linux_dsm_epyc7002/include/uapi/linux/if_link.h

1034 lines
23 KiB
C
Raw Normal View History

License cleanup: add SPDX license identifier to uapi header files with no license Many user space API headers are missing licensing information, which makes it hard for compliance tools to determine the correct license. By default are files without license information under the default license of the kernel, which is GPLV2. Marking them GPLV2 would exclude them from being included in non GPLV2 code, which is obviously not intended. The user space API headers fall under the syscall exception which is in the kernels COPYING file: NOTE! This copyright does *not* cover user programs that use kernel services by normal system calls - this is merely considered normal use of the kernel, and does *not* fall under the heading of "derived work". otherwise syscall usage would not be possible. Update the files which contain no license information with an SPDX license identifier. The chosen identifier is 'GPL-2.0 WITH Linux-syscall-note' which is the officially assigned identifier for the Linux syscall exception. SPDX license identifiers are a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. See the previous patch in this series for the methodology of how this patch was researched. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 21:08:43 +07:00
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI_LINUX_IF_LINK_H
#define _UAPI_LINUX_IF_LINK_H
#include <linux/types.h>
#include <linux/netlink.h>
/* This struct should be in sync with struct rtnl_link_stats64 */
struct rtnl_link_stats {
__u32 rx_packets; /* total packets received */
__u32 tx_packets; /* total packets transmitted */
__u32 rx_bytes; /* total bytes received */
__u32 tx_bytes; /* total bytes transmitted */
__u32 rx_errors; /* bad packets received */
__u32 tx_errors; /* packet transmit problems */
__u32 rx_dropped; /* no space in linux buffers */
__u32 tx_dropped; /* no space available in linux */
__u32 multicast; /* multicast packets received */
__u32 collisions;
/* detailed rx_errors: */
__u32 rx_length_errors;
__u32 rx_over_errors; /* receiver ring buff overflow */
__u32 rx_crc_errors; /* recved pkt with crc error */
__u32 rx_frame_errors; /* recv'd frame alignment error */
__u32 rx_fifo_errors; /* recv'r fifo overrun */
__u32 rx_missed_errors; /* receiver missed packet */
/* detailed tx_errors */
__u32 tx_aborted_errors;
__u32 tx_carrier_errors;
__u32 tx_fifo_errors;
__u32 tx_heartbeat_errors;
__u32 tx_window_errors;
/* for cslip etc */
__u32 rx_compressed;
__u32 tx_compressed;
__u32 rx_nohandler; /* dropped, no handler found */
};
/* The main device statistics structure */
struct rtnl_link_stats64 {
__u64 rx_packets; /* total packets received */
__u64 tx_packets; /* total packets transmitted */
__u64 rx_bytes; /* total bytes received */
__u64 tx_bytes; /* total bytes transmitted */
__u64 rx_errors; /* bad packets received */
__u64 tx_errors; /* packet transmit problems */
__u64 rx_dropped; /* no space in linux buffers */
__u64 tx_dropped; /* no space available in linux */
__u64 multicast; /* multicast packets received */
__u64 collisions;
/* detailed rx_errors: */
__u64 rx_length_errors;
__u64 rx_over_errors; /* receiver ring buff overflow */
__u64 rx_crc_errors; /* recved pkt with crc error */
__u64 rx_frame_errors; /* recv'd frame alignment error */
__u64 rx_fifo_errors; /* recv'r fifo overrun */
__u64 rx_missed_errors; /* receiver missed packet */
/* detailed tx_errors */
__u64 tx_aborted_errors;
__u64 tx_carrier_errors;
__u64 tx_fifo_errors;
__u64 tx_heartbeat_errors;
__u64 tx_window_errors;
/* for cslip etc */
__u64 rx_compressed;
__u64 tx_compressed;
__u64 rx_nohandler; /* dropped, no handler found */
};
/* The struct should be in sync with struct ifmap */
struct rtnl_link_ifmap {
__u64 mem_start;
__u64 mem_end;
__u64 base_addr;
__u16 irq;
__u8 dma;
__u8 port;
};
/*
* IFLA_AF_SPEC
* Contains nested attributes for address family specific attributes.
* Each address family may create a attribute with the address family
* number as type and create its own attribute structure in it.
*
* Example:
* [IFLA_AF_SPEC] = {
* [AF_INET] = {
* [IFLA_INET_CONF] = ...,
* },
* [AF_INET6] = {
* [IFLA_INET6_FLAGS] = ...,
* [IFLA_INET6_CONF] = ...,
* }
* }
*/
enum {
IFLA_UNSPEC,
IFLA_ADDRESS,
IFLA_BROADCAST,
IFLA_IFNAME,
IFLA_MTU,
IFLA_LINK,
IFLA_QDISC,
IFLA_STATS,
IFLA_COST,
#define IFLA_COST IFLA_COST
IFLA_PRIORITY,
#define IFLA_PRIORITY IFLA_PRIORITY
IFLA_MASTER,
#define IFLA_MASTER IFLA_MASTER
IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */
#define IFLA_WIRELESS IFLA_WIRELESS
IFLA_PROTINFO, /* Protocol specific information for a link */
#define IFLA_PROTINFO IFLA_PROTINFO
IFLA_TXQLEN,
#define IFLA_TXQLEN IFLA_TXQLEN
IFLA_MAP,
#define IFLA_MAP IFLA_MAP
IFLA_WEIGHT,
#define IFLA_WEIGHT IFLA_WEIGHT
IFLA_OPERSTATE,
IFLA_LINKMODE,
IFLA_LINKINFO,
#define IFLA_LINKINFO IFLA_LINKINFO
IFLA_NET_NS_PID,
IFLA_IFALIAS,
IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */
IFLA_VFINFO_LIST,
IFLA_STATS64,
IFLA_VF_PORTS,
IFLA_PORT_SELF,
IFLA_AF_SPEC,
IFLA_GROUP, /* Group the device belongs to */
IFLA_NET_NS_FD,
IFLA_EXT_MASK, /* Extended info mask, VFs, etc */
IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */
#define IFLA_PROMISCUITY IFLA_PROMISCUITY
IFLA_NUM_TX_QUEUES,
IFLA_NUM_RX_QUEUES,
IFLA_CARRIER,
IFLA_PHYS_PORT_ID,
IFLA_CARRIER_CHANGES,
IFLA_PHYS_SWITCH_ID,
IFLA_LINK_NETNSID,
IFLA_PHYS_PORT_NAME,
IFLA_PROTO_DOWN,
IFLA_GSO_MAX_SEGS,
IFLA_GSO_MAX_SIZE,
IFLA_PAD,
IFLA_XDP,
IFLA_EVENT,
IFLA_NEW_NETNSID,
IFLA_IF_NETNSID,
IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */
IFLA_CARRIER_UP_COUNT,
IFLA_CARRIER_DOWN_COUNT,
IFLA_NEW_IFINDEX,
IFLA_MIN_MTU,
IFLA_MAX_MTU,
IFLA_PROP_LIST,
IFLA_ALT_IFNAME, /* Alternative ifname */
__IFLA_MAX
};
#define IFLA_MAX (__IFLA_MAX - 1)
/* backwards compatibility for userspace */
#ifndef __KERNEL__
#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg))
#endif
enum {
IFLA_INET_UNSPEC,
IFLA_INET_CONF,
__IFLA_INET_MAX,
};
#define IFLA_INET_MAX (__IFLA_INET_MAX - 1)
/* ifi_flags.
IFF_* flags.
The only change is:
IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are
more not changeable by user. They describe link media
characteristics and set by device driver.
Comments:
- Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid
- If neither of these three flags are set;
the interface is NBMA.
- IFF_MULTICAST does not mean anything special:
multicasts can be used on all not-NBMA links.
IFF_MULTICAST means that this media uses special encapsulation
for multicast frames. Apparently, all IFF_POINTOPOINT and
IFF_BROADCAST devices are able to use multicasts too.
*/
/* IFLA_LINK.
For usual devices it is equal ifi_index.
