[PATCH net-next v9 1/4] virtio_net: Introduce VIRTIO_NET_F_STANDBY feature bit

[PATCH net-next v9 1/4] virtio_net: Introduce VIRTIO_NET_F_STANDBY feature bit

[Sridhar Samudrala]

This feature bit can be used by hypervisor to indicate virtio_net device to
act as a standby for another device with the same MAC address.

VIRTIO_NET_F_STANDBY is defined as bit 62 as it is a device feature bit.

Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
 drivers/net/virtio_net.c        | 2 +-
 include/uapi/linux/virtio_net.h | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3b5991734118..51a085b1a242 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2999,7 +2999,7 @@ static struct virtio_device_id id_table[] = {
 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
 	VIRTIO_NET_F_CTRL_MAC_ADDR, \
 	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
-	VIRTIO_NET_F_SPEED_DUPLEX
+	VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY
 
 static unsigned int features[] = {
 	VIRTNET_FEATURES,
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 5de6ed37695b..a3715a3224c1 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -57,6 +57,9 @@
 					 * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
 
+#define VIRTIO_NET_F_STANDBY	  62	/* Act as standby for another device
+					 * with the same MAC.
+					 */
 #define VIRTIO_NET_F_SPEED_DUPLEX 63	/* Device set linkspeed and duplex */
 
 #ifndef VIRTIO_NET_NO_LEGACY
-- 
2.14.3

[PATCH net-next v9 2/4] net: Introduce generic failover module

[Sridhar Samudrala]

This provides a generic interface for paravirtual drivers to listen
for netdev register/unregister/link change events from pci ethernet
devices with the same MAC and takeover their datapath. The notifier and
event handling code is based on the existing netvsc implementation.

It exposes 2 sets of interfaces to the paravirtual drivers.
1. For paravirtual drivers like virtio_net that use 3 netdev model, the
   the failover module provides interfaces to create/destroy additional
   master netdev and all the slave events are managed internally.
        net_failover_create()
        net_failover_destroy()
   A failover netdev is created that acts a master device and controls 2
   slave devices. The original virtio_net netdev is registered as 'standby'
   netdev and a passthru/vf device with the same MAC gets registered as
   'primary' netdev. Both 'standby' and 'primary' netdevs are associated
   with the same 'pci' device.  The user accesses the network interface via
   'failover' netdev. The 'failover' netdev chooses 'primary' netdev as
   default for transmits when it is available with link up and running.
2. For existing netvsc driver that uses 2 netdev model, no master netdev
   is created. The paravirtual driver registers each instance of netvsc
   as a 'failover' netdev  along with a set of ops to manage the slave
   events. There is no 'standby' netdev in this model. A passthru/vf device
   with the same MAC gets registered as 'primary' netdev.
        net_failover_register()
        net_failover_unregister()

Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
 include/linux/netdevice.h  |  16 +
 include/net/net_failover.h |  62 ++++
 net/Kconfig                |  10 +
 net/core/Makefile          |   1 +
 net/core/net_failover.c    | 892 +++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 981 insertions(+)
 create mode 100644 include/net/net_failover.h
 create mode 100644 net/core/net_failover.c

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 14e0777ffcfb..b04dbf7dcf1b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1401,6 +1401,8 @@ struct net_device_ops {
  *	entity (i.e. the master device for bridged veth)
  * @IFF_MACSEC: device is a MACsec device
  * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook
+ * @IFF_FAILOVER: device is a failover master device
+ * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1430,6 +1432,8 @@ enum netdev_priv_flags {
 	IFF_PHONY_HEADROOM		= 1<<24,
 	IFF_MACSEC			= 1<<25,
 	IFF_NO_RX_HANDLER		= 1<<26,
+	IFF_FAILOVER			= 1<<27,
+	IFF_FAILOVER_SLAVE		= 1<<28,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1458,6 +1462,8 @@ enum netdev_priv_flags {
 #define IFF_RXFH_CONFIGURED		IFF_RXFH_CONFIGURED
 #define IFF_MACSEC			IFF_MACSEC
 #define IFF_NO_RX_HANDLER		IFF_NO_RX_HANDLER
+#define IFF_FAILOVER			IFF_FAILOVER
+#define IFF_FAILOVER_SLAVE		IFF_FAILOVER_SLAVE
 
 /**
  *	struct net_device - The DEVICE structure.
@@ -4308,6 +4314,16 @@ static inline bool netif_is_rxfh_configured(const struct net_device *dev)
 	return dev->priv_flags & IFF_RXFH_CONFIGURED;
 }
 
+static inline bool netif_is_failover(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_FAILOVER;
+}
+
+static inline bool netif_is_failover_slave(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_FAILOVER_SLAVE;
+}
+
 /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
 static inline void netif_keep_dst(struct net_device *dev)
 {
diff --git a/include/net/net_failover.h b/include/net/net_failover.h
new file mode 100644
index 000000000000..d852f17fb2af
--- /dev/null
+++ b/include/net/net_failover.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Intel Corporation. */
+
+#ifndef _NET_FAILOVER_H
+#define _NET_FAILOVER_H
+
+#include <linux/netdevice.h>
+
+struct net_failover_ops {
+	int (*slave_register)(struct net_device *slave_dev,
+			      struct net_device *failover_dev);
+	int (*slave_unregister)(struct net_device *slave_dev,
+				struct net_device *failover_dev);
+	int (*slave_link_change)(struct net_device *slave_dev,
+				 struct net_device *failover_dev);
+};
+
+struct net_failover {
+	struct list_head list;
+	struct net_device __rcu *failover_dev;
+	struct net_failover_ops __rcu *ops;
+};
+
+/* failover state */
+struct net_failover_info {
+	/* primary netdev with same MAC */
+	struct net_device __rcu *primary_dev;
+
+	/* standby netdev */
+	struct net_device __rcu *standby_dev;
+
+	/* primary netdev stats */
+	struct rtnl_link_stats64 primary_stats;
+
+	/* standby netdev stats */
+	struct rtnl_link_stats64 standby_stats;
+
+	/* aggregated stats */
+	struct rtnl_link_stats64 failover_stats;
+
+	/* spinlock while updating stats */
+	spinlock_t stats_lock;
+};
+
+/* Paravirtual drivers supporting 3-netdev model can use these 2 interfaces to
+ * create and destroy a failover device.
+ */
+int net_failover_create(struct net_device *standby_dev,
+			struct net_failover **pfailover);
+void net_failover_destroy(struct net_failover *failover);
+
+/* Paravirtual drivers supporting 2-netdev model can use these 2 interfaces to
+ * register and unregister a failover device.
+ */
+int net_failover_register(struct net_device *standby_dev,
+			  struct net_failover_ops *ops,
+			  struct net_failover **pfailover);
+void net_failover_unregister(struct net_failover *failover);
+
+int net_failover_slave_unregister(struct net_device *slave_dev);
+
+#endif /* _NET_FAILOVER_H */
diff --git a/net/Kconfig b/net/Kconfig
index 6fa1a4493b8c..ebbc9b70418d 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -426,6 +426,16 @@ config MAY_USE_DEVLINK
 config PAGE_POOL
        bool
 
+config NET_FAILOVER
+	tristate "Failover interface"
+	default m
+	help
+	  This provides a generic interface for paravirtual drivers to listen
+	  for netdev register/unregister/link change events from pci ethernet
+	  devices with the same MAC and takeover their datapath. This also
+	  enables live migration of a VM with direct attached VF by failing
+	  over to the paravirtual datapath when the VF is unplugged.
+
 endif   # if NET
 
