diff options
Diffstat (limited to '')
32 files changed, 998 insertions, 479 deletions
diff --git a/Documentation/networking/device_drivers/appletalk/cops.rst b/Documentation/networking/device_drivers/appletalk/cops.rst deleted file mode 100644 index 964ba80599..0000000000 --- a/Documentation/networking/device_drivers/appletalk/cops.rst +++ /dev/null @@ -1,80 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -======================================== -The COPS LocalTalk Linux driver (cops.c) -======================================== - -By Jay Schulist <jschlst@samba.org> - -This driver has two modes and they are: Dayna mode and Tangent mode. -Each mode corresponds with the type of card. It has been found -that there are 2 main types of cards and all other cards are -the same and just have different names or only have minor differences -such as more IO ports. As this driver is tested it will -become more clear exactly what cards are supported. - -Right now these cards are known to work with the COPS driver. The -LT-200 cards work in a somewhat more limited capacity than the -DL200 cards, which work very well and are in use by many people. - -TANGENT driver mode: - - Tangent ATB-II, Novell NL-1000, Daystar Digital LT-200 - -DAYNA driver mode: - - Dayna DL2000/DaynaTalk PC (Half Length), COPS LT-95, - - Farallon PhoneNET PC III, Farallon PhoneNET PC II - -Other cards possibly supported mode unknown though: - - Dayna DL2000 (Full length) - -The COPS driver defaults to using Dayna mode. To change the driver's -mode if you built a driver with dual support use board_type=1 or -board_type=2 for Dayna or Tangent with insmod. - -Operation/loading of the driver -=============================== - -Use modprobe like this: /sbin/modprobe cops.o (IO #) (IRQ #) -If you do not specify any options the driver will try and use the IO = 0x240, -IRQ = 5. As of right now I would only use IRQ 5 for the card, if autoprobing. - -To load multiple COPS driver Localtalk cards you can do one of the following:: - - insmod cops io=0x240 irq=5 - insmod -o cops2 cops io=0x260 irq=3 - -Or in lilo.conf put something like this:: - - append="ether=5,0x240,lt0 ether=3,0x260,lt1" - -Then bring up the interface with ifconfig. It will look something like this:: - - lt0 Link encap:UNSPEC HWaddr 00-00-00-00-00-00-00-F7-00-00-00-00-00-00-00-00 - inet addr:192.168.1.2 Bcast:192.168.1.255 Mask:255.255.255.0 - UP BROADCAST RUNNING NOARP MULTICAST MTU:600 Metric:1 - RX packets:0 errors:0 dropped:0 overruns:0 frame:0 - TX packets:0 errors:0 dropped:0 overruns:0 carrier:0 coll:0 - -Netatalk Configuration -====================== - -You will need to configure atalkd with something like the following to make -it work with the cops.c driver. - -* For single LTalk card use:: - - dummy -seed -phase 2 -net 2000 -addr 2000.10 -zone "1033" - lt0 -seed -phase 1 -net 1000 -addr 1000.50 -zone "1033" - -* For multiple cards, Ethernet and LocalTalk:: - - eth0 -seed -phase 2 -net 3000 -addr 3000.20 -zone "1033" - lt0 -seed -phase 1 -net 1000 -addr 1000.50 -zone "1033" - -* For multiple LocalTalk cards, and an Ethernet card. - -* Order seems to matter here, Ethernet last:: - - lt0 -seed -phase 1 -net 1000 -addr 1000.10 -zone "LocalTalk1" - lt1 -seed -phase 1 -net 2000 -addr 2000.20 -zone "LocalTalk2" - eth0 -seed -phase 2 -net 3000 -addr 3000.30 -zone "EtherTalk" diff --git a/Documentation/networking/device_drivers/appletalk/index.rst b/Documentation/networking/device_drivers/appletalk/index.rst deleted file mode 100644 index c196baeb08..0000000000 --- a/Documentation/networking/device_drivers/appletalk/index.rst +++ /dev/null @@ -1,18 +0,0 @@ -.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) - -AppleTalk Device Drivers -======================== - -Contents: - -.. toctree:: - :maxdepth: 2 - - cops - -.. only:: subproject and html - - Indices - ======= - - * :ref:`genindex` diff --git a/Documentation/networking/device_drivers/ethernet/index.rst b/Documentation/networking/device_drivers/ethernet/index.rst index 9827e81608..43de285b8a 100644 --- a/Documentation/networking/device_drivers/ethernet/index.rst +++ b/Documentation/networking/device_drivers/ethernet/index.rst @@ -32,6 +32,7 @@ Contents: intel/e1000 intel/e1000e intel/fm10k + intel/idpf intel/igb intel/igbvf intel/ixgbe diff --git a/Documentation/networking/device_drivers/ethernet/intel/idpf.rst b/Documentation/networking/device_drivers/ethernet/intel/idpf.rst new file mode 100644 index 0000000000..adb16e2abd --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/intel/idpf.rst @@ -0,0 +1,160 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +========================================================================== +idpf Linux* Base Driver for the Intel(R) Infrastructure Data Path Function +========================================================================== + +Intel idpf Linux driver. +Copyright(C) 2023 Intel Corporation. + +.. contents:: + +The idpf driver serves as both the Physical Function (PF) and Virtual Function +(VF) driver for the Intel(R) Infrastructure Data Path Function. + +Driver information can be obtained using ethtool, lspci, and ip. + +For questions related to hardware requirements, refer to the documentation +supplied with your Intel adapter. All hardware requirements listed apply to use +with Linux. + + +Identifying Your Adapter +======================== +For information on how to identify your adapter, and for the latest Intel +network drivers, refer to the Intel Support website: +http://www.intel.com/support + + +Additional Features and Configurations +====================================== + +ethtool +------- +The driver utilizes the ethtool interface for driver configuration and +diagnostics, as well as displaying statistical information. The latest ethtool +version is required for this functionality. If you don't have one yet, you can +obtain it at: +https://kernel.org/pub/software/network/ethtool/ + + +Viewing Link Messages +--------------------- +Link messages will not be displayed to the console if the distribution is +restricting system messages. In order to see network driver link messages on +your console, set dmesg to eight by entering the following:: + + # dmesg -n 8 + +.. note:: + This setting is not saved across reboots. + + +Jumbo Frames +------------ +Jumbo Frames support is enabled by changing the Maximum Transmission Unit (MTU) +to a value larger than the default value of 1500. + +Use the ip command to increase the MTU size. For example, enter the following +where <ethX> is the interface number:: + + # ip link set mtu 9000 dev <ethX> + # ip link set up dev <ethX> + +.. note:: + The maximum MTU setting for jumbo frames is 9706. This corresponds to the + maximum jumbo frame size of 9728 bytes. + +.. note:: + This driver will attempt to use multiple page sized buffers to receive + each jumbo packet. This should help to avoid buffer starvation issues when + allocating receive packets. + +.. note:: + Packet loss may have a greater impact on throughput when you use jumbo + frames. If you observe a drop in performance after enabling jumbo frames, + enabling flow control may mitigate the issue. + + +Performance Optimization +======================== +Driver defaults are meant to fit a wide variety of workloads, but if further +optimization is required, we recommend experimenting with the following +settings. + + +Interrupt Rate Limiting +----------------------- +This driver supports an adaptive interrupt throttle rate (ITR) mechanism that +is tuned for general workloads. The user can customize the interrupt rate +control for specific workloads, via ethtool, adjusting the number of +microseconds between interrupts. + +To set the interrupt rate manually, you must disable adaptive mode:: + + # ethtool -C <ethX> adaptive-rx off adaptive-tx off + +For lower CPU utilization: + - Disable adaptive ITR and lower Rx and Tx interrupts. The examples below + affect every queue of the specified interface. + + - Setting rx-usecs and tx-usecs to 80 will limit interrupts to about + 12,500 interrupts per second per queue:: + + # ethtool -C <ethX> adaptive-rx off adaptive-tx off rx-usecs 80 + tx-usecs 80 + +For reduced latency: + - Disable adaptive ITR and ITR by setting rx-usecs and tx-usecs to 0 + using ethtool:: + + # ethtool -C <ethX> adaptive-rx off adaptive-tx off rx-usecs 0 + tx-usecs 0 + +Per-queue interrupt rate settings: + - The following examples are for queues 1 and 3, but you can adjust other + queues. + + - To disable Rx adaptive ITR and set static Rx ITR to 10 microseconds or + about 100,000 interrupts/second, for queues 1 and 3:: + + # ethtool --per-queue <ethX> queue_mask 0xa --coalesce adaptive-rx off + rx-usecs 10 + + - To show the current coalesce settings for queues 1 and 3:: + + # ethtool --per-queue <ethX> queue_mask 0xa --show-coalesce + + + +Virtualized Environments +------------------------ +In addition to the other suggestions in this section, the following may be +helpful to optimize performance in VMs. + + - Using the appropriate mechanism (vcpupin) in the VM, pin the CPUs to + individual LCPUs, making sure to use a set of CPUs included in the + device's local_cpulist: /sys/class/net/<ethX>/device/local_cpulist. + + - Configure as many Rx/Tx queues in the VM as available. (See the idpf driver + documentation for the number of queues supported.) For example:: + + # ethtool -L <virt_interface> rx <max> tx <max> + + +Support +======= +For general information, go to the Intel support website at: +http://www.intel.com/support/ + +If an issue is identified with the released source code on a supported kernel +with a supported adapter, email the specific information related to the issue +to intel-wired-lan@lists.osuosl.org. + + +Trademarks +========== +Intel is a trademark or registered trademark of Intel Corporation or its +subsidiaries in the United States and/or other countries. + +* Other names and brands may be claimed as the property of others. diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst index 0a42c3395f..20d3b7e870 100644 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst @@ -67,7 +67,7 @@ Enabling the driver and kconfig options | Enables :ref:`IPSec XFRM cryptography-offload acceleration <xfrm_device>`. -**CONFIG_MLX5_EN_MACSEC=(y/n)** +**CONFIG_MLX5_MACSEC=(y/n)** | Build support for MACsec cryptography-offload acceleration in the NIC. diff --git a/Documentation/networking/device_drivers/ethernet/neterion/s2io.rst b/Documentation/networking/device_drivers/ethernet/neterion/s2io.rst index c5673ec455..d731b5a985 100644 --- a/Documentation/networking/device_drivers/ethernet/neterion/s2io.rst +++ b/Documentation/networking/device_drivers/ethernet/neterion/s2io.rst @@ -64,8 +64,8 @@ c. Multi-buffer receive mode. Scattering of packet across multiple IBM xSeries). d. MSI/MSI-X. Can be enabled on platforms which support this feature - (IA64, Xeon) resulting in noticeable performance improvement(up to 7% - on certain platforms). + resulting in noticeable performance improvement (up to 7% on certain + platforms). e. Statistics. Comprehensive MAC-level and software statistics displayed using "ethtool -S" option. diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst index 601eacaf12..0dd30a84ce 100644 --- a/Documentation/networking/device_drivers/index.rst +++ b/Documentation/networking/device_drivers/index.rst @@ -8,7 +8,6 @@ Contents: .. toctree:: :maxdepth: 2 - appletalk/index atm/index cable/index can/index @@ -16,7 +15,6 @@ Contents: ethernet/index fddi/index hamradio/index - qlogic/index wifi/index wwan/index diff --git a/Documentation/networking/device_drivers/qlogic/index.rst b/Documentation/networking/device_drivers/qlogic/index.rst deleted file mode 100644 index ad05b04286..0000000000 --- a/Documentation/networking/device_drivers/qlogic/index.rst +++ /dev/null @@ -1,18 +0,0 @@ -.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) - -QLogic QLGE Device Drivers -=============================================== - -Contents: - -.. toctree:: - :maxdepth: 2 - - qlge - -.. only:: subproject and html - - Indices - ======= - - * :ref:`genindex` diff --git a/Documentation/networking/device_drivers/qlogic/qlge.rst b/Documentation/networking/device_drivers/qlogic/qlge.rst deleted file mode 100644 index 0b888253d1..0000000000 --- a/Documentation/networking/device_drivers/qlogic/qlge.rst +++ /dev/null @@ -1,118 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -======================================= -QLogic QLGE 10Gb Ethernet device driver -======================================= - -This driver use drgn and devlink for debugging. - -Dump kernel data structures in drgn ------------------------------------ - -To dump kernel data structures, the following Python script can be used -in drgn: - -.. code-block:: python - - def align(x, a): - """the alignment a should be a power of 2 - """ - mask = a - 1 - return (x+ mask) & ~mask - - def struct_size(struct_type): - struct_str = "struct {}".format(struct_type) - return sizeof(Object(prog, struct_str, address=0x0)) - - def netdev_priv(netdevice): - NETDEV_ALIGN = 32 - return netdevice.value_() + align(struct_size("net_device"), NETDEV_ALIGN) - - name = 'xxx' - qlge_device = None - netdevices = prog['init_net'].dev_base_head.address_of_() - for netdevice in list_for_each_entry("struct net_device", netdevices, "dev_list"): - if netdevice.name.string_().decode('ascii') == name: - print(netdevice.name) - - ql_adapter = Object(prog, "struct ql_adapter", address=netdev_priv(qlge_device)) - -The struct ql_adapter will be printed in drgn as follows, - - >>> ql_adapter - (struct ql_adapter){ - .ricb = (struct ricb){ - .base_cq = (u8)0, - .flags = (u8)120, - .mask = (__le16)26637, - .hash_cq_id = (u8 [1024]){ 172, 142, 255, 255 }, - .ipv6_hash_key = (__le32 [10]){}, - .ipv4_hash_key = (__le32 [4]){}, - }, - .flags = (unsigned long)0, - .wol = (u32)0, - .nic_stats = (struct nic_stats){ - .tx_pkts = (u64)0, - .tx_bytes = (u64)0, - .tx_mcast_pkts = (u64)0, - .tx_bcast_pkts = (u64)0, - .tx_ucast_pkts = (u64)0, - .tx_ctl_pkts = (u64)0, - .tx_pause_pkts = (u64)0, - ... - }, - .active_vlans = (unsigned long [64]){ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 52780853100545, 18446744073709551615, - 18446619461681283072, 0, 42949673024, 2147483647, - }, - .rx_ring = (struct rx_ring [17]){ - { - .cqicb = (struct cqicb){ - .msix_vect = (u8)0, - .reserved1 = (u8)0, - .reserved2 = (u8)0, - .flags = (u8)0, - .len = (__le16)0, - .rid = (__le16)0, - ... - }, - .cq_base = (void *)0x0, - .cq_base_dma = (dma_addr_t)0, - } - ... - } - } - -coredump via devlink --------------------- - - -And the coredump obtained via devlink in json format looks like, - -.. code:: shell - - $ devlink health dump show DEVICE reporter coredump -p -j - { - "Core Registers": { - "segment": 1, - "values": [ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 ] - }, - "Test Logic Regs": { - "segment": 2, - "values": [ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 ] - }, - "RMII Registers": { - "segment": 3, - "values": [ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 ] - }, - ... - "Sem Registers": { - "segment": 50, - "values": [ 0,0,0,0 ] - } - } - -When the module parameter qlge_force_coredump is set to be true, the MPI -RISC reset before coredumping. So coredumping will much longer since -devlink tool has to wait for 5 secs for the resetting to be -finished. diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index e33ad2401a..562f46b412 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -126,7 +126,7 @@ Users may also set the RoCE capability of the function using `devlink port function set roce` command. Users may also set the function as migratable using -'devlink port function set migratable' command. +`devlink port function set migratable` command. Users may also set the IPsec crypto capability of the function using `devlink port function set ipsec_crypto` command. diff --git a/Documentation/networking/devlink/i40e.rst b/Documentation/networking/devlink/i40e.rst new file mode 100644 index 0000000000..d3cb5bb519 --- /dev/null +++ b/Documentation/networking/devlink/i40e.rst @@ -0,0 +1,59 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +i40e devlink support +==================== + +This document describes the devlink features implemented by the ``i40e`` +device driver. + +Info versions +============= + +The ``i40e`` driver reports the following versions + +.. list-table:: devlink info versions implemented + :widths: 5 5 5 90 + + * - Name + - Type + - Example + - Description + * - ``board.id`` + - fixed + - K15190-000 + - The Product Board Assembly (PBA) identifier of the board. + * - ``fw.mgmt`` + - running + - 9.130 + - 2-digit version number of the management firmware that controls the + PHY, link, etc. + * - ``fw.mgmt.api`` + - running + - 1.15 + - 2-digit version number of the API exported over the AdminQ by the + management firmware. Used by the driver to identify what commands + are supported. + * - ``fw.mgmt.build`` + - running + - 73618 + - Build number of the source for the management firmware. + * - ``fw.undi`` + - running + - 1.3429.0 + - Version of the Option ROM containing the UEFI driver. The version is + reported in ``major.minor.patch`` format. The major version is + incremented whenever a major breaking change occurs, or when the + minor version would overflow. The minor