If it is a "virtual interface" (f.e. tunnel), ifi_link
can point to real physical interface (f.e. for bandwidth calculations),
or maybe 0, what means, that real media is unknown (usual
for IPIP tunnels, when route to endpoint is allowed to change)
*/
/* Subtype attributes for IFLA_PROTINFO */
enum {
IFLA_INET6_UNSPEC,
IFLA_INET6_FLAGS, /* link flags */
IFLA_INET6_CONF, /* sysctl parameters */
IFLA_INET6_STATS, /* statistics */
IFLA_INET6_MCAST, /* MC things. What of them? */
IFLA_INET6_CACHEINFO, /* time values and max reasm size */
IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */
net: ipv6: add tokenized interface identifier support This patch adds support for IPv6 tokenized IIDs, that allow for administrators to assign well-known host-part addresses to nodes whilst still obtaining global network prefix from Router Advertisements. It is currently in draft status. The primary target for such support is server platforms where addresses are usually manually configured, rather than using DHCPv6 or SLAAC. By using tokenised identifiers, hosts can still determine their network prefix by use of SLAAC, but more readily be automatically renumbered should their network prefix change. [...] The disadvantage with static addresses is that they are likely to require manual editing should the network prefix in use change. If instead there were a method to only manually configure the static identifier part of the IPv6 address, then the address could be automatically updated when a new prefix was introduced, as described in [RFC4192] for example. In such cases a DNS server might be configured with such a tokenised interface identifier of ::53, and SLAAC would use the token in constructing the interface address, using the advertised prefix. [...] http://tools.ietf.org/html/draft-chown-6man-tokenised-ipv6-identifiers-02 The implementation is partially based on top of Mark K. Thompson's proof of concept. However, it uses the Netlink interface for configuration resp. data retrival, so that it can be easily extended in future. Successfully tested by myself. Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Cc: Thomas Graf <tgraf@suug.ch> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-04-08 11:01:30 +07:00
IFLA_INET6_TOKEN, /* device token */
IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */
__IFLA_INET6_MAX
};
#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1)
enum in6_addr_gen_mode {
IN6_ADDR_GEN_MODE_EUI64,
IN6_ADDR_GEN_MODE_NONE,
ipv6: generation of stable privacy addresses for link-local and autoconf This patch implements the stable privacy address generation for link-local and autoconf addresses as specified in RFC7217. RID = F(Prefix, Net_Iface, Network_ID, DAD_Counter, secret_key) is the RID (random identifier). As the hash function F we chose one round of sha1. Prefix will be either the link-local prefix or the router advertised one. As Net_Iface we use the MAC address of the device. DAD_Counter and secret_key are implemented as specified. We don't use Network_ID, as it couples the code too closely to other subsystems. It is specified as optional in the RFC. As Net_Iface we only use the MAC address: we simply have no stable identifier in the kernel we could possibly use: because this code might run very early, we cannot depend on names, as they might be changed by user space early on during the boot process. A new address generation mode is introduced, IN6_ADDR_GEN_MODE_STABLE_PRIVACY. With iproute2 one can switch back to none or eui64 address configuration mode although the stable_secret is already set. We refuse writes to ipv6/conf/all/stable_secret but only allow ipv6/conf/default/stable_secret and the interface specific file to be written to. The default stable_secret is used as the parameter for the namespace, the interface specific can overwrite the secret, e.g. when switching a network configuration from one system to another while inheriting the secret. Cc: Erik Kline <ek@google.com> Cc: Fernando Gont <fgont@si6networks.com> Cc: Lorenzo Colitti <lorenzo@google.com> Cc: YOSHIFUJI Hideaki/吉藤英明 <hideaki.yoshifuji@miraclelinux.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-24 05:36:01 +07:00
IN6_ADDR_GEN_MODE_STABLE_PRIVACY,
IN6_ADDR_GEN_MODE_RANDOM,
};
/* Bridge section */
enum {
IFLA_BR_UNSPEC,
IFLA_BR_FORWARD_DELAY,
IFLA_BR_HELLO_TIME,
IFLA_BR_MAX_AGE,
IFLA_BR_AGEING_TIME,
IFLA_BR_STP_STATE,
IFLA_BR_PRIORITY,
IFLA_BR_VLAN_FILTERING,
IFLA_BR_VLAN_PROTOCOL,
IFLA_BR_GROUP_FWD_MASK,
IFLA_BR_ROOT_ID,
IFLA_BR_BRIDGE_ID,
IFLA_BR_ROOT_PORT,
IFLA_BR_ROOT_PATH_COST,
IFLA_BR_TOPOLOGY_CHANGE,
IFLA_BR_TOPOLOGY_CHANGE_DETECTED,
IFLA_BR_HELLO_TIMER,
IFLA_BR_TCN_TIMER,
IFLA_BR_TOPOLOGY_CHANGE_TIMER,
IFLA_BR_GC_TIMER,
IFLA_BR_GROUP_ADDR,
IFLA_BR_FDB_FLUSH,
IFLA_BR_MCAST_ROUTER,
IFLA_BR_MCAST_SNOOPING,
IFLA_BR_MCAST_QUERY_USE_IFADDR,
IFLA_BR_MCAST_QUERIER,
IFLA_BR_MCAST_HASH_ELASTICITY,
IFLA_BR_MCAST_HASH_MAX,
IFLA_BR_MCAST_LAST_MEMBER_CNT,
IFLA_BR_MCAST_STARTUP_QUERY_CNT,
IFLA_BR_MCAST_LAST_MEMBER_INTVL,
IFLA_BR_MCAST_MEMBERSHIP_INTVL,
IFLA_BR_MCAST_QUERIER_INTVL,
IFLA_BR_MCAST_QUERY_INTVL,
IFLA_BR_MCAST_QUERY_RESPONSE_INTVL,
IFLA_BR_MCAST_STARTUP_QUERY_INTVL,
IFLA_BR_NF_CALL_IPTABLES,
IFLA_BR_NF_CALL_IP6TABLES,
IFLA_BR_NF_CALL_ARPTABLES,
IFLA_BR_VLAN_DEFAULT_PVID,
IFLA_BR_PAD,
IFLA_BR_VLAN_STATS_ENABLED,
IFLA_BR_MCAST_STATS_ENABLED,
IFLA_BR_MCAST_IGMP_VERSION,
IFLA_BR_MCAST_MLD_VERSION,
IFLA_BR_VLAN_STATS_PER_PORT,
net: bridge: add support for user-controlled bool options We have been adding many new bridge options, a big number of which are boolean but still take up netlink attribute ids and waste space in the skb. Recently we discussed learning from link-local packets[1] and decided yet another new boolean option will be needed, thus introducing this API to save some bridge nl space. The API supports changing the value of multiple boolean options at once via the br_boolopt_multi struct which has an optmask (which options to set, bit per opt) and optval (options' new values). Future boolean options will only be added to the br_boolopt_id enum and then will have to be handled in br_boolopt_toggle/get. The API will automatically add the ability to change and export them via netlink, sysfs can use the single boolopt function versions to do the same. The behaviour with failing/succeeding is the same as with normal netlink option changing. If an option requires mapping to internal kernel flag or needs special configuration to be enabled then it should be handled in br_boolopt_toggle. It should also be able to retrieve an option's current state via br_boolopt_get. v2: WARN_ON() on unsupported option as that shouldn't be possible and also will help catch people who add new options without handling them for both set and get. Pass down extack so if an option desires it could set it on error and be more user-friendly. [1] https://www.spinics.net/lists/netdev/msg532698.html Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-24 09:34:20 +07:00
IFLA_BR_MULTI_BOOLOPT,
__IFLA_BR_MAX,
};
#define IFLA_BR_MAX (__IFLA_BR_MAX - 1)
struct ifla_bridge_id {
__u8 prio[2];
__u8 addr[6]; /* ETH_ALEN */
};
enum {
BRIDGE_MODE_UNSPEC,
BRIDGE_MODE_HAIRPIN,
};
enum {
IFLA_BRPORT_UNSPEC,
IFLA_BRPORT_STATE, /* Spanning tree state */
IFLA_BRPORT_PRIORITY, /* " priority */
IFLA_BRPORT_COST, /* " cost */
IFLA_BRPORT_MODE, /* mode (hairpin) */
IFLA_BRPORT_GUARD, /* bpdu guard */
IFLA_BRPORT_PROTECT, /* root port protection */
IFLA_BRPORT_FAST_LEAVE, /* multicast fast leave */
IFLA_BRPORT_LEARNING, /* mac learning */
IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */
IFLA_BRPORT_PROXYARP, /* proxy ARP */
IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */
IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */
IFLA_BRPORT_ROOT_ID, /* designated root */
IFLA_BRPORT_BRIDGE_ID, /* designated bridge */
IFLA_BRPORT_DESIGNATED_PORT,
IFLA_BRPORT_DESIGNATED_COST,
IFLA_BRPORT_ID,
IFLA_BRPORT_NO,
IFLA_BRPORT_TOPOLOGY_CHANGE_ACK,
IFLA_BRPORT_CONFIG_PENDING,
IFLA_BRPORT_MESSAGE_AGE_TIMER,
IFLA_BRPORT_FORWARD_DELAY_TIMER,
IFLA_BRPORT_HOLD_TIMER,
IFLA_BRPORT_FLUSH,
IFLA_BRPORT_MULTICAST_ROUTER,
IFLA_BRPORT_PAD,
IFLA_BRPORT_MCAST_FLOOD,
IFLA_BRPORT_MCAST_TO_UCAST,
IFLA_BRPORT_VLAN_TUNNEL,
IFLA_BRPORT_BCAST_FLOOD,
IFLA_BRPORT_GROUP_FWD_MASK,
IFLA_BRPORT_NEIGH_SUPPRESS,
IFLA_BRPORT_ISOLATED,
net: bridge: add support for backup port This patch adds a new port attribute - IFLA_BRPORT_BACKUP_PORT, which allows to set a backup port to be used for known unicast traffic if the port has gone carrier down. The backup pointer is rcu protected and set only under RTNL, a counter is maintained so when deleting a port we know how many other ports reference it as a backup and we remove it from all. Also the pointer is in the first cache line which is hot at the time of the check and thus in the common case we only add one more test. The backup port will be used only for the non-flooding case since it's a part of the bridge and the flooded packets will be forwarded to it anyway. To remove the forwarding just send a 0/non-existing backup port. This is used to avoid numerous scalability problems when using MLAG most notably if we have thousands of fdbs one would need to change all of them on port carrier going down which takes too long and causes a storm of fdb notifications (and again when the port comes back up). In a Multi-chassis Link Aggregation setup usually hosts are connected to two different switches which act as a single logical switch. Those switches usually have a control and backup link between them called peerlink which might be used for communication in case a host loses connectivity to one of them. We need a fast way to failover in case a host port goes down and currently none of the solutions (like bond) cannot fulfill the requirements because the participating ports are actually the "master" devices and must have the same peerlink as their backup interface and at the same time all of them must participate in the bridge device. As Roopa noted it's normal practice in routing called fast re-route where a precalculated backup path is used when the main one is down. Another use case of this is with EVPN, having a single vxlan device which is backup of every port. Due to the nature of master devices it's not currently possible to use one device as a backup for many and still have all of them participate in the bridge (which is master itself). More detailed information about MLAG is available at the link below. https://docs.cumulusnetworks.com/display/DOCS/Multi-Chassis+Link+Aggregation+-+MLAG Further explanation and a diagram by Roopa: Two switches acting in a MLAG pair are connected by the peerlink interface which is a bridge port. the config on one of the switches looks like the below. The other switch also has a similar config. eth0 is connected to one port on the server. And the server is connected to both switches. br0 -- team0---eth0 | -- switch-peerlink Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-23 15:16:59 +07:00
IFLA_BRPORT_BACKUP_PORT,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
struct ifla_cacheinfo {
__u32 max_reasm_len;
__u32 tstamp; /* ipv6InterfaceTable updated timestamp */
__u32 reachable_time;
__u32 retrans_time;
};
enum {
IFLA_INFO_UNSPEC,
IFLA_INFO_KIND,
IFLA_INFO_DATA,
IFLA_INFO_XSTATS,
IFLA_INFO_SLAVE_KIND,
IFLA_INFO_SLAVE_DATA,
__IFLA_INFO_MAX,
};
#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1)
/* VLAN section */
enum {
IFLA_VLAN_UNSPEC,
IFLA_VLAN_ID,
IFLA_VLAN_FLAGS,
IFLA_VLAN_EGRESS_QOS,
IFLA_VLAN_INGRESS_QOS,
IFLA_VLAN_PROTOCOL,
__IFLA_VLAN_MAX,
};
#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1)
struct ifla_vlan_flags {
__u32 flags;
__u32 mask;
};
enum {
IFLA_VLAN_QOS_UNSPEC,
IFLA_VLAN_QOS_MAPPING,
__IFLA_VLAN_QOS_MAX
};
#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1)
struct ifla_vlan_qos_mapping {
__u32 from;
__u32 to;
};
/* MACVLAN section */
enum {
IFLA_MACVLAN_UNSPEC,
IFLA_MACVLAN_MODE,
IFLA_MACVLAN_FLAGS,
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 21:31:08 +07:00
IFLA_MACVLAN_MACADDR_MODE,
IFLA_MACVLAN_MACADDR,
IFLA_MACVLAN_MACADDR_DATA,
IFLA_MACVLAN_MACADDR_COUNT,
__IFLA_MACVLAN_MAX,
};
#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1)
enum macvlan_mode {
MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */
MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */
MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */
MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */
macvlan: add source mode This patch adds a new mode of operation to macvlan, called "source". It allows one to set a list of allowed mac address, which is used to match against source mac address from received frames on underlying interface. This enables creating mac based VLAN associations, instead of standard port or tag based. The feature is useful to deploy 802.1x mac based behavior, where drivers of underlying interfaces doesn't allows that. Configuration is done through the netlink interface using e.g.: ip link add link eth0 name macvlan0 type macvlan mode source ip link add link eth0 name macvlan1 type macvlan mode source ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11 ip link set link dev macvlan0 type macvlan macaddr add 00:22:22:22:22:22 ip link set link dev macvlan0 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:33:33:33:33:33 ip link set link dev macvlan1 type macvlan macaddr add 00:44:44:44:44:44 This allows clients with MAC addresses 00:11:11:11:11:11, 00:22:22:22:22:22 to be part of only VLAN associated with macvlan0 interface. Clients with MAC addresses 00:44:44:44:44:44 with only VLAN associated with macvlan1 interface. And client with MAC address 00:33:33:33:33:33 to be associated with both VLANs. Based on work of Stefan Gula <steweg@gmail.com> v8: last version of Stefan Gula for Kernel 3.2.1 v9: rework onto linux-next 2014-03-12 by Michael Braun add MACADDR_SET command, enable to configure mac for source mode while creating interface v10: - reduce indention level - rename source_list to source_entry - use aligned 64bit ether address - use hash_64 instead of addr[5] v11: - rebase for 3.14 / linux-next 20.04.2014 v12 - rebase for linux-next 2014-09-25 Signed-off-by: Michael Braun <michael-dev@fami-braun.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-25 21:31:08 +07:00
MACVLAN_MODE_SOURCE = 16,/* use source MAC address list to assign */
};
enum macvlan_macaddr_mode {
MACVLAN_MACADDR_ADD,
MACVLAN_MACADDR_DEL,
MACVLAN_MACADDR_FLUSH,
MACVLAN_MACADDR_SET,
};
#define MACVLAN_FLAG_NOPROMISC 1
/* VRF section */
enum {
IFLA_VRF_UNSPEC,
IFLA_VRF_TABLE,
__IFLA_VRF_MAX
};
#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1)
enum {
IFLA_VRF_PORT_UNSPEC,
IFLA_VRF_PORT_TABLE,
__IFLA_VRF_PORT_MAX
};
#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1)
/* MACSEC section */
enum {
IFLA_MACSEC_UNSPEC,
IFLA_MACSEC_SCI,
IFLA_MACSEC_PORT,
IFLA_MACSEC_ICV_LEN,
IFLA_MACSEC_CIPHER_SUITE,
IFLA_MACSEC_WINDOW,
IFLA_MACSEC_ENCODING_SA,
IFLA_MACSEC_ENCRYPT,
IFLA_MACSEC_PROTECT,
IFLA_MACSEC_INC_SCI,
IFLA_MACSEC_ES,
IFLA_MACSEC_SCB,
IFLA_MACSEC_REPLAY_PROTECT,
IFLA_MACSEC_VALIDATION,
IFLA_MACSEC_PAD,
__IFLA_MACSEC_MAX,
};
#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
