The goal of this is to provide a possibility to suport various switch
chips. Drivers should implement relevant ndos to do so. Now there is a
couple of ndos defines:
- for getting physical switch id is in place.
- for work with flows.
Note that user can use random port netdevice to access the switch.
Signed-off-by: Jiri Pirko <j...@resnulli.us>
---
Documentation/networking/switchdev.txt | 53 +++++++++++
include/linux/netdevice.h | 28 ++++++
include/linux/switchdev.h | 44 +++++++++
net/Kconfig | 6 ++
net/core/Makefile | 1 +
net/core/switchdev.c | 163 +++++++++++++++++++++++++++++++++
6 files changed, 295 insertions(+)
create mode 100644 Documentation/networking/switchdev.txt
create mode 100644 include/linux/switchdev.h
create mode 100644 net/core/switchdev.c
diff --git a/Documentation/networking/switchdev.txt
b/Documentation/networking/switchdev.txt
new file mode 100644
index 0000000..435746a
--- /dev/null
+++ b/Documentation/networking/switchdev.txt
@@ -0,0 +1,53 @@
+Switch device drivers HOWTO
+===========================
+
+First lets describe a topology a bit. Imagine the following example:
+
+ +----------------------------+ +---------------+
+ | SOME switch chip | | CPU |
+ +----------------------------+ +---------------+
+ port1 port2 port3 port4 MNGMNT | PCI-E |
+ | | | | | +---------------+
+ PHY PHY | | | | NIC0 NIC1
+ | | | | | |
+ | | +- PCI-E -+ | |
+ | +------- MII -------+ |
+ +------------- MII ------------+
+
+In this example, there are two independent lines between the switch silicon
+and CPU. NIC0 and NIC1 drivers are not aware of a switch presence. They are
+separate from the switch driver. SOME switch chip is by managed by a driver
+via PCI-E device MNGMNT. Note that MNGMNT device, NIC0 and NIC1 may be
+connected to some other type of bus.
+
+Now, for the previous example show the representation in kernel:
+
+ +----------------------------+ +---------------+
+ | SOME switch chip | | CPU |
+ +----------------------------+ +---------------+
+ sw0p0 sw0p1 sw0p2 sw0p3 MNGMNT | PCI-E |
+ | | | | | +---------------+
+ PHY PHY | | | | eth0 eth1
+ | | | | | |
+ | | +- PCI-E -+ | |
+ | +------- MII -------+ |
+ +------------- MII ------------+
+
+Lets call the example switch driver for SOME switch chip "SOMEswitch". This
+driver takes care of PCI-E device MNGMNT. There is a netdevice instance sw0pX
+created for each port of a switch. These netdevices are instances
+of "SOMEswitch" driver. sw0pX netdevices serve as a "representation"
+of the switch chip. eth0 and eth1 are instances of some other existing driver.
+
+The only difference of the switch-port netdevice from the ordinary netdevice
+is that is implements couple more NDOs:
+
+ ndo_swdev_get_id - This returns the same ID for two port netdevices of
+ the same physical switch chip. This is mandatory to
+ be implemented by all switch drivers and serves
+ the caller for recognition of a port netdevice.
+ ndo_swdev_* - Functions that serve for a manipulation of the switch chip
+ itself. They are not port-specific. Caller might use
+ arbitrary port netdevice of the same switch and it will
+ make no difference.
+ ndo_swportdev_* - Functions that serve for a port-specific manipulation.
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 39294b9..8b5d14c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -49,6 +49,8 @@
#include <linux/netdev_features.h>
#include <linux/neighbour.h>
+#include <linux/sw_flow.h>
+
#include <uapi/linux/netdevice.h>
struct netpoll_info;
@@ -997,6 +999,24 @@ typedef u16 (*select_queue_fallback_t)(struct net_device
*dev,
* Callback to use for xmit over the accelerated station. This
* is used in place of ndo_start_xmit on accelerated net
* devices.
+ *
+ * int (*ndo_swdev_get_id)(struct net_device *dev,
+ * struct netdev_phys_item_id *psid);
+ * Called to get an ID of the switch chip this port is part of.
+ * If driver implements this, it indicates that it represents a port
+ * of a switch chip.
+ *
+ * int (*ndo_swdev_flow_insert)(struct net_device *dev,
+ * const struct sw_flow *flow);
+ * Called to insert a flow into switch device. If driver does
+ * not implement this, it is assumed that the hw does not have
+ * a capability to work with flows.
