new file mode 100644
@@ -0,0 +1,188 @@
+/*
+ * include/linux/net/if_flow.h - Flow table interface for Switch devices
+ * Copyright (c) 2014 John Fastabend <john.r.fastabend@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Author: John Fastabend <john.r.fastabend@intel.com>
+ */
+
+#ifndef _IF_FLOW_H
+#define _IF_FLOW_H
+
+#include <uapi/linux/if_flow.h>
+
+/**
+ * @struct net_flow_fields
+ * @brief defines a field in a header
+ *
+ * @name string identifier for pretty printing
+ * @uid unique identifier for field
+ * @bitwidth length of field in bits
+ */
+struct net_flow_field {
+ char *name;
+ int uid;
+ int bitwidth;
+};
+
+/**
+ * @struct net_flow_hdr
+ * @brief defines a match (header/field) an endpoint can use
+ *
+ * @name string identifier for pretty printing
+ * @uid unique identifier for header
+ * @field_sz number of fields are in the set
+ * @fields the set of fields in the net_flow_hdr
+ */
+struct net_flow_hdr {
+ char *name;
+ int uid;
+ int field_sz;
+ struct net_flow_field *fields;
+};
+
+/**
+ * @struct net_flow_action_arg
+ * @brief encodes action arguments in structures one per argument
+ *
+ * @name string identifier for pretty printing
+ * @type type of argument either u8, u16, u32, u64
+ * @value_# indicate value/mask value type on of u8, u16, u32, or u64
+ */
+struct net_flow_action_arg {
+ char *name;
+ enum net_flow_action_arg_type type;
+ union {
+ __u8 value_u8;
+ __u16 value_u16;
+ __u32 value_u32;
+ __u64 value_u64;
+ };
+};
+
+/**
+ * @struct net_flow_action
+ * @brief a description of a endpoint defined action
+ *
+ * @name printable name
+ * @uid unique action identifier
+ * @args null terminated list of action arguments
+ */
+struct net_flow_action {
+ char *name;
+ int uid;
+ struct net_flow_action_arg *args;
+};
+
+/**
+ * @struct net_flow_field_ref
+ * @brief uniquely identify field as instance:header:field tuple
+ *
+ * @instance identify unique instance of field reference
+ * @header identify unique header reference
+ * @field identify unique field in above header reference
+ * @mask_type indicate mask type
+ * @type indicate value/mask value type on of u8, u16, u32, or u64
+ * @value_u# value of field reference
+ * @mask_u# mask value of field reference
+ */
+struct net_flow_field_ref {
+ int instance;
+ int header;
+ int field;
+ int mask_type;
+ int type;
+ union {
+ struct {
+ __u8 value_u8;
+ __u8 mask_u8;
+ };
+ struct {
+ __u16 value_u16;
+ __u16 mask_u16;
+ };
+ struct {
+ __u32 value_u32;
+ __u32 mask_u32;
+ };
+ struct {
+ __u64 value_u64;
+ __u64 mask_u64;
+ };
+ };
+};
+
+/**
+ * @struct net_flow_tbl
+ * @brief define flow table with supported match/actions
+ *
+ * @name string identifier for pretty printing
+ * @uid unique identifier for table
+ * @source uid of parent table
+ * @apply_action actions in the same apply group are applied in one step
+ * @size max number of entries for table or -1 for unbounded
+ * @matches null terminated set of supported match types given by match uid
+ * @actions null terminated set of supported action types given by action uid
+ */
+struct net_flow_tbl {
+ char *name;
+ int uid;
+ int source;
+ int apply_action;
+ int size;
+ struct net_flow_field_ref *matches;
+ int *actions;
+};
+
+/**
+ * @struct net_flow_jump_table
+ * @brief encodes an edge of the table graph or header graph
+ *
+ * @field field reference must be true to follow edge
+ * @node node identifier to connect edge to
+ */
+
+struct net_flow_jump_table {
+ struct net_flow_field_ref field;
+ int node; /* <0 is a parser error */
+};
+
+/* @struct net_flow_hdr_node
+ * @brief node in a header graph of header fields.
+ *
+ * @name string identifier for pretty printing
+ * @uid unique id of the graph node
+ * @hdrs null terminated list of hdrs identified by this node
+ * @jump encoding of graph structure as a case jump statement
+ */
+struct net_flow_hdr_node {
+ char *name;
+ int uid;
+ int *hdrs;
+ struct net_flow_jump_table *jump;
+};
+
+/* @struct net_flow_tbl_node
+ * @brief
+ *
+ * @uid unique id of the table node
+ * @flags bitmask of table attributes
+ * @jump encoding of graph structure as a case jump statement
+ */
+struct net_flow_tbl_node {
+ int uid;
+ __u32 flags;
+ struct net_flow_jump_table *jump;
+};
+#endif
@@ -52,6 +52,10 @@
#include <linux/neighbour.h>
#include <uapi/linux/netdevice.h>
+#ifdef CONFIG_NET_FLOW_TABLES
+#include <linux/if_flow.h>
+#endif
+
struct netpoll_info;
struct device;
struct phy_device;
@@ -1030,6 +1034,33 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
* int (*ndo_switch_port_stp_update)(struct net_device *dev, u8 state);
* Called to notify switch device port of bridge port STP
* state change.
+ *
+ * struct net_flow_action **(*ndo_flow_get_actions)(struct net_device *dev)
+ * Report a null terminated list of actions supported by the device along
+ * with the arguments they take.
+ *
+ * struct net_flow_tbl **(*ndo_flow_get_tbls)(struct net_device *dev)
+ * Report a null terminated list of tables supported by the device.
+ * Including the match fields and actions supported. The match fields
+ * are defined by the 'ndo_flow_get_hdrs' op and the actions are defined
+ * by 'ndo_flow_get_actions' op.
+ *
+ * struct net_flow_tbl_node **(*ndo_flow_get_tbl_graph)(struct net_device *dev)
+ * Report a null terminated list of nodes defining the table graph. When
+ * a device supports multiple tables we need to identify how the tables
+ * are connected and in what order are the tables traversed. The table
+ * nodes returned here provide the graph required to learn this.
+ *
+ * struct net_flow_hdr **(*ndo_flow_get_hdrs)(struct net_device *dev)
+ * Report a null terminated list of headers+fields supported by the
+ * device. See net_flow_hdr struct for details on header/field layout
+ * the basic logic is by giving the byte/length/offset of each field
+ * the device can define the protocols it supports.
+ *
+ * struct net_flow_hdr_node **(*ndo_flow_get_hdr_graph)(struct net_device *dev)
+ * Report a null terminated list of nodes defining the header graph. This
+ * provides the necessary graph to learn the ordering of headers supported
+ * by the device.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1190,6 +1221,13 @@ struct net_device_ops {
int (*ndo_switch_port_stp_update)(struct net_device *dev,
u8 state);
#endif
+#ifdef CONFIG_NET_FLOW_TABLES
+ struct net_flow_action **(*ndo_flow_get_actions)(struct net_device *dev);
+ struct net_flow_tbl **(*ndo_flow_get_tbls)(struct net_device *dev);
+ struct net_flow_tbl_node **(*ndo_flow_get_tbl_graph)(struct net_device *dev);
+ struct net_flow_hdr **(*ndo_flow_get_hdrs)(struct net_device *dev);
+ struct net_flow_hdr_node **(*ndo_flow_get_hdr_graph)(struct net_device *dev);
+#endif
};
/**
new file mode 100644
@@ -0,0 +1,389 @@
+/*
+ * include/uapi/linux/if_flow.h - Flow table interface for Switch devices
+ * Copyright (c) 2014 John Fastabend <john.r.fastabend@intel.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Author: John Fastabend <john.r.fastabend@intel.com>
+ */
+
+/* Netlink description:
+ *
+ * Table definition used to describe running tables. The following
+ * describes the netlink format used by the flow API.