/* XFRM section */
enum {
IFLA_XFRM_UNSPEC,
IFLA_XFRM_LINK,
IFLA_XFRM_IF_ID,
__IFLA_XFRM_MAX
};
#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1)
enum macsec_validation_type {
MACSEC_VALIDATE_DISABLED = 0,
MACSEC_VALIDATE_CHECK = 1,
MACSEC_VALIDATE_STRICT = 2,
__MACSEC_VALIDATE_END,
MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1,
};
ipvlan: Initial check-in of the IPVLAN driver. This driver is very similar to the macvlan driver except that it uses L3 on the frame to determine the logical interface while functioning as packet dispatcher. It inherits L2 of the master device hence the packets on wire will have the same L2 for all the packets originating from all virtual devices off of the same master device. This driver was developed keeping the namespace use-case in mind. Hence most of the examples given here take that as the base setup where main-device belongs to the default-ns and virtual devices are assigned to the additional namespaces. The device operates in two different modes and the difference in these two modes in primarily in the TX side. (a) L2 mode : In this mode, the device behaves as a L2 device. TX processing upto L2 happens on the stack of the virtual device associated with (namespace). Packets are switched after that into the main device (default-ns) and queued for xmit. RX processing is simple and all multicast, broadcast (if applicable), and unicast belonging to the address(es) are delivered to the virtual devices. (b) L3 mode : In this mode, the device behaves like a L3 device. TX processing upto L3 happens on the stack of the virtual device associated with (namespace). Packets are switched to the main-device (default-ns) for the L2 processing. Hence the routing table of the default-ns will be used in this mode. RX processins is somewhat similar to the L2 mode except that in this mode only Unicast packets are delivered to the virtual device while main-dev will handle all other packets. The devices can be added using the "ip" command from the iproute2 package - ip link add link <master> <virtual> type ipvlan mode [ l2 | l3 ] Signed-off-by: Mahesh Bandewar <maheshb@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Maciej Żenczykowski <maze@google.com> Cc: Laurent Chavey <chavey@google.com> Cc: Tim Hockin <thockin@google.com> Cc: Brandon Philips <brandon.philips@coreos.com> Cc: Pavel Emelianov <xemul@parallels.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-24 14:07:46 +07:00
/* IPVLAN section */
enum {
IFLA_IPVLAN_UNSPEC,
IFLA_IPVLAN_MODE,
IFLA_IPVLAN_FLAGS,
ipvlan: Initial check-in of the IPVLAN driver. This driver is very similar to the macvlan driver except that it uses L3 on the frame to determine the logical interface while functioning as packet dispatcher. It inherits L2 of the master device hence the packets on wire will have the same L2 for all the packets originating from all virtual devices off of the same master device. This driver was developed keeping the namespace use-case in mind. Hence most of the examples given here take that as the base setup where main-device belongs to the default-ns and virtual devices are assigned to the additional namespaces. The device operates in two different modes and the difference in these two modes in primarily in the TX side. (a) L2 mode : In this mode, the device behaves as a L2 device. TX processing upto L2 happens on the stack of the virtual device associated with (namespace). Packets are switched after that into the main device (default-ns) and queued for xmit. RX processing is simple and all multicast, broadcast (if applicable), and unicast belonging to the address(es) are delivered to the virtual devices. (b) L3 mode : In this mode, the device behaves like a L3 device. TX processing upto L3 happens on the stack of the virtual device associated with (namespace). Packets are switched to the main-device (default-ns) for the L2 processing. Hence the routing table of the default-ns will be used in this mode. RX processins is somewhat similar to the L2 mode except that in this mode only Unicast packets are delivered to the virtual device while main-dev will handle all other packets. The devices can be added using the "ip" command from the iproute2 package - ip link add link <master> <virtual> type ipvlan mode [ l2 | l3 ] Signed-off-by: Mahesh Bandewar <maheshb@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Maciej Żenczykowski <maze@google.com> Cc: Laurent Chavey <chavey@google.com> Cc: Tim Hockin <thockin@google.com> Cc: Brandon Philips <brandon.philips@coreos.com> Cc: Pavel Emelianov <xemul@parallels.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-24 14:07:46 +07:00
__IFLA_IPVLAN_MAX
};
#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1)
enum ipvlan_mode {
IPVLAN_MODE_L2 = 0,
IPVLAN_MODE_L3,
IPVLAN_MODE_L3S,
ipvlan: Initial check-in of the IPVLAN driver. This driver is very similar to the macvlan driver except that it uses L3 on the frame to determine the logical interface while functioning as packet dispatcher. It inherits L2 of the master device hence the packets on wire will have the same L2 for all the packets originating from all virtual devices off of the same master device. This driver was developed keeping the namespace use-case in mind. Hence most of the examples given here take that as the base setup where main-device belongs to the default-ns and virtual devices are assigned to the additional namespaces. The device operates in two different modes and the difference in these two modes in primarily in the TX side. (a) L2 mode : In this mode, the device behaves as a L2 device. TX processing upto L2 happens on the stack of the virtual device associated with (namespace). Packets are switched after that into the main device (default-ns) and queued for xmit. RX processing is simple and all multicast, broadcast (if applicable), and unicast belonging to the address(es) are delivered to the virtual devices. (b) L3 mode : In this mode, the device behaves like a L3 device. TX processing upto L3 happens on the stack of the virtual device associated with (namespace). Packets are switched to the main-device (default-ns) for the L2 processing. Hence the routing table of the default-ns will be used in this mode. RX processins is somewhat similar to the L2 mode except that in this mode only Unicast packets are delivered to the virtual device while main-dev will handle all other packets. The devices can be added using the "ip" command from the iproute2 package - ip link add link <master> <virtual> type ipvlan mode [ l2 | l3 ] Signed-off-by: Mahesh Bandewar <maheshb@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Maciej Żenczykowski <maze@google.com> Cc: Laurent Chavey <chavey@google.com> Cc: Tim Hockin <thockin@google.com> Cc: Brandon Philips <brandon.philips@coreos.com> Cc: Pavel Emelianov <xemul@parallels.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-24 14:07:46 +07:00
IPVLAN_MODE_MAX
};
#define IPVLAN_F_PRIVATE 0x01
#define IPVLAN_F_VEPA 0x02
/* VXLAN section */
enum {
IFLA_VXLAN_UNSPEC,
IFLA_VXLAN_ID,
IFLA_VXLAN_GROUP, /* group or remote address */
IFLA_VXLAN_LINK,
IFLA_VXLAN_LOCAL,
IFLA_VXLAN_TTL,
IFLA_VXLAN_TOS,
IFLA_VXLAN_LEARNING,
IFLA_VXLAN_AGEING,
IFLA_VXLAN_LIMIT,
IFLA_VXLAN_PORT_RANGE, /* source port */
IFLA_VXLAN_PROXY,
IFLA_VXLAN_RSC,
IFLA_VXLAN_L2MISS,
IFLA_VXLAN_L3MISS,
IFLA_VXLAN_PORT, /* destination port */
IFLA_VXLAN_GROUP6,
IFLA_VXLAN_LOCAL6,
IFLA_VXLAN_UDP_CSUM,
IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
