diff options
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt | 23 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/can/sun4i_can.txt | 36 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/cpsw.txt | 7 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/fsl-tsec-phy.txt | 4 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt | 4 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt | 49 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt | 22 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt | 47 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt | 20 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/renesas,ravb.txt | 69 | ||||
| -rw-r--r-- | Documentation/filesystems/nfs/nfsroot.txt | 3 | ||||
| -rw-r--r-- | Documentation/networking/ieee802154.txt | 8 | ||||
| -rw-r--r-- | Documentation/networking/ipvs-sysctl.txt | 10 | ||||
| -rw-r--r-- | Documentation/networking/l2tp.txt | 7 | ||||
| -rw-r--r-- | Documentation/networking/switchdev.txt | 58 | ||||
| -rw-r--r-- | Documentation/networking/vrf.txt | 301 |
16 files changed, 629 insertions, 39 deletions
diff --git a/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt new file mode 100644 index 000000000000..8ba9ed11d716 --- /dev/null +++ b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt @@ -0,0 +1,23 @@ +* Broadcom iProc MDIO bus controller + +Required properties: +- compatible: should be "brcm,iproc-mdio" +- reg: address and length of the register set for the MDIO interface +- #size-cells: must be 1 +- #address-cells: must be 0 + +Child nodes of this MDIO bus controller node are standard Ethernet PHY device +nodes as described in Documentation/devicetree/bindings/net/phy.txt + +Example: + +mdio@18002000 { + compatible = "brcm,iproc-mdio"; + reg = <0x18002000 0x8>; + #size-cells = <1>; + #address-cells = <0>; + + enet-gphy@0 { + reg = <0>; + }; +}; diff --git a/Documentation/devicetree/bindings/net/can/sun4i_can.txt b/Documentation/devicetree/bindings/net/can/sun4i_can.txt new file mode 100644 index 000000000000..84ed1909df76 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/sun4i_can.txt @@ -0,0 +1,36 @@ +Allwinner A10/A20 CAN controller Device Tree Bindings +----------------------------------------------------- + +Required properties: +- compatible: "allwinner,sun4i-a10-can" +- reg: physical base address and size of the Allwinner A10/A20 CAN register map. +- interrupts: interrupt specifier for the sole interrupt. +- clock: phandle and clock specifier. + +Example +------- + +SoC common .dtsi file: + + can0_pins_a: can0@0 { + allwinner,pins = "PH20","PH21"; + allwinner,function = "can"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; +... + can0: can@01c2bc00 { + compatible = "allwinner,sun4i-a10-can"; + reg = <0x01c2bc00 0x400>; + interrupts = <0 26 4>; + clocks = <&apb1_gates 4>; + status = "disabled"; + }; + +Board specific .dts file: + + can0: can@01c2bc00 { + pinctrl-names = "default"; + pinctrl-0 = <&can0_pins_a>; + status = "okay"; + }; diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index a9df21aaa154..676ecf62491d 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -30,6 +30,13 @@ Optional properties: - dual_emac : Specifies Switch to act as Dual EMAC - syscon : Phandle to the system control device node, which is the control module device of the am33x +- mode-gpios : Should be added if one/multiple gpio lines are + required to be driven so that cpsw data lines + can be connected to the phy via selective mux. + For example in dra72x-evm, pcf gpio has to be + driven low so that cpsw slave 0 and phy data + lines are connected via mux. + Slave Properties: Required properties: diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt index 1e97532a0b79..db74f0dc290c 100644 --- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt +++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt @@ -57,6 +57,10 @@ Properties: "rgmii-id", as all other connection types are detected by hardware. - fsl,magic-packet : If present, indicates