+ *
+ * Flow table definitions used to define tables.
+ *
+ * [NFL_TABLE_IDENTIFIER_TYPE]
+ * [NFL_TABLE_IDENTIFIER]
+ * [NFL_TABLE_TABLES]
+ * [NFL_TABLE]
+ * [NFL_TABLE_ATTR_NAME]
+ * [NFL_TABLE_ATTR_UID]
+ * [NFL_TABLE_ATTR_SOURCE]
+ * [NFL_TABLE_ATTR_APPLY]
+ * [NFL_TABLE_ATTR_SIZE]
+ * [NFL_TABLE_ATTR_MATCHES]
+ * [NFL_FIELD_REF]
+ * [NFL_FIELD_REF_INSTANCE]
+ * [NFL_FIELD_REF_HEADER]
+ * [NFL_FIELD_REF_FIELD]
+ * [NFL_FIELD_REF_MASK]
+ * [NFL_FIELD_REF_TYPE]
+ * [...]
+ * [NFL_TABLE_ATTR_ACTIONS]
+ * [NFL_ACTION_ATTR_UID]
+ * [...]
+ * [NFL_TABLE]
+ * [...]
+ *
+ * Header definitions used to define headers with user friendly
+ * names.
+ *
+ * [NFL_TABLE_HEADERS]
+ * [NFL_HEADER]
+ * [NFL_HEADER_ATTR_NAME]
+ * [NFL_HEADER_ATTR_UID]
+ * [NFL_HEADER_ATTR_FIELDS]
+ * [NFL_HEADER_ATTR_FIELD]
+ * [NFL_FIELD_ATTR_NAME]
+ * [NFL_FIELD_ATTR_UID]
+ * [NFL_FIELD_ATTR_BITWIDTH]
+ * [NFL_HEADER_ATTR_FIELD]
+ * [...]
+ * [...]
+ * [NFL_HEADER]
+ * [...]
+ * [...]
+ *
+ * Action definitions supported by tables
+ *
+ * [NFL_TABLE_ACTIONS]
+ * [NFL_TABLE_ATTR_ACTIONS]
+ * [NFL_ACTION]
+ * [NFL_ACTION_ATTR_NAME]
+ * [NFL_ACTION_ATTR_UID]
+ * [NFL_ACTION_ATTR_SIGNATURE]
+ * [NFL_ACTION_ARG]
+ * [NFL_ACTION_ARG_NAME]
+ * [NFL_ACTION_ARG_TYPE]
+ * [...]
+ * [NFL_ACTION]
+ * [...]
+ *
+ * Then two get definitions for the headers graph and the table graph
+ * The header graph gives an encoded graph to describe how the device
+ * parses the headers. Use this to learn if a specific protocol is
+ * supported in the current device configuration. The table graph
+ * reports how tables are traversed by packets.
+ *
+ * Get Headers Graph <Request> only requires msg preamble.
+ *
+ * Get Headers Graph <Reply> description
+ *
+ * [NFL_HEADER_GRAPH]
+ * [NFL_HEADER_GRAPH_NODE]
+ * [NFL_HEADER_NODE_NAME]
+ * [NFL_HEADER_NODE_HDRS]
+ * [NFL_HEADER_NODE_HDRS_VALUE]
+ * [...]
+ * [NFL_HEADER_NODE_JUMP]]
+ * [NFL_JUMP_ENTRY]
+ * [NFL_FIELD_REF_NEXT_NODE]
+ * [NFL_FIELD_REF_INSTANCE]
+ * [NFL_FIELD_REF_HEADER]
+ * [NFL_FIELD_REF_FIELD]
+ * [NFL_FIELD_REF_MASK]
+ * [NFL_FIELD_REF_TYPE]
+ * [NFL_FIELD_REF_VALUE]
+ * [NFL_FIELD_REF_MASK]
+ * [...]
+ * [NFL_HEADER_GRAPH_NODE]
+ * [
+ *
+ * Get Table Graph <Request> only requires msg preamble.
+ *
+ * Get Table Graph <Reply> description
+ *
+ * [NFL_TABLE_GRAPH]
+ * [NFL_TABLE_GRAPH_NODE]
+ * [NFL_TABLE_GRAPH_NODE_UID]
+ * [NFL_TABLE_GRAPH_NODE_JUMP]
+ * [NFL_JUMP_ENTRY]
+ * [NFL_FIELD_REF_NEXT_NODE]
+ * [NFL_FIELD_REF_INSTANCE]
+ * [NFL_FIELD_REF_HEADER]
+ * [NFL_FIELD_REF_FIELD]
+ * [NFL_FIELD_REF_MASK]
+ * [NFL_FIELD_REF_TYPE]
+ * [NFL_FIELD_REF_VALUE]
+ * [NFL_FIELD_REF_MASK]
+ * [...]
+ * [NFL_TABLE_GRAPH_NODE]
+ * [..]