 # Used by archs to tell that they support BPF JIT compiler plus which flavour.
diff --git a/net/core/Makefile b/net/core/Makefile
index 7080417f8bc8..283ed9b0e581 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -31,3 +31,4 @@ obj-$(CONFIG_DST_CACHE) += dst_cache.o
 obj-$(CONFIG_HWBM) += hwbm.o
 obj-$(CONFIG_NET_DEVLINK) += devlink.o
 obj-$(CONFIG_GRO_CELLS) += gro_cells.o
+obj-$(CONFIG_NET_FAILOVER) += net_failover.o
diff --git a/net/core/net_failover.c b/net/core/net_failover.c
new file mode 100644
index 000000000000..ac164be17563
--- /dev/null
+++ b/net/core/net_failover.c
@@ -0,0 +1,892 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, Intel Corporation. */
+
+/* A common module to handle registrations and notifications for paravirtual
+ * drivers to enable accelerated datapath and support VF live migration.
+ *
+ * The notifier and event handling code is based on netvsc driver and failover
+ * netdev management routines are based on bond/team driver.
+ *
+ */
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/netpoll.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+#include <linux/pci.h>
+#include <net/sch_generic.h>
+#include <uapi/linux/if_arp.h>
+#include <net/net_failover.h>
+
+static LIST_HEAD(net_failover_list);
+static DEFINE_SPINLOCK(net_failover_lock);
+
+static int net_failover_open(struct net_device *dev)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *primary_dev, *standby_dev;
+	int err;
+
+	netif_carrier_off(dev);
+	netif_tx_wake_all_queues(dev);
+
+	primary_dev = rtnl_dereference(nfo_info->primary_dev);
+	if (primary_dev) {
+		err = dev_open(primary_dev);
+		if (err)
+			goto err_primary_open;
+	}
+
+	standby_dev = rtnl_dereference(nfo_info->standby_dev);
+	if (standby_dev) {
+		err = dev_open(standby_dev);
+		if (err)
+			goto err_standby_open;
+	}
+
+	return 0;
+
+err_standby_open:
+	dev_close(primary_dev);
+err_primary_open:
+	netif_tx_disable(dev);
+	return err;
+}
+
+static int net_failover_close(struct net_device *dev)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *slave_dev;
+
+	netif_tx_disable(dev);
+
+	slave_dev = rtnl_dereference(nfo_info->primary_dev);
+	if (slave_dev)
+		dev_close(slave_dev);
+
+	slave_dev = rtnl_dereference(nfo_info->standby_dev);
+	if (slave_dev)
+		dev_close(slave_dev);
+
+	return 0;
+}
+
+static netdev_tx_t net_failover_drop_xmit(struct sk_buff *skb,
+					  struct net_device *dev)
+{
+	atomic_long_inc(&dev->tx_dropped);
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
+static bool net_failover_xmit_ready(struct net_device *dev)
+{
+	return netif_running(dev) && netif_carrier_ok(dev);
+}
+
+static netdev_tx_t net_failover_start_xmit(struct sk_buff *skb,
+					   struct net_device *dev)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *xmit_dev;
+
+	/* Try xmit via primary netdev followed by standby netdev */
+	xmit_dev = rcu_dereference_bh(nfo_info->primary_dev);
+	if (!xmit_dev || !net_failover_xmit_ready(xmit_dev)) {
+		xmit_dev = rcu_dereference_bh(nfo_info->standby_dev);
+		if (!xmit_dev || !net_failover_xmit_ready(xmit_dev))
+			return net_failover_drop_xmit(skb, dev);
+	}
+
+	skb->dev = xmit_dev;
+	skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;
+
+	return dev_queue_xmit(skb);
+}
+
+static u16 net_failover_select_queue(struct net_device *dev,
+				     struct sk_buff *skb, void *accel_priv,
+				     select_queue_fallback_t fallback)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *primary_dev;
+	u16 txq;
+
+	rcu_read_lock();
+	primary_dev = rcu_dereference(nfo_info->primary_dev);
+	if (primary_dev) {
+		const struct net_device_ops *ops = primary_dev->netdev_ops;
+
+		if (ops->ndo_select_queue)
+			txq = ops->ndo_select_queue(primary_dev, skb,
+						    accel_priv, fallback);
+		else
+			txq = fallback(primary_dev, skb);
+
+		qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
+
+		return txq;
+	}
+
+	txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0;
+
+	/* Save the original txq to restore before passing to the driver */
+	qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
+
+	if (unlikely(txq >= dev->real_num_tx_queues)) {
+		do {
+			txq -= dev->real_num_tx_queues;
+		} while (txq >= dev->real_num_tx_queues);
+	}
+
+	return txq;
+}
+
+/* fold stats, assuming all rtnl_link_stats64 fields are u64, but
+ * that some drivers can provide 32bit values only.
+ */
+static void net_failover_fold_stats(struct rtnl_link_stats64 *_res,
+				    const struct rtnl_link_stats64 *_new,
+				    const struct rtnl_link_stats64 *_old)
+{
+	const u64 *new = (const u64 *)_new;
+	const u64 *old = (const u64 *)_old;
+	u64 *res = (u64 *)_res;
+	int i;
+
+	for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) {
+		u64 nv = new[i];
+		u64 ov = old[i];
+		s64 delta = nv - ov;
+
+		/* detects if this particular field is 32bit only */
+		if (((nv | ov) >> 32) == 0)
+			delta = (s64)(s32)((u32)nv - (u32)ov);
+
+		/* filter anomalies, some drivers reset their stats
+		 * at down/up events.
+		 */
+		if (delta > 0)
+			res[i] += delta;
+	}
+}
+
+static void net_failover_get_stats(struct net_device *dev,
+				   struct rtnl_link_stats64 *stats)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	const struct rtnl_link_stats64 *new;
+	struct rtnl_link_stats64 temp;
+	struct net_device *slave_dev;
+
+	spin_lock(&nfo_info->stats_lock);
+	memcpy(stats, &nfo_info->failover_stats, sizeof(*stats));
+
+	rcu_read_lock();
+
+	slave_dev = rcu_dereference(nfo_info->primary_dev);
+	if (slave_dev) {
+		new = dev_get_stats(slave_dev, &temp);
+		net_failover_fold_stats(stats, new, &nfo_info->primary_stats);
+		memcpy(&nfo_info->primary_stats, new, sizeof(*new));
+	}
+
+	slave_dev = rcu_dereference(nfo_info->standby_dev);
+	if (slave_dev) {
+		new = dev_get_stats(slave_dev, &temp);
+		net_failover_fold_stats(stats, new, &nfo_info->standby_stats);
+		memcpy(&nfo_info->standby_stats, new, sizeof(*new));
+	}
+
+	rcu_read_unlock();
+
+	memcpy(&nfo_info->failover_stats, stats, sizeof(*stats));
+	spin_unlock(&nfo_info->stats_lock);
+}
+
+static int net_failover_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *primary_dev, *standby_dev;
+	int ret = 0;
+
+	primary_dev = rcu_dereference(nfo_info->primary_dev);
+	if (primary_dev) {
+		ret = dev_set_mtu(primary_dev, new_mtu);
+		if (ret)
+			return ret;
+	}
+
+	standby_dev = rcu_dereference(nfo_info->standby_dev);
+	if (standby_dev) {
+		ret = dev_set_mtu(standby_dev, new_mtu);
+		if (ret) {
+			dev_set_mtu(primary_dev, dev->mtu);
+			return ret;
+		}
+	}
+
+	dev->mtu = new_mtu;
+
+	return 0;
+}
+
+static void net_failover_set_rx_mode(struct net_device *dev)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *slave_dev;
+
+	rcu_read_lock();
+
+	slave_dev = rcu_dereference(nfo_info->primary_dev);
+	if (slave_dev) {
+		dev_uc_sync_multiple(slave_dev, dev);
+		dev_mc_sync_multiple(slave_dev, dev);
+	}
+
+	slave_dev = rcu_dereference(nfo_info->standby_dev);
+	if (slave_dev) {
+		dev_uc_sync_multiple(slave_dev, dev);
+		dev_mc_sync_multiple(slave_dev, dev);
+	}
+
+	rcu_read_unlock();
+}
+
+static int net_failover_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
+					u16 vid)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *primary_dev, *standby_dev;
+	int ret = 0;
+
+	primary_dev = rcu_dereference(nfo_info->primary_dev);
+	if (primary_dev) {
+		ret = vlan_vid_add(primary_dev, proto, vid);
+		if (ret)
+			return ret;
+	}
+
+	standby_dev = rcu_dereference(nfo_info->standby_dev);
+	if (standby_dev) {
+		ret = vlan_vid_add(standby_dev, proto, vid);
+		if (ret)
+			vlan_vid_del(primary_dev, proto, vid);
+	}
+
+	return ret;
+}
+
+static int net_failover_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
+					 u16 vid)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *slave_dev;
+
+	slave_dev = rcu_dereference(nfo_info->primary_dev);
+	if (slave_dev)
+		vlan_vid_del(slave_dev, proto, vid);
+
+	slave_dev = rcu_dereference(nfo_info->standby_dev);
+	if (slave_dev)
+		vlan_vid_del(slave_dev, proto, vid);
+
+	return 0;
+}
+
+static const struct net_device_ops failover_dev_ops = {
+	.ndo_open		= net_failover_open,
+	.ndo_stop		= net_failover_close,
+	.ndo_start_xmit		= net_failover_start_xmit,
+	.ndo_select_queue	= net_failover_select_queue,
+	.ndo_get_stats64	= net_failover_get_stats,
+	.ndo_change_mtu		= net_failover_change_mtu,
+	.ndo_set_rx_mode	= net_failover_set_rx_mode,
+	.ndo_vlan_rx_add_vid	= net_failover_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= net_failover_vlan_rx_kill_vid,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_features_check	= passthru_features_check,
+};
+
+#define FAILOVER_NAME "failover"
+#define FAILOVER_VERSION "0.1"
+
+static void nfo_ethtool_get_drvinfo(struct net_device *dev,
+				    struct ethtool_drvinfo *drvinfo)
+{
+	strlcpy(drvinfo->driver, FAILOVER_NAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, FAILOVER_VERSION, sizeof(drvinfo->version));
+}
+
+static int nfo_ethtool_get_link_ksettings(struct net_device *dev,
+					  struct ethtool_link_ksettings *cmd)
+{
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *slave_dev;
+
+	slave_dev = rtnl_dereference(nfo_info->primary_dev);
+	if (!slave_dev || !net_failover_xmit_ready(slave_dev)) {
+		slave_dev = rtnl_dereference(nfo_info->standby_dev);
+		if (!slave_dev || !net_failover_xmit_ready(slave_dev)) {
+			cmd->base.duplex = DUPLEX_UNKNOWN;
+			cmd->base.port = PORT_OTHER;
+			cmd->base.speed = SPEED_UNKNOWN;
+
+			return 0;
+		}
+	}
+
+	return __ethtool_get_link_ksettings(slave_dev, cmd);
+}
+
+static const struct ethtool_ops failover_ethtool_ops = {
+	.get_drvinfo            = nfo_ethtool_get_drvinfo,
+	.get_link               = ethtool_op_get_link,
+	.get_link_ksettings     = nfo_ethtool_get_link_ksettings,
+};
+
+static struct net_device *net_failover_get_bymac(u8 *mac,
+						 struct net_failover_ops **ops)
+{
+	struct net_device *failover_dev;
+	struct net_failover *failover;
+
+	spin_lock(&net_failover_lock);
+	list_for_each_entry(failover, &net_failover_list, list) {
+		failover_dev = rtnl_dereference(failover->failover_dev);
+		if (ether_addr_equal(failover_dev->perm_addr, mac)) {
+			*ops = rtnl_dereference(failover->ops);
+			spin_unlock(&net_failover_lock);
+			return failover_dev;
+		}
+	}
+	spin_unlock(&net_failover_lock);
+	return NULL;
+}
+
+/* Called when slave dev is injecting data into network stack.
+ * Change the associated network device from lower dev to virtio.
+ * note: already called with rcu_read_lock
+ */
+static rx_handler_result_t net_failover_handle_frame(struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+	struct net_device *ndev = rcu_dereference(skb->dev->rx_handler_data);
+
+	skb->dev = ndev;
+
+	return RX_HANDLER_ANOTHER;
+}
+
+#define FAILOVER_VLAN_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
+				 NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
+				 NETIF_F_HIGHDMA | NETIF_F_LRO)
+
+#define FAILOVER_ENC_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
+				 NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
+
+static void net_failover_compute_features(struct net_device *dev)
+{
+	u32 vlan_features = FAILOVER_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
+	netdev_features_t enc_features  = FAILOVER_ENC_FEATURES;
+	unsigned short max_hard_header_len = ETH_HLEN;
+	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
+					IFF_XMIT_DST_RELEASE_PERM;
+	struct net_failover_info *nfo_info = netdev_priv(dev);
+	struct net_device *primary_dev, *standby_dev;
+
+	primary_dev = rcu_dereference(nfo_info->primary_dev);
+	if (primary_dev) {
+		vlan_features =
+			netdev_increment_features(vlan_features,
+						  primary_dev->vlan_features,
+						  FAILOVER_VLAN_FEATURES);
+		enc_features =
+			netdev_increment_features(enc_features,
+						  primary_dev->hw_enc_features,
+						  FAILOVER_ENC_FEATURES);
+
+		dst_release_flag &= primary_dev->priv_flags;
+		if (primary_dev->hard_header_len > max_hard_header_len)
+			max_hard_header_len = primary_dev->hard_header_len;
+	}
+
+	standby_dev = rcu_dereference(nfo_info->standby_dev);
+	if (standby_dev) {
+		vlan_features =
+			netdev_increment_features(vlan_features,
+						  standby_dev->vlan_features,
+						  FAILOVER_VLAN_FEATURES);
+		enc_features =
+			netdev_increment_features(enc_features,
+						  standby_dev->hw_enc_features,
+						  FAILOVER_ENC_FEATURES);
+
+		dst_release_flag &= standby_dev->priv_flags;
+		if (standby_dev->hard_header_len > max_hard_header_len)
+			max_hard_header_len = standby_dev->hard_header_len;
+	}
+
+	dev->vlan_features = vlan_features;
+	dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL;
+	dev->hard_header_len = max_hard_header_len;
+
+	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+	if (dst_release_flag == (IFF_XMIT_DST_RELEASE |
+				 IFF_XMIT_DST_RELEASE_PERM))
+		dev->priv_flags |= IFF_XMIT_DST_RELEASE;
+
+	netdev_change_features(dev);
+}
+
+static int net_failover_slave_register(struct net_device *slave_dev)
+{
+	struct net_failover_info *nfo_info;
+	struct net_failover_ops *nfo_ops;
+	struct net_device *failover_dev;
+	bool slave_is_standby;
+	u32 orig_mtu;
+	int err;
+
+	ASSERT_RTNL();
+
+	failover_dev = net_failover_get_bymac(slave_dev->perm_addr, &nfo_ops);
+	if (!failover_dev)
+		goto done;
+
+	if (failover_dev->type != slave_dev->type)
+		goto done;
+
+	if (nfo_ops && nfo_ops->slave_register)
+		return nfo_ops->slave_register(slave_dev, failover_dev);
+
+	nfo_info = netdev_priv(failover_dev);
+	slave_is_standby = (slave_dev->dev.parent == failover_dev->dev.parent);
+	if (slave_is_standby ? rtnl_dereference(nfo_info->standby_dev) :
+			rtnl_dereference(nfo_info->primary_dev)) {
+		netdev_err(failover_dev, "%s attempting to register as slave dev when %s already present\n",
+			   slave_dev->name,
+			   slave_is_standby ? "standby" : "primary");
+		goto done;
+	}
+
+	/* We want to allow only a direct attached VF device as a primary
+	 * netdev. As there is no easy way to check for a VF device, restrict
+	 * this to a pci device.
+	 */
+	if (!slave_is_standby && (!slave_dev->dev.parent ||
+				  !dev_is_pci(slave_dev->dev.parent)))
+		goto done;
+
+	if (failover_dev->features & NETIF_F_VLAN_CHALLENGED &&
+	    vlan_uses_dev(failover_dev)) {
+		netdev_err(failover_dev, "Device %s is VLAN challenged and failover device has VLAN set up\n",
+			   failover_dev->name);
+		goto done;
+	}
+
+	/* Align MTU of slave with failover dev */
+	orig_mtu = slave_dev->mtu;
+	err = dev_set_mtu(slave_dev, failover_dev->mtu);
+	if (err) {
+		netdev_err(failover_dev, "unable to change mtu of %s to %u register failed\n",
+			   slave_dev->name, failover_dev->mtu);
+		goto done;
+	}
+
+	dev_hold(slave_dev);
+
+	if (netif_running(failover_dev)) {
+		err = dev_open(slave_dev);
+		if (err && (err != -EBUSY)) {
+			netdev_err(failover_dev, "Opening slave %s failed err:%d\n",
+				   slave_dev->name, err);
+			goto err_dev_open;
+		}
+	}
+
+	netif_addr_lock_bh(failover_dev);
+	dev_uc_sync_multiple(slave_dev, failover_dev);
+	dev_uc_sync_multiple(slave_dev, failover_dev);
+	netif_addr_unlock_bh(failover_dev);
+
+	err = vlan_vids_add_by_dev(slave_dev, failover_dev);
+	if (err) {
+		netdev_err(failover_dev, "Failed to add vlan ids to device %s err:%d\n",
+			   slave_dev->name, err);
+		goto err_vlan_add;
+	}
+
+	err = netdev_rx_handler_register(slave_dev, net_failover_handle_frame,
+					 failover_dev);
+	if (err) {
+		netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n",
+			   err);
+		goto err_handler_register;
+	}
+
+	err = netdev_upper_dev_link(slave_dev, failover_dev, NULL);
+	if (err) {
+		netdev_err(slave_dev, "can not set failover device %s (err = %d)\n",
+			   failover_dev->name, err);
+		goto err_upper_link;
+	}
+
+	slave_dev->priv_flags |= IFF_FAILOVER_SLAVE;
+
+	if (slave_is_standby) {
+		rcu_assign_pointer(nfo_info->standby_dev, slave_dev);
+		dev_get_stats(nfo_info->standby_dev, &nfo_info->standby_stats);
+	} else {
+		rcu_assign_pointer(nfo_info->primary_dev, slave_dev);
+		dev_get_stats(nfo_info->primary_dev, &nfo_info->primary_stats);
+		failover_dev->min_mtu = slave_dev->min_mtu;
+		failover_dev->max_mtu = slave_dev->max_mtu;
+	}
+
+	net_failover_compute_features(failover_dev);
+
+	call_netdevice_notifiers(NETDEV_JOIN, slave_dev);
+
+	netdev_info(failover_dev, "failover %s slave:%s registered\n",
+		    slave_is_standby ? "standby" : "primary", slave_dev->name);
+
+	goto done;
+
+err_upper_link:
+	netdev_rx_handler_unregister(slave_dev);
+err_handler_register:
+	vlan_vids_del_by_dev(slave_dev, failover_dev);
+err_vlan_add:
+	dev_uc_unsync(slave_dev, failover_dev);
+	dev_mc_unsync(slave_dev, failover_dev);
+	dev_close(slave_dev);
+err_dev_open:
+	dev_put(slave_dev);
+	dev_set_mtu(slave_dev, orig_mtu);
+done:
+	return NOTIFY_DONE;
+}
+
+int net_failover_slave_unregister(struct net_device *slave_dev)
+{
+	struct net_device *standby_dev, *primary_dev;
+	struct net_failover_info *nfo_info;
+	struct net_failover_ops *nfo_ops;
+	struct net_device *failover_dev;
+	bool slave_is_standby;
+
+	if (!netif_is_failover_slave(slave_dev))
+		goto done;
+
+	ASSERT_RTNL();
+
+	failover_dev = net_failover_get_bymac(slave_dev->perm_addr, &nfo_ops);
+	if (!failover_dev)
+		goto done;
+
+	if (nfo_ops && nfo_ops->slave_unregister)
+		return nfo_ops->slave_unregister(slave_dev, failover_dev);
+
+	nfo_info = netdev_priv(failover_dev);
+	primary_dev = rtnl_dereference(nfo_info->primary_dev);
+	standby_dev = rtnl_dereference(nfo_info->standby_dev);
+
+	if (slave_dev != primary_dev && slave_dev != standby_dev)
+		goto done;
+
+	slave_is_standby = (slave_dev->dev.parent == failover_dev->dev.parent);
+
+	netdev_rx_handler_unregister(slave_dev);
+	netdev_upper_dev_unlink(slave_dev, failover_dev);
+	vlan_vids_del_by_dev(slave_dev, failover_dev);
+	dev_uc_unsync(slave_dev, failover_dev);
+	dev_mc_unsync(slave_dev, failover_dev);
+	dev_close(slave_dev);
+	slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+
+	nfo_info = netdev_priv(failover_dev);
+	net_failover_get_stats(failover_dev, &nfo_info->failover_stats);
+
+	if (slave_is_standby) {
+		RCU_INIT_POINTER(nfo_info->standby_dev, NULL);
+	} else {
+		RCU_INIT_POINTER(nfo_info->primary_dev, NULL);
+		if (standby_dev) {
+			failover_dev->min_mtu = standby_dev->min_mtu;
+			failover_dev->max_mtu = standby_dev->max_mtu;
+		}
+	}
+
+	dev_put(slave_dev);
+
+	net_failover_compute_features(failover_dev);
+
+	netdev_info(failover_dev, "failover %s slave:%s unregistered\n",
+		    slave_is_standby ? "standby" : "primary", slave_dev->name);
+
+done:
+	return NOTIFY_DONE;
+}
+EXPORT_SYMBOL_GPL(net_failover_slave_unregister);
+
+static int net_failover_slave_link_change(struct net_device *slave_dev)
+{
+	struct net_device *failover_dev, *primary_dev, *standby_dev;
+	struct net_failover_info *nfo_info;
+	struct net_failover_ops *nfo_ops;
+
+	if (!netif_is_failover_slave(slave_dev))
+		goto done;
+
+	ASSERT_RTNL();
+
+	failover_dev = net_failover_get_bymac(slave_dev->perm_addr, &nfo_ops);
+	if (!failover_dev)
+		goto done;
+
+	if (nfo_ops && nfo_ops->slave_link_change)
+		return nfo_ops->slave_link_change(slave_dev, failover_dev);
+
+	if (!netif_running(failover_dev))
+		return 0;
+
+	nfo_info = netdev_priv(failover_dev);
+
+	primary_dev = rtnl_dereference(nfo_info->primary_dev);
+	standby_dev = rtnl_dereference(nfo_info->standby_dev);
+
+	if (slave_dev != primary_dev && slave_dev != standby_dev)
+		goto done;
+
+	if ((primary_dev && net_failover_xmit_ready(primary_dev)) ||
+	    (standby_dev && net_failover_xmit_ready(standby_dev))) {
+		netif_carrier_on(failover_dev);
+		netif_tx_wake_all_queues(failover_dev);
+	} else {
+		net_failover_get_stats(failover_dev, &nfo_info->failover_stats);
+		netif_carrier_off(failover_dev);
+		netif_tx_stop_all_queues(failover_dev);
+	}
+
+done:
+	return NOTIFY_DONE;
+}
+
+static int
+net_failover_event(struct notifier_block *this, unsigned long event, void *ptr)
+{
+	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+
+	/* Skip parent events */
+	if (netif_is_failover(event_dev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		return net_failover_slave_register(event_dev);
+	case NETDEV_UNREGISTER:
+		return net_failover_slave_unregister(event_dev);
+	case NETDEV_UP:
+	case NETDEV_DOWN:
+	case NETDEV_CHANGE:
+		return net_failover_slave_link_change(event_dev);
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static struct notifier_block net_failover_notifier = {
+	.notifier_call = net_failover_event,
+};
+
+static void nfo_register_existing_slave(struct net_device *failover_dev)
+{
+	struct net *net = dev_net(failover_dev);
+	struct net_device *dev;
+
+	rtnl_lock();
+	for_each_netdev(net, dev) {
+		if (netif_is_failover(dev))
+			continue;
+		if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr))
+			net_failover_slave_register(dev);
+	}
+	rtnl_unlock();
+}
+
+int net_failover_register(struct net_device *dev, struct net_failover_ops *ops,
+			  struct net_failover **pfailover)
+{
+	struct net_failover *failover;
+
+	failover = kzalloc(sizeof(*failover), GFP_KERNEL);
+	if (!failover)
+		return -ENOMEM;
+
+	rcu_assign_pointer(failover->ops, ops);
+	dev_hold(dev);
+	dev->priv_flags |= IFF_FAILOVER;
+	rcu_assign_pointer(failover->failover_dev, dev);
+
+	spin_lock(&net_failover_lock);
+	list_add_tail(&failover->list, &net_failover_list);
+	spin_unlock(&net_failover_lock);
+
+	netdev_info(dev, "failover master:%s registered\n", dev->name);
+
+	nfo_register_existing_slave(dev);
+
+	*pfailover = failover;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(net_failover_register);
+
+void net_failover_unregister(struct net_failover *failover)
+{
+	struct net_device *failover_dev;
+
+	failover_dev = rcu_dereference(failover->failover_dev);
+
+	netdev_info(failover_dev, "failover master:%s unregistered\n",
+		    failover_dev->name);
+
+	failover_dev->priv_flags &= ~IFF_FAILOVER;
+	dev_put(failover_dev);
+
+	spin_lock(&net_failover_lock);
+	list_del(&failover->list);
+	spin_unlock(&net_failover_lock);
+
+	kfree(failover);
+}
+EXPORT_SYMBOL_GPL(net_failover_unregister);
+
+int net_failover_create(struct net_device *standby_dev,
+			struct net_failover **pfailover)
+{
+	struct device *dev = standby_dev->dev.parent;
+	struct net_device *failover_dev;
+	int err;
+
+	/* Alloc at least 2 queues, for now we are going with 16 assuming
+	 * that VF devices being enslaved won't have too many queues.
+	 */
+	failover_dev = alloc_etherdev_mq(sizeof(struct net_failover_info), 16);
+	if (!failover_dev) {
+		dev_err(dev, "Unable to allocate failover_netdev!\n");
+		return -ENOMEM;
+	}
+
+	dev_net_set(failover_dev, dev_net(standby_dev));
+	SET_NETDEV_DEV(failover_dev, dev);
+
+	failover_dev->netdev_ops = &failover_dev_ops;
+	failover_dev->ethtool_ops = &failover_ethtool_ops;
+
+	/* Initialize the device options */
+	failover_dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE;
+	failover_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE |
+				       IFF_TX_SKB_SHARING);
+
+	/* don't acquire failover netdev's netif_tx_lock when transmitting */
+	failover_dev->features |= NETIF_F_LLTX;
+
+	/* Don't allow failover devices to change network namespaces. */
+	failover_dev->features |= NETIF_F_NETNS_LOCAL;
+
+	failover_dev->hw_features = FAILOVER_VLAN_FEATURES |
+				    NETIF_F_HW_VLAN_CTAG_TX |
+				    NETIF_F_HW_VLAN_CTAG_RX |
+				    NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	failover_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
+	failover_dev->features |= failover_dev->hw_features;
+
+	memcpy(failover_dev->dev_addr, standby_dev->dev_addr,
+	       failover_dev->addr_len);
+
+	failover_dev->min_mtu = standby_dev->min_mtu;
+	failover_dev->max_mtu = standby_dev->max_mtu;
+
+	err = register_netdev(failover_dev);
+	if (err < 0) {
+		dev_err(dev, "Unable to register failover_dev!\n");
+		goto err_register_netdev;
+	}
+
+	netif_carrier_off(failover_dev);
+
+	err = net_failover_register(failover_dev, NULL, pfailover);
+	if (err < 0)
+		goto err_failover_register;
+
+	return 0;
+
+err_failover_register:
+	unregister_netdev(failover_dev);
+err_register_netdev:
+	free_netdev(failover_dev);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(net_failover_create);
+
+void net_failover_destroy(struct net_failover *failover)
+{
+	struct net_failover_info *nfo_info;
+	struct net_device *failover_dev;
+	struct net_device *slave_dev;
+
+	if (!failover)
+		return;
+
+	failover_dev = rcu_dereference(failover->failover_dev);
+	nfo_info = netdev_priv(failover_dev);
+
+	netif_device_detach(failover_dev);
+
+	rtnl_lock();
+
+	slave_dev = rtnl_dereference(nfo_info->primary_dev);
+	if (slave_dev)
+		net_failover_slave_unregister(slave_dev);
+
+	slave_dev = rtnl_dereference(nfo_info->standby_dev);
+	if (slave_dev)
+		net_failover_slave_unregister(slave_dev);
+
+	net_failover_unregister(failover);
+
+	unregister_netdevice(failover_dev);
+
+	rtnl_unlock();
+
+	free_netdev(failover_dev);
+}
+EXPORT_SYMBOL_GPL(net_failover_destroy);
+
+static __init int
+net_failover_init(void)
+{
+	register_netdevice_notifier(&net_failover_notifier);
+
+	return 0;
+}
+module_init(net_failover_init);
+
+static __exit
+void net_failover_exit(void)
+{
+	unregister_netdevice_notifier(&net_failover_notifier);
+}
+module_exit(net_failover_exit);
+
+MODULE_DESCRIPTION("Failover infrastructure/interface for Paravirtual drivers");
+MODULE_LICENSE("GPL v2");
-- 
2.14.3

[PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Sridhar Samudrala]

This patch enables virtio_net to switch over to a VF datapath when a VF
netdev is present with the same MAC address. It allows live migration
of a VM with a direct attached VF without the need to setup a bond/team
between a VF and virtio net device in the guest.