version is incremented for + non-breaking changes and reset to 1 when the major version is + incremented. The patch version is normally 0 but is incremented when + a fix is delivered as a patch against an older base Option ROM. + * - ``fw.psid.api`` + - running + - 9.30 + - Version defining the format of the flash contents. + * - ``fw.bundle_id`` + - running + - 0x8000e5f3 + - Unique identifier of the firmware image file that was loaded onto + the device. Also referred to as the EETRACK identifier of the NVM. diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst index b49749e2b9..e14d7a701b 100644 --- a/Documentation/networking/devlink/index.rst +++ b/Documentation/networking/devlink/index.rst @@ -18,6 +18,34 @@ netlink commands. Drivers are encouraged to use the devlink instance lock for their own needs. +Drivers need to be cautious when taking devlink instance lock and +taking RTNL lock at the same time. Devlink instance lock needs to be taken +first, only after that RTNL lock could be taken. + +Nested instances +---------------- + +Some objects, like linecards or port functions, could have another +devlink instances created underneath. In that case, drivers should make +sure to respect following rules: + + - Lock ordering should be maintained. If driver needs to take instance + lock of both nested and parent instances at the same time, devlink + instance lock of the parent instance should be taken first, only then + instance lock of the nested instance could be taken. + - Driver should use object-specific helpers to setup the + nested relationship: + + - ``devl_nested_devlink_set()`` - called to setup devlink -> nested + devlink relationship (could be user for multiple nested instances. + - ``devl_port_fn_devlink_set()`` - called to setup port function -> + nested devlink relationship. + - ``devlink_linecard_nested_dl_set()`` - called to setup linecard -> + nested devlink relationship. + +The nested devlink info is exposed to the userspace over object-specific +attributes of devlink netlink. + Interface documentation ----------------------- @@ -52,6 +80,7 @@ parameters, info versions, and other features it supports. bnxt etas_es58x hns3 + i40e ionic ice mlx4 diff --git a/Documentation/networking/dsa/b53.rst b/Documentation/networking/dsa/b53.rst index b41637cdb8..1cb3ff648f 100644 --- a/Documentation/networking/dsa/b53.rst +++ b/Documentation/networking/dsa/b53.rst @@ -52,7 +52,7 @@ VLAN programming would basically change the CPU port's default PVID and make it untagged, undesirable. In difference to the configuration described in :ref:`dsa-vlan-configuration` -the default VLAN 1 has to be removed from the slave interface configuration in +the default VLAN 1 has to be removed from the user interface configuration in single port and gateway configuration, while there is no need to add an extra VLAN configuration in the bridge showcase. @@ -68,13 +68,13 @@ By default packages are tagged with vid 1: ip link add link eth0 name eth0.2 type vlan id 2 ip link add link eth0 name eth0.3 type vlan id 3 - # The master interface needs to be brought up before the slave ports. + # The conduit interface needs to be brought up before the user ports. ip link set eth0 up ip link set eth0.1 up ip link set eth0.2 up ip link set eth0.3 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up @@ -113,11 +113,11 @@ bridge # tag traffic on CPU port ip link add link eth0 name eth0.1 type vlan id 1 - # The master interface needs to be brought up before the slave ports. + # The conduit interface needs to be brought up before the user ports. ip link set eth0 up ip link set eth0.1 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up @@ -149,12 +149,12 @@ gateway ip link add link eth0 name eth0.1 type vlan id 1 ip link add link eth0 name eth0.2 type vlan id 2 - # The master interface needs to be brought up before the slave ports. + # The conduit interface needs to be brought up before the user ports. ip link set eth0 up ip link set eth0.1 up ip link set eth0.2 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up diff --git a/Documentation/networking/dsa/bcm_sf2.rst b/Documentation/networking/dsa/bcm_sf2.rst index dee234039e..d257143569 100644 --- a/Documentation/networking/dsa/bcm_sf2.rst +++ b/Documentation/networking/dsa/bcm_sf2.rst @@ -67,7 +67,7 @@ MDIO indirect accesses ---------------------- Due to a limitation in how Broadcom switches have been designed, external -Broadcom switches connected to a SF2 require the use of the DSA slave MDIO bus +Broadcom switches connected to a SF2 require the use of the DSA user MDIO bus in order to properly configure them. By default, the SF2 pseudo-PHY address, and an external switch pseudo-PHY address will both be snooping for incoming MDIO transactions, since they are at the same address (30), resulting in some kind of diff --git a/Documentation/networking/dsa/configuration.rst b/Documentation/networking/dsa/configuration.rst index d2934c40f0..6cc4ded3cc 100644 --- a/Documentation/networking/dsa/configuration.rst +++ b/Documentation/networking/dsa/configuration.rst @@ -31,38 +31,38 @@ at https://www.kernel.org/pub/linux/utils/net/iproute2/ Through DSA every port of a switch is handled like a normal linux Ethernet interface. The CPU port is the switch port connected to an Ethernet MAC chip. -The corresponding linux Ethernet interface is called the master interface. -All other corresponding linux interfaces are called slave interfaces. +The corresponding linux Ethernet interface is called the conduit interface. +All other corresponding linux interfaces are called user interfaces. -The slave interfaces depend on the master interface being up in order for them -to send or receive traffic. Prior to kernel v5.12, the state of the master +The user interfaces depend on the conduit interface being up in order for them +to send or receive traffic. Prior to kernel v5.12, the state of the conduit interface had to be managed explicitly by the user. Starting with kernel v5.12, the behavior is as follows: -- when a DSA slave interface is brought up, the master interface is +- when a DSA user interface is brought up, the conduit interface is automatically brought up. -- when the master interface is brought down, all DSA slave interfaces are +- when the conduit interface is brought down, all DSA user interfaces are automatically brought down. In this documentation the following Ethernet interfaces are used: *eth0* - the master interface + the conduit interface *eth1* - another master interface + another conduit interface *lan1* - a slave interface + a user interface *lan2* - another slave interface + another user interface *lan3* - a third slave interface + a third user interface *wan* - A slave interface dedicated for upstream traffic + A user interface dedicated for upstream traffic Further Ethernet interfaces can be configured similar. The configured IPs and networks are: @@ -96,11 +96,11 @@ without using a VLAN based configuration. ip addr add 192.0.2.5/30 dev lan2 ip addr add 192.0.2.9/30 dev lan3 - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up - # bring up the slave interfaces + # bring up the user interfaces ip link set lan1 up ip link set lan2 up ip link set lan3 up @@ -108,11 +108,11 @@ without using a VLAN based configuration. *bridge* .. code-block:: sh - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up - # bring up the slave interfaces + # bring up the user interfaces ip link set lan1 up ip link set lan2 up ip link set lan3 up @@ -134,11 +134,11 @@ without using a VLAN based configuration. *gateway* .. code-block:: sh - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up @@ -178,14 +178,14 @@ configuration. ip link add link eth0 name eth0.2 type vlan id 2 ip link add link eth0 name eth0.3 type vlan id 3 - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up ip link set eth0.1 up ip link set eth0.2 up ip link set eth0.3 up - # bring up the slave interfaces + # bring up the user interfaces ip link set lan1 up ip link set lan2 up ip link set lan3 up @@ -221,12 +221,12 @@ configuration. # tag traffic on CPU port ip link add link eth0 name eth0.1 type vlan id 1 - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up ip link set eth0.1 up - # bring up the slave interfaces + # bring up the user interfaces ip link set lan1 up ip link set lan2 up ip link set lan3 up @@ -261,13 +261,13 @@ configuration. ip link add link eth0 name eth0.1 type vlan id 1 ip link add link eth0 name eth0.2 type vlan id 2 - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up ip link set eth0.1 up ip link set eth0.2 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up @@ -380,22 +380,22 @@ affinities according to the available