+ */
+
+#ifndef _UAPI_LINUX_IF_FLOW
+#define _UAPI_LINUX_IF_FLOW
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+#include <linux/if.h>
+
+enum {
+ NFL_FIELD_UNSPEC,
+ NFL_FIELD,
+ __NFL_FIELD_MAX,
+};
+
+#define NFL_FIELD_MAX (__NFL_FIELD_MAX - 1)
+
+enum {
+ NFL_FIELD_ATTR_UNSPEC,
+ NFL_FIELD_ATTR_NAME,
+ NFL_FIELD_ATTR_UID,
+ NFL_FIELD_ATTR_BITWIDTH,
+ __NFL_FIELD_ATTR_MAX,
+};
+
+#define NFL_FIELD_ATTR_MAX (__NFL_FIELD_ATTR_MAX - 1)
+
+enum {
+ NFL_HEADER_UNSPEC,
+ NFL_HEADER,
+ __NFL_HEADER_MAX,
+};
+
+#define NFL_HEADER_MAX (__NFL_HEADER_MAX - 1)
+
+enum {
+ NFL_HEADER_ATTR_UNSPEC,
+ NFL_HEADER_ATTR_NAME,
+ NFL_HEADER_ATTR_UID,
+ NFL_HEADER_ATTR_FIELDS,
+ __NFL_HEADER_ATTR_MAX,
+};
+
+#define NFL_HEADER_ATTR_MAX (__NFL_HEADER_ATTR_MAX - 1)
+
+enum {
+ NFL_MASK_TYPE_UNSPEC,
+ NFL_MASK_TYPE_EXACT,
+ NFL_MASK_TYPE_LPM,
+ NFL_MASK_TYPE_MASK,
+};
+
+enum {
+ NFL_FIELD_REF_UNSPEC,
+ NFL_FIELD_REF_NEXT_NODE,
+ NFL_FIELD_REF_INSTANCE,
+ NFL_FIELD_REF_HEADER,
+ NFL_FIELD_REF_FIELD,
+ NFL_FIELD_REF_MASK_TYPE,
+ NFL_FIELD_REF_TYPE,
+ NFL_FIELD_REF_VALUE,
+ NFL_FIELD_REF_MASK,
+ __NFL_FIELD_REF_MAX,
+};
+
+#define NFL_FIELD_REF_MAX (__NFL_FIELD_REF_MAX - 1)
+
+enum {
+ NFL_FIELD_REFS_UNSPEC,
+ NFL_FIELD_REF,
+ __NFL_FIELD_REFS_MAX,
+};
+
+#define NFL_FIELD_REFS_MAX (__NFL_FIELD_REFS_MAX - 1)
+
+enum {
+ NFL_FIELD_REF_ATTR_TYPE_UNSPEC,
+ NFL_FIELD_REF_ATTR_TYPE_U8,
+ NFL_FIELD_REF_ATTR_TYPE_U16,
+ NFL_FIELD_REF_ATTR_TYPE_U32,
+ NFL_FIELD_REF_ATTR_TYPE_U64,
+};
+
+enum net_flow_action_arg_type {
+ NFL_ACTION_ARG_TYPE_NULL,
+ NFL_ACTION_ARG_TYPE_U8,
+ NFL_ACTION_ARG_TYPE_U16,
+ NFL_ACTION_ARG_TYPE_U32,
+ NFL_ACTION_ARG_TYPE_U64,
+ __NFL_ACTION_ARG_TYPE_VAL_MAX,
+};
+
+enum {
+ NFL_ACTION_ARG_UNSPEC,
+ NFL_ACTION_ARG_NAME,
+ NFL_ACTION_ARG_TYPE,
+ NFL_ACTION_ARG_VALUE,
+ __NFL_ACTION_ARG_MAX,
+};
+
+#define NFL_ACTION_ARG_MAX (__NFL_ACTION_ARG_MAX - 1)
+
+enum {
+ NFL_ACTION_ARGS_UNSPEC,
+ NFL_ACTION_ARG,
+ __NFL_ACTION_ARGS_MAX,
+};
+
+#define NFL_ACTION_ARGS_MAX (__NFL_ACTION_ARGS_MAX - 1)
+
+enum {
+ NFL_ACTION_UNSPEC,
+ NFL_ACTION,
+ __NFL_ACTION_MAX,
+};
+
+#define NFL_ACTION_MAX (__NFL_ACTION_MAX - 1)
+
+enum {
+ NFL_ACTION_ATTR_UNSPEC,
+ NFL_ACTION_ATTR_NAME,
+ NFL_ACTION_ATTR_UID,
+ NFL_ACTION_ATTR_SIGNATURE,
+ __NFL_ACTION_ATTR_MAX,
+};
+
+#define NFL_ACTION_ATTR_MAX (__NFL_ACTION_ATTR_MAX - 1)
+
+enum {
+ NFL_ACTION_SET_UNSPEC,
+ NFL_ACTION_SET_ACTIONS,
+ __NFL_ACTION_SET_MAX,
+};
+
+#define NFL_ACTION_SET_MAX (__NFL_ACTION_SET_MAX - 1)
+
+enum {
+ NFL_TABLE_UNSPEC,
+ NFL_TABLE,
+ __NFL_TABLE_MAX,
+};
+
+#define NFL_TABLE_MAX (__NFL_TABLE_MAX - 1)
+
+enum {
+ NFL_TABLE_ATTR_UNSPEC,
+ NFL_TABLE_ATTR_NAME,
+ NFL_TABLE_ATTR_UID,
+ NFL_TABLE_ATTR_SOURCE,
+ NFL_TABLE_ATTR_APPLY,
+ NFL_TABLE_ATTR_SIZE,
+ NFL_TABLE_ATTR_MATCHES,
+ NFL_TABLE_ATTR_ACTIONS,
+ __NFL_TABLE_ATTR_MAX,
+};
+
+#define NFL_TABLE_ATTR_MAX (__NFL_TABLE_ATTR_MAX - 1)
+
+#define NFL_JUMP_TABLE_DONE -1
+enum {
+ NFL_JUMP_ENTRY_UNSPEC,
+ NFL_JUMP_ENTRY,
+ __NFL_JUMP_ENTRY_MAX,
+};
+
+enum {
+ NFL_HEADER_NODE_HDRS_UNSPEC,
+ NFL_HEADER_NODE_HDRS_VALUE,
+ __NFL_HEADER_NODE_HDRS_MAX,
+};
+
+#define NFL_HEADER_NODE_HDRS_MAX (__NFL_HEADER_NODE_HDRS_MAX - 1)
+
+enum {
+ NFL_HEADER_NODE_UNSPEC,
+ NFL_HEADER_NODE_NAME,
+ NFL_HEADER_NODE_UID,
+ NFL_HEADER_NODE_HDRS,
+ NFL_HEADER_NODE_JUMP,
+ __NFL_HEADER_NODE_MAX,
+};
+
+#define NFL_HEADER_NODE_MAX (__NFL_HEADER_NODE_MAX - 1)
+
+enum {
+ NFL_HEADER_GRAPH_UNSPEC,
+ NFL_HEADER_GRAPH_NODE,
+ __NFL_HEADER_GRAPH_MAX,
+};
+
+#define NFL_HEADER_GRAPH_MAX (__NFL_HEADER_GRAPH_MAX - 1)
+
+#define NFL_TABLE_EGRESS_ROOT 1
+#define NFL_TABLE_INGRESS_ROOT 2
+
+enum {
+ NFL_TABLE_GRAPH_NODE_UNSPEC,
+ NFL_TABLE_GRAPH_NODE_UID,
+ NFL_TABLE_GRAPH_NODE_FLAGS,
+ NFL_TABLE_GRAPH_NODE_JUMP,
+ __NFL_TABLE_GRAPH_NODE_MAX,
+};
+
+#define NFL_TABLE_GRAPH_NODE_MAX (__NFL_TABLE_GRAPH_NODE_MAX - 1)
+
+enum {
+ NFL_TABLE_GRAPH_UNSPEC,
+ NFL_TABLE_GRAPH_NODE,
+ __NFL_TABLE_GRAPH_MAX,
+};
+
+#define NFL_TABLE_GRAPH_MAX (__NFL_TABLE_GRAPH_MAX - 1)
+
+enum {
+ NFL_NFL_UNSPEC,
+ NFL_FLOW,
+ __NFL_NFL_MAX,
+};
+
+#define NFL_NFL_MAX (__NFL_NFL_MAX - 1)
+
+enum {
+ NFL_IDENTIFIER_UNSPEC,
+ NFL_IDENTIFIER_IFINDEX, /* net_device ifindex */
+};
+
+enum {
+ NFL_UNSPEC,
+ NFL_IDENTIFIER_TYPE,
+ NFL_IDENTIFIER,
+
+ NFL_TABLES,
+ NFL_HEADERS,
+ NFL_ACTIONS,
+ NFL_HEADER_GRAPH,
+ NFL_TABLE_GRAPH,
+
+ __NFL_MAX,
+ NFL_MAX = (__NFL_MAX - 1),
+};
+
+enum {
+ NFL_TABLE_CMD_GET_TABLES,
+ NFL_TABLE_CMD_GET_HEADERS,
+ NFL_TABLE_CMD_GET_ACTIONS,
+ NFL_TABLE_CMD_GET_HDR_GRAPH,
+ NFL_TABLE_CMD_GET_TABLE_GRAPH,
+
+ __NFL_CMD_MAX,
+ NFL_CMD_MAX = (__NFL_CMD_MAX - 1),
+};
+
+#define NFL_GENL_NAME "net_flow_nl"
+#define NFL_GENL_VERSION 0x1
+#endif /* _UAPI_LINUX_IF_FLOW */
@@ -293,6 +293,13 @@ config NET_FLOW_LIMIT
with many clients some protection against DoS by a single (spoofed)
flow that greatly exceeds average workload.
