[lustre-devel] [PATCH 16/24] lnet: socklnd: fix link state detection
James Simmons
jsimmons at infradead.org
Tue Sep 21 19:19:53 PDT 2021
From: Serguei Smirnov <ssmirnov at whamcloud.com>
Due to matching only the device index, link detection implemented
in LU-14742 has issues with confusing the link events for the
virtual interfaces with the link events for the interface that
LNet was actually configured to use. Fix this by improving
the identification of the event source: use both device name and
device index.
Also, to make sure the link fatal state is cleared only when
the device is bound to the IP address used at NI creation,
subscribe to inetaddr events in addition to the netdev events.
Fixes: 1db29e184712 ("lnet: socklnd: detect link state to set fatal error on ni")
WC-bug-id: https://jira.whamcloud.com/browse/LU-14954
Lustre-commit: 008795508d65bb40b ("LU-14954 socklnd: fix link state detection")
Signed-off-by: Serguei Smirnov <ssmirnov at whamcloud.com>
Reviewed-on: https://review.whamcloud.com/44732
Reviewed-by: Amir Shehata <ashehata at whamcloud.com>
Reviewed-by: Cyril Bordage <cbordage at whamcloud.com>
Reviewed-by: Oleg Drokin <green at whamcloud.com>
Signed-off-by: James Simmons <jsimmons at infradead.org>
---
net/lnet/klnds/socklnd/socklnd.c | 132 ++++++++++++++++++++++++++++++++++++---
1 file changed, 122 insertions(+), 10 deletions(-)
diff --git a/net/lnet/klnds/socklnd/socklnd.c b/net/lnet/klnds/socklnd/socklnd.c
index 7397ac7..b014aa8 100644
--- a/net/lnet/klnds/socklnd/socklnd.c
+++ b/net/lnet/klnds/socklnd/socklnd.c
@@ -1896,11 +1896,15 @@ static int ksocknal_get_link_status(struct net_device *dev)
LASSERT(dev);
- if (!netif_running(dev))
+ if (!netif_running(dev)) {
ret = 0;
+ CDEBUG(D_NET, "device not running\n");
+ }
/* Some devices may not be providing link settings */
- else if (dev->ethtool_ops->get_link)
+ else if (dev->ethtool_ops->get_link) {
ret = dev->ethtool_ops->get_link(dev);
+ CDEBUG(D_NET, "get_link returns %u\n", ret);
+ }
return ret;
}
@@ -1909,11 +1913,16 @@ static int ksocknal_get_link_status(struct net_device *dev)
ksocknal_handle_link_state_change(struct net_device *dev,
unsigned char operstate)
{
- struct lnet_ni *ni;
+ struct lnet_ni *ni = NULL;
struct ksock_net *net;
struct ksock_net *cnxt;
int ifindex;
unsigned char link_down = !(operstate == IF_OPER_UP);
+ struct in_device *in_dev;
+ bool found_ip = false;
+ struct ksock_interface *ksi = NULL;
+ struct sockaddr_in *sa;
+ const struct in_ifaddr *ifa;
ifindex = dev->ifindex;
@@ -1922,20 +1931,91 @@ static int ksocknal_get_link_status(struct net_device *dev)
list_for_each_entry_safe(net, cnxt, &ksocknal_data.ksnd_nets,
ksnn_list) {
- if (net->ksnn_interface.ksni_index != ifindex)
+
+ ksi = &net->ksnn_interface;
+ sa = (void *)&ksi->ksni_addr;
+ found_ip = false;
+
+ if (ksi->ksni_index != ifindex ||
+ strcmp(ksi->ksni_name, dev->name))
continue;
+
ni = net->ksnn_ni;
- if (link_down)
+
+ in_dev = __in_dev_get_rtnl(dev);
+ if (!in_dev) {
+ CDEBUG(D_NET, "Interface %s has no IPv4 status.\n",
+ dev->name);
+ CDEBUG(D_NET, "set link fatal state to 1\n");
+ atomic_set(&ni->ni_fatal_error_on, 1);
+ continue;
+ }
+ in_dev_for_each_ifa_rtnl(ifa, in_dev) {
+ if (sa->sin_addr.s_addr == ifa->ifa_local)
+ found_ip = true;
+ }
+
+ if (!found_ip) {
+ CDEBUG(D_NET, "Interface %s has no matching ip\n",
+ dev->name);
+ CDEBUG(D_NET, "set link fatal state to 1\n");
+ atomic_set(&ni->ni_fatal_error_on, 1);
+ continue;
+ }
+
+ if (link_down) {
+ CDEBUG(D_NET, "set link fatal state to 1\n");
atomic_set(&ni->ni_fatal_error_on, link_down);
- else
+ } else {
+ CDEBUG(D_NET, "set link fatal state to %u\n",
+ (ksocknal_get_link_status(dev) == 0));
atomic_set(&ni->ni_fatal_error_on,
(ksocknal_get_link_status(dev) == 0));
+ }
}
out:
return 0;
}
+static int
+ksocknal_handle_inetaddr_change(struct in_ifaddr *ifa, unsigned long event)
+{
+ struct lnet_ni *ni;
+ struct ksock_net *net;
+ struct ksock_net *cnxt;
+ struct net_device *event_netdev = ifa->ifa_dev->dev;
+ int ifindex;
+ struct ksock_interface *ksi = NULL;
+ struct sockaddr_in *sa;
+
+ if (!ksocknal_data.ksnd_nnets)
+ goto out;
+
+ ifindex = event_netdev->ifindex;
+
+ list_for_each_entry_safe(net, cnxt, &ksocknal_data.ksnd_nets,
+ ksnn_list) {
+
+ ksi = &net->ksnn_interface;
+ sa = (void *)&ksi->ksni_addr;
+
+ if (ksi->ksni_index != ifindex ||
+ strcmp(ksi->ksni_name, event_netdev->name))
+ continue;
+
+ if (sa->sin_addr.s_addr == ifa->ifa_local) {
+ CDEBUG(D_NET, "set link fatal state to %u\n",
+ (event == NETDEV_DOWN));
+ ni = net->ksnn_ni;
+ atomic_set(&ni->ni_fatal_error_on,
+ (event == NETDEV_DOWN));
+ }
+ }
+out:
+ return 0;
+}
+
/************************************
* Net device notifier event handler
************************************/
@@ -1947,6 +2027,9 @@ static int ksocknal_device_event(struct notifier_block *unused,
operstate = dev->operstate;
+ CDEBUG(D_NET, "devevent: status=%ld, iface=%s ifindex %d state %u\n",
+ event, dev->name, dev->ifindex, operstate);
+
switch (event) {
case NETDEV_UP:
case NETDEV_DOWN:
@@ -1958,10 +2041,36 @@ static int ksocknal_device_event(struct notifier_block *unused,
return NOTIFY_OK;
}
-static struct notifier_block ksocknal_notifier_block = {
+/************************************
+ * Inetaddr notifier event handler
+ ************************************/
+static int ksocknal_inetaddr_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct in_ifaddr *ifa = ptr;
+
+ CDEBUG(D_NET, "addrevent: status %ld ip addr %pI4, netmask %pI4.\n",
+ event, &ifa->ifa_address, &ifa->ifa_mask);
+
+ switch (event) {
+ case NETDEV_UP:
+ case NETDEV_DOWN:
+ case NETDEV_CHANGE:
+ ksocknal_handle_inetaddr_change(ifa, event);
+ break;
+
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block ksocknal_dev_notifier_block = {
.notifier_call = ksocknal_device_event,
};
+static struct notifier_block ksocknal_inetaddr_notifier_block = {
+ .notifier_call = ksocknal_inetaddr_event,
+};
+
static void
ksocknal_base_shutdown(void)
{
@@ -1971,8 +2080,10 @@ static int ksocknal_device_event(struct notifier_block *unused,
LASSERT(!ksocknal_data.ksnd_nnets);
- if (ksocknal_data.ksnd_init == SOCKNAL_INIT_ALL)
- unregister_netdevice_notifier(&ksocknal_notifier_block);
+ if (ksocknal_data.ksnd_init == SOCKNAL_INIT_ALL) {
+ unregister_netdevice_notifier(&ksocknal_dev_notifier_block);
+ unregister_inetaddr_notifier(&ksocknal_inetaddr_notifier_block);
+ }
switch (ksocknal_data.ksnd_init) {
default:
@@ -2135,7 +2246,8 @@ static int ksocknal_device_event(struct notifier_block *unused,
goto failed;
}
- register_netdevice_notifier(&ksocknal_notifier_block);
+ register_netdevice_notifier(&ksocknal_dev_notifier_block);
+ register_inetaddr_notifier(&ksocknal_inetaddr_notifier_block);
/* flag everything initialised */
ksocknal_data.ksnd_init = SOCKNAL_INIT_ALL;
--
1.8.3.1
More information about the lustre-devel
mailing list