net: Introduce generic failover module

The failover module provides a generic interface for paravirtual drivers to register a netdev and a set of ops with a failover instance. The ops are used as event handlers that get called to handle netdev register/ unregister/link change/name change events on slave pci ethernet devices with the same mac address as the failover netdev. This enables paravirtual drivers to use a VF as an accelerated low latency datapath. It also allows migration of VMs with direct attached VFs by failing over to the paravirtual datapath when the VF is unplugged. Signed-off-by: Sridhar Samudrala <[email protected]> Signed-off-by: David S. Miller <[email protected]>
zandrey · May 29, 2018 · 30c8bd5 · 30c8bd5
1 parent cb16039
commit 30c8bd5
Show file tree

Hide file tree

Showing 7 changed files with 407 additions and 0 deletions.
diff --git a/Documentation/networking/failover.rst b/Documentation/networking/failover.rst
@@ -0,0 +1,18 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========
+FAILOVER
+========
+
+Overview
+========
+
+The failover module provides a generic interface for paravirtual drivers
+to register a netdev and a set of ops with a failover instance. The ops
+are used as event handlers that get called to handle netdev register/
+unregister/link change/name change events on slave pci ethernet devices
+with the same mac address as the failover netdev.
+
+This enables paravirtual drivers to use a VF as an accelerated low latency
+datapath. It also allows live migration of VMs with direct attached VFs by
+failing over to the paravirtual datapath when the VF is unplugged.
diff --git a/MAINTAINERS b/MAINTAINERS
@@ -5411,6 +5411,14 @@ S:	Maintained
 F:	Documentation/hwmon/f71805f
 F:	drivers/hwmon/f71805f.c
 
+FAILOVER MODULE
+M:	Sridhar Samudrala <[email protected]>
+L:	[email protected]
+S:	Supported
+F:	net/core/failover.c
+F:	include/net/failover.h
+F:	Documentation/networking/failover.rst
+
 FANOTIFY
 M:	Jan Kara <[email protected]>
 R:	Amir Goldstein <[email protected]>

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
@@ -1425,6 +1425,8 @@ 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,
@@ -1454,6 +1456,8 @@ 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
@@ -1482,6 +1486,8 @@ 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.
@@ -4336,6 +4342,16 @@ 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/failover.h b/include/net/failover.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Intel Corporation. */
+
+#ifndef _FAILOVER_H
+#define _FAILOVER_H
+
+#include <linux/netdevice.h>
+
+struct failover_ops {
+	int (*slave_pre_register)(struct net_device *slave_dev,
+				  struct net_device *failover_dev);
+	int (*slave_register)(struct net_device *slave_dev,
+			      struct net_device *failover_dev);
+	int (*slave_pre_unregister)(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);
+	int (*slave_name_change)(struct net_device *slave_dev,
+				 struct net_device *failover_dev);
+	rx_handler_result_t (*slave_handle_frame)(struct sk_buff **pskb);
+};
+
+struct failover {
+	struct list_head list;
+	struct net_device __rcu *failover_dev;
+	struct failover_ops __rcu *ops;
+};
+
+struct failover *failover_register(struct net_device *dev,
+				   struct failover_ops *ops);
+void failover_unregister(struct failover *failover);
+int failover_slave_unregister(struct net_device *slave_dev);
+
+#endif /* _FAILOVER_H */
diff --git a/net/Kconfig b/net/Kconfig
@@ -432,6 +432,19 @@ config MAY_USE_DEVLINK
 config PAGE_POOL
        bool
 
+config FAILOVER
+	tristate "Generic failover module"
+	help
+	  The failover module provides a generic interface for paravirtual
+	  drivers to register a netdev and a set of ops with a failover
+	  instance. The ops are used as event handlers that get called to
+	  handle netdev register/unregister/link change/name change events
+	  on slave pci ethernet devices with the same mac address as the
+	  failover netdev. This enables paravirtual drivers to use a
+	  VF as an accelerated low latency datapath. It also allows live
+	  migration of VMs with direct attached VFs 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
@@ -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_FAILOVER) += failover.o