CPU ports. Secondly, it is possible to perform load balancing between CPU ports on a per packet basis, rather than statically assigning user ports to CPU ports. -This can be achieved by placing the DSA masters under a LAG interface (bonding +This can be achieved by placing the DSA conduits under a LAG interface (bonding or team). DSA monitors this operation and creates a mirror of this software LAG -on the CPU ports facing the physical DSA masters that constitute the LAG slave +on the CPU ports facing the physical DSA conduits that constitute the LAG slave devices. To make use of multiple CPU ports, the firmware (device tree) description of -the switch must mark all the links between CPU ports and their DSA masters +the switch must mark all the links between CPU ports and their DSA conduits using the ``ethernet`` reference/phandle. At startup, only a single CPU port -and DSA master will be used - the numerically first port from the firmware +and DSA conduit will be used - the numerically first port from the firmware description which has an ``ethernet`` property. It is up to the user to -configure the system for the switch to use other masters. +configure the system for the switch to use other conduits. DSA uses the ``rtnl_link_ops`` mechanism (with a "dsa" ``kind``) to allow -changing the DSA master of a user port. The ``IFLA_DSA_MASTER`` u32 netlink -attribute contains the ifindex of the master device that handles each slave -device. The DSA master must be a valid candidate based on firmware node +changing the DSA conduit of a user port. The ``IFLA_DSA_CONDUIT`` u32 netlink +attribute contains the ifindex of the conduit device that handles each user +device. The DSA conduit must be a valid candidate based on firmware node information, or a LAG interface which contains only slaves which are valid candidates. @@ -403,7 +403,7 @@ Using iproute2, the following manipulations are possible: .. code-block:: sh - # See the DSA master in current use + # See the DSA conduit in current use ip -d link show dev swp0 (...) dsa master eth0 @@ -414,7 +414,7 @@ Using iproute2, the following manipulations are possible: ip link set swp2 type dsa master eth1 ip link set swp3 type dsa master eth0 - # CPU ports in LAG, using explicit assignment of the DSA master + # CPU ports in LAG, using explicit assignment of the DSA conduit ip link add bond0 type bond mode balance-xor && ip link set bond0 up ip link set eth1 down && ip link set eth1 master bond0 ip link set swp0 type dsa master bond0 @@ -426,7 +426,7 @@ Using iproute2, the following manipulations are possible: (...) dsa master bond0 - # CPU ports in LAG, relying on implicit migration of the DSA master + # CPU ports in LAG, relying on implicit migration of the DSA conduit ip link add bond0 type bond mode balance-xor && ip link set bond0 up ip link set eth0 down && ip link set eth0 master bond0 ip link set eth1 down && ip link set eth1 master bond0 @@ -435,24 +435,24 @@ Using iproute2, the following manipulations are possible: dsa master bond0 Notice that in the case of CPU ports under a LAG, the use of the -``IFLA_DSA_MASTER`` netlink attribute is not strictly needed, but rather, DSA -reacts to the ``IFLA_MASTER`` attribute change of its present master (``eth0``) +``IFLA_DSA_CONDUIT`` netlink attribute is not strictly needed, but rather, DSA +reacts to the ``IFLA_MASTER`` attribute change of its present conduit (``eth0``) and migrates all user ports to the new upper of ``eth0``, ``bond0``. Similarly, when ``bond0`` is destroyed using ``RTM_DELLINK``, DSA migrates the user ports -that were assigned to this interface to the first physical DSA master which is +that were assigned to this interface to the first physical DSA conduit which is eligible, based on the firmware description (it effectively reverts to the startup configuration). In a setup with more than 2 physical CPU ports, it is therefore possible to mix -static user to CPU port assignment with LAG between DSA masters. It is not -possible to statically assign a user port towards a DSA master that has any -upper interfaces (this includes LAG devices - the master must always be the LAG +static user to CPU port assignment with LAG between DSA conduits. It is not +possible to statically assign a user port towards a DSA conduit that has any +upper interfaces (this includes LAG devices - the conduit must always be the LAG in this case). -Live changing of the DSA master (and thus CPU port) affinity of a user port is +Live changing of the DSA conduit (and thus CPU port) affinity of a user port is permitted, in order to allow dynamic redistribution in response to traffic. -Physical DSA masters are allowed to join and leave at any time a LAG interface -used as a DSA master; however, DSA will reject a LAG interface as a valid -candidate for being a DSA master unless it has at least one physical DSA master +Physical DSA conduits are allowed to join and leave at any time a LAG interface +used as a DSA conduit; however, DSA will reject a LAG interface as a valid +candidate for being a DSA conduit unless it has at least one physical DSA conduit as a slave device. diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index a94ddf8334..7b2e69cd7e 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -25,7 +25,7 @@ presence of a management port connected to an Ethernet controller capable of receiving Ethernet frames from the switch. This is a very common setup for all kinds of Ethernet switches found in Small Home and Office products: routers, gateways, or even top-of-rack switches. This host Ethernet controller will -be later referred to as "master" and "cpu" in DSA terminology and code. +be later referred to as "conduit" and "cpu" in DSA terminology and code. The D in DSA stands for Distributed, because the subsystem has been designed with the ability to configure and manage cascaded switches on top of each other @@ -35,7 +35,7 @@ of multiple switches connected to each other is called a "switch tree". For each front-panel port, DSA creates specialized network devices which are used as controlling and data-flowing endpoints for use by the Linux networking -stack. These specialized network interfaces are referred to as "slave" network +stack. These specialized network interfaces are referred to as "user" network interfaces in DSA terminology and code. The ideal case for using DSA is when an Ethernet switch supports a "switch tag" @@ -56,12 +56,16 @@ Note that DSA does not currently create network interfaces for the "cpu" and - the "cpu" port is the Ethernet switch facing side of the management controller, and as such, would create a duplication of feature, since you - would get two interfaces for the same conduit: master netdev, and "cpu" netdev + would get two interfaces for the same conduit: conduit netdev, and "cpu" netdev - the "dsa" port(s) are just conduits between two or more switches, and as such cannot really be used as proper network interfaces either, only the downstream, or the top-most upstream interface makes sense with that model +NB: for the past 15 years, the DSA subsystem had been making use of the terms +"master" (rather than "conduit") and "slave" (rather than "user"). These terms +have been removed from the DSA codebase and phased out of the uAPI. + Switch tagging protocols ------------------------ @@ -80,14 +84,14 @@ methods of the ``struct dsa_device_ops`` structure, which are detailed below. Tagging protocols generally fall in one of three categories: 1. The switch-specific frame header is located before the Ethernet header, - shifting to the right (from the perspective of the DSA master's frame + shifting to the right (from the perspective of the DSA conduit's frame parser) the MAC DA, MAC SA, EtherType and the entire L2 payload. 2. The switch-specific frame header is located before the EtherType, keeping - the MAC DA and MAC SA in place from the DSA master's perspective, but + the MAC DA and MAC SA in place from the DSA conduit's perspective, but shifting the 'real' EtherType and L2 payload to the right. 