vxlan: Remote checksum offload Add support for remote checksum offload in VXLAN. This uses a reserved bit to indicate that RCO is being done, and uses the low order reserved eight bits of the VNI to hold the start and offset values in a compressed manner. Start is encoded in the low order seven bits of VNI. This is start >> 1 so that the checksum start offset is 0-254 using even values only. Checksum offset (transport checksum field) is indicated in the high order bit in the low order byte of the VNI. If the bit is set, the checksum field is for UDP (so offset = start + 6), else checksum field is for TCP (so offset = start + 16). Only TCP and UDP are supported in this implementation. Remote checksum offload for VXLAN is described in: https://tools.ietf.org/html/draft-herbert-vxlan-rco-00 Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4). With UDP checksums and Remote Checksum Offload IPv4 Client 11.84% CPU utilization Server 12.96% CPU utilization 9197 Mbps IPv6 Client 12.46% CPU utilization Server 14.48% CPU utilization 8963 Mbps With UDP checksums, no remote checksum offload IPv4 Client 15.67% CPU utilization Server 14.83% CPU utilization 9094 Mbps IPv6 Client 16.21% CPU utilization Server 14.32% CPU utilization 9058 Mbps No UDP checksums IPv4 Client 15.03% CPU utilization Server 23.09% CPU utilization 9089 Mbps IPv6 Client 16.18% CPU utilization Server 26.57% CPU utilization 8954 Mbps Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-13 08:00:38 +07:00
IFLA_VXLAN_REMCSUM_TX,
IFLA_VXLAN_REMCSUM_RX,
vxlan: Group Policy extension Implements supports for the Group Policy VXLAN extension [0] to provide a lightweight and simple security label mechanism across network peers based on VXLAN. The security context and associated metadata is mapped to/from skb->mark. This allows further mapping to a SELinux context using SECMARK, to implement ACLs directly with nftables, iptables, OVS, tc, etc. The group membership is defined by the lower 16 bits of skb->mark, the upper 16 bits are used for flags. SELinux allows to manage label to secure local resources. However, distributed applications require ACLs to implemented across hosts. This is typically achieved by matching on L2-L4 fields to identify the original sending host and process on the receiver. On top of that, netlabel and specifically CIPSO [1] allow to map security contexts to universal labels. However, netlabel and CIPSO are relatively complex. This patch provides a lightweight alternative for overlay network environments with a trusted underlay. No additional control protocol is required. Host 1: Host 2: Group A Group B Group B Group A +-----+ +-------------+ +-------+ +-----+ | lxc | | SELinux CTX | | httpd | | VM | +--+--+ +--+----------+ +---+---+ +--+--+ \---+---/ \----+---/ | | +---+---+ +---+---+ | vxlan | | vxlan | +---+---+ +---+---+ +------------------------------+ Backwards compatibility: A VXLAN-GBP socket can receive standard VXLAN frames and will assign the default group 0x0000 to such frames. A Linux VXLAN socket will drop VXLAN-GBP frames. The extension is therefore disabled by default and needs to be specifically enabled: ip link add [...] type vxlan [...] gbp In a mixed environment with VXLAN and VXLAN-GBP sockets, the GBP socket must run on a separate port number. Examples: iptables: host1# iptables -I OUTPUT -m owner --uid-owner 101 -j MARK --set-mark 0x200 host2# iptables -I INPUT -m mark --mark 0x200 -j DROP OVS: # ovs-ofctl add-flow br0 'in_port=1,actions=load:0x200->NXM_NX_TUN_GBP_ID[],NORMAL' # ovs-ofctl add-flow br0 'in_port=2,tun_gbp_id=0x200,actions=drop' [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy [1] http://lwn.net/Articles/204905/ Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-15 09:53:55 +07:00
IFLA_VXLAN_GBP,
IFLA_VXLAN_REMCSUM_NOPARTIAL,
IFLA_VXLAN_COLLECT_METADATA,
IFLA_VXLAN_LABEL,
IFLA_VXLAN_GPE,
IFLA_VXLAN_TTL_INHERIT,
IFLA_VXLAN_DF,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
struct ifla_vxlan_port_range {
__be16 low;
__be16 high;
};
enum ifla_vxlan_df {
VXLAN_DF_UNSET = 0,
VXLAN_DF_SET,
VXLAN_DF_INHERIT,
__VXLAN_DF_END,
VXLAN_DF_MAX = __VXLAN_DF_END - 1,
};
/* GENEVE section */
enum {
IFLA_GENEVE_UNSPEC,
IFLA_GENEVE_ID,
IFLA_GENEVE_REMOTE,
IFLA_GENEVE_TTL,
IFLA_GENEVE_TOS,
IFLA_GENEVE_PORT, /* destination port */
IFLA_GENEVE_COLLECT_METADATA,
IFLA_GENEVE_REMOTE6,
IFLA_GENEVE_UDP_CSUM,
IFLA_GENEVE_UDP_ZERO_CSUM6_TX,
IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
IFLA_GENEVE_LABEL,
IFLA_GENEVE_TTL_INHERIT,
IFLA_GENEVE_DF,
__IFLA_GENEVE_MAX
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
enum ifla_geneve_df {
GENEVE_DF_UNSET = 0,
GENEVE_DF_SET,
GENEVE_DF_INHERIT,
__GENEVE_DF_END,
GENEVE_DF_MAX = __GENEVE_DF_END - 1,
};
/* PPP section */
enum {
IFLA_PPP_UNSPEC,
IFLA_PPP_DEV_FD,
__IFLA_PPP_MAX
};
#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1)
/* GTP section */
enum ifla_gtp_role {
GTP_ROLE_GGSN = 0,
GTP_ROLE_SGSN,
};
enum {
IFLA_GTP_UNSPEC,
IFLA_GTP_FD0,
IFLA_GTP_FD1,
IFLA_GTP_PDP_HASHSIZE,
IFLA_GTP_ROLE,
__IFLA_GTP_MAX,
};
#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
/* Bonding section */
enum {
IFLA_BOND_UNSPEC,
IFLA_BOND_MODE,
IFLA_BOND_ACTIVE_SLAVE,
IFLA_BOND_MIIMON,
IFLA_BOND_UPDELAY,
IFLA_BOND_DOWNDELAY,
IFLA_BOND_USE_CARRIER,
IFLA_BOND_ARP_INTERVAL,
IFLA_BOND_ARP_IP_TARGET,
IFLA_BOND_ARP_VALIDATE,
IFLA_BOND_ARP_ALL_TARGETS,
IFLA_BOND_PRIMARY,
IFLA_BOND_PRIMARY_RESELECT,
IFLA_BOND_FAIL_OVER_MAC,
IFLA_BOND_XMIT_HASH_POLICY,
IFLA_BOND_RESEND_IGMP,
IFLA_BOND_NUM_PEER_NOTIF,
IFLA_BOND_ALL_SLAVES_ACTIVE,
IFLA_BOND_MIN_LINKS,
IFLA_BOND_LP_INTERVAL,
IFLA_BOND_PACKETS_PER_SLAVE,
IFLA_BOND_AD_LACP_RATE,
IFLA_BOND_AD_SELECT,
IFLA_BOND_AD_INFO,
IFLA_BOND_AD_ACTOR_SYS_PRIO,
IFLA_BOND_AD_USER_PORT_KEY,
IFLA_BOND_AD_ACTOR_SYSTEM,
IFLA_BOND_TLB_DYNAMIC_LB,
IFLA_BOND_PEER_NOTIF_DELAY,
__IFLA_BOND_MAX,
};
#define IFLA_BOND_MAX (__IFLA_BOND_MAX - 1)
enum {
IFLA_BOND_AD_INFO_UNSPEC,
IFLA_BOND_AD_INFO_AGGREGATOR,
IFLA_BOND_AD_INFO_NUM_PORTS,
IFLA_BOND_AD_INFO_ACTOR_KEY,
IFLA_BOND_AD_INFO_PARTNER_KEY,
IFLA_BOND_AD_INFO_PARTNER_MAC,
__IFLA_BOND_AD_INFO_MAX,
};
#define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1)
enum {
IFLA_BOND_SLAVE_UNSPEC,
IFLA_BOND_SLAVE_STATE,
IFLA_BOND_SLAVE_MII_STATUS,
IFLA_BOND_SLAVE_LINK_FAILURE_COUNT,
IFLA_BOND_SLAVE_PERM_HWADDR,
IFLA_BOND_SLAVE_QUEUE_ID,
IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
__IFLA_BOND_SLAVE_MAX,
};
#define IFLA_BOND_SLAVE_MAX (__IFLA_BOND_SLAVE_MAX - 1)
/* SR-IOV virtual function management section */
enum {
IFLA_VF_INFO_UNSPEC,
IFLA_VF_INFO,
__IFLA_VF_INFO_MAX,
};
#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1)
enum {
IFLA_VF_UNSPEC,
IFLA_VF_MAC, /* Hardware queue specific attributes */
IFLA_VF_VLAN, /* VLAN ID and QoS */