The hypervisor needs to enable only one datapath at any time so that
packets don't get looped back to the VM over the other datapath. When a VF
is plugged, the virtio datapath link state can be marked as down. The
hypervisor needs to unplug the VF device from the guest on the source host
and reset the MAC filter of the VF to initiate failover of datapath to
virtio before starting the migration. After the migration is completed,
the destination hypervisor sets the MAC filter on the VF and plugs it back
to the guest to switch over to VF datapath.

It uses the generic failover framework that provides 2 functions to create
and destroy a master failover netdev. When STANDBY feature is enabled, an
additional netdev(failover netdev) is created that acts as a master device
and tracks the state of the 2 lower netdevs. The original virtio_net netdev
is marked as 'standby' netdev and a passthru device with the same MAC is
registered as 'primary' netdev.

This patch is based on the discussion initiated by Jesse on this thread.
https://marc.info/?l=linux-virtualization&m=151189725224231&w=2

Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
 drivers/net/Kconfig      |  1 +
 drivers/net/virtio_net.c | 35 ++++++++++++++++++++++++++++++++++-
 2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 891846655000..c4995625d9b1 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -331,6 +331,7 @@ config VETH
 config VIRTIO_NET
 	tristate "Virtio network driver"
 	depends on VIRTIO
+	select NET_FAILOVER
 	---help---
 	  This is the virtual network driver for virtio.  It can be used with
 	  QEMU based VMMs (like KVM or Xen).  Say Y or M.
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 51a085b1a242..c326ee5344c0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -30,8 +30,11 @@
 #include <linux/cpu.h>
 #include <linux/average.h>
 #include <linux/filter.h>
+#include <linux/netdevice.h>
+#include <linux/pci.h>
 #include <net/route.h>
 #include <net/xdp.h>
+#include <net/net_failover.h>
 
 static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);
@@ -210,6 +213,9 @@ struct virtnet_info {
 	u32 speed;
 
 	unsigned long guest_offloads;
+
+	/* failover when STANDBY feature enabled */
+	struct net_failover *failover;
 };
 
 struct padded_vnet_hdr {
@@ -2306,6 +2312,22 @@ static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
+static int virtnet_get_phys_port_name(struct net_device *dev, char *buf,
+				      size_t len)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	int ret;
+
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY))
+		return -EOPNOTSUPP;
+
+	ret = snprintf(buf, len, "_sby");
+	if (ret >= len)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
@@ -2323,6 +2345,7 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_xdp_xmit		= virtnet_xdp_xmit,
 	.ndo_xdp_flush		= virtnet_xdp_flush,
 	.ndo_features_check	= passthru_features_check,
+	.ndo_get_phys_port_name	= virtnet_get_phys_port_name,
 };
 
 static void virtnet_config_changed_work(struct work_struct *work)
@@ -2876,10 +2899,16 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 	virtnet_init_settings(dev);
 
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY)) {
+		err = net_failover_create(vi->dev, &vi->failover);
+		if (err)
+			goto free_vqs;
+	}
+
 	err = register_netdev(dev);
 	if (err) {
 		pr_debug("virtio_net: registering device failed\n");
-		goto free_vqs;
+		goto free_failover;
 	}
 
 	virtio_device_ready(vdev);
@@ -2916,6 +2945,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 	vi->vdev->config->reset(vdev);
 
 	unregister_netdev(dev);
+free_failover:
+	net_failover_destroy(vi->failover);
 free_vqs:
 	cancel_delayed_work_sync(&vi->refill);
 	free_receive_page_frags(vi);
@@ -2950,6 +2981,8 @@ static void virtnet_remove(struct virtio_device *vdev)
 
 	unregister_netdev(vi->dev);
 
+	net_failover_destroy(vi->failover);
+
 	remove_vq_common(vi);
 
 	free_netdev(vi->dev);
-- 
2.14.3

[PATCH net-next v9 4/4] netvsc: refactor notifier/event handling code to use the failover framework

[Sridhar Samudrala]

Use the registration/notification framework supported by the generic
failover infrastructure.

Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
---
 drivers/net/hyperv/Kconfig      |   1 +
 drivers/net/hyperv/hyperv_net.h |   2 +
 drivers/net/hyperv/netvsc_drv.c | 134 +++++++---------------------------------
 3 files changed, 26 insertions(+), 111 deletions(-)

diff --git a/drivers/net/hyperv/Kconfig b/drivers/net/hyperv/Kconfig
index 0765d5f61714..1f8419fc7c7f 100644
--- a/drivers/net/hyperv/Kconfig
+++ b/drivers/net/hyperv/Kconfig
@@ -2,5 +2,6 @@ config HYPERV_NET
 	tristate "Microsoft Hyper-V virtual network driver"
 	depends on HYPERV
 	select UCS2_STRING
+	select NET_FAILOVER
 	help
 	  Select this option to enable the Hyper-V virtual network driver.
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 6ebe39a3dde6..2ec18344c0e8 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -932,6 +932,8 @@ struct net_device_context {
 	u32 vf_alloc;
 	/* Serial number of the VF to team with */
 	u32 vf_serial;
+
+	struct net_failover *failover;
 };
 
 /* Per channel data */
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index ecc84954c511..fa446234bc11 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -43,6 +43,7 @@
 #include <net/pkt_sched.h>
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
+#include <net/net_failover.h>
 
 #include "hyperv_net.h"
 
@@ -1763,46 +1764,6 @@ static void netvsc_link_change(struct work_struct *w)
 	rtnl_unlock();
 }
 
-static struct net_device *get_netvsc_bymac(const u8 *mac)
-{
-	struct net_device *dev;
-
-	ASSERT_RTNL();
-
-	for_each_netdev(&init_net, dev) {
-		if (dev->netdev_ops != &device_ops)
-			continue;	/* not a netvsc device */
-
-		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 *dev;
-
-	ASSERT_RTNL();
-
-	for_each_netdev(&init_net, dev) {
-		struct net_device_context *net_device_ctx;
-
-		if (dev->netdev_ops != &device_ops)
-			continue;	/* not a netvsc device */
-
-		net_device_ctx = netdev_priv(dev);
-		if (!rtnl_dereference(net_device_ctx->nvdev))
-			continue;	/* device is removed */
-
-		if (rtnl_dereference(net_device_ctx->vf_netdev) == vf_netdev)
-			return dev;	/* a match */
-	}
-
-	return NULL;
-}
-
 /* Called when VF is injecting data into network stack.
  * Change the associated network device from VF to netvsc.
  * note: already called with rcu_read_lock
@@ -1914,24 +1875,15 @@ static void netvsc_vf_setup(struct work_struct *w)
 	rtnl_unlock();
 }
 
-static int netvsc_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 netvsc_device *netvsc_dev;
 
 	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);
 	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 	if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
@@ -1948,17 +1900,13 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 }
 
 /* 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 netvsc_device *netvsc_dev;
-	struct net_device *ndev;
 	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);
 	netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
 	if (!netvsc_dev)
@@ -1971,15 +1919,11 @@ static int netvsc_vf_changed(struct net_device *vf_netdev)
 	return NOTIFY_OK;
 }
 
-static int netvsc_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;
 
-	ndev = get_netvsc_byref(vf_netdev);
-	if (!ndev)
-		return NOTIFY_DONE;
-
 	net_device_ctx = netdev_priv(ndev);
 	cancel_delayed_work_sync(&net_device_ctx->vf_takeover);
 
@@ -1993,6 +1937,12 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 	return NOTIFY_OK;
 }
 
+static struct net_failover_ops netvsc_failover_ops = {
+	.slave_register		= netvsc_register_vf,
+	.slave_unregister	= netvsc_unregister_vf,
+	.slave_link_change	= netvsc_vf_changed,
+};
+
 static int netvsc_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
 {
@@ -2082,8 +2032,15 @@ static int netvsc_probe(struct hv_device *dev,
 		goto register_failed;
 	}
 
+	ret = net_failover_register(net, &netvsc_failover_ops,
+				    &net_device_ctx->failover);
+	if (ret != 0)
+		goto err_failover;
+
 	return ret;
 
+err_failover:
+	unregister_netdev(net);
 register_failed:
 	rndis_filter_device_remove(dev, nvdev);
 rndis_failed:
@@ -2124,13 +2081,15 @@ static int netvsc_remove(struct hv_device *dev)
 	rtnl_lock();
 	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
 	if (vf_netdev)
-		netvsc_unregister_vf(vf_netdev);
+		net_failover_slave_unregister(vf_netdev);
 
 	if (nvdev)
 		rndis_filter_device_remove(dev, nvdev);
 
 	unregister_netdevice(net);
 
+	net_failover_unregister(ndev_ctx->failover);
+
 	rtnl_unlock();
 	rcu_read_unlock();
 
@@ -2157,54 +2116,8 @@ static struct  hv_driver netvsc_drv = {
 	.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)
 {
-	unregister_netdevice_notifier(&netvsc_netdev_notifier);
 	vmbus_driver_unregister(&netvsc_drv);
 }
 
@@ -2224,7 +2137,6 @@ static int __init netvsc_drv_init(void)
 	if (ret)
 		return ret;
 
-	register_netdevice_notifier(&netvsc_netdev_notifier);
 	return 0;
 }
 
-- 
2.14.3

Re: [PATCH net-next v9 0/4] Enable virtio_net to act as a standby for a passthru device

[Jiri Pirko]

Fri, Apr 27, 2018 at 07:06:56PM CEST, sridhar.samudrala@intel.com wrote:
>v9:
>Select NET_FAILOVER automatically when VIRTIO_NET/HYPERV_NET 
>are enabled. (stephen)
>
>Tested live migration with virtio-net/AVF(i40evf) configured in 
>failover mode while running iperf in background.
>Build tested netvsc module.
>
>The main motivation for this patch is to enable cloud service providers
>to provide an accelerated datapath to virtio-net enabled VMs in a 
>transparent manner with no/minimal guest userspace changes. This also
>enables hypervisor controlled live migration to be supported with VMs that
>have direct attached SR-IOV VF devices.
>
>Patch 1 introduces a new feature bit VIRTIO_NET_F_STANDBY that can be
>used by hypervisor to indicate that virtio_net interface should act as
>a standby for another device with the same MAC address.
>
>Patch 2 introduces a failover module that provides a generic interface for 
>paravirtual drivers to listen for netdev register/unregister/link change
>events from pci ethernet devices with the same MAC and takeover their
>datapath. The notifier and event handling code is based on the existing
>netvsc implementation. It provides 2 sets of interfaces to paravirtual 
>drivers to support 2-netdev(netvsc) and 3-netdev(virtio_net) models.
>
>Patch 3 extends virtio_net to use alternate datapath when available and
>registered. When STANDBY feature is enabled, virtio_net driver creates
>an additional 'failover' netdev that acts as a master device and controls
>2 slave devices.  The original virtio_net netdev is registered as
>'standby' netdev and a passthru/vf device with the same MAC gets
>registered as 'primary' netdev. Both 'standby' and 'primary' netdevs are
>associated with the same 'pci' device.  The user accesses the network
>interface via 'failover' netdev. The 'failover' netdev chooses 'primary'
>netdev as default for transmits when it is available with link up and
>running.
>
>Patch 4 refactors netvsc to use the registration/notification framework
>supported by failover module.
>
>As this patch series is initially focusing on usecases where hypervisor 
>fully controls the VM networking and the guest is not expected to directly 
>configure any hardware settings, it doesn't expose all the ndo/ethtool ops
>that are supported by virtio_net at this time. To support additional usecases,
>it should be possible to enable additional ops later by caching the state
>in virtio netdev and replaying when the 'primary' netdev gets registered. 
> 
>The hypervisor needs to enable only one datapath at any time so that packets
>don't get looped back to the VM over the other datapath. When a VF is
>plugged, the virtio datapath link state can be marked as down.
>At the time of live migration, the hypervisor needs to unplug the VF device
>from the guest on the source host and reset the MAC filter of the VF to
>initiate failover of datapath to virtio before starting the migration. After
>the migration is completed, the destination hypervisor sets the MAC filter
>on the VF and plugs it back to the guest to switch over to VF datapath.
>
>This patch is based on the discussion initiated by Jesse on this thread.
>https://marc.info/?l=linux-virtualization&m=151189725224231&w=2


No changes in v9?


>
>v8:
>- Made the failover managment routines more robust by updating the feature 
>  bits/other fields in the failover netdev when slave netdevs are 
>  registered/unregistered. (mst)
>- added support for handling vlans.
>- Limited the changes in netvsc to only use the notifier/event/lookups
>  from the failover module. The slave register/unregister/link-change 
>  handlers are only updated to use the getbymac routine to get the 
>  upper netdev. There is no change in their functionality. (stephen)
>- renamed structs/function/file names to use net_failover prefix. (mst)
>
>v7
>- Rename 'bypass/active/backup' terminology with 'failover/primary/standy'
>  (jiri, mst)
>- re-arranged dev_open() and dev_set_mtu() calls in the register routines
>  so that they don't get called for 2-netdev model. (stephen)
>- fixed select_queue() routine to do queue selection based on VF if it is
>  registered as primary. (stephen)
>-  minor bugfixes
>
>v6 RFC:
>  Simplified virtio_net changes by moving all the ndo_ops of the 
>  bypass_netdev and create/destroy of bypass_netdev to 'bypass' module.
>  avoided 2 phase registration(driver + instances).
>  introduced IFF_BYPASS/IFF_BYPASS_SLAVE dev->priv_flags 
>  replaced mutex with a spinlock
>
>v5 RFC:
>  Based on Jiri's comments, moved the common functionality to a 'bypass'
>  module so that the same notifier and event handlers to handle child
>  register/unregister/link change events can be shared between virtio_net
>  and netvsc.
>  Improved error handling based on Siwei's comments.
>v4:
>- Based on the review comments on the v3 version of the RFC patch and
>  Jakub's suggestion for the naming issue with 3 netdev solution,
>  proposed 3 netdev in-driver bonding solution for virtio-net.
>v3 RFC:
>- Introduced 3 netdev model and pointed out a couple of issues with
>  that model and proposed 2 netdev model to avoid these issues.
>- Removed broadcast/multicast optimization and only use virtio as
>  backup path when VF is unplugged.
>v2 RFC:
>- Changed VIRTIO_NET_F_MASTER to VIRTIO_NET_F_BACKUP (mst)
>- made a small change to the virtio-net xmit path to only use VF datapath
>  for unicasts. Broadcasts/multicasts use virtio datapath. This avoids
>  east-west broadcasts to go over the PCI link.
>- added suppport for the feature bit in qemu
>
>Sridhar Samudrala (4):
>  virtio_net: Introduce VIRTIO_NET_F_STANDBY feature bit
>  net: Introduce generic failover module
>  virtio_net: Extend virtio to use VF datapath when available
>  netvsc: refactor notifier/event handling code to use the failover
>    framework
>
> drivers/net/Kconfig             |   1 +
> drivers/net/hyperv/Kconfig      |   1 +
> drivers/net/hyperv/hyperv_net.h |   2 +
> drivers/net/hyperv/netvsc_drv.c | 134 ++----
> drivers/net/virtio_net.c        |  37 +-
> include/linux/netdevice.h       |  16 +
> include/net/net_failover.h      |  62 +++
> include/uapi/linux/virtio_net.h |   3 +
> net/Kconfig                     |  10 +
> net/core/Makefile               |   1 +
> net/core/net_failover.c         | 892 ++++++++++++++++++++++++++++++++++++++++
> 11 files changed, 1046 insertions(+), 113 deletions(-)
> create mode 100644 include/net/net_failover.h
> create mode 100644 net/core/net_failover.c
>
>-- 
>2.14.3

Re: [PATCH net-next v9 0/4] Enable virtio_net to act as a standby for a passthru device

[Samudrala, Sridhar]

On 4/27/2018 10:45 AM, Jiri Pirko wrote:
> Fri, Apr 27, 2018 at 07:06:56PM CEST, sridhar.samudrala@intel.com wrote:
>> v9:
>> Select NET_FAILOVER automatically when VIRTIO_NET/HYPERV_NET
>> are enabled. (stephen)
>>
>> Tested live migration with virtio-net/AVF(i40evf) configured in
>> failover mode while running iperf in background.
>> Build tested netvsc module.
>>
>> The main motivation for this patch is to enable cloud service providers
>> to provide an accelerated datapath to virtio-net enabled VMs in a
>> transparent manner with no/minimal guest userspace changes. This also
>> enables hypervisor controlled live migration to be supported with VMs that
>> have direct attached SR-IOV VF devices.
>>
>> Patch 1 introduces a new feature bit VIRTIO_NET_F_STANDBY that can be
>> used by hypervisor to indicate that virtio_net interface should act as
>> a standby for another device with the same MAC address.
>>
>> Patch 2 introduces a failover module that provides a generic interface for
>> paravirtual drivers to listen for netdev register/unregister/link change
>> events from pci ethernet devices with the same MAC and takeover their
>> datapath. The notifier and event handling code is based on the existing
>> netvsc implementation. It provides 2 sets of interfaces to paravirtual
>> drivers to support 2-netdev(netvsc) and 3-netdev(virtio_net) models.
>>
>> Patch 3 extends virtio_net to use alternate datapath when available and
>> registered. When STANDBY feature is enabled, virtio_net driver creates
>> an additional 'failover' netdev that acts as a master device and controls
>> 2 slave devices.  The original virtio_net netdev is registered as
>> 'standby' netdev and a passthru/vf device with the same MAC gets
>> registered as 'primary' netdev. Both 'standby' and 'primary' netdevs are
>> associated with the same 'pci' device.  The user accesses the network
>> interface via 'failover' netdev. The 'failover' netdev chooses 'primary'
>> netdev as default for transmits when it is available with link up and
>> running.
>>
>> Patch 4 refactors netvsc to use the registration/notification framework
>> supported by failover module.
>>
>> As this patch series is initially focusing on usecases where hypervisor
>> fully controls the VM networking and the guest is not expected to directly
>> configure any hardware settings, it doesn't expose all the ndo/ethtool ops
>> that are supported by virtio_net at this time. To support additional usecases,
>> it should be possible to enable additional ops later by caching the state
>> in virtio netdev and replaying when the 'primary' netdev gets registered.
>>
>> The hypervisor needs to enable only one datapath at any time so that packets
>> don't get looped back to the VM over the other datapath. When a VF is
>> plugged, the virtio datapath link state can be marked as down.
>> At the time of live migration, the hypervisor needs to unplug the VF device
> >from the guest on the source host and reset the MAC filter of the VF to
>> initiate failover of datapath to virtio before starting the migration. After
>> the migration is completed, the destination hypervisor sets the MAC filter
>> on the VF and plugs it back to the guest to switch over to VF datapath.
>>
>> This patch is based on the discussion initiated by Jesse on this thread.
>> https://marc.info/?l=linux-virtualization&m=151189725224231&w=2
>
> No changes in v9?