+ *
+ * int (*ndo_swdev_flow_remove)(struct net_device *dev,
+ * const struct sw_flow *flow);
+ * Called to remove a flow from switch device. If driver does
+ * not implement this, it is assumed that the hw does not have
+ * a capability to work with flows.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1146,6 +1166,14 @@ struct net_device_ops {
struct net_device *dev,
void *priv);
int (*ndo_get_lock_subclass)(struct net_device
*dev);
+#ifdef CONFIG_NET_SWITCHDEV
+ int (*ndo_swdev_get_id)(struct net_device *dev,
+ struct netdev_phys_item_id
*psid);
+ int (*ndo_swdev_flow_insert)(struct net_device *dev,
+ const struct sw_flow
*flow);
+ int (*ndo_swdev_flow_remove)(struct net_device *dev,
+ const struct sw_flow
*flow);
+#endif
};
/**
diff --git a/include/linux/switchdev.h b/include/linux/switchdev.h
new file mode 100644
index 0000000..ba77a68
--- /dev/null
+++ b/include/linux/switchdev.h
@@ -0,0 +1,44 @@
+/*
+ * include/linux/switchdev.h - Switch device API
+ * Copyright (c) 2014 Jiri Pirko <j...@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef _LINUX_SWITCHDEV_H_
+#define _LINUX_SWITCHDEV_H_
+
+#include <linux/netdevice.h>
+#include <linux/sw_flow.h>
+
+#ifdef CONFIG_NET_SWITCHDEV
+
+int swdev_get_id(struct net_device *dev, struct netdev_phys_item_id *psid);
+int swdev_flow_insert(struct net_device *dev, const struct sw_flow *flow);
+int swdev_flow_remove(struct net_device *dev, const struct sw_flow *flow);
+
+#else
+
+static inline int swdev_get_id(struct net_device *dev,
+ struct netdev_phys_item_id *psid)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int swdev_flow_insert(struct net_device *dev,
+ const struct sw_flow *flow)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int swdev_flow_remove(struct net_device *dev,
+ const struct sw_flow *flow)
+{
+ return -EOPNOTSUPP;
+}
+
+#endif
+
+#endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/Kconfig b/net/Kconfig
index 4051fdf..40f729f 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -290,6 +290,12 @@ config NET_FLOW_LIMIT
with many clients some protection against DoS by a single (spoofed)
flow that greatly exceeds average workload.
+config NET_SWITCHDEV
+ boolean "Switch device support"
+ depends on INET
+ ---help---
+ This module provides support for hardware switch chips.
+
menu "Network testing"
config NET_PKTGEN
diff --git a/net/core/Makefile b/net/core/Makefile
index 71093d9..8583c38 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -24,3 +24,4 @@ obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o
obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
+obj-$(CONFIG_NET_SWITCHDEV) += switchdev.o
diff --git a/net/core/switchdev.c b/net/core/switchdev.c
new file mode 100644
index 0000000..4fad097
--- /dev/null
+++ b/net/core/switchdev.c
@@ -0,0 +1,163 @@
+/*
+ * net/core/switchdev.c - Switch device API
+ * Copyright (c) 2014 Jiri Pirko <j...@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/switchdev.h>
+
+/**
+ * swdev_get_id - Get ID of a switch
+ * @dev: port device
+ * @psid: switch ID
+ *
+ * Get ID of a switch this port is part of.