net-next:v4: Add support to configure SR-IOV VF minimum and maximum Tx rate through ip tool. o min_tx_rate puts lower limit on the VF bandwidth. VF is guaranteed to have a bandwidth of at least this value. max_tx_rate puts cap on the VF bandwidth. VF can have a bandwidth of up to this value. o A new handler set_vf_rate for attr IFLA_VF_RATE has been introduced which takes 4 arguments: netdev, VF number, min_tx_rate, max_tx_rate o ndo_set_vf_rate replaces ndo_set_vf_tx_rate handler. o Drivers that currently implement ndo_set_vf_tx_rate should now call ndo_set_vf_rate instead and reject attempt to set a minimum bandwidth greater than 0 for IFLA_VF_TX_RATE when IFLA_VF_RATE is not yet implemented by driver. o If user enters only one of either min_tx_rate or max_tx_rate, then, userland should read back the other value from driver and set both for IFLA_VF_RATE. Drivers that have not yet implemented IFLA_VF_RATE should always return min_tx_rate as 0 when read from ip tool. o If both IFLA_VF_TX_RATE and IFLA_VF_RATE options are specified, then IFLA_VF_RATE should override. o Idea is to have consistent display of rate values to user. o Usage example: - ./ip link set p4p1 vf 0 rate 900 ./ip link show p4p1 32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 900 (Mbps), max_tx_rate 900Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a ./ip link set p4p1 vf 0 max_tx_rate 300 min_tx_rate 200 ./ip link show p4p1 32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 300 (Mbps), max_tx_rate 300Mbps, min_tx_rate 200Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a ./ip link set p4p1 vf 0 max_tx_rate 600 rate 300 ./ip link show p4p1 32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5, tx rate 600 (Mbps), max_tx_rate 600Mbps, min_tx_rate 200Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a Signed-off-by: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-22 20:59:05 +07:00
IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */
IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */
IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */
net-next:v4: Add support to configure SR-IOV VF minimum and maximum Tx rate through ip tool. o min_tx_rate puts lower limit on the VF bandwidth. VF is guaranteed to have a bandwidth of at least this value. max_tx_rate puts cap on the VF bandwidth. VF can have a bandwidth of up to this value. o A new handler set_vf_rate for attr IFLA_VF_RATE has been introduced which takes 4 arguments: netdev, VF number, min_tx_rate, max_tx_rate o ndo_set_vf_rate replaces ndo_set_vf_tx_rate handler. o Drivers that currently implement ndo_set_vf_tx_rate should now call ndo_set_vf_rate instead and reject attempt to set a minimum bandwidth greater than 0 for IFLA_VF_TX_RATE when IFLA_VF_RATE is not yet implemented by driver. o If user enters only one of either min_tx_rate or max_tx_rate, then, userland should read back the other value from driver and set both for IFLA_VF_RATE. Drivers that have not yet implemented IFLA_VF_RATE should always return min_tx_rate as 0 when read from ip tool. o If both IFLA_VF_TX_RATE and IFLA_VF_RATE options are specified, then IFLA_VF_RATE should override. o Idea is to have consistent display of rate values to user. o Usage example: - ./ip link set p4p1 vf 0 rate 900 ./ip link show p4p1 32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 900 (Mbps), max_tx_rate 900Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a ./ip link set p4p1 vf 0 max_tx_rate 300 min_tx_rate 200 ./ip link show p4p1 32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 300 (Mbps), max_tx_rate 300Mbps, min_tx_rate 200Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a ./ip link set p4p1 vf 0 max_tx_rate 600 rate 300 ./ip link show p4p1 32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5, tx rate 600 (Mbps), max_tx_rate 600Mbps, min_tx_rate 200Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a Signed-off-by: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-22 20:59:05 +07:00
IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */
IFLA_VF_RSS_QUERY_EN, /* RSS Redirection Table and Hash Key query
* on/off switch
*/
IFLA_VF_STATS, /* network device statistics */
IFLA_VF_TRUST, /* Trust VF */
IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */
IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */
IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */
IFLA_VF_BROADCAST, /* VF broadcast */
__IFLA_VF_MAX,
};
#define IFLA_VF_MAX (__IFLA_VF_MAX - 1)
struct ifla_vf_mac {
__u32 vf;
__u8 mac[32]; /* MAX_ADDR_LEN */
};
struct ifla_vf_broadcast {
__u8 broadcast[32];
};
struct ifla_vf_vlan {
__u32 vf;
__u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
__u32 qos;
};
enum {
IFLA_VF_VLAN_INFO_UNSPEC,
IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */
__IFLA_VF_VLAN_INFO_MAX,
};
#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1)
#define MAX_VLAN_LIST_LEN 1
struct ifla_vf_vlan_info {
__u32 vf;
__u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
__u32 qos;
__be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */
};
struct ifla_vf_tx_rate {
__u32 vf;
__u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */
};
net-next:v4: Add support to configure SR-IOV VF minimum and maximum Tx rate through ip tool. o min_tx_rate puts lower limit on the VF bandwidth. VF is guaranteed to have a bandwidth of at least this value. max_tx_rate puts cap on the VF bandwidth. VF can have a bandwidth of up to this value. o A new handler set_vf_rate for attr IFLA_VF_RATE has been introduced which takes 4 arguments: netdev, VF number, min_tx_rate, max_tx_rate o ndo_set_vf_rate replaces ndo_set_vf_tx_rate handler. o Drivers that currently implement ndo_set_vf_tx_rate should now call ndo_set_vf_rate instead and reject attempt to set a minimum bandwidth greater than 0 for IFLA_VF_TX_RATE when IFLA_VF_RATE is not yet implemented by driver. o If user enters only one of either min_tx_rate or max_tx_rate, then, userland should read back the other value from driver and set both for IFLA_VF_RATE. Drivers that have not yet implemented IFLA_VF_RATE should always return min_tx_rate as 0 when read from ip tool. o If both IFLA_VF_TX_RATE and IFLA_VF_RATE options are specified, then IFLA_VF_RATE should override. o Idea is to have consistent display of rate values to user. o Usage example: - ./ip link set p4p1 vf 0 rate 900 ./ip link show p4p1 32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 900 (Mbps), max_tx_rate 900Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a ./ip link set p4p1 vf 0 max_tx_rate 300 min_tx_rate 200 ./ip link show p4p1 32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f0 brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5a, tx rate 300 (Mbps), max_tx_rate 300Mbps, min_tx_rate 200Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a ./ip link set p4p1 vf 0 max_tx_rate 600 rate 300 ./ip link show p4p1 32: p4p1: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT qlen 1000 link/ether 00:0e:1e:08:b0:f brd ff:ff:ff:ff:ff:ff vf 0 MAC 3e:a0:ca:bd:ae:5, tx rate 600 (Mbps), max_tx_rate 600Mbps, min_tx_rate 200Mbps vf 1 MAC f6:c6:7c:3f:3d:6c vf 2 MAC 56:32:43:98:d7:71 vf 3 MAC d6:be:c3:b5:85:ff vf 4 MAC ee:a9:9a:1e:19:14 vf 5 MAC 4a:d0:4c:07:52:18 vf 6 MAC 3a:76:44:93:62:f9 vf 7 MAC 82:e9:e7:e3:15:1a Signed-off-by: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-05-22 20:59:05 +07:00
struct ifla_vf_rate {
__u32 vf;
__u32 min_tx_rate; /* Min Bandwidth in Mbps */
__u32 max_tx_rate; /* Max Bandwidth in Mbps */
};
struct ifla_vf_spoofchk {
__u32 vf;
__u32 setting;
};
struct ifla_vf_guid {
__u32 vf;
__u64 guid;
};
enum {
IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */
IFLA_VF_LINK_STATE_ENABLE, /* link always up */
IFLA_VF_LINK_STATE_DISABLE, /* link always down */
__IFLA_VF_LINK_STATE_MAX,
};
struct ifla_vf_link_state {
__u32 vf;
__u32 link_state;
};
struct ifla_vf_rss_query_en {
__u32 vf;
__u32 setting;
};
enum {
IFLA_VF_STATS_RX_PACKETS,
IFLA_VF_STATS_TX_PACKETS,
IFLA_VF_STATS_RX_BYTES,
IFLA_VF_STATS_TX_BYTES,
IFLA_VF_STATS_BROADCAST,
IFLA_VF_STATS_MULTICAST,
IFLA_VF_STATS_PAD,
IFLA_VF_STATS_RX_DROPPED,
IFLA_VF_STATS_TX_DROPPED,
__IFLA_VF_STATS_MAX,
};
#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1)
struct ifla_vf_trust {
__u32 vf;
__u32 setting;
};
/* VF ports management section
*
* Nested layout of set/get msg is:
*
* [IFLA_NUM_VF]
* [IFLA_VF_PORTS]
* [IFLA_VF_PORT]
* [IFLA_PORT_*], ...
* [IFLA_VF_PORT]
* [IFLA_PORT_*], ...
* ...
* [IFLA_PORT_SELF]
* [IFLA_PORT_*], ...