I listed v9 updates at the start of the message.

v9:
Select NET_FAILOVER automatically when VIRTIO_NET/HYPERV_NET
are enabled. (stephen)

Tested live migration with virtio-net/AVF(i40evf) configured in
failover mode while running iperf in background.
Build tested netvsc module.



>
>> v8:
>> - Made the failover managment routines more robust by updating the feature
>>   bits/other fields in the failover netdev when slave netdevs are
>>   registered/unregistered. (mst)
>> - added support for handling vlans.
>> - Limited the changes in netvsc to only use the notifier/event/lookups
>>   from the failover module. The slave register/unregister/link-change
>>   handlers are only updated to use the getbymac routine to get the
>>   upper netdev. There is no change in their functionality. (stephen)
>> - renamed structs/function/file names to use net_failover prefix. (mst)
>>
>> v7
>> - Rename 'bypass/active/backup' terminology with 'failover/primary/standy'
>>   (jiri, mst)
>> - re-arranged dev_open() and dev_set_mtu() calls in the register routines
>>   so that they don't get called for 2-netdev model. (stephen)
>> - fixed select_queue() routine to do queue selection based on VF if it is
>>   registered as primary. (stephen)
>> -  minor bugfixes
>>
>> v6 RFC:
>>   Simplified virtio_net changes by moving all the ndo_ops of the
>>   bypass_netdev and create/destroy of bypass_netdev to 'bypass' module.
>>   avoided 2 phase registration(driver + instances).
>>   introduced IFF_BYPASS/IFF_BYPASS_SLAVE dev->priv_flags
>>   replaced mutex with a spinlock
>>
>> v5 RFC:
>>   Based on Jiri's comments, moved the common functionality to a 'bypass'
>>   module so that the same notifier and event handlers to handle child
>>   register/unregister/link change events can be shared between virtio_net
>>   and netvsc.
>>   Improved error handling based on Siwei's comments.
>> v4:
>> - Based on the review comments on the v3 version of the RFC patch and
>>   Jakub's suggestion for the naming issue with 3 netdev solution,
>>   proposed 3 netdev in-driver bonding solution for virtio-net.
>> v3 RFC:
>> - Introduced 3 netdev model and pointed out a couple of issues with
>>   that model and proposed 2 netdev model to avoid these issues.
>> - Removed broadcast/multicast optimization and only use virtio as
>>   backup path when VF is unplugged.
>> v2 RFC:
>> - Changed VIRTIO_NET_F_MASTER to VIRTIO_NET_F_BACKUP (mst)
>> - made a small change to the virtio-net xmit path to only use VF datapath
>>   for unicasts. Broadcasts/multicasts use virtio datapath. This avoids
>>   east-west broadcasts to go over the PCI link.
>> - added suppport for the feature bit in qemu
>>
>> Sridhar Samudrala (4):
>>   virtio_net: Introduce VIRTIO_NET_F_STANDBY feature bit
>>   net: Introduce generic failover module
>>   virtio_net: Extend virtio to use VF datapath when available
>>   netvsc: refactor notifier/event handling code to use the failover
>>     framework
>>
>> drivers/net/Kconfig             |   1 +
>> drivers/net/hyperv/Kconfig      |   1 +
>> drivers/net/hyperv/hyperv_net.h |   2 +
>> drivers/net/hyperv/netvsc_drv.c | 134 ++----
>> drivers/net/virtio_net.c        |  37 +-
>> include/linux/netdevice.h       |  16 +
>> include/net/net_failover.h      |  62 +++
>> include/uapi/linux/virtio_net.h |   3 +
>> net/Kconfig                     |  10 +
>> net/core/Makefile               |   1 +
>> net/core/net_failover.c         | 892 ++++++++++++++++++++++++++++++++++++++++
>> 11 files changed, 1046 insertions(+), 113 deletions(-)
>> create mode 100644 include/net/net_failover.h
>> create mode 100644 net/core/net_failover.c
>>
>> -- 
>> 2.14.3

Re: [PATCH net-next v9 0/4] Enable virtio_net to act as a standby for a passthru device

[Jiri Pirko]

Fri, Apr 27, 2018 at 07:53:01PM CEST, sridhar.samudrala@intel.com wrote:
>On 4/27/2018 10:45 AM, Jiri Pirko wrote:
>> Fri, Apr 27, 2018 at 07:06:56PM CEST, sridhar.samudrala@intel.com wrote:

[...]

>> 
>> No changes in v9?
>
>I listed v9 updates at the start of the message.

Hmm, odd. I expected that at the end, in the changelog among other Vs
changes.

Will review this patchset tomorrow.
Thanks!

Re: [PATCH net-next v9 1/4] virtio_net: Introduce VIRTIO_NET_F_STANDBY feature bit

[Jiri Pirko]

Fri, Apr 27, 2018 at 07:06:57PM CEST, sridhar.samudrala@intel.com wrote:
>This feature bit can be used by hypervisor to indicate virtio_net device to
>act as a standby for another device with the same MAC address.
>
>VIRTIO_NET_F_STANDBY is defined as bit 62 as it is a device feature bit.
>
>Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
>---
> drivers/net/virtio_net.c        | 2 +-
> include/uapi/linux/virtio_net.h | 3 +++
> 2 files changed, 4 insertions(+), 1 deletion(-)
>
>diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>index 3b5991734118..51a085b1a242 100644
>--- a/drivers/net/virtio_net.c
>+++ b/drivers/net/virtio_net.c
>@@ -2999,7 +2999,7 @@ static struct virtio_device_id id_table[] = {
> 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
> 	VIRTIO_NET_F_CTRL_MAC_ADDR, \
> 	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
>-	VIRTIO_NET_F_SPEED_DUPLEX
>+	VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY


This is not part of current qemu master (head 6f0c4706b35dead265509115ddbd2a8d1af516c1)
Were I can find the qemu code?

Also, I think it makes sense to push HW (qemu HW in this case) first
and only then the driver.



> 
> static unsigned int features[] = {
> 	VIRTNET_FEATURES,
>diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
>index 5de6ed37695b..a3715a3224c1 100644
>--- a/include/uapi/linux/virtio_net.h
>+++ b/include/uapi/linux/virtio_net.h
>@@ -57,6 +57,9 @@
> 					 * Steering */
> #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
> 
>+#define VIRTIO_NET_F_STANDBY	  62	/* Act as standby for another device
>+					 * with the same MAC.
>+					 */
> #define VIRTIO_NET_F_SPEED_DUPLEX 63	/* Device set linkspeed and duplex */
> 
> #ifndef VIRTIO_NET_NO_LEGACY
>-- 
>2.14.3
>

Re: [PATCH net-next v9 1/4] virtio_net: Introduce VIRTIO_NET_F_STANDBY feature bit

[Samudrala, Sridhar]

[-- Attachment #1.1: Type: text/plain, Size: 1370 bytes --]

On 4/28/2018 12:50 AM, Jiri Pirko wrote:
> Fri, Apr 27, 2018 at 07:06:57PM CEST,sridhar.samudrala@intel.com  wrote:
>> This feature bit can be used by hypervisor to indicate virtio_net device to
>> act as a standby for another device with the same MAC address.
>>
>> VIRTIO_NET_F_STANDBY is defined as bit 62 as it is a device feature bit.
>>
>> Signed-off-by: Sridhar Samudrala<sridhar.samudrala@intel.com>
>> ---
>> drivers/net/virtio_net.c        | 2 +-
>> include/uapi/linux/virtio_net.h | 3 +++
>> 2 files changed, 4 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>> index 3b5991734118..51a085b1a242 100644
>> --- a/drivers/net/virtio_net.c
>> +++ b/drivers/net/virtio_net.c
>> @@ -2999,7 +2999,7 @@ static struct virtio_device_id id_table[] = {
>> 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
>> 	VIRTIO_NET_F_CTRL_MAC_ADDR, \
>> 	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
>> -	VIRTIO_NET_F_SPEED_DUPLEX
>> +	VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY
> This is not part of current qemu master (head 6f0c4706b35dead265509115ddbd2a8d1af516c1)
> Were I can find the qemu code?
>
> Also, I think it makes sense to push HW (qemu HW in this case) first
> and only then the driver.

I had sent qemu patch with a couple of earlier versions of this patchset.
Will include it when i send out v10.



[-- Attachment #1.2: Type: text/html, Size: 1897 bytes --]

[-- Attachment #2: Type: text/plain, Size: 183 bytes --]

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net-next v9 1/4] virtio_net: Introduce VIRTIO_NET_F_STANDBY feature bit

[Jiri Pirko]

Mon, Apr 30, 2018 at 04:47:03AM CEST, sridhar.samudrala@intel.com wrote:
>On 4/28/2018 12:50 AM, Jiri Pirko wrote:
>> Fri, Apr 27, 2018 at 07:06:57PM CEST,sridhar.samudrala@intel.com  wrote:
>> > This feature bit can be used by hypervisor to indicate virtio_net device to
>> > act as a standby for another device with the same MAC address.
>> > 
>> > VIRTIO_NET_F_STANDBY is defined as bit 62 as it is a device feature bit.
>> > 
>> > Signed-off-by: Sridhar Samudrala<sridhar.samudrala@intel.com>
>> > ---
>> > drivers/net/virtio_net.c        | 2 +-
>> > include/uapi/linux/virtio_net.h | 3 +++
>> > 2 files changed, 4 insertions(+), 1 deletion(-)
>> > 
>> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>> > index 3b5991734118..51a085b1a242 100644
>> > --- a/drivers/net/virtio_net.c
>> > +++ b/drivers/net/virtio_net.c
>> > @@ -2999,7 +2999,7 @@ static struct virtio_device_id id_table[] = {
>> > 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
>> > 	VIRTIO_NET_F_CTRL_MAC_ADDR, \
>> > 	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
>> > -	VIRTIO_NET_F_SPEED_DUPLEX
>> > +	VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY
>> This is not part of current qemu master (head 6f0c4706b35dead265509115ddbd2a8d1af516c1)
>> Were I can find the qemu code?
>> 
>> Also, I think it makes sense to push HW (qemu HW in this case) first
>> and only then the driver.
>
>I had sent qemu patch with a couple of earlier versions of this patchset.
>Will include it when i send out v10.

The point was, don't you want to push it to qemu first? Did you at least
send RFC to qemu?

Re: [PATCH net-next v9 1/4] virtio_net: Introduce VIRTIO_NET_F_STANDBY feature bit

[Samudrala, Sridhar]

On 4/30/2018 12:03 AM, Jiri Pirko wrote:
> Mon, Apr 30, 2018 at 04:47:03AM CEST, sridhar.samudrala@intel.com wrote:
>> On 4/28/2018 12:50 AM, Jiri Pirko wrote:
>>> Fri, Apr 27, 2018 at 07:06:57PM CEST,sridhar.samudrala@intel.com  wrote:
>>>> This feature bit can be used by hypervisor to indicate virtio_net device to
>>>> act as a standby for another device with the same MAC address.
>>>>
>>>> VIRTIO_NET_F_STANDBY is defined as bit 62 as it is a device feature bit.
>>>>
>>>> Signed-off-by: Sridhar Samudrala<sridhar.samudrala@intel.com>
>>>> ---
>>>> drivers/net/virtio_net.c        | 2 +-
>>>> include/uapi/linux/virtio_net.h | 3 +++
>>>> 2 files changed, 4 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>>>> index 3b5991734118..51a085b1a242 100644
>>>> --- a/drivers/net/virtio_net.c
>>>> +++ b/drivers/net/virtio_net.c
>>>> @@ -2999,7 +2999,7 @@ static struct virtio_device_id id_table[] = {
>>>> 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
>>>> 	VIRTIO_NET_F_CTRL_MAC_ADDR, \
>>>> 	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
>>>> -	VIRTIO_NET_F_SPEED_DUPLEX
>>>> +	VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY
>>> This is not part of current qemu master (head 6f0c4706b35dead265509115ddbd2a8d1af516c1)
>>> Were I can find the qemu code?
>>>
>>> Also, I think it makes sense to push HW (qemu HW in this case) first
>>> and only then the driver.
>> I had sent qemu patch with a couple of earlier versions of this patchset.
>> Will include it when i send out v10.
> The point was, don't you want to push it to qemu first? Did you at least
> send RFC to qemu?

Yes. Here is the link to the RFC patch.
https://patchwork.ozlabs.org/patch/859521/

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Jiri Pirko]

Fri, Apr 27, 2018 at 07:06:59PM CEST, sridhar.samudrala@intel.com wrote:
>This patch enables virtio_net to switch over to a VF datapath when a VF
>netdev is present with the same MAC address. It allows live migration
>of a VM with a direct attached VF without the need to setup a bond/team
>between a VF and virtio net device in the guest.
>
>The hypervisor needs to enable only one datapath at any time so that
>packets don't get looped back to the VM over the other datapath. When a VF

Why? Both datapaths could be enabled at a time. Why the loop on
hypervisor side would be a problem. This in not an issue for
bonding/team as well.


>is plugged, the virtio datapath link state can be marked as down. The
>hypervisor needs to unplug the VF device from the guest on the source host
>and reset the MAC filter of the VF to initiate failover of datapath to

"reset the MAC filter of the VF" - you mean "set the VF mac"?


>virtio before starting the migration. After the migration is completed,
>the destination hypervisor sets the MAC filter on the VF and plugs it back
>to the guest to switch over to VF datapath.
>
>It uses the generic failover framework that provides 2 functions to create
>and destroy a master failover netdev. When STANDBY feature is enabled, an
>additional netdev(failover netdev) is created that acts as a master device
>and tracks the state of the 2 lower netdevs. The original virtio_net netdev
>is marked as 'standby' netdev and a passthru device with the same MAC is
>registered as 'primary' netdev.
>
>This patch is based on the discussion initiated by Jesse on this thread.
>https://marc.info/?l=linux-virtualization&m=151189725224231&w=2

[...]

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Samudrala, Sridhar]

On 4/28/2018 1:24 AM, Jiri Pirko wrote:
> Fri, Apr 27, 2018 at 07:06:59PM CEST, sridhar.samudrala@intel.com wrote:
>> This patch enables virtio_net to switch over to a VF datapath when a VF
>> netdev is present with the same MAC address. It allows live migration
>> of a VM with a direct attached VF without the need to setup a bond/team
>> between a VF and virtio net device in the guest.
>>
>> The hypervisor needs to enable only one datapath at any time so that
>> packets don't get looped back to the VM over the other datapath. When a VF
> Why? Both datapaths could be enabled at a time. Why the loop on
> hypervisor side would be a problem. This in not an issue for
> bonding/team as well.

Somehow the hypervisor needs to make sure that the broadcasts/multicasts from the VM
sent over the VF datapath don't get looped back to the VM via the virtio-net datapth.
This can happen if both datapaths are enabled at the same time.

I would think this is an issue even with bonding/team as well when virtio-net and
VF are backed by the same PF.


>
>
>> is plugged, the virtio datapath link state can be marked as down. The
>> hypervisor needs to unplug the VF device from the guest on the source host
>> and reset the MAC filter of the VF to initiate failover of datapath to
> "reset the MAC filter of the VF" - you mean "set the VF mac"?

Yes.  the PF should take away the MAC address assigned to the VF so that the PF
starts receiving those packets.

>
>
>> virtio before starting the migration. After the migration is completed,
>> the destination hypervisor sets the MAC filter on the VF and plugs it back
>> to the guest to switch over to VF datapath.
>>
>> It uses the generic failover framework that provides 2 functions to create
>> and destroy a master failover netdev. When STANDBY feature is enabled, an
>> additional netdev(failover netdev) is created that acts as a master device
>> and tracks the state of the 2 lower netdevs. The original virtio_net netdev
>> is marked as 'standby' netdev and a passthru device with the same MAC is
>> registered as 'primary' netdev.
>>
>> This patch is based on the discussion initiated by Jesse on this thread.
>> https://marc.info/?l=linux-virtualization&m=151189725224231&w=2
> [...]
>

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Jiri Pirko]

Mon, Apr 30, 2018 at 05:00:33AM CEST, sridhar.samudrala@intel.com wrote:
>
>On 4/28/2018 1:24 AM, Jiri Pirko wrote:
>> Fri, Apr 27, 2018 at 07:06:59PM CEST, sridhar.samudrala@intel.com wrote:
>> > This patch enables virtio_net to switch over to a VF datapath when a VF
>> > netdev is present with the same MAC address. It allows live migration
>> > of a VM with a direct attached VF without the need to setup a bond/team
>> > between a VF and virtio net device in the guest.
>> > 
>> > The hypervisor needs to enable only one datapath at any time so that
>> > packets don't get looped back to the VM over the other datapath. When a VF
>> Why? Both datapaths could be enabled at a time. Why the loop on
>> hypervisor side would be a problem. This in not an issue for
>> bonding/team as well.
>
>Somehow the hypervisor needs to make sure that the broadcasts/multicasts from the VM
>sent over the VF datapath don't get looped back to the VM via the virtio-net datapth.

Why? Please see below.


>This can happen if both datapaths are enabled at the same time.
>
>I would think this is an issue even with bonding/team as well when virtio-net and
>VF are backed by the same PF.
>
>

I believe that the scenario is the same as on an ordinary nic/swich
network:

...................

  host
 
       bond0
      /     \
    eth0   eth1
     |       |
...................
     |       |
     p1      p2

  switch

...................