+ */
+int swdev_get_id(struct net_device *dev, struct netdev_phys_item_id *psid)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (!ops->ndo_swdev_get_id)
+ return -EOPNOTSUPP;
+ return ops->ndo_swdev_get_id(dev, psid);
+}
+EXPORT_SYMBOL(swdev_get_id);
+
+static void print_flow_key_tun(const char *prefix,
+ const struct sw_flow_key *key)
+{
+ pr_debug("%s tun { id %08llx, s %pI4, d %pI4, f %02x, tos %x, ttl %x
}\n",
+ prefix,
+ be64_to_cpu(key->tun_key.tun_id), &key->tun_key.ipv4_src,
+ &key->tun_key.ipv4_dst, ntohs(key->tun_key.tun_flags),
+ key->tun_key.ipv4_tos, key->tun_key.ipv4_ttl);
+}
+
+static void print_flow_key_phy(const char *prefix,
+ const struct sw_flow_key *key)
+{
+ pr_debug("%s phy { prio %04x, mark %04x, in_port %02x }\n",
+ prefix,
+ key->phy.priority, key->phy.skb_mark, key->phy.in_port);
+}
+
+static void print_flow_key_eth(const char *prefix,
+ const struct sw_flow_key *key)
+{
+ pr_debug("%s eth { sm %pM, dm %pM, tci %04x, type %04x }\n",
+ prefix,
+ key->eth.src, key->eth.dst, ntohs(key->eth.tci),
+ ntohs(key->eth.type));
+}
+
+static void print_flow_key_ip(const char *prefix,
+ const struct sw_flow_key *key)
+{
+ pr_debug("%s ip { proto %02x, tos %02x, ttl %02x }\n",
+ prefix,
+ key->ip.proto, key->ip.tos, key->ip.ttl);
+}
+
+static void print_flow_key_ipv4(const char *prefix,
+ const struct sw_flow_key *key)
+{
+ pr_debug("%s ipv4 { si %pI4, di %pI4, sm %pM, dm %pM }\n",
+ prefix,
+ &key->ipv4.addr.src, &key->ipv4.addr.dst,
+ key->ipv4.arp.sha, key->ipv4.arp.tha);
+}
+
+static void print_flow_actions(struct sw_flow_actions *actions)
+{
+ int i;
+
+ pr_debug(" actions:\n");
+ if (!actions)
+ return;
+ for (i = 0; i < actions->count; i++) {
+ struct sw_flow_action *action = &actions->actions[i];
+
+ switch (action->type) {
+ case SW_FLOW_ACTION_TYPE_OUTPUT:
+ pr_debug(" output { dev %s }\n",
+ action->output_dev->name);
+ break;
+ case SW_FLOW_ACTION_TYPE_VLAN_PUSH:
+ pr_debug(" vlan push { proto %04x, tci %04x }\n",
+ ntohs(action->vlan.vlan_proto),
+ ntohs(action->vlan.vlan_tci));
+ break;
+ case SW_FLOW_ACTION_TYPE_VLAN_POP:
+ pr_debug(" vlan pop\n");
+ break;
+ }
+ }
+}
+
+#define PREFIX_NONE " "
+#define PREFIX_MASK " mask"
+
+static void print_flow(const struct sw_flow *flow, struct net_device *dev,
+ const char *comment)
+{
+ pr_debug("%s flow %s (%x-%x):\n", dev->name, comment,
+ flow->mask->range.start, flow->mask->range.end);
+ print_flow_key_tun(PREFIX_NONE, &flow->key);
+ print_flow_key_tun(PREFIX_MASK, &flow->mask->key);
+ print_flow_key_phy(PREFIX_NONE, &flow->key);
+ print_flow_key_phy(PREFIX_MASK, &flow->mask->key);
+ print_flow_key_eth(PREFIX_NONE, &flow->key);
+ print_flow_key_eth(PREFIX_MASK, &flow->mask->key);
+ print_flow_key_ip(PREFIX_NONE, &flow->key);
+ print_flow_key_ip(PREFIX_MASK, &flow->mask->key);
+ print_flow_key_ipv4(PREFIX_NONE, &flow->key);
+ print_flow_key_ipv4(PREFIX_MASK, &flow->mask->key);
+ print_flow_actions(flow->actions);
+}
+
+/**
+ * swdev_flow_insert - Insert a flow into switch
+ * @dev: port device
+ * @flow: flow descriptor
+ *
+ * Insert a flow into switch this port is part of.
+ */
+int swdev_flow_insert(struct net_device *dev, const struct sw_flow *flow)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ print_flow(flow, dev, "insert");
+ if (!ops->ndo_swdev_flow_insert)
+ return -EOPNOTSUPP;
+ WARN_ON(!ops->ndo_swdev_get_id);
+ BUG_ON(!flow->actions);
+ return ops->ndo_swdev_flow_insert(dev, flow);
+}
+EXPORT_SYMBOL(swdev_flow_insert);
+
+/**
+ * swdev_flow_remove - Remove a flow from switch
+ * @dev: port device
+ * @flow: flow descriptor
+ *
+ * Remove a flow from switch this port is part of.
+ */
+int swdev_flow_remove(struct net_device *dev, const struct sw_flow *flow)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ print_flow(flow, dev, "remove");
+ if (!ops->ndo_swdev_flow_remove)
+ return -EOPNOTSUPP;
+ WARN_ON(!ops->ndo_swdev_get_id);
+ return ops->ndo_swdev_flow_remove(dev, flow);
+}
+EXPORT_SYMBOL(swdev_flow_remove);
--
1.9.3
_______________________________________________
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