*/
enum {
IFLA_VF_PORT_UNSPEC,
IFLA_VF_PORT, /* nest */
__IFLA_VF_PORT_MAX,
};
#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1)
enum {
IFLA_PORT_UNSPEC,
IFLA_PORT_VF, /* __u32 */
IFLA_PORT_PROFILE, /* string */
IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */
IFLA_PORT_INSTANCE_UUID, /* binary UUID */
IFLA_PORT_HOST_UUID, /* binary UUID */
IFLA_PORT_REQUEST, /* __u8 */
IFLA_PORT_RESPONSE, /* __u16, output only */
__IFLA_PORT_MAX,
};
#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1)
#define PORT_PROFILE_MAX 40
#define PORT_UUID_MAX 16
#define PORT_SELF_VF -1
enum {
PORT_REQUEST_PREASSOCIATE = 0,
PORT_REQUEST_PREASSOCIATE_RR,
PORT_REQUEST_ASSOCIATE,
PORT_REQUEST_DISASSOCIATE,
};
enum {
PORT_VDP_RESPONSE_SUCCESS = 0,
PORT_VDP_RESPONSE_INVALID_FORMAT,
PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES,
PORT_VDP_RESPONSE_UNUSED_VTID,
PORT_VDP_RESPONSE_VTID_VIOLATION,
PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION,
PORT_VDP_RESPONSE_OUT_OF_SYNC,
/* 0x08-0xFF reserved for future VDP use */
PORT_PROFILE_RESPONSE_SUCCESS = 0x100,
PORT_PROFILE_RESPONSE_INPROGRESS,
PORT_PROFILE_RESPONSE_INVALID,
PORT_PROFILE_RESPONSE_BADSTATE,
PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES,
PORT_PROFILE_RESPONSE_ERROR,
};
struct ifla_port_vsi {
__u8 vsi_mgr_id;
__u8 vsi_type_id[3];
__u8 vsi_type_version;
__u8 pad[3];
};
/* IPoIB section */
enum {
IFLA_IPOIB_UNSPEC,
IFLA_IPOIB_PKEY,
IFLA_IPOIB_MODE,
IFLA_IPOIB_UMCAST,
__IFLA_IPOIB_MAX
};
enum {
IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */
IPOIB_MODE_CONNECTED = 1, /* using connected QPs */
};
#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
/* HSR section */
enum {
IFLA_HSR_UNSPEC,
IFLA_HSR_SLAVE1,
IFLA_HSR_SLAVE2,
IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */
IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */
IFLA_HSR_SEQ_NR,
IFLA_HSR_VERSION, /* HSR version */
__IFLA_HSR_MAX,
};
#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1)
rtnetlink: add new RTM_GETSTATS message to dump link stats This patch adds a new RTM_GETSTATS message to query link stats via netlink from the kernel. RTM_NEWLINK also dumps stats today, but RTM_NEWLINK returns a lot more than just stats and is expensive in some cases when frequent polling for stats from userspace is a common operation. RTM_GETSTATS is an attempt to provide a light weight netlink message to explicity query only link stats from the kernel on an interface. The idea is to also keep it extensible so that new kinds of stats can be added to it in the future. This patch adds the following attribute for NETDEV stats: struct nla_policy ifla_stats_policy[IFLA_STATS_MAX + 1] = { [IFLA_STATS_LINK_64] = { .len = sizeof(struct rtnl_link_stats64) }, }; Like any other rtnetlink message, RTM_GETSTATS can be used to get stats of a single interface or all interfaces with NLM_F_DUMP. Future possible new types of stat attributes: link af stats: - IFLA_STATS_LINK_IPV6 (nested. for ipv6 stats) - IFLA_STATS_LINK_MPLS (nested. for mpls/mdev stats) extended stats: - IFLA_STATS_LINK_EXTENDED (nested. extended software netdev stats like bridge, vlan, vxlan etc) - IFLA_STATS_LINK_HW_EXTENDED (nested. extended hardware stats which are available via ethtool today) This patch also declares a filter mask for all stat attributes. User has to provide a mask of stats attributes to query. filter mask can be specified in the new hdr 'struct if_stats_msg' for stats messages. Other important field in the header is the ifindex. This api can also include attributes for global stats (eg tcp) in the future. When global stats are included in a stats msg, the ifindex in the header must be zero. A single stats message cannot contain both global and netdev specific stats. To easily distinguish them, netdev specific stat attributes name are prefixed with IFLA_STATS_LINK_ Without any attributes in the filter_mask, no stats will be returned. This patch has been tested with mofified iproute2 ifstat. Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-20 22:43:43 +07:00
/* STATS section */
struct if_stats_msg {
__u8 family;
__u8 pad1;
__u16 pad2;
__u32 ifindex;
__u32 filter_mask;
};
/* A stats attribute can be netdev specific or a global stat.
* For netdev stats, lets use the prefix IFLA_STATS_LINK_*
*/
enum {
IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */
IFLA_STATS_LINK_64,
IFLA_STATS_LINK_XSTATS,
IFLA_STATS_LINK_XSTATS_SLAVE,
IFLA_STATS_LINK_OFFLOAD_XSTATS,
IFLA_STATS_AF_SPEC,
rtnetlink: add new RTM_GETSTATS message to dump link stats This patch adds a new RTM_GETSTATS message to query link stats via netlink from the kernel. RTM_NEWLINK also dumps stats today, but RTM_NEWLINK returns a lot more than just stats and is expensive in some cases when frequent polling for stats from userspace is a common operation. RTM_GETSTATS is an attempt to provide a light weight netlink message to explicity query only link stats from the kernel on an interface. The idea is to also keep it extensible so that new kinds of stats can be added to it in the future. This patch adds the following attribute for NETDEV stats: struct nla_policy ifla_stats_policy[IFLA_STATS_MAX + 1] = { [IFLA_STATS_LINK_64] = { .len = sizeof(struct rtnl_link_stats64) }, }; Like any other rtnetlink message, RTM_GETSTATS can be used to get stats of a single interface or all interfaces with NLM_F_DUMP. Future possible new types of stat attributes: link af stats: - IFLA_STATS_LINK_IPV6 (nested. for ipv6 stats) - IFLA_STATS_LINK_MPLS (nested. for mpls/mdev stats) extended stats: - IFLA_STATS_LINK_EXTENDED (nested. extended software netdev stats like bridge, vlan, vxlan etc) - IFLA_STATS_LINK_HW_EXTENDED (nested. extended hardware stats which are available via ethtool today) This patch also declares a filter mask for all stat attributes. User has to provide a mask of stats attributes to query. filter mask can be specified in the new hdr 'struct if_stats_msg' for stats messages. Other important field in the header is the ifindex. This api can also include attributes for global stats (eg tcp) in the future. When global stats are included in a stats msg, the ifindex in the header must be zero. A single stats message cannot contain both global and netdev specific stats. To easily distinguish them, netdev specific stat attributes name are prefixed with IFLA_STATS_LINK_ Without any attributes in the filter_mask, no stats will be returned. This patch has been tested with mofified iproute2 ifstat. Suggested-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-20 22:43:43 +07:00
__IFLA_STATS_MAX,
};
#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1)
#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1))
/* These are embedded into IFLA_STATS_LINK_XSTATS:
* [IFLA_STATS_LINK_XSTATS]
* -> [LINK_XSTATS_TYPE_xxx]
* -> [rtnl link type specific attributes]
*/
enum {
LINK_XSTATS_TYPE_UNSPEC,
LINK_XSTATS_TYPE_BRIDGE,
LINK_XSTATS_TYPE_BOND,
__LINK_XSTATS_TYPE_MAX
};
#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1)
/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */
enum {
IFLA_OFFLOAD_XSTATS_UNSPEC,
IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */
__IFLA_OFFLOAD_XSTATS_MAX
};
#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1)
/* XDP section */
#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0)
#define XDP_FLAGS_SKB_MODE (1U << 1)
#define XDP_FLAGS_DRV_MODE (1U << 2)
#define XDP_FLAGS_HW_MODE (1U << 3)
#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \
XDP_FLAGS_DRV_MODE | \
XDP_FLAGS_HW_MODE)