that the hardware supports waking up via magic packet. + - fsl,wake-on-filer : If present, indicates that the hardware supports + waking up by Filer General Purpose Interrupt (FGPI) asserted on the + Rx int line. This is an advanced power management capability allowing + certain packet types (user) defined by filer rules to wake up the system. - bd-stash : If present, indicates that the hardware supports stashing buffer descriptors in the L2. - rx-stash-len : Denotes the number of bytes of a received buffer to stash diff --git a/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt b/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt index 988fc694b663..d1df8a00e1f3 100644 --- a/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt +++ b/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt @@ -32,13 +32,13 @@ Required properties: Required properties: -- compatible: should be "hisilicon,hip04-mdio". +- compatible: should be "hisilicon,mdio". - Inherits from MDIO bus node binding [2] [2] Documentation/devicetree/bindings/net/phy.txt Example: mdio { - compatible = "hisilicon,hip04-mdio"; + compatible = "hisilicon,mdio"; reg = <0x28f1000 0x1000>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt new file mode 100644 index 000000000000..80411b2f0490 --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt @@ -0,0 +1,49 @@ +Hisilicon DSA Fabric device controller + +Required properties: +- compatible: should be "hisilicon,hns-dsaf-v1" or "hisilicon,hns-dsaf-v2". + "hisilicon,hns-dsaf-v1" is for hip05. + "hisilicon,hns-dsaf-v2" is for Hi1610 and Hi1612. +- dsa-name: dsa fabric name who provide this interface. + should be "dsafX", X is the dsaf id. +- mode: dsa fabric mode string. only support one of dsaf modes like these: + "2port-64vf", + "6port-16rss", + "6port-16vf". +- interrupt-parent: the interrupt parent of this device. +- interrupts: should contain the DSA Fabric and rcb interrupt. +- reg: specifies base physical address(es) and size of the device registers. + The first region is external interface control register base and size. + The second region is SerDes base register and size. + The third region is the PPE register base and size. + The fourth region is dsa fabric base register and size. + The fifth region is cpld base register and size, it is not required if do not use cpld. +- phy-handle: phy handle of physicl port, 0 if not any phy device. see ethernet.txt [1]. +- buf-size: rx buffer size, should be 16-1024. +- desc-num: number of description in TX and RX queue, should be 512, 1024, 2048 or 4096. + +[1] Documentation/devicetree/bindings/net/phy.txt + +Example: + +dsa: dsa@c7000000 { + compatible = "hisilicon,hns-dsaf-v1"; + dsa_name = "dsaf0"; + mode = "6port-16rss"; + interrupt-parent = <&mbigen_dsa>; + reg = <0x0 0xC0000000 0x0 0x420000 + 0x0 0xC2000000 0x0 0x300000 + 0x0 0xc5000000 0x0 0x890000 + 0x0 0xc7000000 0x0 0x60000>; + phy-handle = <0 0 0 0 &soc0_phy4 &soc0_phy5 0 0>; + interrupts = <131 4>,<132 4>, <133 4>,<134 4>, + <135 4>,<136 4>, <137 4>,<138 4>, + <139 4>,<140 4>, <141 4>,<142 4>, + <143 4>,<144 4>, <145 4>,<146 4>, + <147 4>,<148 4>, <384 1>,<385 1>, + <386 1>,<387 1>, <388 1>,<389 1>, + <390 1>,<391 1>, + buf-size = <4096>; + desc-num = <1024>; + dma-coherent; +}; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt new file mode 100644 index 000000000000..9940aa02b8bd --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt @@ -0,0 +1,22 @@ +Hisilicon MDIO bus controller + +Properties: +- compatible: "hisilicon,mdio","hisilicon,hns-mdio". +- reg: The base address of the MDIO bus controller register bank. +- #address-cells: Must be <1>. +- #size-cells: Must be <0>. MDIO addresses have no size component. + +Typically an MDIO bus might have several children. + +Example: + mdio@803c0000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "hisilicon,mdio","hisilicon,hns-mdio"; + reg = <0x0 0x803c0000 0x0 0x10000>; + + ethernet-phy@0 { + ... + reg = <0>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt new file mode 100644 index 000000000000..41d19be7011e --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt @@ -0,0 +1,47 @@ +Hisilicon Network Subsystem NIC controller + +Required properties: +- compatible: "hisilicon,hns-nic-v1" or "hisilicon,hns-nic-v2". + "hisilicon,hns-nic-v1" is for hip05. + "hisilicon,hns-nic-v2" is for Hi1610 and Hi1612. +- ae-name: accelerator name who provides this interface, + is simply a name referring to the name of name in the accelerator node. +- port-id: is the index of port provided by DSAF (the accelerator). DSAF can + connect to 8 PHYs. Port 0 to 1 are both used for adminstration purpose. They + are called debug ports. + + The remaining 6 PHYs are taken according to the mode of DSAF. + + In NIC mode of DSAF, all 6 PHYs are taken as ethernet ports to the CPU. The + port-id can be 2 to 7. Here is the diagram: + +-----+---------------+ + | CPU | + +-+-+-+---+-+-+-+-+-+-+ + | | | | | | | | + debug service + port port + (0,1) (2-7) + + In Switch mode of DSAF, all 6 PHYs are taken as physical ports connect to a + LAN Switch while the CPU side assume itself have one single NIC connect to + this switch. In this case, the port-id will be 2 only. + +-----+---------------+ + | CPU | + +-+-+-+---+-+-+-+-+-+-+ + | | service| port(2) + debug +------------+ + port | switch | + (0,1) +-+-+-+-+-+-++ + | | | | | | + external port + +- local-mac-address: mac addr of the ethernet interface + +Example: + + ethernet@0{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <0>; + local-mac-address = [a2 14 e4 4b 56 76]; + }; diff --git a/Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt b/Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt new file mode 100644 index 000000000000..a4ed2efb5b73 --- /dev/null +++ b/Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt @@ -0,0 +1,20 @@ +* MRF24J40 IEEE 802.15.4 * + +Required properties: + - compatible: should be "microchip,mrf24j40", "microchip,mrf24j40ma", + or "microchip,mrf24j40mc" depends on your transceiver + board + - spi-max-frequency: maximal bus speed, should be set something under or equal + 10000000 + - reg: the chipselect index + - interrupts: the interrupt generated by the device. + +Example: + + mrf24j40ma@0 { + compatible = "microchip,mrf24j40ma"; + spi-max-frequency = <8500000>; + reg = <0>; + interrupts = <19 8>; + interrupt-parent = <&gpio3>; + }; diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index 1fd8831437bf..b486f3f5f6a3 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -6,8 +6,12 @@ interface contains. Required properties: - compatible: "renesas,etheravb-r8a7790" if the device is a part of R8A7790 SoC. "renesas,etheravb-r8a7794" if the device is a part of R8A7794 SoC. + "renesas,etheravb-r8a7795" if the device is a part of R8A7795 SoC. - reg: offset and length of (1) the register block and (2) the stream buffer. -- interrupts: interrupt specifier for the sole interrupt. +- interrupts: A list of interrupt-specifiers, one for each entry in + interrupt-names. + If interrupt-names is not present, an interrupt specifier + for a single muxed interrupt. - phy-mode: see ethernet.txt file in the same directory. - phy-handle: see ethernet.txt file in the same directory. - #address-cells: number of address cells for the MDIO bus, must be equal to 1. @@ -18,6 +22,12 @@ Required properties: Optional properties: - interrupt-parent: the phandle for the interrupt controller that services interrupts for this device. +- interrupt-names: A list of interrupt names. + For the R8A7795 SoC this property is mandatory; + it should include one entry per channel, named "ch%u", + where %u is the channel number ranging from 0 to 24. + For other SoCs this property is optional; if present + it should contain "mux" for a single muxed interrupt. - pinctrl-names: pin configuration state name ("default"). - renesas,no-ether-link: boolean, specify when a board does not provide a proper AVB_LINK signal. @@ -27,13 +37,46 @@ Optional properties: Example: ethernet@e6800000 { - compatible = "renesas,etheravb-r8a7790"; - reg = <0 0xe6800000 0 0x800>, <0 0xee0e8000 0 0x4000>; + compatible = "renesas,etheravb-r8a7795"; + reg = <0 0xe6800000 0 0x800>, <0 0xe6a00000 0 0x10000>; interrupt-parent = <&gic>; - interrupts = <0 163 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&mstp8_clks R8A7790_CLK_ETHERAVB>; - phy-mode = "rmii"; + interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "ch0", "ch1", "ch2", "ch3", + "ch4", "ch5", "ch6", "ch7", + "ch8", "ch9", "ch10", "ch11", + "ch12", "ch13", "ch14", "ch15", + "ch16", "ch17", "ch18", "ch19", + "ch20", "ch21", "ch22", "ch23", + "ch24"; + clocks = <&mstp8_clks R8A7795_CLK_ETHERAVB>; + power-domains = <&cpg_clocks>; + phy-mode = "rgmii-id"; phy-handle = <&phy0>; + pinctrl-0 = <ðer_pins>; pinctrl-names = "default"; renesas,no-ether-link; @@ -41,8 +84,20 @@ Example: #size-cells = <0>; phy0: ethernet-phy@0 { + rxc-skew-ps = <900>; + rxdv-skew-ps = <0>; + rxd0-skew-ps = <0>; + rxd1-skew-ps = <0>; + rxd2-skew-ps = <0>; + rxd3-skew-ps = <0>; + txc-skew-ps = <900>; + txen-skew-ps = <0>; + txd0-skew-ps = <0>; + txd1-skew-ps = <0>; + txd2-skew-ps = <0>; + txd3-skew-ps = <0>; reg = <0>; interrupt-parent = <&gpio2>; - interrupts = <15 IRQ_TYPE_LEVEL_LOW>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; }; }; diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt index 2d66ed688125..bb5ab6de5924 100644 --- a/Documentation/filesystems/nfs/nfsroot.txt +++ b/Documentation/filesystems/nfs/nfsroot.txt @@ -157,6 +157,9 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>: both: use both BOOTP and RARP but not DHCP (old option kept for backwards compatibility) + if dhcp is used, the client identifier can be used by following + format "ip=dhcp,client-id-type,client-id-value" + Default: any <dns0-ip> IP address of first nameserver. diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt index 1700756af057..aa69ccc481db 100644 --- a/Documentation/networking/ieee802154.txt +++ b/Documentation/networking/ieee802154.txt @@ -7,11 +7,11 @@ Introduction The IEEE 802.15.4 working group focuses on standardization of bottom two layers: Medium Access Control (MAC) and Physical (PHY). And there are mainly two options available for upper layers: - - ZigBee - proprietary protocol from ZigBee Alliance - - 6LowPAN - IPv6 networking over low rate personal area networks + - ZigBee - proprietary protocol from the ZigBee Alliance + - 6LoWPAN - IPv6 networking over low rate personal area networks -The Linux-ZigBee project goal is to provide complete implementation -of IEEE 802.15.4 and 6LoWPAN protocols. IEEE 802.15.4 is a stack +The linux-wpan project goal is to provide a complete implementation +of the IEEE 802.15.4 and 6LoWPAN protocols. IEEE 802.15.4 is a stack of protocols for organizing Low-Rate Wireless Personal Area Networks. The stack is composed of three main parts: diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index 3ba709531adb..e6b1c025fdd8 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -157,6 +157,16 @@ expire_quiescent_template - BOOLEAN persistence template if it is to be used to schedule a new connection and the destination server is quiescent. +ignore_tunneled - BOOLEAN + 0 - disabled (default) + not 0 - enabled + + If set, ipvs will set the ipvs_property on all packets which are of + unrecognized protocols. This prevents us from routing tunneled + protocols like ipip, which is useful to prevent rescheduling + packets that have been tunneled to the ipvs host (i.e. to prevent + ipvs routing loops when ipvs is also acting as a real server). + nat_icmp_send - BOOLEAN 0 - disabled (default) not 0 - enabled diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt index c74434de2fa5..4650a00ed012 100644 --- a/Documentation/networking/l2tp.txt +++ b/Documentation/networking/l2tp.txt @@ -213,15 +213,12 @@ To create an L2TPv3 ethernet pseudowire between local host 192.168.1.1 and peer 192.168.1.2, using IP addresses 10.5.1.1 and 10.5.1.2 