It is perfectly valid to p1 and p2 be up and "bridged" together. Bond
has to cope with loop-backed frames. "Failover driver" should too,
it's the same scenario.


>> 
>> 
>> > is plugged, the virtio datapath link state can be marked as down. The
>> > hypervisor needs to unplug the VF device from the guest on the source host
>> > and reset the MAC filter of the VF to initiate failover of datapath to
>> "reset the MAC filter of the VF" - you mean "set the VF mac"?
>
>Yes.  the PF should take away the MAC address assigned to the VF so that the PF
>starts receiving those packets.

Okay, got it. Please put this in the description.


>
>> 
>> 
>> > virtio before starting the migration. After the migration is completed,
>> > the destination hypervisor sets the MAC filter on the VF and plugs it back
>> > to the guest to switch over to VF datapath.
>> > 
>> > It uses the generic failover framework that provides 2 functions to create
>> > and destroy a master failover netdev. When STANDBY feature is enabled, an
>> > additional netdev(failover netdev) is created that acts as a master device
>> > and tracks the state of the 2 lower netdevs. The original virtio_net netdev
>> > is marked as 'standby' netdev and a passthru device with the same MAC is
>> > registered as 'primary' netdev.
>> > 
>> > This patch is based on the discussion initiated by Jesse on this thread.
>> > https://marc.info/?l=linux-virtualization&m=151189725224231&w=2
>> [...]
>> 
>

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Samudrala, Sridhar]

On 4/30/2018 12:12 AM, Jiri Pirko wrote:
> Mon, Apr 30, 2018 at 05:00:33AM CEST, sridhar.samudrala@intel.com wrote:
>> On 4/28/2018 1:24 AM, Jiri Pirko wrote:
>>> Fri, Apr 27, 2018 at 07:06:59PM CEST, sridhar.samudrala@intel.com wrote:
>>>> This patch enables virtio_net to switch over to a VF datapath when a VF
>>>> netdev is present with the same MAC address. It allows live migration
>>>> of a VM with a direct attached VF without the need to setup a bond/team
>>>> between a VF and virtio net device in the guest.
>>>>
>>>> The hypervisor needs to enable only one datapath at any time so that
>>>> packets don't get looped back to the VM over the other datapath. When a VF
>>> Why? Both datapaths could be enabled at a time. Why the loop on
>>> hypervisor side would be a problem. This in not an issue for
>>> bonding/team as well.
>> Somehow the hypervisor needs to make sure that the broadcasts/multicasts from the VM
>> sent over the VF datapath don't get looped back to the VM via the virtio-net datapth.
> Why? Please see below.
>
>
>> This can happen if both datapaths are enabled at the same time.
>>
>> I would think this is an issue even with bonding/team as well when virtio-net and
>> VF are backed by the same PF.
>>
>>
> I believe that the scenario is the same as on an ordinary nic/swich
> network:
>
> ...................
>
>    host
>   
>         bond0
>        /     \
>      eth0   eth1
>       |       |
> ...................
>       |       |
>       p1      p2
>
>    switch
>
> ...................
>
> It is perfectly valid to p1 and p2 be up and "bridged" together. Bond
> has to cope with loop-backed frames. "Failover driver" should too,
> it's the same scenario.

OK. So looks like we should be able to handle this by returning RX_HANDLER_EXACT
for frames received on standby device when primary is present.

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Jiri Pirko]

Mon, Apr 30, 2018 at 09:26:34PM CEST, sridhar.samudrala@intel.com wrote:
>On 4/30/2018 12:12 AM, Jiri Pirko wrote:
>> Mon, Apr 30, 2018 at 05:00:33AM CEST, sridhar.samudrala@intel.com wrote:
>> > On 4/28/2018 1:24 AM, Jiri Pirko wrote:
>> > > Fri, Apr 27, 2018 at 07:06:59PM CEST, sridhar.samudrala@intel.com wrote:
>> > > > This patch enables virtio_net to switch over to a VF datapath when a VF
>> > > > netdev is present with the same MAC address. It allows live migration
>> > > > of a VM with a direct attached VF without the need to setup a bond/team
>> > > > between a VF and virtio net device in the guest.
>> > > > 
>> > > > The hypervisor needs to enable only one datapath at any time so that
>> > > > packets don't get looped back to the VM over the other datapath. When a VF
>> > > Why? Both datapaths could be enabled at a time. Why the loop on
>> > > hypervisor side would be a problem. This in not an issue for
>> > > bonding/team as well.
>> > Somehow the hypervisor needs to make sure that the broadcasts/multicasts from the VM
>> > sent over the VF datapath don't get looped back to the VM via the virtio-net datapth.
>> Why? Please see below.
>> 
>> 
>> > This can happen if both datapaths are enabled at the same time.
>> > 
>> > I would think this is an issue even with bonding/team as well when virtio-net and
>> > VF are backed by the same PF.
>> > 
>> > 
>> I believe that the scenario is the same as on an ordinary nic/swich
>> network:
>> 
>> ...................
>> 
>>    host
>>         bond0
>>        /     \
>>      eth0   eth1
>>       |       |
>> ...................
>>       |       |
>>       p1      p2
>> 
>>    switch
>> 
>> ...................
>> 
>> It is perfectly valid to p1 and p2 be up and "bridged" together. Bond
>> has to cope with loop-backed frames. "Failover driver" should too,
>> it's the same scenario.
>
>OK. So looks like we should be able to handle this by returning RX_HANDLER_EXACT
>for frames received on standby device when primary is present.

Yep.

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Jiri Pirko]

Fri, Apr 27, 2018 at 07:06:59PM CEST, sridhar.samudrala@intel.com wrote:
>This patch enables virtio_net to switch over to a VF datapath when a VF
>netdev is present with the same MAC address. It allows live migration
>of a VM with a direct attached VF without the need to setup a bond/team
>between a VF and virtio net device in the guest.
>
>The hypervisor needs to enable only one datapath at any time so that
>packets don't get looped back to the VM over the other datapath. When a VF
>is plugged, the virtio datapath link state can be marked as down. The
>hypervisor needs to unplug the VF device from the guest on the source host
>and reset the MAC filter of the VF to initiate failover of datapath to
>virtio before starting the migration. After the migration is completed,
>the destination hypervisor sets the MAC filter on the VF and plugs it back
>to the guest to switch over to VF datapath.
>
>It uses the generic failover framework that provides 2 functions to create
>and destroy a master failover netdev. When STANDBY feature is enabled, an
>additional netdev(failover netdev) is created that acts as a master device
>and tracks the state of the 2 lower netdevs. The original virtio_net netdev
>is marked as 'standby' netdev and a passthru device with the same MAC is
>registered as 'primary' netdev.
>
>This patch is based on the discussion initiated by Jesse on this thread.
>https://marc.info/?l=linux-virtualization&m=151189725224231&w=2
>

When I enabled the standby feature (hardcoded), I have 2 netdevices now:
4: ens3: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
    link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
    inet6 fe80::5054:ff:feb2:a7f1/64 scope link 
       valid_lft forever preferred_lft forever
5: ens3n_sby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP group default qlen 1000
    link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
    inet6 fe80::5054:ff:feb2:a7f1/64 scope link 
       valid_lft forever preferred_lft forever

However, it seems to confuse my initscripts on Fedora:
[root@test1 ~]# ifup ens3
./network-functions: line 78: [: /etc/dhcp/dhclient-ens3: binary operator expected
./network-functions: line 80: [: /etc/dhclient-ens3: binary operator expected
./network-functions: line 69: [: /var/lib/dhclient/dhclient-ens3: binary operator expected

Determining IP information for ens3
ens3n_sby...Cannot find device "ens3n_sby.pid"
Cannot find device "ens3n_sby.lease"
 failed.

I tried to change the standby device mac:
ip link set ens3n_sby addr 52:54:00:b2:a7:f2
[root@test1 ~]# ifup ens3

Determining IP information for ens3... done.
[root@test1 ~]#

But now the network does not work. I think that the mac change on
standby device should be probably refused, no?

When I change the mac back, all works fine.


Now I try to change mac of the failover master:
[root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
RTNETLINK answers: Operation not supported

That I did expect to work. I would expect this would change the mac of
the master and both standby and primary slaves.


Now I tried to add a primary pci device. I don't have any fancy VF on my
test setup, but I expected the good old 8139cp to work:
[root@test1 ~]# ethtool -i ens9
driver: 8139cp
....
[root@test1 ~]# ip link set ens9 addr 52:54:00:b2:a7:f1

I see no message in dmesg, so I guess the failover module did not
enslave this netdev. The mac change is not monitored. I would expect
that it is and whenever a device changes mac to the failover one, it
should be enslaved and whenever it changes mac back to something else,
it should be released - the primary one ofcourse.



[...]

>+static int virtnet_get_phys_port_name(struct net_device *dev, char *buf,
>+				      size_t len)
>+{
>+	struct virtnet_info *vi = netdev_priv(dev);
>+	int ret;
>+
>+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY))
>+		return -EOPNOTSUPP;
>+
>+	ret = snprintf(buf, len, "_sby");

please avoid the "_".

[...]

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Siwei Liu]

On Sat, Apr 28, 2018 at 2:42 AM, Jiri Pirko <jiri@resnulli.us> wrote:
> Fri, Apr 27, 2018 at 07:06:59PM CEST, sridhar.samudrala@intel.com wrote:
>>This patch enables virtio_net to switch over to a VF datapath when a VF
>>netdev is present with the same MAC address. It allows live migration
>>of a VM with a direct attached VF without the need to setup a bond/team
>>between a VF and virtio net device in the guest.
>>
>>The hypervisor needs to enable only one datapath at any time so that
>>packets don't get looped back to the VM over the other datapath. When a VF
>>is plugged, the virtio datapath link state can be marked as down. The
>>hypervisor needs to unplug the VF device from the guest on the source host
>>and reset the MAC filter of the VF to initiate failover of datapath to
>>virtio before starting the migration. After the migration is completed,
>>the destination hypervisor sets the MAC filter on the VF and plugs it back
>>to the guest to switch over to VF datapath.
>>
>>It uses the generic failover framework that provides 2 functions to create
>>and destroy a master failover netdev. When STANDBY feature is enabled, an
>>additional netdev(failover netdev) is created that acts as a master device
>>and tracks the state of the 2 lower netdevs. The original virtio_net netdev
>>is marked as 'standby' netdev and a passthru device with the same MAC is
>>registered as 'primary' netdev.
>>
>>This patch is based on the discussion initiated by Jesse on this thread.
>>https://marc.info/?l=linux-virtualization&m=151189725224231&w=2
>>
>
> When I enabled the standby feature (hardcoded), I have 2 netdevices now:
> 4: ens3: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
>     link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
>     inet6 fe80::5054:ff:feb2:a7f1/64 scope link
>        valid_lft forever preferred_lft forever
> 5: ens3n_sby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP group default qlen 1000
>     link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
>     inet6 fe80::5054:ff:feb2:a7f1/64 scope link
>        valid_lft forever preferred_lft forever
>
> However, it seems to confuse my initscripts on Fedora:
> [root@test1 ~]# ifup ens3
> ./network-functions: line 78: [: /etc/dhcp/dhclient-ens3: binary operator expected
> ./network-functions: line 80: [: /etc/dhclient-ens3: binary operator expected
> ./network-functions: line 69: [: /var/lib/dhclient/dhclient-ens3: binary operator expected
>
You should teach Fedora and all cloud vendors to upgrade their
initscripts and other userspace tools, no?

> Determining IP information for ens3
> ens3n_sby...Cannot find device "ens3n_sby.pid"
> Cannot find device "ens3n_sby.lease"
>  failed.
>
> I tried to change the standby device mac:
> ip link set ens3n_sby addr 52:54:00:b2:a7:f2
> [root@test1 ~]# ifup ens3
>
> Determining IP information for ens3... done.
> [root@test1 ~]#
>
> But now the network does not work. I think that the mac change on
> standby device should be probably refused, no?
>
> When I change the mac back, all works fine.
>
>
> Now I try to change mac of the failover master:
> [root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
> RTNETLINK answers: Operation not supported
>
> That I did expect to work. I would expect this would change the mac of
> the master and both standby and primary slaves.
>
>
> Now I tried to add a primary pci device. I don't have any fancy VF on my
> test setup, but I expected the good old 8139cp to work:
> [root@test1 ~]# ethtool -i ens9
> driver: 8139cp
> ....
> [root@test1 ~]# ip link set ens9 addr 52:54:00:b2:a7:f1
>
> I see no message in dmesg, so I guess the failover module did not
> enslave this netdev. The mac change is not monitored. I would expect
> that it is and whenever a device changes mac to the failover one, it
> should be enslaved and whenever it changes mac back to something else,
> it should be released - the primary one ofcourse.
>
>
>
> [...]
>
>>+static int virtnet_get_phys_port_name(struct net_device *dev, char *buf,
>>+                                    size_t len)
>>+{
>>+      struct virtnet_info *vi = netdev_priv(dev);
>>+      int ret;
>>+
>>+      if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY))
>>+              return -EOPNOTSUPP;
>>+
>>+      ret = snprintf(buf, len, "_sby");
>
> please avoid the "_".
>
> [...]

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Jiri Pirko]

Sun, Apr 29, 2018 at 10:56:30AM CEST, loseweigh@gmail.com wrote:
>On Sat, Apr 28, 2018 at 2:42 AM, Jiri Pirko <jiri@resnulli.us> wrote:
>> Fri, Apr 27, 2018 at 07:06:59PM CEST, sridhar.samudrala@intel.com wrote:
>>>This patch enables virtio_net to switch over to a VF datapath when a VF
>>>netdev is present with the same MAC address. It allows live migration
>>>of a VM with a direct attached VF without the need to setup a bond/team
>>>between a VF and virtio net device in the guest.
>>>
>>>The hypervisor needs to enable only one datapath at any time so that
>>>packets don't get looped back to the VM over the other datapath. When a VF
>>>is plugged, the virtio datapath link state can be marked as down. The
>>>hypervisor needs to unplug the VF device from the guest on the source host
>>>and reset the MAC filter of the VF to initiate failover of datapath to
>>>virtio before starting the migration. After the migration is completed,
>>>the destination hypervisor sets the MAC filter on the VF and plugs it back
>>>to the guest to switch over to VF datapath.
>>>
>>>It uses the generic failover framework that provides 2 functions to create
>>>and destroy a master failover netdev. When STANDBY feature is enabled, an
>>>additional netdev(failover netdev) is created that acts as a master device
>>>and tracks the state of the 2 lower netdevs. The original virtio_net netdev
>>>is marked as 'standby' netdev and a passthru device with the same MAC is
>>>registered as 'primary' netdev.
>>>
>>>This patch is based on the discussion initiated by Jesse on this thread.
>>>https://marc.info/?l=linux-virtualization&m=151189725224231&w=2
>>>
>>
>> When I enabled the standby feature (hardcoded), I have 2 netdevices now:
>> 4: ens3: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
>>     link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
>>     inet6 fe80::5054:ff:feb2:a7f1/64 scope link
>>        valid_lft forever preferred_lft forever
>> 5: ens3n_sby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP group default qlen 1000
>>     link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
>>     inet6 fe80::5054:ff:feb2:a7f1/64 scope link
>>        valid_lft forever preferred_lft forever
>>
>> However, it seems to confuse my initscripts on Fedora:
>> [root@test1 ~]# ifup ens3
>> ./network-functions: line 78: [: /etc/dhcp/dhclient-ens3: binary operator expected
>> ./network-functions: line 80: [: /etc/dhclient-ens3: binary operator expected
>> ./network-functions: line 69: [: /var/lib/dhclient/dhclient-ens3: binary operator expected
>>
>You should teach Fedora and all cloud vendors to upgrade their
>initscripts and other userspace tools, no?

I just wanted to point out that the conversion from "nostandby" to
"standby" isn't always that smooth as claimed. The claim was "no change
for the current user" iirc.

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Samudrala, Sridhar]

[-- Attachment #1.1: Type: text/plain, Size: 4928 bytes --]

On 4/28/2018 2:42 AM, Jiri Pirko wrote:
> Fri, Apr 27, 2018 at 07:06:59PM CEST,sridhar.samudrala@intel.com  wrote:
>> This patch enables virtio_net to switch over to a VF datapath when a VF
>> netdev is present with the same MAC address. It allows live migration
>> of a VM with a direct attached VF without the need to setup a bond/team
>> between a VF and virtio net device in the guest.
>>
>> The hypervisor needs to enable only one datapath at any time so that
>> packets don't get looped back to the VM over the other datapath. When a VF
>> is plugged, the virtio datapath link state can be marked as down. The
>> hypervisor needs to unplug the VF device from the guest on the source host
>> and reset the MAC filter of the VF to initiate failover of datapath to
>> virtio before starting the migration. After the migration is completed,
>> the destination hypervisor sets the MAC filter on the VF and plugs it back
>> to the guest to switch over to VF datapath.
>>
>> It uses the generic failover framework that provides 2 functions to create
>> and destroy a master failover netdev. When STANDBY feature is enabled, an
>> additional netdev(failover netdev) is created that acts as a master device
>> and tracks the state of the 2 lower netdevs. The original virtio_net netdev
>> is marked as 'standby' netdev and a passthru device with the same MAC is
>> registered as 'primary' netdev.
>>
>> This patch is based on the discussion initiated by Jesse on this thread.
>> https://marc.info/?l=linux-virtualization&m=151189725224231&w=2
>>
> When I enabled the standby feature (hardcoded), I have 2 netdevices now:
> 4: ens3: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
>      link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
>      inet6 fe80::5054:ff:feb2:a7f1/64 scope link
>         valid_lft forever preferred_lft forever
> 5: ens3n_sby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP group default qlen 1000
>      link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
>      inet6 fe80::5054:ff:feb2:a7f1/64 scope link
>         valid_lft forever preferred_lft forever
>
> However, it seems to confuse my initscripts on Fedora:
> [root@test1 ~]# ifup ens3
> ./network-functions: line 78: [: /etc/dhcp/dhclient-ens3: binary operator expected
> ./network-functions: line 80: [: /etc/dhclient-ens3: binary operator expected
> ./network-functions: line 69: [: /var/lib/dhclient/dhclient-ens3: binary operator expected
>
> Determining IP information for ens3
> ens3n_sby...Cannot find device "ens3n_sby.pid"
> Cannot find device "ens3n_sby.lease"
>   failed.
>
> I tried to change the standby device mac:
> ip link set ens3n_sby addr 52:54:00:b2:a7:f2
> [root@test1 ~]# ifup ens3
>
> Determining IP information for ens3... done.
> [root@test1 ~]#
>
> But now the network does not work. I think that the mac change on
> standby device should be probably refused, no?