+config NET_FLOW_TABLES
+ boolean "Support network flow tables"
+ ---help---
+ This feature provides an interface for device drivers to report
+ flow tables and supported matches and actions. If you do not
+ want to support hardware offloads for flow tables, say N here.
+
menu "Network testing"
config NET_PKTGEN
@@ -23,3 +23,4 @@ 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_FLOW_TABLES) += flow_table.o
new file mode 100644
@@ -0,0 +1,942 @@
+/*
+ * include/uapi/linux/if_flow.h - Flow table interface for Switch devices
+ * Copyright (c) 2014 John Fastabend <john.r.fastabend@intel.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Author: John Fastabend <john.r.fastabend@intel.com>
+ */
+
+#include <uapi/linux/if_flow.h>
+#include <linux/if_flow.h>
+#include <linux/if_bridge.h>
+#include <linux/types.h>
+#include <net/netlink.h>
+#include <net/genetlink.h>
+#include <net/rtnetlink.h>
+#include <linux/module.h>
+
+static struct genl_family net_flow_nl_family = {
+ .id = GENL_ID_GENERATE,
+ .name = NFL_GENL_NAME,
+ .version = NFL_GENL_VERSION,
+ .maxattr = NFL_MAX,
+ .netnsok = true,
+};
+
+static struct net_device *net_flow_get_dev(struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ int type, ifindex;
+
+ if (!info->attrs[NFL_IDENTIFIER_TYPE] ||
+ !info->attrs[NFL_IDENTIFIER])
+ return NULL;
+
+ type = nla_get_u32(info->attrs[NFL_IDENTIFIER_TYPE]);
+ switch (type) {
+ case NFL_IDENTIFIER_IFINDEX:
+ ifindex = nla_get_u32(info->attrs[NFL_IDENTIFIER]);
+ break;
+ default:
+ return NULL;
+ }
+
+ return dev_get_by_index(net, ifindex);
+}
+
+static int net_flow_put_act_types(struct sk_buff *skb,
+ struct net_flow_action_arg *args)
+{
+ struct nlattr *arg;
+ int i, err;
+
+ for (i = 0; args[i].type; i++) {
+ arg = nla_nest_start(skb, NFL_ACTION_ARG);
+ if (!arg)
+ return -EMSGSIZE;
+
+ if (args[i].name) {
+ err = nla_put_string(skb, NFL_ACTION_ARG_NAME,
+ args[i].name);
+ if (err)
+ goto out;
+ }
+
+ err = nla_put_u32(skb, NFL_ACTION_ARG_TYPE, args[i].type);
+ if (err)
+ goto out;
+
+ nla_nest_end(skb, arg);
+ }
+ return 0;
+out:
+ nla_nest_cancel(skb, arg);
+ return err;
+}
+
+static const
+struct nla_policy net_flow_action_policy[NFL_ACTION_ATTR_MAX + 1] = {
+ [NFL_ACTION_ATTR_NAME] = {.type = NLA_STRING },
+ [NFL_ACTION_ATTR_UID] = {.type = NLA_U32 },
+ [NFL_ACTION_ATTR_SIGNATURE] = {.type = NLA_NESTED },
+};
+
+static int net_flow_put_action(struct sk_buff *skb, struct net_flow_action *a)
+{
+ struct nlattr *nest;
+ int err;
+
+ if (a->name && nla_put_string(skb, NFL_ACTION_ATTR_NAME, a->name))
+ return -EMSGSIZE;
+
+ if (nla_put_u32(skb, NFL_ACTION_ATTR_UID, a->uid))
+ return -EMSGSIZE;
+
+ if (a->args) {
+ nest = nla_nest_start(skb, NFL_ACTION_ATTR_SIGNATURE);
+ if (!nest)
+ return -EMSGSIZE;
+
+ err = net_flow_put_act_types(skb, a->args);
+ if (err) {
+ nla_nest_cancel(skb, nest);
+ return err;
+ }
+ nla_nest_end(skb, nest);
+ }
+
+ return 0;
+}
+
+static int net_flow_put_actions(struct sk_buff *skb,
+ struct net_flow_action **acts)
+{
+ struct nlattr *actions;
+ int i, err;
+
+ actions = nla_nest_start(skb, NFL_ACTIONS);
+ if (!actions)
+ return -EMSGSIZE;
+
+ for (i = 0; acts[i]; i++) {
+ struct nlattr *action = nla_nest_start(skb, NFL_ACTION);
+
+ if (!action)
+ goto action_put_failure;
+
+ err = net_flow_put_action(skb, acts[i]);
+ if (err)
+ goto action_put_failure;
+ nla_nest_end(skb, action);
+ }
+ nla_nest_end(skb, actions);
+
+ return 0;
+action_put_failure:
+ nla_nest_cancel(skb, actions);
+ return -EMSGSIZE;
+}
+
+static struct sk_buff *net_flow_build_actions_msg(struct net_flow_action **a,
+ struct net_device *dev,
+ u32 portid, int seq, u8 cmd)
+{
+ struct genlmsghdr *hdr;
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return ERR_PTR(-ENOBUFS);
+
+ hdr = genlmsg_put(skb, portid, seq, &net_flow_nl_family, 0, cmd);
+ if (!hdr)
+ goto out;
+
+ if (nla_put_u32(skb,
+ NFL_IDENTIFIER_TYPE,
+ NFL_IDENTIFIER_IFINDEX) ||
+ nla_put_u32(skb, NFL_IDENTIFIER, dev->ifindex)) {
+ err = -ENOBUFS;
+ goto out;
+ }
+
+ err = net_flow_put_actions(skb, a);
+ if (err < 0)
+ goto out;
+
+ err = genlmsg_end(skb, hdr);
+ if (err < 0)
+ goto out;
+
+ return skb;
+out:
+ nlmsg_free(skb);
+ return ERR_PTR(err);
+}
+
+static int net_flow_cmd_get_actions(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct net_flow_action **a;
+ struct net_device *dev;
+ struct sk_buff *msg;
+
+ dev = net_flow_get_dev(info);
+ if (!dev)
+ return -EINVAL;
+
+ if (!dev->netdev_ops->ndo_flow_get_actions) {
+ dev_put(dev);
+ return -EOPNOTSUPP;
+ }
+
+ a = dev->netdev_ops->ndo_flow_get_actions(dev);
+ if (!a) {
+ dev_put(dev);
+ return -EBUSY;
+ }
+
+ msg = net_flow_build_actions_msg(a, dev,
+ info->snd_portid,
+ info->snd_seq,
+ NFL_TABLE_CMD_GET_ACTIONS);
+ dev_put(dev);
+
+ if (IS_ERR(msg))
+ return PTR_ERR(msg);
+
+ return genlmsg_reply(msg, info);
+}
+
+static int net_flow_put_field_ref(struct sk_buff *skb,
+ struct net_flow_field_ref *ref)
+{
+ if (nla_put_u32(skb, NFL_FIELD_REF_INSTANCE, ref->instance) ||
+ nla_put_u32(skb, NFL_FIELD_REF_HEADER, ref->header) ||
+ nla_put_u32(skb, NFL_FIELD_REF_FIELD, ref->field) ||
+ nla_put_u32(skb, NFL_FIELD_REF_MASK_TYPE, ref->mask_type) ||
+ nla_put_u32(skb, NFL_FIELD_REF_TYPE, ref->type))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int net_flow_put_field_value(struct sk_buff *skb,
+ struct net_flow_field_ref *r)
+{
+ int err = -EINVAL;
+
+ switch (r->type) {
+ case NFL_FIELD_REF_ATTR_TYPE_UNSPEC:
+ err = 0;
+ break;
+ case NFL_FIELD_REF_ATTR_TYPE_U8:
+ err = nla_put_u8(skb, NFL_FIELD_REF_VALUE, r->value_u8);
+ if (err)
+ break;
+ err = nla_put_u8(skb, NFL_FIELD_REF_MASK, r->mask_u8);