3. The switch-specific frame header is located at the tail of the packet, keeping all frame headers in place and not altering the view of the packet - that the DSA master's frame parser has. + that the DSA conduit's frame parser has. A tagging protocol may tag all packets with switch tags of the same length, or the tag length might vary (for example packets with PTP timestamps might @@ -95,7 +99,7 @@ require an extended switch tag, or there might be one tag length on TX and a different one on RX). Either way, the tagging protocol driver must populate the ``struct dsa_device_ops::needed_headroom`` and/or ``struct dsa_device_ops::needed_tailroom`` with the length in octets of the longest switch frame header/trailer. The DSA -framework will automatically adjust the MTU of the master interface to +framework will automatically adjust the MTU of the conduit interface to accommodate for this extra size in order for DSA user ports to support the standard MTU (L2 payload length) of 1500 octets. The ``needed_headroom`` and ``needed_tailroom`` properties are also used to request from the network stack, @@ -140,18 +144,18 @@ adding or removing the ``ETH_P_EDSA`` EtherType and some padding octets). It is possible to construct cascaded setups of DSA switches even if their tagging protocols are not compatible with one another. In this case, there are no DSA links in this fabric, and each switch constitutes a disjoint DSA switch -tree. The DSA links are viewed as simply a pair of a DSA master (the out-facing +tree. The DSA links are viewed as simply a pair of a DSA conduit (the out-facing port of the upstream DSA switch) and a CPU port (the in-facing port of the downstream DSA switch). The tagging protocol of the attached DSA switch tree can be viewed through the -``dsa/tagging`` sysfs attribute of the DSA master:: +``dsa/tagging`` sysfs attribute of the DSA conduit:: cat /sys/class/net/eth0/dsa/tagging If the hardware and driver are capable, the tagging protocol of the DSA switch tree can be changed at runtime. This is done by writing the new tagging -protocol name to the same sysfs device attribute as above (the DSA master and +protocol name to the same sysfs device attribute as above (the DSA conduit and all attached switch ports must be down while doing this). It is desirable that all tagging protocols are testable with the ``dsa_loop`` @@ -159,7 +163,7 @@ mockup driver, which can be attached to any network interface. The goal is that any network interface should be capable of transmitting the same packet in the same way, and the tagger should decode the same received packet in the same way regardless of the driver used for the switch control path, and the driver used -for the DSA master. +for the DSA conduit. The transmission of a packet goes through the tagger's ``xmit`` function. The passed ``struct sk_buff *skb`` has ``skb->data`` pointing at @@ -183,44 +187,44 @@ virtual DSA user network interface corresponding to the physical front-facing switch port that the packet was received on. Since tagging protocols in category 1 and 2 break software (and most often also -hardware) packet dissection on the DSA master, features such as RPS (Receive -Packet Steering) on the DSA master would be broken. The DSA framework deals +hardware) packet dissection on the DSA conduit, features such as RPS (Receive +Packet Steering) on the DSA conduit would be broken. The DSA framework deals with this by hooking into the flow dissector and shifting the offset at which -the IP header is to be found in the tagged frame as seen by the DSA master. +the IP header is to be found in the tagged frame as seen by the DSA conduit. This behavior is automatic based on the ``overhead`` value of the tagging protocol. If not all packets are of equal size, the tagger can implement the ``flow_dissect`` method of the ``struct dsa_device_ops`` and override this default behavior by specifying the correct offset incurred by each individual RX packet. Tail taggers do not cause issues to the flow dissector. -Checksum offload should work with category 1 and 2 taggers when the DSA master +Checksum offload should work with category 1 and 2 taggers when the DSA conduit driver declares NETIF_F_HW_CSUM in vlan_features and looks at csum_start and csum_offset. For those cases, DSA will shift the checksum start and offset by -the tag size. If the DSA master driver still uses the legacy NETIF_F_IP_CSUM +the tag size. If the DSA conduit driver still uses the legacy NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM in vlan_features, the offload might only work if the offload hardware already expects that specific tag (perhaps due to matching -vendors). DSA slaves inherit those flags from the master port, and it is up to +vendors). DSA user ports inherit those flags from the conduit, and it is up to the driver to correctly fall back to software checksum when the IP header is not where the hardware expects. If that check is ineffective, the packets might go to the network without a proper checksum (the checksum field will have the pseudo IP header sum). For category 3, when the offload hardware does not already expect the switch tag in use, the checksum must be calculated before any -tag is inserted (i.e. inside the tagger). Otherwise, the DSA master would +tag is inserted (i.e. inside the tagger). Otherwise, the DSA conduit would include the tail tag in the (software or hardware) checksum calculation. Then, when the tag gets stripped by the switch during transmission, it will leave an incorrect IP checksum in place. Due to various reasons (most common being category 1 taggers being associated -with DSA-unaware masters, mangling what the master perceives as MAC DA), the -tagging protocol may require the DSA master to operate in promiscuous mode, to +with DSA-unaware conduits, mangling what the conduit perceives as MAC DA), the +tagging protocol may require the DSA conduit to operate in promiscuous mode, to receive all frames regardless of the value of the MAC DA. This can be done by -setting the ``promisc_on_master`` property of the ``struct dsa_device_ops``. -Note that this assumes a DSA-unaware master driver, which is the norm. +setting the ``promisc_on_conduit`` property of the ``struct dsa_device_ops``. +Note that this assumes a DSA-unaware conduit driver, which is the norm. -Master network devices ----------------------- +Conduit network devices +----------------------- -Master network devices are regular, unmodified Linux network device drivers for +Conduit network devices are regular, unmodified Linux network device drivers for the CPU/management Ethernet interface. Such a driver might occasionally need to know whether DSA is enabled (e.g.: to enable/disable specific offload features), but the DSA subsystem has been proven to work with industry standard drivers: @@ -232,14 +236,14 @@ Ethernet switch. Networking stack hooks ---------------------- -When a master netdev is used with DSA, a small hook is placed in the +When a conduit netdev is used with DSA, a small hook is placed in the networking stack is in order to have the DSA subsystem process the Ethernet switch specific tagging protocol. DSA accomplishes this by registering a specific (and fake) Ethernet type (later becoming ``skb->protocol``) with the networking stack, this is also known as a ``ptype`` or ``packet_type``. A typical Ethernet Frame receive sequence looks like this: -Master network device (e.g.: e1000e): +Conduit network device (e.g.: e1000e): 1. Receive interrupt fires: @@ -269,16 +273,16 @@ Master network device (e.g.: e1000e): - inspect and strip switch tag protocol to determine originating port - locate per-port network device - - invoke ``eth_type_trans()`` with the DSA slave network device + - invoke ``eth_type_trans()`` with the DSA user network device - invoked ``netif_receive_skb()`` -Past this point, the DSA slave network devices get delivered regular Ethernet +Past this point, the DSA user network devices get delivered regular Ethernet frames that can be processed by the networking stack. -Slave network devices ---------------------- +User network devices +-------------------- -Slave network devices created by DSA are stacked on top of their master network +User network devices created by DSA are stacked on top of their conduit network device, each of these network interfaces will be responsible for being a controlling and data-flowing end-point for each front-panel port of the switch. These interfaces are specialized in order to: @@ -289,31 +293,31 @@ These interfaces are specialized in order to: Wake-on-LAN, register dumps... - manage external/internal PHY: link, auto-negotiation, etc. -These slave network devices have custom net_device_ops and ethtool_ops function +These user network devices have custom net_device_ops and ethtool_ops function pointers which allow DSA to introduce a level of layering between the networking stack/ethtool and the switch driver implementation. -Upon frame transmission from these slave network devices, DSA will look up which +Upon frame transmission from these user network devices, DSA will look up which switch tagging protocol is currently registered with these network devices and invoke a specific transmit routine which takes care of adding the relevant switch tag in the Ethernet frames. -These frames are then queued for