Yes. we should block changing standby device mac.

> When I change the mac back, all works fine.

This is strange. So you had to change the standby device mac twice to
get dhcp working.

I do see NetworkManager trying to get dhcp address on standby device, but
i don't see any issue with connectivity.  To be totally transparent, we
need to only expose one netdev.

>
> Now I try to change mac of the failover master:
> [root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
> RTNETLINK answers: Operation not supported
>
> That I did expect to work. I would expect this would change the mac of
> the master and both standby and primary slaves.

If a VF is untrusted, a VM will not able to change its MAC and moreover
in this mode we are assuming that the hypervisor has assigned the MAC and
guest is not expected to change the MAC.

For the initial implementation, i would propose not allowing the guest to
change the MAC of failover or standby dev.


>
> Now I tried to add a primary pci device. I don't have any fancy VF on my
> test setup, but I expected the good old 8139cp to work:
> [root@test1 ~]# ethtool -i ens9
> driver: 8139cp
> ....
> [root@test1 ~]# ip link set ens9 addr 52:54:00:b2:a7:f1
>
> I see no message in dmesg, so I guess the failover module did not
> enslave this netdev. The mac change is not monitored. I would expect
> that it is and whenever a device changes mac to the failover one, it
> should be enslaved and whenever it changes mac back to something else,
> it should be released - the primary one ofcourse.

Sure. that may be the best way to handle the guest changing the primary
netdev's mac.

>
>
>
> [...]
>
>> +static int virtnet_get_phys_port_name(struct net_device *dev, char *buf,
>> +				      size_t len)
>> +{
>> +	struct virtnet_info *vi = netdev_priv(dev);
>> +	int ret;
>> +
>> +	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY))
>> +		return -EOPNOTSUPP;
>> +
>> +	ret = snprintf(buf, len, "_sby");
> please avoid the "_".
>
> [...]


[-- Attachment #1.2: Type: text/html, Size: 6088 bytes --]

[-- Attachment #2: Type: text/plain, Size: 183 bytes --]

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Jiri Pirko]

Mon, Apr 30, 2018 at 06:16:58AM CEST, sridhar.samudrala@intel.com wrote:
>On 4/28/2018 2:42 AM, Jiri Pirko wrote:
>> Fri, Apr 27, 2018 at 07:06:59PM CEST,sridhar.samudrala@intel.com  wrote:
>> > This patch enables virtio_net to switch over to a VF datapath when a VF
>> > netdev is present with the same MAC address. It allows live migration
>> > of a VM with a direct attached VF without the need to setup a bond/team
>> > between a VF and virtio net device in the guest.
>> > 
>> > The hypervisor needs to enable only one datapath at any time so that
>> > packets don't get looped back to the VM over the other datapath. When a VF
>> > is plugged, the virtio datapath link state can be marked as down. The
>> > hypervisor needs to unplug the VF device from the guest on the source host
>> > and reset the MAC filter of the VF to initiate failover of datapath to
>> > virtio before starting the migration. After the migration is completed,
>> > the destination hypervisor sets the MAC filter on the VF and plugs it back
>> > to the guest to switch over to VF datapath.
>> > 
>> > It uses the generic failover framework that provides 2 functions to create
>> > and destroy a master failover netdev. When STANDBY feature is enabled, an
>> > additional netdev(failover netdev) is created that acts as a master device
>> > and tracks the state of the 2 lower netdevs. The original virtio_net netdev
>> > is marked as 'standby' netdev and a passthru device with the same MAC is
>> > registered as 'primary' netdev.
>> > 
>> > This patch is based on the discussion initiated by Jesse on this thread.
>> > https://marc.info/?l=linux-virtualization&m=151189725224231&w=2
>> > 
>> When I enabled the standby feature (hardcoded), I have 2 netdevices now:
>> 4: ens3: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
>>      link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
>>      inet6 fe80::5054:ff:feb2:a7f1/64 scope link
>>         valid_lft forever preferred_lft forever
>> 5: ens3n_sby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP group default qlen 1000
>>      link/ether 52:54:00:b2:a7:f1 brd ff:ff:ff:ff:ff:ff
>>      inet6 fe80::5054:ff:feb2:a7f1/64 scope link
>>         valid_lft forever preferred_lft forever
>> 
>> However, it seems to confuse my initscripts on Fedora:
>> [root@test1 ~]# ifup ens3
>> ./network-functions: line 78: [: /etc/dhcp/dhclient-ens3: binary operator expected
>> ./network-functions: line 80: [: /etc/dhclient-ens3: binary operator expected
>> ./network-functions: line 69: [: /var/lib/dhclient/dhclient-ens3: binary operator expected
>> 
>> Determining IP information for ens3
>> ens3n_sby...Cannot find device "ens3n_sby.pid"
>> Cannot find device "ens3n_sby.lease"
>>   failed.
>> 
>> I tried to change the standby device mac:
>> ip link set ens3n_sby addr 52:54:00:b2:a7:f2
>> [root@test1 ~]# ifup ens3
>> 
>> Determining IP information for ens3... done.
>> [root@test1 ~]#
>> 
>> But now the network does not work. I think that the mac change on
>> standby device should be probably refused, no?
>
>Yes. we should block changing standby device mac.
>
>> When I change the mac back, all works fine.
>
>This is strange. So you had to change the standby device mac twice to
>get dhcp working.

Yes. First to some other mac to not to confuse initscripts, second back
to the "failover mac" in order to make frames go through (I'm guessing
that virtio_net also has mac filter for incoming frames).


>
>I do see NetworkManager trying to get dhcp address on standby device, but

Not using NM. Just good old Fedora initscripts.


>i don't see any issue with connectivity.  To be totally transparent, we
>need to only expose one netdev.

Yep.


>
>> 
>> Now I try to change mac of the failover master:
>> [root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
>> RTNETLINK answers: Operation not supported
>> 
>> That I did expect to work. I would expect this would change the mac of
>> the master and both standby and primary slaves.
>
>If a VF is untrusted, a VM will not able to change its MAC and moreover

Note that at this point, I have no VF. So I'm not sure why you mention
that.


>in this mode we are assuming that the hypervisor has assigned the MAC and
>guest is not expected to change the MAC.

Wait, for ordinary old-fashioned virtio_net, as a VM user, I can change
mac and all works fine. How is this different? Change mac on "failover
instance" should work and should propagate the mac down to its slaves.


>
>For the initial implementation, i would propose not allowing the guest to
>change the MAC of failover or standby dev.

I see no reason for such restriction.


>
>
>> 
>> Now I tried to add a primary pci device. I don't have any fancy VF on my
>> test setup, but I expected the good old 8139cp to work:
>> [root@test1 ~]# ethtool -i ens9
>> driver: 8139cp
>> ....
>> [root@test1 ~]# ip link set ens9 addr 52:54:00:b2:a7:f1
>> 
>> I see no message in dmesg, so I guess the failover module did not
>> enslave this netdev. The mac change is not monitored. I would expect
>> that it is and whenever a device changes mac to the failover one, it
>> should be enslaved and whenever it changes mac back to something else,
>> it should be released - the primary one ofcourse.
>
>Sure. that may be the best way to handle the guest changing the primary
>netdev's mac.

Yep.


>
>> 
>> 
>> 
>> [...]
>> 
>> > +static int virtnet_get_phys_port_name(struct net_device *dev, char *buf,
>> > +				      size_t len)
>> > +{
>> > +	struct virtnet_info *vi = netdev_priv(dev);
>> > +	int ret;
>> > +
>> > +	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY))
>> > +		return -EOPNOTSUPP;
>> > +
>> > +	ret = snprintf(buf, len, "_sby");
>> please avoid the "_".
>> 
>> [...]
>

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Samudrala, Sridhar]

On 4/30/2018 12:20 AM, Jiri Pirko wrote:
>
>>> Now I try to change mac of the failover master:
>>> [root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
>>> RTNETLINK answers: Operation not supported
>>>
>>> That I did expect to work. I would expect this would change the mac of
>>> the master and both standby and primary slaves.
>> If a VF is untrusted, a VM will not able to change its MAC and moreover
> Note that at this point, I have no VF. So I'm not sure why you mention
> that.
>
>
>> in this mode we are assuming that the hypervisor has assigned the MAC and
>> guest is not expected to change the MAC.
> Wait, for ordinary old-fashioned virtio_net, as a VM user, I can change
> mac and all works fine. How is this different? Change mac on "failover
> instance" should work and should propagate the mac down to its slaves.
>
>
>> For the initial implementation, i would propose not allowing the guest to
>> change the MAC of failover or standby dev.
> I see no reason for such restriction.
>

It is true that a VM user can change mac address of a normal virtio-net interface,
however when it is in STANDBY mode i think we should not allow this change specifically
because we are creating a failover instance based on a MAC that is assigned by the
hypervisor.

Moreover,  in a cloud environment i would think that PF/hypervisor assigns a MAC to
the VF and it cannot be changed by the guest.

So for the initial implementation, do you see any issues with having this restriction
in STANDBY mode.


_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Jiri Pirko]

Wed, May 02, 2018 at 02:20:26AM CEST, sridhar.samudrala@intel.com wrote:
>On 4/30/2018 12:20 AM, Jiri Pirko wrote:
>> 
>> > > Now I try to change mac of the failover master:
>> > > [root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
>> > > RTNETLINK answers: Operation not supported
>> > > 
>> > > That I did expect to work. I would expect this would change the mac of
>> > > the master and both standby and primary slaves.
>> > If a VF is untrusted, a VM will not able to change its MAC and moreover
>> Note that at this point, I have no VF. So I'm not sure why you mention
>> that.
>> 
>> 
>> > in this mode we are assuming that the hypervisor has assigned the MAC and
>> > guest is not expected to change the MAC.
>> Wait, for ordinary old-fashioned virtio_net, as a VM user, I can change
>> mac and all works fine. How is this different? Change mac on "failover
>> instance" should work and should propagate the mac down to its slaves.
>> 
>> 
>> > For the initial implementation, i would propose not allowing the guest to
>> > change the MAC of failover or standby dev.
>> I see no reason for such restriction.
>> 
>
>It is true that a VM user can change mac address of a normal virtio-net interface,
>however when it is in STANDBY mode i think we should not allow this change specifically
>because we are creating a failover instance based on a MAC that is assigned by the
>hypervisor.
>
>Moreover,  in a cloud environment i would think that PF/hypervisor assigns a MAC to
>the VF and it cannot be changed by the guest.

So that is easy. You allow the change of the mac and in the "failover"
mac change implementation you propagate the change down to slaves. If
one slave does not support the change, you bail out. And since VF does
not allow it as you say, once it will be enslaved, the mac change could
not be done. Seems like a correct behavior to me and is in-sync with how
bond/team behaves.


>
>So for the initial implementation, do you see any issues with having this restriction
>in STANDBY mode.
>
>

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Samudrala, Sridhar]

On 5/2/2018 12:50 AM, Jiri Pirko wrote:
> Wed, May 02, 2018 at 02:20:26AM CEST, sridhar.samudrala@intel.com wrote:
>> On 4/30/2018 12:20 AM, Jiri Pirko wrote:
>>>>> Now I try to change mac of the failover master:
>>>>> [root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
>>>>> RTNETLINK answers: Operation not supported
>>>>>
>>>>> That I did expect to work. I would expect this would change the mac of
>>>>> the master and both standby and primary slaves.
>>>> If a VF is untrusted, a VM will not able to change its MAC and moreover
>>> Note that at this point, I have no VF. So I'm not sure why you mention
>>> that.
>>>
>>>
>>>> in this mode we are assuming that the hypervisor has assigned the MAC and
>>>> guest is not expected to change the MAC.
>>> Wait, for ordinary old-fashioned virtio_net, as a VM user, I can change
>>> mac and all works fine. How is this different? Change mac on "failover
>>> instance" should work and should propagate the mac down to its slaves.
>>>
>>>
>>>> For the initial implementation, i would propose not allowing the guest to
>>>> change the MAC of failover or standby dev.
>>> I see no reason for such restriction.
>>>
>> It is true that a VM user can change mac address of a normal virtio-net interface,
>> however when it is in STANDBY mode i think we should not allow this change specifically
>> because we are creating a failover instance based on a MAC that is assigned by the
>> hypervisor.
>>
>> Moreover,  in a cloud environment i would think that PF/hypervisor assigns a MAC to
>> the VF and it cannot be changed by the guest.
> So that is easy. You allow the change of the mac and in the "failover"
> mac change implementation you propagate the change down to slaves. If
> one slave does not support the change, you bail out. And since VF does
> not allow it as you say, once it will be enslaved, the mac change could
> not be done. Seems like a correct behavior to me and is in-sync with how
> bond/team behaves.

If we allow the mac to be changed when the VF is not yet plugged in
and the guest changes the mac, then VF cannot join the failover when
it is hot plugged with the original mac assigned by the hypervisor.
Specifically there could be timing window during the live migration where
VF would be unplugged at the source and if we allow the guest to change the
failover mac, then VF would not be able to register with the failover after
the VM is migrated to the destination.

>
>> So for the initial implementation, do you see any issues with having this restriction
>> in STANDBY mode.
>>
>>

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Michael S. Tsirkin]

On Wed, May 02, 2018 at 09:50:21AM +0200, Jiri Pirko wrote:
> Wed, May 02, 2018 at 02:20:26AM CEST, sridhar.samudrala@intel.com wrote:
> >On 4/30/2018 12:20 AM, Jiri Pirko wrote:
> >> 
> >> > > Now I try to change mac of the failover master:
> >> > > [root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
> >> > > RTNETLINK answers: Operation not supported
> >> > > 
> >> > > That I did expect to work. I would expect this would change the mac of
> >> > > the master and both standby and primary slaves.
> >> > If a VF is untrusted, a VM will not able to change its MAC and moreover
> >> Note that at this point, I have no VF. So I'm not sure why you mention
> >> that.
> >> 
> >> 
> >> > in this mode we are assuming that the hypervisor has assigned the MAC and
> >> > guest is not expected to change the MAC.
> >> Wait, for ordinary old-fashioned virtio_net, as a VM user, I can change
> >> mac and all works fine. How is this different? Change mac on "failover
> >> instance" should work and should propagate the mac down to its slaves.
> >> 
> >> 
> >> > For the initial implementation, i would propose not allowing the guest to
> >> > change the MAC of failover or standby dev.
> >> I see no reason for such restriction.
> >> 
> >
> >It is true that a VM user can change mac address of a normal virtio-net interface,
> >however when it is in STANDBY mode i think we should not allow this change specifically
> >because we are creating a failover instance based on a MAC that is assigned by the
> >hypervisor.
> >
> >Moreover,  in a cloud environment i would think that PF/hypervisor assigns a MAC to
> >the VF and it cannot be changed by the guest.
> 
> So that is easy. You allow the change of the mac and in the "failover"
> mac change implementation you propagate the change down to slaves. If
> one slave does not support the change, you bail out. And since VF does

I wish people would say primary/standby and not "VF" :)

> not allow it as you say, once it will be enslaved, the mac change could
> not be done. Seems like a correct behavior to me


what if primary does not allow mac changes and is attached after
mac is changed on standy?


> and is in-sync with how
> bond/team behaves.

I think in the end virtio can just block MAC changes for simplicity.

I personally don't see softmac as a must have feature in v1,
we can add it later.

What's the situation with init scripts and whether it's
possible to make them work well would be a better question.

> 
> >
> >So for the initial implementation, do you see any issues with having this restriction
> >in STANDBY mode.
> >
> >

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Jiri Pirko]

Wed, May 02, 2018 at 05:47:27PM CEST, mst@redhat.com wrote:
>On Wed, May 02, 2018 at 09:50:21AM +0200, Jiri Pirko wrote:
>> Wed, May 02, 2018 at 02:20:26AM CEST, sridhar.samudrala@intel.com wrote:
>> >On 4/30/2018 12:20 AM, Jiri Pirko wrote:
>> >> 
>> >> > > Now I try to change mac of the failover master:
>> >> > > [root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
>> >> > > RTNETLINK answers: Operation not supported
>> >> > > 
>> >> > > That I did expect to work. I would expect this would change the mac of
>> >> > > the master and both standby and primary slaves.
>> >> > If a VF is untrusted, a VM will not able to change its MAC and moreover
>> >> Note that at this point, I have no VF. So I'm not sure why you mention
>> >> that.
>> >> 
>> >> 
>> >> > in this mode we are assuming that the hypervisor has assigned the MAC and
>> >> > guest is not expected to change the MAC.
>> >> Wait, for ordinary old-fashioned virtio_net, as a VM user, I can change
>> >> mac and all works fine. How is this different? Change mac on "failover
>> >> instance" should work and should propagate the mac down to its slaves.
>> >> 
>> >> 
>> >> > For the initial implementation, i would propose not allowing the guest to
>> >> > change the MAC of failover or standby dev.
>> >> I see no reason for such restriction.
>> >> 
>> >
>> >It is true that a VM user can change mac address of a normal virtio-net interface,
>> >however when it is in STANDBY mode i think we should not allow this change specifically
>> >because we are creating a failover instance based on a MAC that is assigned by the
>> >hypervisor.
>> >
>> >Moreover,  in a cloud environment i would think that PF/hypervisor assigns a MAC to
>> >the VF and it cannot be changed by the guest.
>> 
>> So that is easy. You allow the change of the mac and in the "failover"
>> mac change implementation you propagate the change down to slaves. If
>> one slave does not support the change, you bail out. And since VF does
>
>I wish people would say primary/standby and not "VF" :)

Sure, sorry.


>
>> not allow it as you say, once it will be enslaved, the mac change could
>> not be done. Seems like a correct behavior to me
>
>
>what if primary does not allow mac changes and is attached after
>mac is changed on standy?

Mac should be changed on failover. In that case, the primary would have
a different mac and therefore it won't get enslaved.

>
>
>> and is in-sync with how
>> bond/team behaves.
>
>I think in the end virtio can just block MAC changes for simplicity.
>
>I personally don't see softmac as a must have feature in v1,
>we can add it later.

Okay.