net: Generic XDP This provides a generic SKB based non-optimized XDP path which is used if either the driver lacks a specific XDP implementation, or the user requests it via a new IFLA_XDP_FLAGS value named XDP_FLAGS_SKB_MODE. It is arguable that perhaps I should have required something like this as part of the initial XDP feature merge. I believe this is critical for two reasons: 1) Accessibility. More people can play with XDP with less dependencies. Yes I know we have XDP support in virtio_net, but that just creates another depedency for learning how to use this facility. I wrote this to make life easier for the XDP newbies. 2) As a model for what the expected semantics are. If there is a pure generic core implementation, it serves as a semantic example for driver folks adding XDP support. One thing I have not tried to address here is the issue of XDP_PACKET_HEADROOM, thanks to Daniel for spotting that. It seems incredibly expensive to do a skb_cow(skb, XDP_PACKET_HEADROOM) or whatever even if the XDP program doesn't try to push headers at all. I think we really need the verifier to somehow propagate whether certain XDP helpers are used or not. v5: - Handle both negative and positive offset after running prog - Fix mac length in XDP_TX case (Alexei) - Use rcu_dereference_protected() in free_netdev (kbuild test robot) v4: - Fix MAC header adjustmnet before calling prog (David Ahern) - Disable LRO when generic XDP is installed (Michael Chan) - Bypass qdisc et al. on XDP_TX and record the event (Alexei) - Do not perform generic XDP on reinjected packets (DaveM) v3: - Make sure XDP program sees packet at MAC header, push back MAC header if we do XDP_TX. (Alexei) - Elide GRO when generic XDP is in use. (Alexei) - Add XDP_FLAG_SKB_MODE flag which the user can use to request generic XDP even if the driver has an XDP implementation. (Alexei) - Report whether SKB mode is in use in rtnl_xdp_fill() via XDP_FLAGS attribute. (Daniel) v2: - Add some "fall through" comments in switch statements based upon feedback from Andrew Lunn - Use RCU for generic xdp_prog, thanks to Johannes Berg. Tested-by: Andy Gospodarek <andy@greyhouse.net> Tested-by: Jesper Dangaard Brouer <brouer@redhat.com> Tested-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-19 02:36:58 +07:00
#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \
XDP_FLAGS_MODES)
xdp: refine xdp api with regards to generic xdp While working on the iproute2 generic XDP frontend, I noticed that as of right now it's possible to have native *and* generic XDP programs loaded both at the same time for the case when a driver supports native XDP. The intended model for generic XDP from b5cdae3291f7 ("net: Generic XDP") is, however, that only one out of the two can be present at once which is also indicated as such in the XDP netlink dump part. The main rationale for generic XDP is to ease accessibility (in case a driver does not yet have XDP support) and to generically provide a semantical model as an example for driver developers wanting to add XDP support. The generic XDP option for an XDP aware driver can still be useful for comparing and testing both implementations. However, it is not intended to have a second XDP processing stage or layer with exactly the same functionality of the first native stage. Only reason could be to have a partial fallback for future XDP features that are not supported yet in the native implementation and we probably also shouldn't strive for such fallback and instead encourage native feature support in the first place. Given there's currently no such fallback issue or use case, lets not go there yet if we don't need to. Therefore, change semantics for loading XDP and bail out if the user tries to load a generic XDP program when a native one is present and vice versa. Another alternative to bailing out would be to handle the transition from one flavor to another gracefully, but that would require to bring the device down, exchange both types of programs, and bring it up again in order to avoid a tiny window where a packet could hit both hooks. Given this complicates the logic for just a debugging feature in the native case, I went with the simpler variant. For the dump, remove IFLA_XDP_FLAGS that was added with b5cdae3291f7 and reuse IFLA_XDP_ATTACHED for indicating the mode. Dumping all or just a subset of flags that were used for loading the XDP prog is suboptimal in the long run since not all flags are useful for dumping and if we start to reuse the same flag definitions for load and dump, then we'll waste bit space. What we really just want is to dump the mode for now. Current IFLA_XDP_ATTACHED semantics are: nothing was installed (0), a program is running at the native driver layer (1). Thus, add a mode that says that a program is running at generic XDP layer (2). Applications will handle this fine in that older binaries will just indicate that something is attached at XDP layer, effectively this is similar to IFLA_XDP_FLAGS attr that we would have had modulo the redundancy. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-12 06:04:46 +07:00
/* These are stored into IFLA_XDP_ATTACHED on dump. */
enum {
XDP_ATTACHED_NONE = 0,
XDP_ATTACHED_DRV,
XDP_ATTACHED_SKB,
XDP_ATTACHED_HW,
XDP_ATTACHED_MULTI,
xdp: refine xdp api with regards to generic xdp While working on the iproute2 generic XDP frontend, I noticed that as of right now it's possible to have native *and* generic XDP programs loaded both at the same time for the case when a driver supports native XDP. The intended model for generic XDP from b5cdae3291f7 ("net: Generic XDP") is, however, that only one out of the two can be present at once which is also indicated as such in the XDP netlink dump part. The main rationale for generic XDP is to ease accessibility (in case a driver does not yet have XDP support) and to generically provide a semantical model as an example for driver developers wanting to add XDP support. The generic XDP option for an XDP aware driver can still be useful for comparing and testing both implementations. However, it is not intended to have a second XDP processing stage or layer with exactly the same functionality of the first native stage. Only reason could be to have a partial fallback for future XDP features that are not supported yet in the native implementation and we probably also shouldn't strive for such fallback and instead encourage native feature support in the first place. Given there's currently no such fallback issue or use case, lets not go there yet if we don't need to. Therefore, change semantics for loading XDP and bail out if the user tries to load a generic XDP program when a native one is present and vice versa. Another alternative to bailing out would be to handle the transition from one flavor to another gracefully, but that would require to bring the device down, exchange both types of programs, and bring it up again in order to avoid a tiny window where a packet could hit both hooks. Given this complicates the logic for just a debugging feature in the native case, I went with the simpler variant. For the dump, remove IFLA_XDP_FLAGS that was added with b5cdae3291f7 and reuse IFLA_XDP_ATTACHED for indicating the mode. Dumping all or just a subset of flags that were used for loading the XDP prog is suboptimal in the long run since not all flags are useful for dumping and if we start to reuse the same flag definitions for load and dump, then we'll waste bit space. What we really just want is to dump the mode for now. Current IFLA_XDP_ATTACHED semantics are: nothing was installed (0), a program is running at the native driver layer (1). Thus, add a mode that says that a program is running at generic XDP layer (2). Applications will handle this fine in that older binaries will just indicate that something is attached at XDP layer, effectively this is similar to IFLA_XDP_FLAGS attr that we would have had modulo the redundancy. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-12 06:04:46 +07:00
};
enum {
IFLA_XDP_UNSPEC,
IFLA_XDP_FD,
IFLA_XDP_ATTACHED,
IFLA_XDP_FLAGS,
IFLA_XDP_PROG_ID,
IFLA_XDP_DRV_PROG_ID,
IFLA_XDP_SKB_PROG_ID,
IFLA_XDP_HW_PROG_ID,
__IFLA_XDP_MAX,
};
#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1)
enum {
IFLA_EVENT_NONE,
IFLA_EVENT_REBOOT, /* internal reset / reboot */
IFLA_EVENT_FEATURES, /* change in offload features */
IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */
IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */
IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */
IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */
};
/* tun section */
enum {
IFLA_TUN_UNSPEC,
IFLA_TUN_OWNER,
IFLA_TUN_GROUP,
IFLA_TUN_TYPE,
IFLA_TUN_PI,
IFLA_TUN_VNET_HDR,
IFLA_TUN_PERSIST,
IFLA_TUN_MULTI_QUEUE,
IFLA_TUN_NUM_QUEUES,
IFLA_TUN_NUM_DISABLED_QUEUES,
__IFLA_TUN_MAX,
};
#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1)
/* rmnet section */
#define RMNET_FLAGS_INGRESS_DEAGGREGATION (1U << 0)
#define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1)
#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2)
#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3)
enum {
IFLA_RMNET_UNSPEC,
IFLA_RMNET_MUX_ID,
IFLA_RMNET_FLAGS,
__IFLA_RMNET_MAX,
};
#define IFLA_RMNET_MAX (__IFLA_RMNET_MAX - 1)
struct ifla_rmnet_flags {
__u32 flags;
__u32 mask;
};
#endif /* _UAPI_LINUX_IF_LINK_H */