transmission using the master network device +These frames are then queued for transmission using the conduit network device ``ndo_start_xmit()`` function. Since they contain the appropriate switch tag, the Ethernet switch will be able to process these incoming frames from the management interface and deliver them to the physical switch port. When using multiple CPU ports, it is possible to stack a LAG (bonding/team) -device between the DSA slave devices and the physical DSA masters. The LAG -device is thus also a DSA master, but the LAG slave devices continue to be DSA -masters as well (just with no user port assigned to them; this is needed for -recovery in case the LAG DSA master disappears). Thus, the data path of the LAG -DSA master is used asymmetrically. On RX, the ``ETH_P_XDSA`` handler, which -calls ``dsa_switch_rcv()``, is invoked early (on the physical DSA master; -LAG slave). Therefore, the RX data path of the LAG DSA master is not used. -On the other hand, TX takes place linearly: ``dsa_slave_xmit`` calls -``dsa_enqueue_skb``, which calls ``dev_queue_xmit`` towards the LAG DSA master. -The latter calls ``dev_queue_xmit`` towards one physical DSA master or the +device between the DSA user devices and the physical DSA conduits. The LAG +device is thus also a DSA conduit, but the LAG slave devices continue to be DSA +conduits as well (just with no user port assigned to them; this is needed for +recovery in case the LAG DSA conduit disappears). Thus, the data path of the LAG +DSA conduit is used asymmetrically. On RX, the ``ETH_P_XDSA`` handler, which +calls ``dsa_switch_rcv()``, is invoked early (on the physical DSA conduit; +LAG slave). Therefore, the RX data path of the LAG DSA conduit is not used. +On the other hand, TX takes place linearly: ``dsa_user_xmit`` calls +``dsa_enqueue_skb``, which calls ``dev_queue_xmit`` towards the LAG DSA conduit. +The latter calls ``dev_queue_xmit`` towards one physical DSA conduit or the other, and in both cases, the packet exits the system through a hardware path towards the switch. @@ -352,11 +356,11 @@ perspective:: || swp0 | | swp1 | | swp2 | | swp3 || ++------+-+------+-+------+-+------++ -Slave MDIO bus --------------- +User MDIO bus +------------- -In order to be able to read to/from a switch PHY built into it, DSA creates a -slave MDIO bus which allows a specific switch driver to divert and intercept +In order to be able to read to/from a switch PHY built into it, DSA creates an +user MDIO bus which allows a specific switch driver to divert and intercept MDIO reads/writes towards specific PHY addresses. In most MDIO-connected switches, these functions would utilize direct or indirect PHY addressing mode to return standard MII registers from the switch builtin PHYs, allowing the PHY @@ -364,7 +368,7 @@ library and/or to return link status, link partner pages, auto-negotiation results, etc. For Ethernet switches which have both external and internal MDIO buses, the -slave MII bus can be utilized to mux/demux MDIO reads and writes towards either +user MII bus can be utilized to mux/demux MDIO reads and writes towards either internal or external MDIO devices this switch might be connected to: internal PHYs, external PHYs, or even external switches. @@ -381,10 +385,10 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as - ``dsa_platform_data``: platform device configuration data which can reference a collection of dsa_chip_data structures if multiple switches are cascaded, - the master network device this switch tree is attached to needs to be + the conduit network device this switch tree is attached to needs to be referenced -- ``dsa_switch_tree``: structure assigned to the master network device under +- ``dsa_switch_tree``: structure assigned to the conduit network device under ``dsa_ptr``, this structure references a dsa_platform_data structure as well as the tagging protocol supported by the switch tree, and which receive/transmit function hooks should be invoked, information about the directly attached @@ -392,7 +396,7 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as referenced to address individual switches in the tree. - ``dsa_switch``: structure describing a switch device in the tree, referencing - a ``dsa_switch_tree`` as a backpointer, slave network devices, master network + a ``dsa_switch_tree`` as a backpointer, user network devices, conduit network device, and a reference to the backing``dsa_switch_ops`` - ``dsa_switch_ops``: structure referencing function pointers, see below for a @@ -404,7 +408,7 @@ Design limitations Lack of CPU/DSA network devices ------------------------------- -DSA does not currently create slave network devices for the CPU or DSA ports, as +DSA does not currently create user network devices for the CPU or DSA ports, as described before. This might be an issue in the following cases: - inability to fetch switch CPU port statistics counters using ethtool, which @@ -419,7 +423,7 @@ described before. This might be an issue in the following cases: Common pitfalls using DSA setups -------------------------------- -Once a master network device is configured to use DSA (dev->dsa_ptr becomes +Once a conduit network device is configured to use DSA (dev->dsa_ptr becomes non-NULL), and the switch behind it expects a tagging protocol, this network interface can only exclusively be used as a conduit interface. Sending packets directly through this interface (e.g.: opening a socket using this interface) @@ -440,7 +444,7 @@ DSA currently leverages the following subsystems: MDIO/PHY library ---------------- -Slave network devices exposed by DSA may or may not be interfacing with PHY +User network devices exposed by DSA may or may not be interfacing with PHY devices (``struct phy_device`` as defined in ``include/linux/phy.h)``, but the DSA subsystem deals with all possible combinations: @@ -450,7 +454,7 @@ subsystem deals with all possible combinations: - special, non-autonegotiated or non MDIO-managed PHY devices: SFPs, MoCA; a.k.a fixed PHYs -The PHY configuration is done by the ``dsa_slave_phy_setup()`` function and the +The PHY configuration is done by the ``dsa_user_phy_setup()`` function and the logic basically looks like this: - if Device Tree is used, the PHY device is looked up using the standard @@ -463,7 +467,7 @@ logic basically looks like this: and connected transparently using the special fixed MDIO bus driver - finally, if the PHY is built into the switch, as is very common with - standalone switch packages, the PHY is probed using the slave MII bus created + standalone switch packages, the PHY is probed using the user MII bus created by DSA @@ -472,7 +476,7 @@ SWITCHDEV DSA directly utilizes SWITCHDEV when interfacing with the bridge layer, and more specifically with its VLAN filtering portion when configuring VLANs on top -of per-port slave network devices. As of today, the only SWITCHDEV objects +of per-port user network devices. As of today, the only SWITCHDEV objects supported by DSA are the FDB and VLAN objects. Devlink @@ -589,8 +593,8 @@ is torn down when the first switch unregisters. It is mandatory for DSA switch drivers to implement the ``shutdown()`` callback of their respective bus, and call ``dsa_switch_shutdown()`` from it (a minimal version of the full teardown performed by ``dsa_unregister_switch()``). -The reason is that DSA keeps a reference on the master net device, and if the -driver for the master device decides to unbind on shutdown, DSA's reference +The reason is that DSA keeps a reference on the conduit net device, and if the +driver for the conduit device decides to unbind on shutdown, DSA's reference will block that operation from finalizing. Either ``dsa_switch_shutdown()`` or ``dsa_unregister_switch()`` must be called, @@ -615,7 +619,7 @@ Switch configuration tag formats. - ``change_tag_protocol``: when the default tagging protocol has compatibility - problems with the master or other issues, the driver may support changing it + problems with the conduit or other issues, the driver may support changing it at runtime, either through a device tree property or through sysfs. In that case, further calls to ``get_tag_protocol`` should report the protocol in current use. @@ -643,22 +647,22 @@ Switch configuration PHY cannot be found. In this case, probing of the DSA switch continues without that particular port. -- ``port_change_master``: method through which the affinity (association used +- ``port_change_conduit``: method through which the affinity (association used for traffic termination purposes) between a user port and a CPU port can be changed. By default all user ports from a tree are assigned to the first available CPU