>
>What's the situation with init scripts and whether it's
>possible to make them work well would be a better question.
>
>> 
>> >
>> >So for the initial implementation, do you see any issues with having this restriction
>> >in STANDBY mode.
>> >
>> >

Re: [PATCH net-next v9 3/4] virtio_net: Extend virtio to use VF datapath when available

[Jiri Pirko]

Wed, May 02, 2018 at 05:34:44PM CEST, sridhar.samudrala@intel.com wrote:
>On 5/2/2018 12:50 AM, Jiri Pirko wrote:
>> Wed, May 02, 2018 at 02:20:26AM CEST, sridhar.samudrala@intel.com wrote:
>> > On 4/30/2018 12:20 AM, Jiri Pirko wrote:
>> > > > > Now I try to change mac of the failover master:
>> > > > > [root@test1 ~]# ip link set ens3 addr 52:54:00:b2:a7:f3
>> > > > > RTNETLINK answers: Operation not supported
>> > > > > 
>> > > > > That I did expect to work. I would expect this would change the mac of
>> > > > > the master and both standby and primary slaves.
>> > > > If a VF is untrusted, a VM will not able to change its MAC and moreover
>> > > Note that at this point, I have no VF. So I'm not sure why you mention
>> > > that.
>> > > 
>> > > 
>> > > > in this mode we are assuming that the hypervisor has assigned the MAC and
>> > > > guest is not expected to change the MAC.
>> > > Wait, for ordinary old-fashioned virtio_net, as a VM user, I can change
>> > > mac and all works fine. How is this different? Change mac on "failover
>> > > instance" should work and should propagate the mac down to its slaves.
>> > > 
>> > > 
>> > > > For the initial implementation, i would propose not allowing the guest to
>> > > > change the MAC of failover or standby dev.
>> > > I see no reason for such restriction.
>> > > 
>> > It is true that a VM user can change mac address of a normal virtio-net interface,
>> > however when it is in STANDBY mode i think we should not allow this change specifically
>> > because we are creating a failover instance based on a MAC that is assigned by the
>> > hypervisor.
>> > 
>> > Moreover,  in a cloud environment i would think that PF/hypervisor assigns a MAC to
>> > the VF and it cannot be changed by the guest.
>> So that is easy. You allow the change of the mac and in the "failover"
>> mac change implementation you propagate the change down to slaves. If
>> one slave does not support the change, you bail out. And since VF does
>> not allow it as you say, once it will be enslaved, the mac change could
>> not be done. Seems like a correct behavior to me and is in-sync with how
>> bond/team behaves.
>
>If we allow the mac to be changed when the VF is not yet plugged in
>and the guest changes the mac, then VF cannot join the failover when
>it is hot plugged with the original mac assigned by the hypervisor.
>Specifically there could be timing window during the live migration where
>VF would be unplugged at the source and if we allow the guest to change the
>failover mac, then VF would not be able to register with the failover after
>the VM is migrated to the destination.

Okay. So as suggested by mst, just forbid the mac changes all together.


>
>> 
>> > So for the initial implementation, do you see any issues with having this restriction
>> > in STANDBY mode.
>> > 
>> > 
>

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Jiri Pirko]

Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:
>This provides a generic interface for paravirtual drivers to listen
>for netdev register/unregister/link change events from pci ethernet
>devices with the same MAC and takeover their datapath. The notifier and
>event handling code is based on the existing netvsc implementation.
>
>It exposes 2 sets of interfaces to the paravirtual drivers.
>1. For paravirtual drivers like virtio_net that use 3 netdev model, the
>   the failover module provides interfaces to create/destroy additional
>   master netdev and all the slave events are managed internally.
>        net_failover_create()
>        net_failover_destroy()
>   A failover netdev is created that acts a master device and controls 2
>   slave devices. The original virtio_net netdev is registered as 'standby'
>   netdev and a passthru/vf device with the same MAC gets registered as
>   'primary' netdev. Both 'standby' and 'primary' netdevs are associated
>   with the same 'pci' device.  The user accesses the network interface via
>   'failover' netdev. The 'failover' netdev chooses 'primary' netdev as
>   default for transmits when it is available with link up and running.
>2. For existing netvsc driver that uses 2 netdev model, no master netdev
>   is created. The paravirtual driver registers each instance of netvsc
>   as a 'failover' netdev  along with a set of ops to manage the slave
>   events. There is no 'standby' netdev in this model. A passthru/vf device
>   with the same MAC gets registered as 'primary' netdev.
>        net_failover_register()
>        net_failover_unregister()
>
>Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
>---
> include/linux/netdevice.h  |  16 +
> include/net/net_failover.h |  62 ++++
> net/Kconfig                |  10 +
> net/core/Makefile          |   1 +
> net/core/net_failover.c    | 892 +++++++++++++++++++++++++++++++++++++++++++++
> 5 files changed, 981 insertions(+)
> create mode 100644 include/net/net_failover.h
> create mode 100644 net/core/net_failover.c

checkpatch says:

_exportax/0002-net-Introduce-generic-failover-module.patch
----------------------------------------------------------
WARNING: added, moved or deleted file(s), does MAINTAINERS need updating?
#92: 
new file mode 100644

Please add an entry to the MAINTAINERS file.

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Jiri Pirko]

Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:
>This provides a generic interface for paravirtual drivers to listen
>for netdev register/unregister/link change events from pci ethernet
>devices with the same MAC and takeover their datapath. The notifier and
>event handling code is based on the existing netvsc implementation.
>
>It exposes 2 sets of interfaces to the paravirtual drivers.
>1. For paravirtual drivers like virtio_net that use 3 netdev model, the
>   the failover module provides interfaces to create/destroy additional
>   master netdev and all the slave events are managed internally.
>        net_failover_create()
>        net_failover_destroy()
>   A failover netdev is created that acts a master device and controls 2
>   slave devices. The original virtio_net netdev is registered as 'standby'
>   netdev and a passthru/vf device with the same MAC gets registered as
>   'primary' netdev. Both 'standby' and 'primary' netdevs are associated
>   with the same 'pci' device.  The user accesses the network interface via

'standby' and 'primary' netdevs are not associated with the same 'pci'
device.
"Primary" is the VF netdevice and "standby" is virtio_net. Each
associated with different pci device.


>   'failover' netdev. The 'failover' netdev chooses 'primary' netdev as
>   default for transmits when it is available with link up and running.
>2. For existing netvsc driver that uses 2 netdev model, no master netdev
>   is created. The paravirtual driver registers each instance of netvsc
>   as a 'failover' netdev  along with a set of ops to manage the slave
>   events. There is no 'standby' netdev in this model. A passthru/vf device
>   with the same MAC gets registered as 'primary' netdev.
>        net_failover_register()
>        net_failover_unregister()

[...]

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Jiri Pirko]

Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:
>This provides a generic interface for paravirtual drivers to listen
>for netdev register/unregister/link change events from pci ethernet
>devices with the same MAC and takeover their datapath. The notifier and
>event handling code is based on the existing netvsc implementation.
>
>It exposes 2 sets of interfaces to the paravirtual drivers.
>1. For paravirtual drivers like virtio_net that use 3 netdev model, the
>   the failover module provides interfaces to create/destroy additional
>   master netdev and all the slave events are managed internally.
>        net_failover_create()
>        net_failover_destroy()
>   A failover netdev is created that acts a master device and controls 2
>   slave devices. The original virtio_net netdev is registered as 'standby'
>   netdev and a passthru/vf device with the same MAC gets registered as
>   'primary' netdev. Both 'standby' and 'primary' netdevs are associated
>   with the same 'pci' device.  The user accesses the network interface via
>   'failover' netdev. The 'failover' netdev chooses 'primary' netdev as
>   default for transmits when it is available with link up and running.
>2. For existing netvsc driver that uses 2 netdev model, no master netdev
>   is created. The paravirtual driver registers each instance of netvsc
>   as a 'failover' netdev  along with a set of ops to manage the slave
>   events. There is no 'standby' netdev in this model. A passthru/vf device
>   with the same MAC gets registered as 'primary' netdev.
>        net_failover_register()
>        net_failover_unregister()
>

First of all, I like this v9 very much. Nice progress!
Couple of notes inlined.


>Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
>---
> include/linux/netdevice.h  |  16 +
> include/net/net_failover.h |  62 ++++
> net/Kconfig                |  10 +
> net/core/Makefile          |   1 +
> net/core/net_failover.c    | 892 +++++++++++++++++++++++++++++++++++++++++++++
> 5 files changed, 981 insertions(+)
> create mode 100644 include/net/net_failover.h
> create mode 100644 net/core/net_failover.c

[...]


>+static int net_failover_slave_register(struct net_device *slave_dev)
>+{
>+	struct net_failover_info *nfo_info;
>+	struct net_failover_ops *nfo_ops;
>+	struct net_device *failover_dev;
>+	bool slave_is_standby;
>+	u32 orig_mtu;
>+	int err;
>+
>+	ASSERT_RTNL();
>+
>+	failover_dev = net_failover_get_bymac(slave_dev->perm_addr, &nfo_ops);
>+	if (!failover_dev)
>+		goto done;
>+
>+	if (failover_dev->type != slave_dev->type)
>+		goto done;
>+
>+	if (nfo_ops && nfo_ops->slave_register)
>+		return nfo_ops->slave_register(slave_dev, failover_dev);
>+
>+	nfo_info = netdev_priv(failover_dev);
>+	slave_is_standby = (slave_dev->dev.parent == failover_dev->dev.parent);

No parentheses needed.


>+	if (slave_is_standby ? rtnl_dereference(nfo_info->standby_dev) :
>+			rtnl_dereference(nfo_info->primary_dev)) {
>+		netdev_err(failover_dev, "%s attempting to register as slave dev when %s already present\n",
>+			   slave_dev->name,
>+			   slave_is_standby ? "standby" : "primary");
>+		goto done;
>+	}
>+
>+	/* We want to allow only a direct attached VF device as a primary
>+	 * netdev. As there is no easy way to check for a VF device, restrict
>+	 * this to a pci device.
>+	 */
>+	if (!slave_is_standby && (!slave_dev->dev.parent ||
>+				  !dev_is_pci(slave_dev->dev.parent)))

Yeah, this is good for now.


>+		goto done;
>+
>+	if (failover_dev->features & NETIF_F_VLAN_CHALLENGED &&
>+	    vlan_uses_dev(failover_dev)) {
>+		netdev_err(failover_dev, "Device %s is VLAN challenged and failover device has VLAN set up\n",
>+			   failover_dev->name);
>+		goto done;
>+	}
>+
>+	/* Align MTU of slave with failover dev */
>+	orig_mtu = slave_dev->mtu;
>+	err = dev_set_mtu(slave_dev, failover_dev->mtu);
>+	if (err) {
>+		netdev_err(failover_dev, "unable to change mtu of %s to %u register failed\n",
>+			   slave_dev->name, failover_dev->mtu);
>+		goto done;
>+	}
>+
>+	dev_hold(slave_dev);
>+
>+	if (netif_running(failover_dev)) {
>+		err = dev_open(slave_dev);
>+		if (err && (err != -EBUSY)) {
>+			netdev_err(failover_dev, "Opening slave %s failed err:%d\n",
>+				   slave_dev->name, err);
>+			goto err_dev_open;
>+		}
>+	}
>+
>+	netif_addr_lock_bh(failover_dev);
>+	dev_uc_sync_multiple(slave_dev, failover_dev);
>+	dev_uc_sync_multiple(slave_dev, failover_dev);
>+	netif_addr_unlock_bh(failover_dev);
>+
>+	err = vlan_vids_add_by_dev(slave_dev, failover_dev);
>+	if (err) {
>+		netdev_err(failover_dev, "Failed to add vlan ids to device %s err:%d\n",
>+			   slave_dev->name, err);
>+		goto err_vlan_add;
>+	}
>+
>+	err = netdev_rx_handler_register(slave_dev, net_failover_handle_frame,
>+					 failover_dev);
>+	if (err) {
>+		netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n",
>+			   err);
>+		goto err_handler_register;
>+	}
>+
>+	err = netdev_upper_dev_link(slave_dev, failover_dev, NULL);

Please use netdev_master_upper_dev_link().



>+	if (err) {
>+		netdev_err(slave_dev, "can not set failover device %s (err = %d)\n",
>+			   failover_dev->name, err);
>+		goto err_upper_link;
>+	}
>+
>+	slave_dev->priv_flags |= IFF_FAILOVER_SLAVE;
>+
>+	if (slave_is_standby) {
>+		rcu_assign_pointer(nfo_info->standby_dev, slave_dev);
>+		dev_get_stats(nfo_info->standby_dev, &nfo_info->standby_stats);
>+	} else {
>+		rcu_assign_pointer(nfo_info->primary_dev, slave_dev);
>+		dev_get_stats(nfo_info->primary_dev, &nfo_info->primary_stats);
>+		failover_dev->min_mtu = slave_dev->min_mtu;
>+		failover_dev->max_mtu = slave_dev->max_mtu;
>+	}
>+
>+	net_failover_compute_features(failover_dev);
>+
>+	call_netdevice_notifiers(NETDEV_JOIN, slave_dev);
>+
>+	netdev_info(failover_dev, "failover %s slave:%s registered\n",
>+		    slave_is_standby ? "standby" : "primary", slave_dev->name);

I wonder if noise like this is needed in dmesg...


>+
>+	goto done;
>+
>+err_upper_link:
>+	netdev_rx_handler_unregister(slave_dev);
>+err_handler_register:
>+	vlan_vids_del_by_dev(slave_dev, failover_dev);
>+err_vlan_add:
>+	dev_uc_unsync(slave_dev, failover_dev);
>+	dev_mc_unsync(slave_dev, failover_dev);
>+	dev_close(slave_dev);
>+err_dev_open:
>+	dev_put(slave_dev);
>+	dev_set_mtu(slave_dev, orig_mtu);
>+done:
>+	return NOTIFY_DONE;
>+}
>+
>+int net_failover_slave_unregister(struct net_device *slave_dev)
>+{
>+	struct net_device *standby_dev, *primary_dev;
>+	struct net_failover_info *nfo_info;
>+	struct net_failover_ops *nfo_ops;
>+	struct net_device *failover_dev;
>+	bool slave_is_standby;
>+
>+	if (!netif_is_failover_slave(slave_dev))
>+		goto done;
>+
>+	ASSERT_RTNL();
>+
>+	failover_dev = net_failover_get_bymac(slave_dev->perm_addr, &nfo_ops);
>+	if (!failover_dev)
>+		goto done;
>+
>+	if (nfo_ops && nfo_ops->slave_unregister)
>+		return nfo_ops->slave_unregister(slave_dev, failover_dev);
>+
>+	nfo_info = netdev_priv(failover_dev);
>+	primary_dev = rtnl_dereference(nfo_info->primary_dev);
>+	standby_dev = rtnl_dereference(nfo_info->standby_dev);
>+
>+	if (slave_dev != primary_dev && slave_dev != standby_dev)
>+		goto done;
>+
>+	slave_is_standby = (slave_dev->dev.parent == failover_dev->dev.parent);
>+
>+	netdev_rx_handler_unregister(slave_dev);
>+	netdev_upper_dev_unlink(slave_dev, failover_dev);
>+	vlan_vids_del_by_dev(slave_dev, failover_dev);
>+	dev_uc_unsync(slave_dev, failover_dev);
>+	dev_mc_unsync(slave_dev, failover_dev);
>+	dev_close(slave_dev);
>+	slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
>+
>+	nfo_info = netdev_priv(failover_dev);
>+	net_failover_get_stats(failover_dev, &nfo_info->failover_stats);
>+
>+	if (slave_is_standby) {
>+		RCU_INIT_POINTER(nfo_info->standby_dev, NULL);
>+	} else {
>+		RCU_INIT_POINTER(nfo_info->primary_dev, NULL);
>+		if (standby_dev) {
>+			failover_dev->min_mtu = standby_dev->min_mtu;
>+			failover_dev->max_mtu = standby_dev->max_mtu;
>+		}
>+	}
>+
>+	dev_put(slave_dev);
>+
>+	net_failover_compute_features(failover_dev);
>+
>+	netdev_info(failover_dev, "failover %s slave:%s unregistered\n",
>+		    slave_is_standby ? "standby" : "primary", slave_dev->name);
>+
>+done:
>+	return NOTIFY_DONE;
>+}
>+EXPORT_SYMBOL_GPL(net_failover_slave_unregister);
>+
>+static int net_failover_slave_link_change(struct net_device *slave_dev)
>+{
>+	struct net_device *failover_dev, *primary_dev, *standby_dev;
>+	struct net_failover_info *nfo_info;
>+	struct net_failover_ops *nfo_ops;
>+
>+	if (!netif_is_failover_slave(slave_dev))
>+		goto done;
>+
>+	ASSERT_RTNL();
>+
>+	failover_dev = net_failover_get_bymac(slave_dev->perm_addr, &nfo_ops);
>+	if (!failover_dev)
>+		goto done;
>+
>+	if (nfo_ops && nfo_ops->slave_link_change)
>+		return nfo_ops->slave_link_change(slave_dev, failover_dev);
>+
>+	if (!netif_running(failover_dev))
>+		return 0;
>+
>+	nfo_info = netdev_priv(failover_dev);
>+
>+	primary_dev = rtnl_dereference(nfo_info->primary_dev);
>+	standby_dev = rtnl_dereference(nfo_info->standby_dev);
>+
>+	if (slave_dev != primary_dev && slave_dev != standby_dev)
>+		goto done;
>+
>+	if ((primary_dev && net_failover_xmit_ready(primary_dev)) ||
>+	    (standby_dev && net_failover_xmit_ready(standby_dev))) {
>+		netif_carrier_on(failover_dev);
>+		netif_tx_wake_all_queues(failover_dev);
>+	} else {
>+		net_failover_get_stats(failover_dev, &nfo_info->failover_stats);
>+		netif_carrier_off(failover_dev);
>+		netif_tx_stop_all_queues(failover_dev);
>+	}
>+
>+done:
>+	return NOTIFY_DONE;
>+}
>+
>+static int
>+net_failover_event(struct notifier_block *this, unsigned long event, void *ptr)
>+{
>+	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
>+
>+	/* Skip parent events */
>+	if (netif_is_failover(event_dev))
>+		return NOTIFY_DONE;
>+
>+	switch (event) {
>+	case NETDEV_REGISTER:
>+		return net_failover_slave_register(event_dev);
>+	case NETDEV_UNREGISTER:
>+		return net_failover_slave_unregister(event_dev);
>+	case NETDEV_UP:
>+	case NETDEV_DOWN:
>+	case NETDEV_CHANGE:
>+		return net_failover_slave_link_change(event_dev);
>+	default:
>+		return NOTIFY_DONE;
>+	}
>+}
>+
>+static struct notifier_block net_failover_notifier = {
>+	.notifier_call = net_failover_event,
>+};
>+
>+static void nfo_register_existing_slave(struct net_device *failover_dev)

Please maintain the same function prefixes withing the whole code.

