unregister_vf,
.slave_link_change = netvsc_vf_changed,
.slave_handle_frame = netvsc_vf_handle_frame,
};
static int netvsc_probe(struct hv_device *dev, static int netvsc_probe(struct hv_device *dev,
const struct hv_vmbus_device_id *dev_id) const struct hv_vmbus_device_id *dev_id)
{ {
...@@ -2024,23 +2104,19 @@ static int netvsc_probe(struct hv_device *dev, ...@@ -2024,23 +2104,19 @@ static int netvsc_probe(struct hv_device *dev,
else else
net->max_mtu = ETH_DATA_LEN; net->max_mtu = ETH_DATA_LEN;
ret = register_netdev(net); rtnl_lock();
ret = register_netdevice(net);
if (ret != 0) { if (ret != 0) {
pr_err("Unable to register netdev.\n"); pr_err("Unable to register netdev.\n");
goto register_failed; goto register_failed;
} }
net_device_ctx->failover = failover_register(net, &netvsc_failover_ops); list_add(&net_device_ctx->list, &netvsc_dev_list);
if (IS_ERR(net_device_ctx->failover)) { rtnl_unlock();
ret = PTR_ERR(net_device_ctx->failover); return 0;
goto err_failover;
}
return ret;
err_failover:
unregister_netdev(net);
register_failed: register_failed:
rtnl_unlock();
rndis_filter_device_remove(dev, nvdev); rndis_filter_device_remove(dev, nvdev);
rndis_failed: rndis_failed:
free_percpu(net_device_ctx->vf_stats); free_percpu(net_device_ctx->vf_stats);
...@@ -2080,14 +2156,13 @@ static int netvsc_remove(struct hv_device *dev) ...@@ -2080,14 +2156,13 @@ static int netvsc_remove(struct hv_device *dev)
rtnl_lock(); rtnl_lock();
vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
if (vf_netdev) if (vf_netdev)
failover_slave_unregister(vf_netdev); netvsc_unregister_vf(vf_netdev);
if (nvdev) if (nvdev)
rndis_filter_device_remove(dev, nvdev); rndis_filter_device_remove(dev, nvdev);
unregister_netdevice(net); unregister_netdevice(net);
list_del(&ndev_ctx->list);
failover_unregister(ndev_ctx->failover);
rtnl_unlock(); rtnl_unlock();
rcu_read_unlock(); rcu_read_unlock();
...@@ -2115,8 +2190,54 @@ static struct hv_driver netvsc_drv = { ...@@ -2115,8 +2190,54 @@ static struct hv_driver netvsc_drv = {
.remove = netvsc_remove, .remove = netvsc_remove,
}; };
/*
* On Hyper-V, every VF interface is matched with a corresponding
* synthetic interface. The synthetic interface is presented first
* to the guest. When the corresponding VF instance is registered,
* we will take care of switching the data path.
*/
static int netvsc_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
/* Skip our own events */
if (event_dev->netdev_ops == &device_ops)
return NOTIFY_DONE;
/* Avoid non-Ethernet type devices */
if (event_dev->type != ARPHRD_ETHER)
return NOTIFY_DONE;
/* Avoid Vlan dev with same MAC registering as VF */
if (is_vlan_dev(event_dev))
return NOTIFY_DONE;
/* Avoid Bonding master dev with same MAC registering as VF */
if ((event_dev->priv_flags & IFF_BONDING) &&
(event_dev->flags & IFF_MASTER))
return NOTIFY_DONE;
switch (event) {
case NETDEV_REGISTER:
return netvsc_register_vf(event_dev);
case NETDEV_UNREGISTER:
return netvsc_unregister_vf(event_dev);
case NETDEV_UP:
case NETDEV_DOWN:
return netvsc_vf_changed(event_dev);
default:
return NOTIFY_DONE;
}
}
static struct notifier_block netvsc_netdev_notifier = {
.notifier_call = netvsc_netdev_event,
};
static void __exit netvsc_drv_exit(void) static void __exit netvsc_drv_exit(void)
{ {
unregister_netdevice_notifier(&netvsc_netdev_notifier);
vmbus_driver_unregister(&netvsc_drv); vmbus_driver_unregister(&netvsc_drv);
} }
...@@ -2135,6 +2256,7 @@ static int __init netvsc_drv_init(void) ...@@ -2135,6 +2256,7 @@ static int __init netvsc_drv_init(void)
if (ret) if (ret)
return ret; return ret;
register_netdevice_notifier(&netvsc_netdev_notifier);
return 0; return 0;
} }
......
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