for the tunnel endpoints:- -# modprobe l2tp_eth -# modprobe l2tp_netlink - # ip l2tp add tunnel tunnel_id 1 peer_tunnel_id 1 udp_sport 5000 \ udp_dport 5000 encap udp local 192.168.1.1 remote 192.168.1.2 # ip l2tp add session tunnel_id 1 session_id 1 peer_session_id 1 -# ifconfig -a +# ip -s -d show dev l2tpeth0 # ip addr add 10.5.1.2/32 peer 10.5.1.1/32 dev l2tpeth0 -# ifconfig l2tpeth0 up +# ip li set dev l2tpeth0 up Choose IP addresses to be the address of a local IP interface and that of the remote system. The IP addresses of the l2tpeth0 interface can be diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 476df0496686..0714fe555016 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -115,7 +115,7 @@ Switch ID ^^^^^^^^^ The switchdev driver must implement the switchdev op switchdev_port_attr_get -for SWITCHDEV_ATTR_PORT_PARENT_ID for each port netdev, returning the same +for SWITCHDEV_ATTR_ID_PORT_PARENT_ID for each port netdev, returning the same physical ID for each port of a switch. The ID must be unique between switches on the same system. The ID does not need to be unique between switches on different systems. @@ -178,7 +178,7 @@ entries are installed, for example, using iproute2 bridge cmd: bridge fdb add ADDR dev DEV [vlan VID] [self] The driver should use the helper switchdev_port_fdb_xxx ops for ndo_fdb_xxx -ops, and handle add/delete/dump of SWITCHDEV_OBJ_PORT_FDB object using +ops, and handle add/delete/dump of SWITCHDEV_OBJ_ID_PORT_FDB object using switchdev_port_obj_xxx ops. XXX: what should be done if offloading this rule to hardware fails (for @@ -233,26 +233,27 @@ the bridge's FDB. It's possible, but not optimal, to enable learning on the device port and on the bridge port, and disable learning_sync. To support learning and learning_sync port attributes, the driver implements -switchdev op switchdev_port_attr_get/set for SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS. -The driver should initialize the attributes to the hardware defaults. +switchdev op switchdev_port_attr_get/set for +SWITCHDEV_ATTR_PORT_ID_BRIDGE_FLAGS. The driver should initialize the attributes +to the hardware defaults. FDB Ageing ^^^^^^^^^^ -There are two FDB ageing models supported: 1) ageing by the device, and 2) -ageing by the kernel. Ageing by the device is preferred if many FDB entries -are supported. The driver calls call_switchdev_notifiers(SWITCHDEV_FDB_DEL, -...) to age out the FDB entry. In this model, ageing by the kernel should be -turned off. XXX: how to turn off ageing in kernel on a per-port basis or -otherwise prevent the kernel from ageing out the FDB entry? - -In the kernel ageing model, the standard bridge ageing mechanism is used to age -out stale FDB entries. To keep an FDB entry "alive", the driver should refresh -the FDB entry by calling call_switchdev_notifiers(SWITCHDEV_FDB_ADD, ...). The +The bridge will skip ageing FDB entries marked with NTF_EXT_LEARNED and it is +the responsibility of the port driver/device to age out these entries. If the +port device supports ageing, when the FDB entry expires, it will notify the +driver which in turn will notify the bridge with SWITCHDEV_FDB_DEL. If the +device does not support ageing, the driver can simulate ageing using a +garbage collection timer to monitor FBD entries. Expired entries will be +notified to the bridge using SWITCHDEV_FDB_DEL. See rocker driver for +example of driver running ageing timer. + +To keep an NTF_EXT_LEARNED entry "alive", the driver should refresh the FDB +entry by calling call_switchdev_notifiers(SWITCHDEV_FDB_ADD, ...). The notification will reset the FDB entry's last-used time to now. The driver should rate limit refresh notifications, for example, no more than once a -second. If the FDB entry expires, fdb_delete is called to remove entry from -the device. +second. (The last-used time is visible using the bridge -s fdb option). STP State Change on Port ^^^^^^^^^^^^^^^^^^^^^^^^ @@ -260,7 +261,7 @@ STP State Change on Port Internally or with a third-party STP protocol implementation (e.g. mstpd), the bridge driver maintains the STP state for ports, and will notify the switch driver of STP state change on a port using the switchdev op -switchdev_attr_port_set for SWITCHDEV_ATTR_PORT_STP_UPDATE. +switchdev_attr_port_set for SWITCHDEV_ATTR_PORT_ID_STP_UPDATE. State is one of BR_STATE_*. The switch driver can use STP state updates to update ingress packet filter list for the port. For example, if port is @@ -316,9 +317,9 @@ SWITCHDEV_OBJ_IPV[4|6]_FIB object using switchdev_port_obj_xxx ops. switchdev_port_obj_add is used for both adding a new FIB entry to the device, or modifying an existing entry on the device. -XXX: Currently, only SWITCHDEV_OBJ_IPV4_FIB objects are supported. +XXX: Currently, only SWITCHDEV_OBJ_ID_IPV4_FIB objects are supported. -SWITCHDEV_OBJ_IPV4_FIB object passes: +SWITCHDEV_OBJ_ID_IPV4_FIB object passes: struct switchdev_obj_ipv4_fib { /* IPV4_FIB */ u32 dst; @@ -369,3 +370,22 @@ The driver can monitor for updates to arp_tbl using the netevent notifier NETEVENT_NEIGH_UPDATE. The device can be programmed with resolved nexthops for the routes as arp_tbl updates. The driver implements ndo_neigh_destroy to know when arp_tbl neighbor entries are purged from the port. + +Transaction item queue +^^^^^^^^^^^^^^^^^^^^^^ + +For switchdev ops attr_set and obj_add, there is a 2 phase transaction model +used. First phase is to "prepare" anything needed, including various checks, +memory allocation, etc. The goal is to handle the stuff that is not unlikely +to fail here. The second phase is to "commit" the actual changes. + +Switchdev provides an inftrastructure for sharing items (for example memory +allocations) between the two phases. + +The object created by a driver in "prepare" phase and it is queued up by: +switchdev_trans_item_enqueue() +During the "commit" phase, the driver gets the object by: +switchdev_trans_item_dequeue() + +If a transaction is aborted during "prepare" phase, switchdev code will handle +cleanup of the queued-up objects. diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt index 031ef4a63485..d52aa10cfe91 100644 --- a/Documentation/networking/vrf.txt +++ b/Documentation/networking/vrf.txt @@ -90,7 +90,304 @@ or to specify the output device using cmsg and IP_PKTINFO. Limitations ----------- -VRF device currently only works for IPv4. Support for IPv6 is under development. - Index of original ingress interface is not available via cmsg. Will address soon. + +################################################################################ + +Using iproute2 for VRFs +======================= +VRF devices do *not* have to start with 'vrf-'. That is a convention used here +for emphasis of the device type, similar to use of 'br' in bridge names. + +1. Create a VRF + + To instantiate a VRF device and associate it with a table: + $ ip link add dev NAME type vrf table ID + + Remember to add the ip rules as well: + $ ip ru add oif NAME table 10 + $ ip ru add iif NAME table 10 + $ ip -6 ru add oif NAME table 10 + $ ip -6 ru add iif NAME table 10 + + Without the rules route lookups are not directed to the table. + + For example: + $ ip link add dev vrf-blue type vrf table 10 + $ ip ru add pref 200 oif vrf-blue table 10 + $ ip ru add pref 200 iif vrf-blue table 10 + $ ip -6 ru add pref 200 oif vrf-blue table 10 + $ ip -6 ru add pref 200 iif vrf-blue table 10 + + +2. List VRFs + + To list VRFs that have been created: + $ ip [-d] link show type vrf + NOTE: The -d option is needed to show the table id + + For example: + $ ip -d link show type vrf + 11: vrf-mgmt: <NOARP,MASTER,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether 72:b3:ba:91:e2:24 brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 1 addrgenmode eui64 + 12: vrf-red: <NOARP,MASTER,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether b6:6f:6e:f6:da:73 brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 10 addrgenmode eui64 + 13: vrf-blue: <NOARP,MASTER,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether 36:62:e8:7d:bb:8c brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 66 addrgenmode eui64 + 14: vrf-green: <NOARP,MASTER,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether e6:28:b8:63:70:bb brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 81 addrgenmode eui64 + + + Or in brief output: + + $ ip -br link show type vrf + vrf-mgmt UP 72:b3:ba:91:e2:24 <NOARP,MASTER,UP,LOWER_UP> + vrf-red UP b6:6f:6e:f6:da:73 <NOARP,MASTER,UP,LOWER_UP> + vrf-blue UP 36:62:e8:7d:bb:8c <NOARP,MASTER,UP,LOWER_UP> + vrf-green UP e6:28:b8:63:70:bb <NOARP,MASTER,UP,LOWER_UP> + + +3. Assign a Network Interface to a VRF + + Network interfaces are assigned to a VRF by enslaving the netdevice to a + VRF device: + $ ip link set dev NAME master VRF-NAME + + On enslavement connected and local routes are automatically moved to the + table associated with the VRF device. + + For example: + $ ip link set dev eth0 master vrf-mgmt + + +4. Show Devices Assigned to a VRF + + To show devices that have been assigned to a specific VRF add the master + option to the ip command: + $ ip link show master VRF-NAME + + For example: + $ ip link show master vrf-red + 3: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master vrf-red state UP mode DEFAULT group default qlen 1000 + link/ether 02:00:00:00:02:02 brd ff:ff:ff:ff:ff:ff + 4: eth2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master vrf-red state UP mode DEFAULT group default qlen 1000 + link/ether 02:00:00:00:02:03 brd ff:ff:ff:ff:ff:ff + 7: eth5: <BROADCAST,MULTICAST> mtu 1500 qdisc noop master vrf-red state DOWN mode DEFAULT group default qlen 1000 + link/ether 02:00:00:00:02:06 brd ff:ff:ff:ff:ff:ff + + + Or using the brief output: + $ ip -br link show master vrf-red + eth1 UP 02:00:00:00:02:02 <BROADCAST,MULTICAST,UP,LOWER_UP> + eth2 UP 02:00:00:00:02:03 <BROADCAST,MULTICAST,UP,LOWER_UP> + eth5 DOWN 02:00:00:00:02:06 <BROADCAST,MULTICAST> + + +5. Show Neighbor Entries for a VRF + + To list neighbor entries associated with devices enslaved to a VRF device + add the master option to the ip command: + $ ip [-6] neigh show master VRF-NAME + + For example: + $ ip neigh show master vrf-red + 10.2.1.254 dev eth1 lladdr a6:d9:c7:4f:06:23 REACHABLE + 10.2.2.254 dev eth2 lladdr 5e:54:01:6a:ee:80 REACHABLE + + $ ip -6 neigh show master vrf-red + 2002:1::64 dev eth1 lladdr a6:d9:c7:4f:06:23 REACHABLE + + +6. Show Addresses for a VRF + + To show addresses for interfaces associated with a VRF add the master + option to the ip command: + $ ip addr show master VRF-NAME + + For example: + $ ip addr show master vrf-red + 3: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master vrf-red state UP group default qlen 1000 + link/ether 02:00:00:00:02:02 brd ff:ff:ff:ff:ff:ff + inet 10.2.1.2/24 brd 10.2.1.255 scope global eth1 + valid_lft forever preferred_lft forever + inet6 2002:1::2/120 scope global + valid_lft forever preferred_lft forever + inet6 fe80::ff:fe00:202/64 scope link + valid_lft forever preferred_lft forever + 4: eth2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast master vrf-red state UP group default qlen 1000 + link/ether 02:00:00:00:02:03 brd ff:ff:ff:ff:ff:ff + inet 10.2.2.2/24 brd 10.2.2.255 scope global eth2 + valid_lft forever preferred_lft forever + inet6 2002:2::2/120 scope global + valid_lft forever preferred_lft forever + inet6 fe80::ff:fe00:203/64 scope link + valid_lft forever preferred_lft forever + 7: eth5: <BROADCAST,MULTICAST> mtu 1500 qdisc noop master vrf-red state DOWN group default qlen 1000 + link/ether 02:00:00:00:02:06 brd ff:ff:ff:ff:ff:ff + + Or in brief format: + $ ip -br addr show master vrf-red + eth1 UP 10.2.1.2/24 2002:1::2/120 fe80::ff:fe00:202/64 + eth2 UP 10.2.2.2/24 2002:2::2/120 fe80::ff:fe00:203/64 + eth5 DOWN + + +7. Show Routes for a VRF + + To show routes for a VRF use the ip command to display the table associated + with the VRF device: + $ ip [-6] route show table ID + + For example: + $ ip route show table vrf-red + prohibit default + broadcast 10.2.1.0 dev eth1 proto kernel scope link src 10.2.1.2 + 10.2.1.0/24 dev eth1 proto kernel scope link src 10.2.1.2 + local 10.2.1.2 dev eth1 proto kernel scope host src 10.2.1.2 + broadcast 10.2.1.255 dev eth1 proto kernel scope link src 10.2.1.2 + broadcast 10.2.2.0 dev eth2 proto kernel scope link src 10.2.2.2 + 10.2.2.0/24 dev eth2 proto kernel scope link src 10.2.2.2 + local 10.2.2.2 dev eth2 proto kernel scope host src 10.2.2.2 + broadcast 10.2.2.255 dev eth2 proto kernel scope link src 10.2.2.2 + + $ ip -6 route show table vrf-red + local 2002:1:: dev lo proto none metric 0 pref medium + local 2002:1::2 dev lo proto none metric 0 pref medium + 2002:1::/120 dev eth1 proto kernel metric 256 pref medium + local 2002:2:: dev lo proto none metric 0 pref medium + local 2002:2::2 dev lo proto none metric 0 pref medium + 2002:2::/120 dev eth2 proto kernel metric 256 pref medium + local fe80:: dev lo proto none metric 0 pref medium + local fe80:: dev lo proto none metric 0 pref medium + local fe80::ff:fe00:202 dev lo proto none metric 0 pref medium + local fe80::ff:fe00:203 dev lo proto none metric 0 pref medium + fe80::/64 dev eth1 proto kernel metric 256 pref medium + fe80::/64 dev eth2 proto kernel metric 256 pref medium + ff00::/8 dev vrf-red metric 256 pref medium + ff00::/8 dev eth1 metric 256 pref medium + ff00::/8 dev eth2 metric 256 pref medium + + +8. Route Lookup for a VRF + + A test route lookup can be done for a VRF by adding the oif option to ip: + $ ip [-6] route get oif VRF-NAME ADDRESS + + For example: + $ ip route get 10.2.1.40 oif vrf-red + 10.2.1.40 dev eth1 table vrf-red src 10.2.1.2 + cache + + $ ip -6 route get 2002:1::32 oif vrf-red + 2002:1::32 from :: dev eth1 table vrf-red proto kernel src 2002:1::2 metric 256 pref medium + + +9. Removing Network Interface from a VRF + + Network interfaces are removed from a VRF by breaking the enslavement to + the VRF device: + $ ip link set dev NAME nomaster + + Connected routes are moved back to the default table and local entries are + moved to the local table. + + For example: + $ ip link set dev eth0 nomaster + +-------------------------------------------------------------------------------- + +Commands used in this example: + +cat >> /etc/iproute2/rt_tables <<EOF +1 vrf-mgmt +10 vrf-red +66 vrf-blue +81 vrf-green +EOF + +function vrf_create +{ + VRF=$1 + TBID=$2 + # create VRF device + ip link add vrf-${VRF} type vrf table ${TBID} + + # add rules that direct lookups to vrf table + ip ru add pref 200 oif vrf-${VRF} table ${TBID} + ip ru add pref 200 iif vrf-${VRF} table ${TBID} + ip -6 ru add pref 200 oif vrf-${VRF} table ${TBID} + ip -6 ru add pref 200 iif vrf-${VRF} table ${TBID} + + if [ "${VRF}" != "mgmt" ]; then + ip route add table ${TBID} prohibit default + fi + ip link set dev vrf-${VRF} up + ip link set dev vrf-${VRF} state up +} + +vrf_create mgmt 1 +ip link set dev eth0 master vrf-mgmt + +vrf_create red 10 +ip link set dev eth1 master vrf-red +ip link set dev eth2 master vrf-red +ip link set dev eth5 master vrf-red + +vrf_create blue 66 +ip link set dev eth3 master vrf-blue + +vrf_create green 81 +ip link set dev eth4 master vrf-green + + +Interface addresses from /etc/network/interfaces: +auto eth0 +iface eth0 inet static + address 10.0.0.2 + netmask 255.255.255.0 + gateway 10.0.0.254 + +iface eth0 inet6 static + address 2000:1::2 + netmask 120 + +auto eth1 +iface eth1 inet static + address 10.2.1.2 + netmask 255.255.255.0 + +iface eth1 inet6 static + address 2002:1::2 + netmask 120 + +auto eth2 +iface eth2 inet static + address 10.2.2.2 + netmask 255.255.255.0 + +iface eth2 inet6 static + address 2002:2::2 + netmask 120 + +auto eth3 +iface eth3 inet static + address 10.2.3.2 + netmask 255.255.255.0 + +iface eth3 inet6 static + address 2002:3::2 + netmask 120 + +auto eth4 +iface eth4 inet static + address 10.2.4.2 + netmask 255.255.255.0 + +iface eth4 inet6 static + address 2002:4::2 + netmask 120 |