+ break;
+ case NFL_FIELD_REF_ATTR_TYPE_U16:
+ err = nla_put_u16(skb, NFL_FIELD_REF_VALUE, r->value_u16);
+ if (err)
+ break;
+ err = nla_put_u16(skb, NFL_FIELD_REF_MASK, r->mask_u16);
+ break;
+ case NFL_FIELD_REF_ATTR_TYPE_U32:
+ err = nla_put_u32(skb, NFL_FIELD_REF_VALUE, r->value_u32);
+ if (err)
+ break;
+ err = nla_put_u32(skb, NFL_FIELD_REF_MASK, r->mask_u32);
+ break;
+ case NFL_FIELD_REF_ATTR_TYPE_U64:
+ err = nla_put_u64(skb, NFL_FIELD_REF_VALUE, r->value_u64);
+ if (err)
+ break;
+ err = nla_put_u64(skb, NFL_FIELD_REF_MASK, r->mask_u64);
+ break;
+ default:
+ break;
+ }
+ return err;
+}
+
+static int net_flow_put_table(struct net_device *dev,
+ struct sk_buff *skb,
+ struct net_flow_tbl *t)
+{
+ struct nlattr *matches, *actions, *field;
+ int i, err;
+
+ if (nla_put_string(skb, NFL_TABLE_ATTR_NAME, t->name) ||
+ nla_put_u32(skb, NFL_TABLE_ATTR_UID, t->uid) ||
+ nla_put_u32(skb, NFL_TABLE_ATTR_SOURCE, t->source) ||
+ nla_put_u32(skb, NFL_TABLE_ATTR_APPLY, t->apply_action) ||
+ nla_put_u32(skb, NFL_TABLE_ATTR_SIZE, t->size))
+ return -EMSGSIZE;
+
+ matches = nla_nest_start(skb, NFL_TABLE_ATTR_MATCHES);
+ if (!matches)
+ return -EMSGSIZE;
+
+ for (i = 0; t->matches[i].instance; i++) {
+ field = nla_nest_start(skb, NFL_FIELD_REF);
+
+ err = net_flow_put_field_ref(skb, &t->matches[i]);
+ if (err) {
+ nla_nest_cancel(skb, matches);
+ return -EMSGSIZE;
+ }
+
+ nla_nest_end(skb, field);
+ }
+ nla_nest_end(skb, matches);
+
+ actions = nla_nest_start(skb, NFL_TABLE_ATTR_ACTIONS);
+ if (!actions)
+ return -EMSGSIZE;
+
+ for (i = 0; t->actions[i]; i++) {
+ if (nla_put_u32(skb,
+ NFL_ACTION_ATTR_UID,
+ t->actions[i])) {
+ nla_nest_cancel(skb, actions);
+ return -EMSGSIZE;
+ }
+ }
+ nla_nest_end(skb, actions);
+
+ return 0;
+}
+
+static int net_flow_put_tables(struct net_device *dev,
+ struct sk_buff *skb,
+ struct net_flow_tbl **tables)
+{
+ struct nlattr *nest, *t;
+ int i, err = 0;
+
+ nest = nla_nest_start(skb, NFL_TABLES);
+ if (!nest)
+ return -EMSGSIZE;
+
+ for (i = 0; tables[i]; i++) {
+ t = nla_nest_start(skb, NFL_TABLE);
+ if (!t) {
+ err = -EMSGSIZE;
+ goto errout;
+ }
+
+ err = net_flow_put_table(dev, skb, tables[i]);
+ if (err) {
+ nla_nest_cancel(skb, t);
+ goto errout;
+ }
+ nla_nest_end(skb, t);
+ }
+ nla_nest_end(skb, nest);
+ return 0;
+errout:
+ nla_nest_cancel(skb, nest);
+ return err;
+}
+
+static struct sk_buff *net_flow_build_tables_msg(struct net_flow_tbl **t,
+ struct net_device *dev,
+ u32 portid, int seq, u8 cmd)
+{
+ struct genlmsghdr *hdr;
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return ERR_PTR(-ENOBUFS);
+
+ hdr = genlmsg_put(skb, portid, seq, &net_flow_nl_family, 0, cmd);
+ if (!hdr)
+ goto out;
+
+ if (nla_put_u32(skb,
+ NFL_IDENTIFIER_TYPE,
+ NFL_IDENTIFIER_IFINDEX) ||
+ nla_put_u32(skb, NFL_IDENTIFIER, dev->ifindex)) {
+ err = -ENOBUFS;
+ goto out;
+ }
+
+ err = net_flow_put_tables(dev, skb, t);
+ if (err < 0)
+ goto out;
+
+ err = genlmsg_end(skb, hdr);
+ if (err < 0)
+ goto out;
+
+ return skb;
+out:
+ nlmsg_free(skb);
+ return ERR_PTR(err);
+}
+
+static int net_flow_cmd_get_tables(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct net_flow_tbl **tables;
+ struct net_device *dev;
+ struct sk_buff *msg;
+
+ dev = net_flow_get_dev(info);
+ if (!dev)
+ return -EINVAL;
+
+ if (!dev->netdev_ops->ndo_flow_get_tbls) {
+ dev_put(dev);
+ return -EOPNOTSUPP;
+ }
+
+ tables = dev->netdev_ops->ndo_flow_get_tbls(dev);
+ if (!tables) {
+ dev_put(dev);
+ return -EBUSY;
+ }
+
+ msg = net_flow_build_tables_msg(tables, dev,
+ info->snd_portid,
+ info->snd_seq,
+ NFL_TABLE_CMD_GET_TABLES);
+ dev_put(dev);
+
+ if (IS_ERR(msg))
+ return PTR_ERR(msg);
+
+ return genlmsg_reply(msg, info);
+}
+
+static
+int net_flow_put_fields(struct sk_buff *skb, const struct net_flow_hdr *h)
+{
+ struct net_flow_field *f;
+ int count = h->field_sz;
+ struct nlattr *field;
+
+ for (f = h->fields; count; count--, f++) {
+ field = nla_nest_start(skb, NFL_FIELD);
+ if (!field)
+ goto field_put_failure;
+
+ if (nla_put_string(skb, NFL_FIELD_ATTR_NAME, f->name) ||
+ nla_put_u32(skb, NFL_FIELD_ATTR_UID, f->uid) ||
+ nla_put_u32(skb, NFL_FIELD_ATTR_BITWIDTH, f->bitwidth))
+ goto out;
+
+ nla_nest_end(skb, field);
+ }
+
+ return 0;
+out:
+ nla_nest_cancel(skb, field);
+field_put_failure:
+ return -EMSGSIZE;
+}
+
+static int net_flow_put_headers(struct sk_buff *skb,
+ struct net_flow_hdr **headers)
+{
+ struct nlattr *nest, *hdr, *fields;
+ struct net_flow_hdr *h;
+ int i, err;
+
+ nest = nla_nest_start(skb, NFL_HEADERS);
+ if (!nest)
+ return -EMSGSIZE;
+
+ for (i = 0; headers[i]; i++) {
+ err = -EMSGSIZE;
+ h = headers[i];
+
+ hdr = nla_nest_start(skb, NFL_HEADER);
+ if (!hdr)
+ goto put_failure;
+
+ if (nla_put_string(skb, NFL_HEADER_ATTR_NAME, h->name) ||
+ nla_put_u32(skb, NFL_HEADER_ATTR_UID, h->uid))
+ goto put_failure;
+
+ fields = nla_nest_start(skb, NFL_HEADER_ATTR_FIELDS);
+ if (!fields)
+ goto put_failure;
+
+ err = net_flow_put_fields(skb, h);
+ if (err)
+ goto put_failure;
+
+ nla_nest_end(skb, fields);
+
+ nla_nest_end(skb, hdr);
+ }
+ nla_nest_end(skb, nest);
+
+ return 0;
+put_failure:
+ nla_nest_cancel(skb, nest);
+ return err;
+}
+
+static struct sk_buff *net_flow_build_headers_msg(struct net_flow_hdr **h,
+ struct net_device *dev,
+ u32 portid, int seq, u8 cmd)
+{
+ struct genlmsghdr *hdr;
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return ERR_PTR(-ENOBUFS);
+
+ hdr = genlmsg_put(skb, portid, seq, &net_flow_nl_family, 0, cmd);
+ if (!hdr)
+ goto out;
+
+ if (nla_put_u32(skb,
+ NFL_IDENTIFIER_TYPE,
+ NFL_IDENTIFIER_IFINDEX) ||
+ nla_put_u32(skb, NFL_IDENTIFIER, dev->ifindex)) {