Also, to be consistent with the rest of the code, have "_register" as a
suffix.


>+{
>+	struct net *net = dev_net(failover_dev);
>+	struct net_device *dev;
>+
>+	rtnl_lock();
>+	for_each_netdev(net, dev) {
>+		if (netif_is_failover(dev))
>+			continue;
>+		if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr))
>+			net_failover_slave_register(dev);
>+	}
>+	rtnl_unlock();
>+}
>+


For every exported function, please provide documentation in format:

/**
 *	net_failover_register - Register net failover device
 *
 *	@dev: netdevice the failover is registerd for
 *	@ops: failover ops
 *
 *	Describe what the function does, what are expected inputs and
 *	outputs, etc. Don't hesistate to be verbose. Mention the 2/3netdev
 *	model here. Then you don't need the comment in the header file
 *	for there functions.
 */

>+int net_failover_register(struct net_device *dev, struct net_failover_ops *ops,
>+			  struct net_failover **pfailover)

Just return "struct net_failover *" instead of arg ** and use ERR_PTR
macro to propagate an error.


>+{
>+	struct net_failover *failover;
>+
>+	failover = kzalloc(sizeof(*failover), GFP_KERNEL);
>+	if (!failover)
>+		return -ENOMEM;
>+
>+	rcu_assign_pointer(failover->ops, ops);
>+	dev_hold(dev);
>+	dev->priv_flags |= IFF_FAILOVER;
>+	rcu_assign_pointer(failover->failover_dev, dev);
>+
>+	spin_lock(&net_failover_lock);
>+	list_add_tail(&failover->list, &net_failover_list);
>+	spin_unlock(&net_failover_lock);
>+
>+	netdev_info(dev, "failover master:%s registered\n", dev->name);
>+
>+	nfo_register_existing_slave(dev);
>+
>+	*pfailover = failover;
>+
>+	return 0;
>+}
>+EXPORT_SYMBOL_GPL(net_failover_register);
>+
>+void net_failover_unregister(struct net_failover *failover)
>+{
>+	struct net_device *failover_dev;
>+
>+	failover_dev = rcu_dereference(failover->failover_dev);
>+
>+	netdev_info(failover_dev, "failover master:%s unregistered\n",
>+		    failover_dev->name);
>+
>+	failover_dev->priv_flags &= ~IFF_FAILOVER;
>+	dev_put(failover_dev);
>+
>+	spin_lock(&net_failover_lock);
>+	list_del(&failover->list);
>+	spin_unlock(&net_failover_lock);
>+
>+	kfree(failover);
>+}
>+EXPORT_SYMBOL_GPL(net_failover_unregister);
>+
>+int net_failover_create(struct net_device *standby_dev,
>+			struct net_failover **pfailover)

Same here, just return "struct net_failover *"


>+{
>+	struct device *dev = standby_dev->dev.parent;
>+	struct net_device *failover_dev;
>+	int err;
>+
>+	/* Alloc at least 2 queues, for now we are going with 16 assuming
>+	 * that VF devices being enslaved won't have too many queues.
>+	 */
>+	failover_dev = alloc_etherdev_mq(sizeof(struct net_failover_info), 16);
>+	if (!failover_dev) {
>+		dev_err(dev, "Unable to allocate failover_netdev!\n");
>+		return -ENOMEM;
>+	}
>+
>+	dev_net_set(failover_dev, dev_net(standby_dev));
>+	SET_NETDEV_DEV(failover_dev, dev);
>+
>+	failover_dev->netdev_ops = &failover_dev_ops;
>+	failover_dev->ethtool_ops = &failover_ethtool_ops;
>+
>+	/* Initialize the device options */
>+	failover_dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE;
>+	failover_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE |
>+				       IFF_TX_SKB_SHARING);
>+
>+	/* don't acquire failover netdev's netif_tx_lock when transmitting */
>+	failover_dev->features |= NETIF_F_LLTX;
>+
>+	/* Don't allow failover devices to change network namespaces. */
>+	failover_dev->features |= NETIF_F_NETNS_LOCAL;
>+
>+	failover_dev->hw_features = FAILOVER_VLAN_FEATURES |
>+				    NETIF_F_HW_VLAN_CTAG_TX |
>+				    NETIF_F_HW_VLAN_CTAG_RX |
>+				    NETIF_F_HW_VLAN_CTAG_FILTER;
>+
>+	failover_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
>+	failover_dev->features |= failover_dev->hw_features;
>+
>+	memcpy(failover_dev->dev_addr, standby_dev->dev_addr,
>+	       failover_dev->addr_len);
>+
>+	failover_dev->min_mtu = standby_dev->min_mtu;
>+	failover_dev->max_mtu = standby_dev->max_mtu;
>+
>+	err = register_netdev(failover_dev);
>+	if (err < 0) {

if (err)
is enough


>+		dev_err(dev, "Unable to register failover_dev!\n");
>+		goto err_register_netdev;
>+	}
>+
>+	netif_carrier_off(failover_dev);
>+
>+	err = net_failover_register(failover_dev, NULL, pfailover);
>+	if (err < 0)

if (err)
is enough


>+		goto err_failover_register;
>+
>+	return 0;
>+
>+err_failover_register:
>+	unregister_netdev(failover_dev);
>+err_register_netdev:
>+	free_netdev(failover_dev);
>+
>+	return err;
>+}
>+EXPORT_SYMBOL_GPL(net_failover_create);

[...]

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Samudrala, Sridhar]

On 4/28/2018 2:06 AM, Jiri Pirko wrote:
> Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:
>> This provides a generic interface for paravirtual drivers to listen
>> for netdev register/unregister/link change events from pci ethernet
>> devices with the same MAC and takeover their datapath. The notifier and
>> event handling code is based on the existing netvsc implementation.
>>
>> It exposes 2 sets of interfaces to the paravirtual drivers.
>> 1. For paravirtual drivers like virtio_net that use 3 netdev model, the
>>    the failover module provides interfaces to create/destroy additional
>>    master netdev and all the slave events are managed internally.
>>         net_failover_create()
>>         net_failover_destroy()
>>    A failover netdev is created that acts a master device and controls 2
>>    slave devices. The original virtio_net netdev is registered as 'standby'
>>    netdev and a passthru/vf device with the same MAC gets registered as
>>    'primary' netdev. Both 'standby' and 'primary' netdevs are associated
>>    with the same 'pci' device.  The user accesses the network interface via
>>    'failover' netdev. The 'failover' netdev chooses 'primary' netdev as
>>    default for transmits when it is available with link up and running.
>> 2. For existing netvsc driver that uses 2 netdev model, no master netdev
>>    is created. The paravirtual driver registers each instance of netvsc
>>    as a 'failover' netdev  along with a set of ops to manage the slave
>>    events. There is no 'standby' netdev in this model. A passthru/vf device
>>    with the same MAC gets registered as 'primary' netdev.
>>         net_failover_register()
>>         net_failover_unregister()
>>
> First of all, I like this v9 very much. Nice progress!
> Couple of notes inlined.

Thanks for the detailed reviews and all your suggestions for improvements
agree with all your comments. will address them in v10.

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Jiri Pirko]

Sat, Apr 28, 2018 at 11:06:01AM CEST, jiri@resnulli.us wrote:
>Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:

[...]


>>+
>>+	err = netdev_rx_handler_register(slave_dev, net_failover_handle_frame,
>>+					 failover_dev);
>>+	if (err) {
>>+		netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n",
>>+			   err);
>>+		goto err_handler_register;
>>+	}
>>+
>>+	err = netdev_upper_dev_link(slave_dev, failover_dev, NULL);
>
>Please use netdev_master_upper_dev_link().

Don't forget to fillup struct netdev_lag_upper_info - NETDEV_LAG_TX_TYPE_ACTIVEBACKUP


Also, please call netdev_lower_state_changed() when the active slave
device changes from primary->backup of backup->primary and whenever link
state of a slave changes

[...]

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Samudrala, Sridhar]

On 5/2/2018 9:15 AM, Jiri Pirko wrote:
> Sat, Apr 28, 2018 at 11:06:01AM CEST, jiri@resnulli.us wrote:
>> Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:
> [...]
>
>
>>> +
>>> +	err = netdev_rx_handler_register(slave_dev, net_failover_handle_frame,
>>> +					 failover_dev);
>>> +	if (err) {
>>> +		netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n",
>>> +			   err);
>>> +		goto err_handler_register;
>>> +	}
>>> +
>>> +	err = netdev_upper_dev_link(slave_dev, failover_dev, NULL);
>> Please use netdev_master_upper_dev_link().
> Don't forget to fillup struct netdev_lag_upper_info - NETDEV_LAG_TX_TYPE_ACTIVEBACKUP
>
>
> Also, please call netdev_lower_state_changed() when the active slave
> device changes from primary->backup of backup->primary and whenever link
> state of a slave changes
>
Sure. will look into it.  Do you think this will help with the issue
you saw with having to change mac on standy twice to get the init scripts
working? We are now going to block changing the mac on both standby and
failover.

Also, i was wondering if we should set dev->flags to IFF_MASTER on failover
and IFF_SLAVE on primary and standby. netvsc does this.
Does this help with the init scripts and network manager to skip slave
devices for dhcp requests?

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Michael S. Tsirkin]

On Wed, May 02, 2018 at 10:51:12AM -0700, Samudrala, Sridhar wrote:
> 
> 
> On 5/2/2018 9:15 AM, Jiri Pirko wrote:
> > Sat, Apr 28, 2018 at 11:06:01AM CEST, jiri@resnulli.us wrote:
> > > Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:
> > [...]
> > 
> > 
> > > > +
> > > > +	err = netdev_rx_handler_register(slave_dev, net_failover_handle_frame,
> > > > +					 failover_dev);
> > > > +	if (err) {
> > > > +		netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n",
> > > > +			   err);
> > > > +		goto err_handler_register;
> > > > +	}
> > > > +
> > > > +	err = netdev_upper_dev_link(slave_dev, failover_dev, NULL);
> > > Please use netdev_master_upper_dev_link().
> > Don't forget to fillup struct netdev_lag_upper_info - NETDEV_LAG_TX_TYPE_ACTIVEBACKUP
> > 
> > 
> > Also, please call netdev_lower_state_changed() when the active slave
> > device changes from primary->backup of backup->primary and whenever link
> > state of a slave changes
> > 
> Sure. will look into it.  Do you think this will help with the issue
> you saw with having to change mac on standy twice to get the init scripts
> working? We are now going to block changing the mac on both standby and
> failover.
> 
> Also, i was wondering if we should set dev->flags to IFF_MASTER on failover
> and IFF_SLAVE on primary and standby.

We do need a way to find things out, that's for sure.
How does userspace know it's a failover
config and find the failover device right now?

> netvsc does this.
> Does this help with the init scripts and network manager to skip slave
> devices for dhcp requests?

Try it?

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Samudrala, Sridhar]

On 5/2/2018 1:30 PM, Michael S. Tsirkin wrote:
> On Wed, May 02, 2018 at 10:51:12AM -0700, Samudrala, Sridhar wrote:
>>
>> On 5/2/2018 9:15 AM, Jiri Pirko wrote:
>>> Sat, Apr 28, 2018 at 11:06:01AM CEST, jiri@resnulli.us wrote:
>>>> Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:
>>> [...]
>>>
>>>
>>>>> +
>>>>> +	err = netdev_rx_handler_register(slave_dev, net_failover_handle_frame,
>>>>> +					 failover_dev);
>>>>> +	if (err) {
>>>>> +		netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n",
>>>>> +			   err);
>>>>> +		goto err_handler_register;
>>>>> +	}
>>>>> +
>>>>> +	err = netdev_upper_dev_link(slave_dev, failover_dev, NULL);
>>>> Please use netdev_master_upper_dev_link().
>>> Don't forget to fillup struct netdev_lag_upper_info - NETDEV_LAG_TX_TYPE_ACTIVEBACKUP
>>>
>>>
>>> Also, please call netdev_lower_state_changed() when the active slave
>>> device changes from primary->backup of backup->primary and whenever link
>>> state of a slave changes
>>>
>> Sure. will look into it.  Do you think this will help with the issue
>> you saw with having to change mac on standy twice to get the init scripts
>> working? We are now going to block changing the mac on both standby and
>> failover.
>>
>> Also, i was wondering if we should set dev->flags to IFF_MASTER on failover
>> and IFF_SLAVE on primary and standby.
> We do need a way to find things out, that's for sure.
> How does userspace know it's a failover
> config and find the failover device right now?

# ethtool -i ens12|grep driver
driver: failover

# ethtool -i ens12n_sby|grep driver
driver: virtio_net


_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Jiri Pirko]

Wed, May 02, 2018 at 07:51:12PM CEST, sridhar.samudrala@intel.com wrote:
>
>
>On 5/2/2018 9:15 AM, Jiri Pirko wrote:
>> Sat, Apr 28, 2018 at 11:06:01AM CEST, jiri@resnulli.us wrote:
>> > Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:
>> [...]
>> 
>> 
>> > > +
>> > > +	err = netdev_rx_handler_register(slave_dev, net_failover_handle_frame,
>> > > +					 failover_dev);
>> > > +	if (err) {
>> > > +		netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n",
>> > > +			   err);
>> > > +		goto err_handler_register;
>> > > +	}
>> > > +
>> > > +	err = netdev_upper_dev_link(slave_dev, failover_dev, NULL);
>> > Please use netdev_master_upper_dev_link().
>> Don't forget to fillup struct netdev_lag_upper_info - NETDEV_LAG_TX_TYPE_ACTIVEBACKUP
>> 
>> 
>> Also, please call netdev_lower_state_changed() when the active slave
>> device changes from primary->backup of backup->primary and whenever link
>> state of a slave changes
>> 
>Sure. will look into it.  Do you think this will help with the issue
>you saw with having to change mac on standy twice to get the init scripts
>working? We are now going to block changing the mac on both standby and
>failover.
>
>Also, i was wondering if we should set dev->flags to IFF_MASTER on failover
>and IFF_SLAVE on primary and standby. netvsc does this.

No. Don't set it. It is wrong.



>Does this help with the init scripts and network manager to skip slave
>devices for dhcp requests?
>

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Jiri Pirko]

Wed, May 02, 2018 at 07:51:12PM CEST, sridhar.samudrala@intel.com wrote:
>
>
>On 5/2/2018 9:15 AM, Jiri Pirko wrote:
>> Sat, Apr 28, 2018 at 11:06:01AM CEST, jiri@resnulli.us wrote:
>> > Fri, Apr 27, 2018 at 07:06:58PM CEST, sridhar.samudrala@intel.com wrote:
>> [...]
>> 
>> 
>> > > +
>> > > +	err = netdev_rx_handler_register(slave_dev, net_failover_handle_frame,
>> > > +					 failover_dev);
>> > > +	if (err) {
>> > > +		netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n",
>> > > +			   err);
>> > > +		goto err_handler_register;
>> > > +	}
>> > > +
>> > > +	err = netdev_upper_dev_link(slave_dev, failover_dev, NULL);
>> > Please use netdev_master_upper_dev_link().
>> Don't forget to fillup struct netdev_lag_upper_info - NETDEV_LAG_TX_TYPE_ACTIVEBACKUP
>> 
>> 
>> Also, please call netdev_lower_state_changed() when the active slave
>> device changes from primary->backup of backup->primary and whenever link
>> state of a slave changes
>> 
>Sure. will look into it.  Do you think this will help with the issue
>you saw with having to change mac on standy twice to get the init scripts
>working? We are now going to block changing the mac on both standby and
>failover.

I don't see any relation to that.

Re: [PATCH net-next v9 2/4] net: Introduce generic failover module

[Samudrala, Sridhar]

[-- Attachment #1.1: Type: text/plain, Size: 2046 bytes --]

On 4/28/2018 1:15 AM, Jiri Pirko wrote:
> Fri, Apr 27, 2018 at 07:06:58PM CEST,sridhar.samudrala@intel.com  wrote:
>> This provides a generic interface for paravirtual drivers to listen
>> for netdev register/unregister/link change events from pci ethernet
>> devices with the same MAC and takeover their datapath. The notifier and
>> event handling code is based on the existing netvsc implementation.
>>
>> It exposes 2 sets of interfaces to the paravirtual drivers.
>> 1. For paravirtual drivers like virtio_net that use 3 netdev model, the
>>    the failover module provides interfaces to create/destroy additional
>>    master netdev and all the slave events are managed internally.
>>         net_failover_create()
>>         net_failover_destroy()
>>    A failover netdev is created that acts a master device and controls 2
>>    slave devices. The original virtio_net netdev is registered as 'standby'
>>    netdev and a passthru/vf device with the same MAC gets registered as
>>    'primary' netdev. Both 'standby' and 'primary' netdevs are associated
>>    with the same 'pci' device.  The user accesses the network interface via
> 'standby' and 'primary' netdevs are not associated with the same 'pci'
> device.
> "Primary" is the VF netdevice and "standby" is virtio_net. Each
> associated with different pci device.

I meant to say that 'standby' and 'failover' netdevs are associated with
the same 'pci' device. will fix it in v10.


>
>>    'failover' netdev. The 'failover' netdev chooses 'primary' netdev as
>>    default for transmits when it is available with link up and running.
>> 2. For existing netvsc driver that uses 2 netdev model, no master netdev
>>    is created. The paravirtual driver registers each instance of netvsc
>>    as a 'failover' netdev  along with a set of ops to manage the slave
>>    events. There is no 'standby' netdev in this model. A passthru/vf device
>>    with the same MAC gets registered as 'primary' netdev.
>>         net_failover_register()
>>         net_failover_unregister()
> [...]


[-- Attachment #1.2: Type: text/html, Size: 2696 bytes --]

[-- Attachment #2: Type: text/plain, Size: 183 bytes --]

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization