Virtualization - Apr 2011 - [PATCH] staging: hv: Fix GARP not sent after Quick Migration

After Quick Migration, the network is not immediately operational in the
current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, I put
the netif_notify_peers() into a scheduled work, otherwise GARP packet will
not be sent after quick migration, and cause network disconnection.

Thanks to Mike Surcouf <mike at surcouf.co.uk> for reporting the bug and
testing the patch.

This patch should also be backported to stable kernel 2.6.32 and later.

Signed-off-by: Haiyang Zhang <haiyangz at microsoft.com>
Signed-off-by: Hank Janssen <hjanssen at microsoft.com>
Signed-off-by: Abhishek Kane <v-abkane at microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys at microsoft.com>
Cc: Mike Surcouf <mike at surcouf.co.uk>
Cc: stable <stable at kernel.org>
---
 drivers/staging/hv/netvsc_drv.c |   17 ++++++++++++++++-
 1 files changed, 16 insertions(+), 1 deletions(-)

diff --git a/drivers/staging/hv/netvsc_drv.c b/drivers/staging/hv/netvsc_drv.c
index 2d40f5f..417e5f7 100644
--- a/drivers/staging/hv/netvsc_drv.c
+++ b/drivers/staging/hv/netvsc_drv.c
@@ -46,6 +46,7 @@ struct net_device_context {
 	/* point back to our device context */
 	struct hv_device *device_ctx;
 	unsigned long avail;
+	struct work_struct work;
 };
 
 
@@ -219,6 +220,7 @@ static void netvsc_linkstatus_callback(struct hv_device
*device_obj,
 				       unsigned int status)
 {
 	struct net_device *net = dev_get_drvdata(&device_obj->device);
+	struct net_device_context *ndev_ctx;
 
 	if (!net) {
 		DPRINT_ERR(NETVSC_DRV, "got link status but net device "
@@ -229,7 +231,8 @@ static void netvsc_linkstatus_callback(struct hv_device
*device_obj,
 	if (status == 1) {
 		netif_carrier_on(net);
 		netif_wake_queue(net);
-		netif_notify_peers(net);
+		ndev_ctx = netdev_priv(net);
+		schedule_work(&ndev_ctx->work);
 	} else {
 		netif_carrier_off(net);
 		netif_stop_queue(net);
@@ -328,6 +331,17 @@ static const struct net_device_ops device_ops = {
 	.ndo_set_mac_address =		eth_mac_addr,
 };
 
+static void netvsc_send_garp(struct work_struct *w)
+{
+	struct net_device_context *ndev_ctx;
+	struct net_device *net;
+
+	ndev_ctx = container_of(w, struct net_device_context, work);
+	net = dev_get_drvdata(&ndev_ctx->device_ctx->device);
+	netif_notify_peers(net);
+}
+
+
 static int netvsc_probe(struct device *device)
 {
 	struct hv_driver *drv @@ -353,6 +367,7 @@ static int netvsc_probe(struct
device *device)
 	net_device_ctx->device_ctx = device_obj;
 	net_device_ctx->avail = ring_size;
 	dev_set_drvdata(device, net);
+	INIT_WORK(&net_device_ctx->work, netvsc_send_garp);
 
 	/* Notify the netvsc driver of the new device */
 	ret = net_drv_obj->base.dev_add(device_obj, &device_info);
-- 
1.6.3.2

On Tue, Apr 05, 2011 at 08:27:48AM -0700, Haiyang Zhang
wrote:
> After Quick Migration, the network is not immediately operational in the
> current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, I put
> the netif_notify_peers() into a scheduled work, otherwise GARP packet will
> not be sent after quick migration, and cause network disconnection.
But that's a hypervisor bug, right?  It shouldn't be sending a
"connect"
event on the ethernet device if the network really isn't present.  How
about getting it fixed there, which will resolve the issues for all
guest operating systems, not just Linux.

Or, if this is something that the hyperv developers are not going to
fix, we need to document it in the code itself so that people don't try
to remove it in a few years as an "optimization".

thanks,

greg k-h

After Quick Migration, the network is not immediately operational in the
current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, I put
the netif_notify_peers() into a scheduled work, otherwise GARP packet will
not be sent after quick migration, and cause network disconnection.

Thanks to Mike Surcouf <mike at surcouf.co.uk> for reporting the bug and
testing the patch.

This patch should also be backported to stable kernel 2.6.32 and later.

Signed-off-by: Haiyang Zhang <haiyangz at microsoft.com>
Signed-off-by: Hank Janssen <hjanssen at microsoft.com>
Signed-off-by: Abhishek Kane <v-abkane at microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys at microsoft.com>
Cc: Mike Surcouf <mike at surcouf.co.uk>
Cc: stable <stable at kernel.org>
---
 drivers/staging/hv/netvsc_drv.c |   24 +++++++++++++++++++++++-
 1 files changed, 23 insertions(+), 1 deletions(-)

diff --git a/drivers/staging/hv/netvsc_drv.c b/drivers/staging/hv/netvsc_drv.c
index 2d40f5f..3566456 100644
--- a/drivers/staging/hv/netvsc_drv.c
+++ b/drivers/staging/hv/netvsc_drv.c
@@ -46,6 +46,7 @@ struct net_device_context {
 	/* point back to our device context */
 	struct hv_device *device_ctx;
 	unsigned long avail;
+	struct work_struct work;
 };
 
 
@@ -219,6 +220,7 @@ static void netvsc_linkstatus_callback(struct hv_device
*device_obj,
 				       unsigned int status)
 {
 	struct net_device *net = dev_get_drvdata(&device_obj->device);
+	struct net_device_context *ndev_ctx;
 
 	if (!net) {
 		DPRINT_ERR(NETVSC_DRV, "got link status but net device "
@@ -229,7 +231,8 @@ static void netvsc_linkstatus_callback(struct hv_device
*device_obj,
 	if (status == 1) {
 		netif_carrier_on(net);
 		netif_wake_queue(net);
-		netif_notify_peers(net);
+		ndev_ctx = netdev_priv(net);
+		schedule_work(&ndev_ctx->work);
 	} else {
 		netif_carrier_off(net);
 		netif_stop_queue(net);
@@ -328,6 +331,24 @@ static const struct net_device_ops device_ops = {
 	.ndo_set_mac_address =		eth_mac_addr,
 };
 
+/*
+ * Send GARP packet to network peers after migrations.
+ * After Quick Migration, the network is not immediately operational in the
+ * current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, I put
+ * the netif_notify_peers() into a scheduled work, otherwise GARP packet will
+ * not be sent after quick migration, and cause network disconnection.
+ */
+static void netvsc_send_garp(struct work_struct *w)
+{
+	struct net_device_context *ndev_ctx;
+	struct net_device *net;
+
+	ndev_ctx = container_of(w, struct net_device_context, work);
+	net = dev_get_drvdata(&ndev_ctx->device_ctx->device);
+	netif_notify_peers(net);
+}
+
+
 static int netvsc_probe(struct device *device)
 {
 	struct hv_driver *drv @@ -353,6 +374,7 @@ static int netvsc_probe(struct
device *device)
 	net_device_ctx->device_ctx = device_obj;
 	net_device_ctx->avail = ring_size;
 	dev_set_drvdata(device, net);
+	INIT_WORK(&net_device_ctx->work, netvsc_send_garp);
 
 	/* Notify the netvsc driver of the new device */
 	ret = net_drv_obj->base.dev_add(device_obj, &device_info);
-- 
1.7.4.1

After Quick Migration, the network is not immediately operational in the
current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, I added
another netif_notify_peers() into a scheduled work, otherwise GARP packet will
not be sent after quick migration, and cause network disconnection.

Thanks to Mike Surcouf <mike at surcouf.co.uk> for reporting the bug and
testing the patch.

This patch should also be backported to stable kernel 2.6.32 and later.

Signed-off-by: Haiyang Zhang <haiyangz at microsoft.com>
Signed-off-by: Hank Janssen <hjanssen at microsoft.com>
Signed-off-by: Abhishek Kane <v-abkane at microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys at microsoft.com>
Cc: Mike Surcouf <mike at surcouf.co.uk>
Cc: stable <stable at kernel.org>
---
 drivers/staging/hv/netvsc_drv.c |   24 ++++++++++++++++++++++++
 1 files changed, 24 insertions(+), 0 deletions(-)

diff --git a/drivers/staging/hv/netvsc_drv.c b/drivers/staging/hv/netvsc_drv.c
index 54a203b..258233d 100644
--- a/drivers/staging/hv/netvsc_drv.c
+++ b/drivers/staging/hv/netvsc_drv.c
@@ -48,6 +48,7 @@ struct net_device_context {
 	/* point back to our device context */
 	struct hv_device *device_ctx;
 	unsigned long avail;
+	struct work_struct work;
 };
 
 
@@ -214,6 +215,7 @@ static void netvsc_linkstatus_callback(struct hv_device
*device_obj,
 				       unsigned int status)
 {
 	struct net_device *net = dev_get_drvdata(&device_obj->device);
+	struct net_device_context *ndev_ctx;
 
 	if (!net) {
 		netdev_err(net, "got link status but net device "
@@ -225,6 +227,8 @@ static void netvsc_linkstatus_callback(struct hv_device
*device_obj,
 		netif_carrier_on(net);
 		netif_wake_queue(net);
 		netif_notify_peers(net);
+		ndev_ctx = netdev_priv(net);
+		schedule_work(&ndev_ctx->work);
 	} else {
 		netif_carrier_off(net);
 		netif_stop_queue(net);
@@ -320,6 +324,25 @@ static const struct net_device_ops device_ops = {
 	.ndo_set_mac_address =		eth_mac_addr,
 };
 
+/*
+ * Send GARP packet to network peers after migrations.
+ * After Quick Migration, the network is not immediately operational in the
+ * current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, add
+ * another netif_notify_peers() into a scheduled work, otherwise GARP packet
+ * will not be sent after quick migration, and cause network disconnection.
+ */
+static void netvsc_send_garp(struct work_struct *w)
+{
+	struct net_device_context *ndev_ctx;
+	struct net_device *net;
+
+	msleep(20);
+	ndev_ctx = container_of(w, struct net_device_context, work);
+	net = dev_get_drvdata(&ndev_ctx->device_ctx->device);
+	netif_notify_peers(net);
+}
+
+
 static int netvsc_probe(struct device *device)
 {
 	struct hv_driver *drv @@ -345,6 +368,7 @@ static int netvsc_probe(struct
device *device)
 	net_device_ctx->device_ctx = device_obj;
 	net_device_ctx->avail = ring_size;
 	dev_set_drvdata(device, net);
+	INIT_WORK(&net_device_ctx->work, netvsc_send_garp);
 
 	/* Notify the netvsc driver of the new device */
 	ret = net_drv_obj->base.dev_add(device_obj, &device_info);
-- 
1.7.4.1