+ err = -ENOBUFS;
+ goto out;
+ }
+
+ err = net_flow_put_headers(skb, h);
+ if (err < 0)
+ goto out;
+
+ err = genlmsg_end(skb, hdr);
+ if (err < 0)
+ goto out;
+
+ return skb;
+out:
+ nlmsg_free(skb);
+ return ERR_PTR(err);
+}
+
+static int net_flow_cmd_get_headers(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct net_flow_hdr **h;
+ struct net_device *dev;
+ struct sk_buff *msg;
+
+ dev = net_flow_get_dev(info);
+ if (!dev)
+ return -EINVAL;
+
+ if (!dev->netdev_ops->ndo_flow_get_hdrs) {
+ dev_put(dev);
+ return -EOPNOTSUPP;
+ }
+
+ h = dev->netdev_ops->ndo_flow_get_hdrs(dev);
+ if (!h) {
+ dev_put(dev);
+ return -EBUSY;
+ }
+
+ msg = net_flow_build_headers_msg(h, dev,
+ info->snd_portid,
+ info->snd_seq,
+ NFL_TABLE_CMD_GET_HEADERS);
+ dev_put(dev);
+
+ if (IS_ERR(msg))
+ return PTR_ERR(msg);
+
+ return genlmsg_reply(msg, info);
+}
+
+static int net_flow_put_header_node(struct sk_buff *skb,
+ struct net_flow_hdr_node *node)
+{
+ struct nlattr *hdrs, *jumps;
+ int i, err;
+
+ if (nla_put_string(skb, NFL_HEADER_NODE_NAME, node->name) ||
+ nla_put_u32(skb, NFL_HEADER_NODE_UID, node->uid))
+ return -EMSGSIZE;
+
+ /* Insert the set of headers that get extracted at this node */
+ hdrs = nla_nest_start(skb, NFL_HEADER_NODE_HDRS);
+ if (!hdrs)
+ return -EMSGSIZE;
+ for (i = 0; node->hdrs[i]; i++) {
+ if (nla_put_u32(skb, NFL_HEADER_NODE_HDRS_VALUE,
+ node->hdrs[i])) {
+ nla_nest_cancel(skb, hdrs);
+ return -EMSGSIZE;
+ }
+ }
+ nla_nest_end(skb, hdrs);
+
+ /* Then give the jump table to find next header node in graph */
+ jumps = nla_nest_start(skb, NFL_HEADER_NODE_JUMP);
+ if (!jumps)
+ return -EMSGSIZE;
+
+ for (i = 0; node->jump[i].node; i++) {
+ struct nlattr *entry;
+
+ entry = nla_nest_start(skb, NFL_JUMP_ENTRY);
+ if (!entry) {
+ nla_nest_cancel(skb, jumps);
+ return -EMSGSIZE;
+ }
+
+ err = nla_put_u32(skb, NFL_FIELD_REF_NEXT_NODE,
+ node->jump[i].node);
+ if (err) {
+ nla_nest_cancel(skb, jumps);
+ return err;
+ }
+
+ err = net_flow_put_field_ref(skb, &node->jump[i].field);
+ if (err) {
+ nla_nest_cancel(skb, jumps);
+ return err;
+ }
+
+ err = net_flow_put_field_value(skb, &node->jump[i].field);
+ if (err) {
+ nla_nest_cancel(skb, jumps);
+ return err;
+ }
+ nla_nest_end(skb, entry);
+ }
+ nla_nest_end(skb, jumps);
+
+ return 0;
+}
+
+static int net_flow_put_header_graph(struct sk_buff *skb,
+ struct net_flow_hdr_node **g)
+{
+ struct nlattr *nodes, *node;
+ int i, err;
+
+ nodes = nla_nest_start(skb, NFL_HEADER_GRAPH);
+ if (!nodes)
+ return -EMSGSIZE;
+
+ for (i = 0; g[i]; i++) {
+ node = nla_nest_start(skb, NFL_HEADER_GRAPH_NODE);
+ if (!node) {
+ err = -EMSGSIZE;
+ goto nodes_put_error;
+ }
+
+ err = net_flow_put_header_node(skb, g[i]);
+ if (err)
+ goto nodes_put_error;
+
+ nla_nest_end(skb, node);
+ }
+
+ nla_nest_end(skb, nodes);
+ return 0;
+nodes_put_error:
+ nla_nest_cancel(skb, nodes);
+ return err;
+}
+
+static
+struct sk_buff *net_flow_build_header_graph_msg(struct net_flow_hdr_node **g,
+ struct net_device *dev,
+ u32 portid, int seq, u8 cmd)
+{
+ struct genlmsghdr *hdr;
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return ERR_PTR(-ENOBUFS);
+
+ hdr = genlmsg_put(skb, portid, seq, &net_flow_nl_family, 0, cmd);
+ if (!hdr)
+ goto out;
+
+ if (nla_put_u32(skb,
+ NFL_IDENTIFIER_TYPE,
+ NFL_IDENTIFIER_IFINDEX) ||
+ nla_put_u32(skb, NFL_IDENTIFIER, dev->ifindex)) {
+ err = -ENOBUFS;
+ goto out;
+ }
+
+ err = net_flow_put_header_graph(skb, g);
+ if (err < 0)
+ goto out;
+
+ err = genlmsg_end(skb, hdr);
+ if (err < 0)
+ goto out;
+
+ return skb;
+out:
+ nlmsg_free(skb);
+ return ERR_PTR(err);
+}
+
+static int net_flow_cmd_get_header_graph(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct net_flow_hdr_node **h;
+ struct net_device *dev;
+ struct sk_buff *msg;
+
+ dev = net_flow_get_dev(info);
+ if (!dev)
+ return -EINVAL;
+
+ if (!dev->netdev_ops->ndo_flow_get_hdr_graph) {
+ dev_put(dev);
+ return -EOPNOTSUPP;
+ }
+
+ h = dev->netdev_ops->ndo_flow_get_hdr_graph(dev);
+ if (!h) {
+ dev_put(dev);
+ return -EBUSY;
+ }
+
+ msg = net_flow_build_header_graph_msg(h, dev,
+ info->snd_portid,
+ info->snd_seq,
+ NFL_TABLE_CMD_GET_HDR_GRAPH);
+ dev_put(dev);
+
+ if (IS_ERR(msg))
+ return PTR_ERR(msg);
+
+ return genlmsg_reply(msg, info);
+}
+
+static int net_flow_put_table_node(struct sk_buff *skb,
+ struct net_flow_tbl_node *node)
+{
+ struct nlattr *nest, *jump;
+ int i, err = -EMSGSIZE;
+
+ nest = nla_nest_start(skb, NFL_TABLE_GRAPH_NODE);
+ if (!nest)
+ return err;
+
+ if (nla_put_u32(skb, NFL_TABLE_GRAPH_NODE_UID, node->uid) ||
+ nla_put_u32(skb, NFL_TABLE_GRAPH_NODE_FLAGS, node->flags))
+ goto node_put_failure;
+
+ jump = nla_nest_start(skb, NFL_TABLE_GRAPH_NODE_JUMP);
+ if (!jump)
+ goto node_put_failure;
+
+ for (i = 0; node->jump[i].node; i++) {
+ struct nlattr *entry;
+
+ entry = nla_nest_start(skb, NFL_JUMP_ENTRY);
+ if (!entry)
+ goto node_put_failure;
+
+ err = nla_put_u32(skb, NFL_FIELD_REF_NEXT_NODE,
+ node->jump[i].node);
+ if (err) {
+ nla_nest_cancel(skb, jump);
+ return err;
+ }
+
+ err = net_flow_put_field_ref(skb, &node->jump[i].field);
+ if (err)
+ goto node_put_failure;
+
+ err = net_flow_put_field_value(skb, &node->jump[i].field);
+ if (err)
+ goto node_put_failure;
+
+ nla_nest_end(skb, entry);
+ }
+
+ nla_nest_end(skb, jump);
+ nla_nest_end(skb, nest);
+ return 0;
+node_put_failure:
+ nla_nest_cancel(skb, nest);
+ return err;
+}
+
+static int net_flow_put_table_graph(struct sk_buff *skb,
+ struct net_flow_tbl_node **nodes)
+{
+ struct nlattr *graph;
+ int i, err;
+
+ graph = nla_nest_start(skb, NFL_TABLE_GRAPH);
+ if (!graph)
+ return -EMSGSIZE;
+
+ for (i = 0; nodes[i]; i++) {
+ err = net_flow_put_table_node(skb, nodes[i]);
+ if (err) {
+ nla_nest_cancel(skb, graph);
+ return -EMSGSIZE;
+ }
+ }
+
+ nla_nest_end(skb, graph);
+ return 0;
+}
+
+static
+struct sk_buff *net_flow_build_graph_msg(struct net_flow_tbl_node **g,
+ struct net_device *dev,
+ u32 portid, int seq, u8 cmd)
+{
+ struct genlmsghdr *hdr;
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return ERR_PTR(-ENOBUFS);
+
+ hdr = genlmsg_put(skb, portid, seq, &net_flow_nl_family, 0, cmd);
+ if (!hdr)
+ goto out;
+
+ if (nla_put_u32(skb,
+ NFL_IDENTIFIER_TYPE,
+ NFL_IDENTIFIER_IFINDEX) ||
+ nla_put_u32(skb, NFL_IDENTIFIER, dev->ifindex)) {
+ err = -ENOBUFS;
+ goto out;
+ }
+
+ err = net_flow_put_table_graph(skb, g);
+ if (err < 0)
+ goto out;
+
+ err = genlmsg_end(skb, hdr);
+ if (err < 0)
+ goto out;
+
+ return skb;
+out:
+ nlmsg_free(skb);
+ return ERR_PTR(err);
+}
+
+static int net_flow_cmd_get_table_graph(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct net_flow_tbl_node **g;
+ struct net_device *dev;
+ struct sk_buff *msg;
+
+ dev = net_flow_get_dev(info);
+ if (!dev)
+ return -EINVAL;
+
+ if (!dev->netdev_ops->ndo_flow_get_tbl_graph) {
+ dev_put(dev);
+ return -EOPNOTSUPP;
+ }
+
+ g = dev->netdev_ops->ndo_flow_get_tbl_graph(dev);
+ if (!g) {
+ dev_put(dev);
+ return -EBUSY;
+ }
+
+ msg = net_flow_build_graph_msg(g, dev,
+ info->snd_portid,
+ info->snd_seq,
+ NFL_TABLE_CMD_GET_TABLE_GRAPH);
+ dev_put(dev);
+
+ if (IS_ERR(msg))
+ return PTR_ERR(msg);
+
+ return genlmsg_reply(msg, info);
+}
+
+static const struct nla_policy net_flow_cmd_policy[NFL_MAX + 1] = {
+ [NFL_IDENTIFIER_TYPE] = {.type = NLA_U32, },
+ [NFL_IDENTIFIER] = {.type = NLA_U32, },
+ [NFL_TABLES] = {.type = NLA_NESTED, },
+ [NFL_HEADERS] = {.type = NLA_NESTED, },
+ [NFL_ACTIONS] = {.type = NLA_NESTED, },
+ [NFL_HEADER_GRAPH] = {.type = NLA_NESTED, },
+ [NFL_TABLE_GRAPH] = {.type = NLA_NESTED, },
+};
+
+static const struct genl_ops net_flow_table_nl_ops[] = {
+ {
+ .cmd = NFL_TABLE_CMD_GET_TABLES,
+ .doit = net_flow_cmd_get_tables,
+ .policy = net_flow_cmd_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = NFL_TABLE_CMD_GET_HEADERS,
+ .doit = net_flow_cmd_get_headers,
+ .policy = net_flow_cmd_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = NFL_TABLE_CMD_GET_ACTIONS,
+ .doit = net_flow_cmd_get_actions,
+ .policy = net_flow_cmd_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = NFL_TABLE_CMD_GET_HDR_GRAPH,
+ .doit = net_flow_cmd_get_header_graph,
+ .policy = net_flow_cmd_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = NFL_TABLE_CMD_GET_TABLE_GRAPH,
+ .doit = net_flow_cmd_get_table_graph,
+ .policy = net_flow_cmd_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+};
+
+static int __init net_flow_nl_module_init(void)
+{
+ return genl_register_family_with_ops(&net_flow_nl_family,
+ net_flow_table_nl_ops);
+}
+
+static void net_flow_nl_module_fini(void)
+{
+ genl_unregister_family(&net_flow_nl_family);
+}
+
+module_init(net_flow_nl_module_init);
+module_exit(net_flow_nl_module_fini);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("John Fastabend <john.r.fastabend@intel.com>");
+MODULE_DESCRIPTION("Netlink interface to Flow Tables (Net Flow Netlink)");
+MODULE_ALIAS_GENL_FAMILY(NFL_GENL_NAME);
Currently, we do not have an interface to query hardware and learn the capabilities of the device. This makes it very difficult to use hardware flow tables. At the moment the only interface we have to work with hardware flow tables is ethtool. This has many deficiencies, first its ioctl based making it difficult to use in systems that need to monitor interfaces because there is no support for multicast, notifiers, etc. The next big gap is it doesn't support querying devices for capabilities. The only way to learn hardware entries is by doing a "try and see" operation. An error perhaps indicating the device can not support your request but could be possibly for other reasons. Maybe a table is full for example. The existing flow interface only supports a single ingress table which is sufficient for some of the existing NIC host interfaces but limiting for more advanced NIC interfaces and switch devices. Also it is not extensible without recompiling both drivers and core interfaces. It may be possible to reprogram a device with additional header types, new protocols, whatever and it would be great if the flow table infrastructure can handle this. So this patch scraps the ethtool flow classifier interface and creates a new flow table interface. It is expected that device that support the existing ethtool interface today can support both interfaces without too much difficulty. I did a proof point on the ixgbe driver. Only choosing ixgbe because I have a 82599 10Gbps device in my development system. A more thorough implementation was done for the rocker switch showing how to use the interface. In this patch we create interfaces to get the headers a device supports, the actions it supports, a header graph showing the relationship between headers the device supports, the tables supported by the device and how they are connected. This patch _only_ provides the get routines in an attempt to make the patch sequence manageable. get_headers : report a set of headers/fields the device supports. These are specified as length/offsets so we can support standard protocols or vendor specific headers. This is more flexible then bitmasks of pre-defined packet types. In 'tc' for example I may use u32 to match on proprietary or vendor specific fields. A bitmask approach does not allow for this, but defining the fields as a set of offsets and lengths allows for this. A device that supports Openflow version 1.x for example could provide the set of field/offsets that are equivelent to the specification. One property of this type of interface is I don't have to rebuild my kernel/driver header interfaces, etc to support the latest and greatest trendy protocol foo. For some types of metadata the device understands we also use header fields to represent these. One example of this is we may have an ingress_port metadata field to report the port a packet was received on. At the moment we expect the metadata fields to be defined outside the interface. We can standardize on common ones such "ingress_port" across devices. Some examples of outside definitions specifying metadata might be OVS, internal definitions like skb->mark, or some FoRCES definitions. get_header_graph : Simply providing a header/field offset I support is not sufficient to learn how many nested 802.1Q tags I can support and other similar cases where the ordering of headers matters. So we use this operation to query the device for a header graph showing how the headers need to be related. With this operation and the 'get_headers' operation you can interrogate the driver with questions like "do you support Q'in'Q?", "how many VLAN tags can I nest before the parser breaks?", "Do you support MPLS?", "How about Foo Header in a VXLAN tunnel?". get_actions : Report a list of actions supported by the device along with the arguments they take. So "drop_packet" action takes no arguments and "set_field" action takes two arguments a field and value. This suffers again from being slightly opaque. Meaning if a device reports back action "foo_bar" with three arguments how do I as a consumer of this "know" what that action is? The easy thing to do is punt on it and say it should be described outside the driver somewhere. OVS for example defines a set of actions. If my FoRCeS quick read is correct they define actions using text in the messaging interface. A follow up patch series could use a description language to describe actions. Possibly using something from eBPF or nftables for example. This patch will not try to solve the isuse now and expect actions are defined outside the API or are well known. get_tables : Hardware may support one or more tables. Each table supports a set of matches and a set of actions. The match fields supported are defined above by the 'get_headers' operations. Similarly the actions supported are defined by the 'get_actions' operation. This allows the hardware to report several tables all with distinct capabilities. Tables also have table attributes used to describe features of the table. Because netlink messages are TLV based we can easily add new table attribues as needed. Currently a table has two attributes size and source. The size indicates how many "slots" are in the table for flow entries. One caveat here is a rule in the flow table may consume multiple slots in the table. We deal with this in a subsequent patch. The source field is used to indicate table boundaries where actions are applied. A table with the same source value will not "see" actions from tables with the same source. An example where this is relavent would be to have an action to re-write the destiniation IP address of a packet. If you have a match rule in a table with the same source that matches on the new IP address it will not be hit. However if it is in a table with a different source value _and_ in another table that gets applied the rule will be hit. See the next operatoin for querying table ordering. Some basic hardware may only support a single table which simplifies some things. But even the simple 10/40Gbps NICs support multiple tables and different tables depending on ingress/egress. get_table_graph : When a device supports multiple tables we need to identify how the tables are connected when each table is executed. To do this we provide a table graph which gives the pipeline of the device. The graph gives nodes representing each table and the edges indicate the criteria to progress to the next flow table. There are examples of this type of thing in both FoRCES and OVS. OVS prescribes a set of tables reachable with goto actions and FoRCES a slightly more flexible arrangement. In software tc's u32 classifier allows "linking" hash tables together. The OVS dataplane with the support of 'goto' action is completely connected. Without the 'goto' action the tables are progressed linearly. By querying the graph from hardware we can "learn" what table flows are supported and map them into software. We also provide a bit to indicate if the node is a root node of the ingress pipeline or egress pipeline. This is used on devices that have different pipelines for ingres and egress. This appears to be fairly common for devices. The realtek chip presented at LPC in Dusseldorf for example appeared to have a separate ingress/egress pipeline. With these five operations software can learn what types of fields the hardware flow table supports and how they are arranged. Subsequent patches will address programming the flow tables. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> --- include/linux/if_flow.h | 188 ++++++++ include/linux/netdevice.h | 38 ++ include/uapi/linux/if_flow.h | 389 +++++++++++++++++ net/Kconfig | 7 net/core/Makefile | 1 net/core/flow_table.c | 942 ++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 1565 insertions(+) create mode 100644 include/linux/if_flow.h create mode 100644 include/uapi/linux/if_flow.h create mode 100644 net/core/flow_table.c -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html