port that makes sense for them (most of the times this means the user ports of a tree are all assigned to the same CPU port, except for H topologies as described in commit 2c0b03258b8b). The ``port`` argument - represents the index of the user port, and the ``master`` argument represents - the new DSA master ``net_device``. The CPU port associated with the new - master can be retrieved by looking at ``struct dsa_port *cpu_dp = - master->dsa_ptr``. Additionally, the master can also be a LAG device where - all the slave devices are physical DSA masters. LAG DSA masters also have a - valid ``master->dsa_ptr`` pointer, however this is not unique, but rather a - duplicate of the first physical DSA master's (LAG slave) ``dsa_ptr``. In case - of a LAG DSA master, a further call to ``port_lag_join`` will be emitted + represents the index of the user port, and the ``conduit`` argument represents + the new DSA conduit ``net_device``. The CPU port associated with the new + conduit can be retrieved by looking at ``struct dsa_port *cpu_dp = + conduit->dsa_ptr``. Additionally, the conduit can also be a LAG device where + all the slave devices are physical DSA conduits. LAG DSA also have a + valid ``conduit->dsa_ptr`` pointer, however this is not unique, but rather a + duplicate of the first physical DSA conduit's (LAG slave) ``dsa_ptr``. In case + of a LAG DSA conduit, a further call to ``port_lag_join`` will be emitted separately for the physical CPU ports associated with the physical DSA - masters, requesting them to create a hardware LAG associated with the LAG + conduits, requesting them to create a hardware LAG associated with the LAG interface. PHY devices and link management @@ -670,16 +674,16 @@ PHY devices and link management should return a 32-bit bitmask of "flags" that is private between the switch driver and the Ethernet PHY driver in ``drivers/net/phy/\*``. -- ``phy_read``: Function invoked by the DSA slave MDIO bus when attempting to read +- ``phy_read``: Function invoked by the DSA user MDIO bus when attempting to read the switch port MDIO registers. If unavailable, return 0xffff for each read. For builtin switch Ethernet PHYs, this function should allow reading the link status, auto-negotiation results, link partner pages, etc. -- ``phy_write``: Function invoked by the DSA slave MDIO bus when attempting to write +- ``phy_write``: Function invoked by the DSA user MDIO bus when attempting to write to the switch port MDIO registers. If unavailable return a negative error code. -- ``adjust_link``: Function invoked by the PHY library when a slave network device +- ``adjust_link``: Function invoked by the PHY library when a user network device is attached to a PHY device. This function is responsible for appropriately configuring the switch port link parameters: speed, duplex, pause based on what the ``phy_device`` is providing. @@ -698,14 +702,14 @@ Ethtool operations typically return statistics strings, private flags strings, etc. - ``get_ethtool_stats``: ethtool function used to query per-port statistics and - return their values. DSA overlays slave network devices general statistics: + return their values. DSA overlays user network devices general statistics: RX/TX counters from the network device, with switch driver specific statistics per port - ``get_sset_count``: ethtool function used to query the number of statistics items - ``get_wol``: ethtool function used to obtain Wake-on-LAN settings per-port, this - function may for certain implementations also query the master network device + function may for certain implementations also query the conduit network device Wake-on-LAN settings if this interface needs to participate in Wake-on-LAN - ``set_wol``: ethtool function used to configure Wake-on-LAN settings per-port, @@ -747,13 +751,13 @@ Power management should resume all Ethernet switch activities and re-configure the switch to be in a fully active state -- ``port_enable``: function invoked by the DSA slave network device ndo_open +- ``port_enable``: function invoked by the DSA user network device ndo_open function when a port is administratively brought up, this function should fully enable a given switch port. DSA takes care of marking the port with ``BR_STATE_BLOCKING`` if the port is a bridge member, or ``BR_STATE_FORWARDING`` if it was not, and propagating these changes down to the hardware -- ``port_disable``: function invoked by the DSA slave network device ndo_close +- ``port_disable``: function invoked by the DSA user network device ndo_close function when a port is administratively brought down, this function should fully disable a given switch port. DSA takes care of marking the port with ``BR_STATE_DISABLED`` and propagating changes to the hardware if this port is diff --git a/Documentation/networking/dsa/lan9303.rst b/Documentation/networking/dsa/lan9303.rst index e3c820db28..ab81b4e013 100644 --- a/Documentation/networking/dsa/lan9303.rst +++ b/Documentation/networking/dsa/lan9303.rst @@ -4,7 +4,7 @@ LAN9303 Ethernet switch driver The LAN9303 is a three port 10/100 Mbps ethernet switch with integrated phys for the two external ethernet ports. The third port is an RMII/MII interface to a -host master network interface (e.g. fixed link). +host conduit network interface (e.g. fixed link). Driver details diff --git a/Documentation/networking/dsa/sja1105.rst b/Documentation/networking/dsa/sja1105.rst index e0219c1452..8ab60eef07 100644 --- a/Documentation/networking/dsa/sja1105.rst +++ b/Documentation/networking/dsa/sja1105.rst @@ -79,7 +79,7 @@ The hardware tags all traffic internally with a port-based VLAN (pvid), or it decodes the VLAN information from the 802.1Q tag. Advanced VLAN classification is not possible. Once attributed a VLAN tag, frames are checked against the port's membership rules and dropped at ingress if they don't match any VLAN. -This behavior is available when switch ports are enslaved to a bridge with +This behavior is available when switch ports join a bridge with ``vlan_filtering 1``. Normally the hardware is not configurable with respect to VLAN awareness, but @@ -122,7 +122,7 @@ on egress. Using ``vlan_filtering=1``, the behavior is the other way around: offloaded flows can be steered to TX queues based on the VLAN PCP, but the DSA net devices are no longer able to do that. To inject frames into a hardware TX queue with VLAN awareness active, it is necessary to create a VLAN -sub-interface on the DSA master port, and send normal (0x8100) VLAN-tagged +sub-interface on the DSA conduit port, and send normal (0x8100) VLAN-tagged towards the switch, with the VLAN PCP bits set appropriately. Management traffic (having DMAC 01-80-C2-xx-xx-xx or 01-19-1B-xx-xx-xx) is the @@ -389,7 +389,7 @@ MDIO bus and PHY management The SJA1105 does not have an MDIO bus and does not perform in-band AN either. Therefore there is no link state notification coming from the switch device. A board would need to hook up the PHYs connected to the switch to any other -MDIO bus available to Linux within the system (e.g. to the DSA master's MDIO +MDIO bus available to Linux within the system (e.g. to the DSA conduit's MDIO bus). Link state management then works by the driver manually keeping in sync (over SPI commands) the MAC link speed with the settings negotiated by the PHY. diff --git a/Documentation/networking/filter.rst b/Documentation/networking/filter.rst index f69da50748..7d8c538049 100644 --- a/Documentation/networking/filter.rst +++ b/Documentation/networking/filter.rst @@ -650,8 +650,8 @@ before a conversion to the new layout is being done behind the scenes! Currently, the classic BPF format is being used for JITing on most 32-bit architectures, whereas x86-64, aarch64, s390x, powerpc64, -sparc64, arm32, riscv64, riscv32 perform JIT compilation from eBPF -instruction set. +sparc64, arm32, riscv64, riscv32, loongarch64 perform JIT compilation +from eBPF instruction set. Testing ------- diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 5b75c3f7a1..683eb42309 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -59,7 +59,6 @@ Contents: gtp ila ioam6-sysctl - ipddp ip_dynaddr ipsec ip-sysctl @@ -107,6 +106,7 @@ Contents: sysfs-tagging tc-actions-env-rules tc-queue-filters + tcp_ao tcp-thin team timestamping diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index a66054d076..7afff42612 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -745,6 +745,13 @@ tcp_comp_sack_nr - INTEGER Default : 44 +tcp_backlog_ack_defer - BOOLEAN + If set, user thread processing socket backlog tries sending + one ACK for the whole queue. This helps to avoid potential + long latencies at end of a TCP socket syscall. + + Default : true + tcp_slow_start_after_idle - BOOLEAN If set, provide RFC2861 behavior and time out the congestion window after an idle period. An idle period is defined at @@ -1176,6 +1183,19 @@ tcp_plb_cong_thresh - INTEGER Default: 128 +tcp_pingpong_thresh - INTEGER + The number of estimated data replies sent for estimated incoming data + requests that must happen before TCP considers that a connection is a + "ping-pong" (request-response) connection for which delayed + acknowledgments can provide benefits. + + This threshold is 1 by default, but some applications may need a higher + threshold for optimal performance. + + Possible Values: 1 - 255 + + Default: 1 + UDP variables ============= @@ -2304,6 +2324,17 @@ accept_ra_pinfo - BOOLEAN - enabled if accept_ra is enabled. - disabled if accept_ra is disabled. +ra_honor_pio_life - BOOLEAN + Whether to use RFC4862 Section 5.5.3e to determine the valid + lifetime of an address matching a prefix sent in a Router + Advertisement Prefix Information Option. + + - If enabled, the PIO valid lifetime will always be honored. + - If disabled, RFC4862 section 5.5.3e is used to determine + the valid lifetime of the address. + + Default: 0 (disabled) + accept_ra_rt_info_min_plen - INTEGER Minimum prefix length of Route Information in RA. @@ -2471,12 +2502,18 @@ use_tempaddr - INTEGER * -1 (for point-to-point devices and loopback devices) temp_valid_lft - INTEGER - valid lifetime (in seconds) for temporary addresses. + valid lifetime (in seconds) for temporary addresses. If less than the + minimum required lifetime (typically 5 seconds), temporary addresses + will not be created. Default: 172800 (2 days) temp_prefered_lft - INTEGER - Preferred lifetime (in seconds) for temporary addresses. + Preferred lifetime (in seconds) for temporary addresses. If + temp_prefered_lft is less than the minimum required lifetime (typically + 5 seconds), temporary addresses will not be created. If + temp_prefered_lft is greater than temp_valid_lft, the preferred lifetime + is temp_valid_lft. Default: 86400 (1 day) diff --git a/Documentation/networking/ipddp.rst b/Documentation/networking/ipddp.rst deleted file mode 100644 index be7091b779..0000000000 --- a/Documentation/networking/ipddp.rst +++ /dev/null @@ -1,78 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -========================================================= -AppleTalk-IP Decapsulation and AppleTalk-IP Encapsulation -========================================================= - -Documentation ipddp.c - -This file is written by Jay Schulist <jschlst@samba.org> - -Introduction ------------- - -AppleTalk-IP (IPDDP) is the method computers connected to AppleTalk -networks can use to communicate via IP. AppleTalk-IP is simply IP datagrams -inside AppleTalk packets. - -Through this driver you can either allow your Linux box to communicate -IP over an AppleTalk network or you can provide IP gatewaying functions -for your AppleTalk users. - -You can currently encapsulate or decapsulate AppleTalk-IP on LocalTalk, -EtherTalk and PPPTalk. The only limit on the protocol is that of what -kernel AppleTalk layer and drivers are available. - -Each mode requires its own user space software. - -Compiling AppleTalk-IP Decapsulation/Encapsulation -================================================== - -AppleTalk-IP decapsulation needs to be compiled into your kernel. You -will need to turn on AppleTalk-IP driver support. Then you will need to -select ONE of the two options; IP to AppleTalk-IP encapsulation support or -AppleTalk-IP to IP decapsulation support. If you compile the driver -statically you will only be able to use the driver for the function you have -enabled in the kernel. If you compile the driver as a module you can -select what mode you want it to run in via a module loading param. -ipddp_mode=1 for AppleTalk-IP encapsulation and ipddp_mode=2 for -AppleTalk-IP to IP decapsulation. - -Basic instructions for user space tools -======================================= - -I will briefly describe the operation of the tools, but you will -need to consult the supporting documentation for each set of tools. - -Decapsulation - You will need to download a software package called -MacGate. In this distribution there will be a tool called MacRoute -which enables you to add routes to the kernel for your Macs by hand. -Also the tool MacRegGateWay is included to register the -proper IP Gateway and IP addresses for your machine. Included in this -distribution is a patch to netatalk-1.4b2+asun2.0a17.2 (available from -ftp.u.washington.edu/pub/user-supported/asun/) this patch is optional -but it allows automatic adding and deleting of routes for Macs. (Handy -for locations with large Mac installations) - -Encapsulation - You will need to download a software daemon called ipddpd. -This software expects there to be an AppleTalk-IP gateway on the network. -You will also need to add the proper routes to route your Linux box's IP -traffic out the ipddp interface. - -Common Uses of ipddp.c ----------------------- -Of course AppleTalk-IP decapsulation and encapsulation, but specifically -decapsulation is being used most for connecting LocalTalk networks to -IP networks. Although it has been used on EtherTalk networks to allow -Macs that are only able to tunnel IP over EtherTalk. - -Encapsulation has been used to allow a Linux box stuck on a LocalTalk -network to use IP. It should work equally well if you are stuck on an -EtherTalk only network. - -Further Assistance -------------------- -You can contact me (Jay Schulist <jschlst@samba.org>) with any -questions regarding decapsulation or encapsulation. Bradford W. Johnson -<johns393@maroon.tc.umn.edu> originally wrote the ipddp.c driver for IP -encapsulation in AppleTalk. diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index 15f1919d64..69975ce25a 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -25,6 +25,17 @@ add_addr_timeout - INTEGER (seconds) Default: 120 +close_timeout - INTEGER (seconds) + Set the make-after-break timeout: in absence of any close or + shutdown syscall, MPTCP sockets will maintain the status + unchanged for such time, after the last subflow removal, before + moving to TCP_CLOSE. + + The default value matches TCP_TIMEWAIT_LEN. This is a per-namespace + sysctl. + + Default: 60 + checksum_enabled - BOOLEAN Control whether DSS checksum can be enabled. diff --git a/Documentation/networking/msg_zerocopy.rst b/Documentation/networking/msg_zerocopy.rst index b3ea96af9b..78fb70e748 100644 --- a/Documentation/networking/msg_zerocopy.rst +++ b/Documentation/networking/msg_zerocopy.rst @@ -7,7 +7,8 @@ Intro ===== The MSG_ZEROCOPY flag enables copy avoidance for socket send calls. -The feature is currently implemented for TCP and UDP sockets. +The feature is currently implemented for TCP, UDP and VSOCK (with +virtio transport) sockets. Opportunity and Caveats @@ -174,7 +175,9 @@ read_notification() call in the previous snippet. A notification is encoded in the standard error format, sock_extended_err. The level and type fields in the control data are protocol family -specific, IP_RECVERR or IPV6_RECVERR. +specific, IP_RECVERR or IPV6_RECVERR (for TCP or UDP socket). +For VSOCK socket, cmsg_level will be SOL_VSOCK and cmsg_type will be +VSOCK_RECVERR. Error origin is the new type SO_EE_ORIGIN_ZEROCOPY. ee_errno is zero, as explained before, to avoid blocking read and write system calls on @@ -235,12 +238,15 @@ Implementation Loopback -------- +For TCP and UDP: Data sent to local sockets can be queued indefinitely if the receive process does not read its socket. Unbound notification latency is not acceptable. For this reason all packets generated with MSG_ZEROCOPY that are looped to a local socket will incur a deferred copy. This includes looping onto packet sockets (e.g., tcpdump) and tun devices. +For VSOCK: +Data path sent to local sockets is the same as for non-local sockets. Testing ======= @@ -254,3 +260,6 @@ instance when run with msg_zerocopy.sh between a veth pair across namespaces, the test will not show any improvement. For testing, the loopback restriction can be temporarily relaxed by making skb_orphan_frags_rx identical to skb_orphan_frags. + +For VSOCK type of socket example can be found in +tools/testing/vsock/vsock_test_zerocopy.c. diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index 7a9de0568e..390730a743 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -99,9 +99,6 @@ Dynamic reconfiguration: Dynamic reconfigurability is a useful addition to netconsole that enables remote logging targets to be dynamically added, removed, or have their parameters reconfigured at runtime from a configfs-based userspace interface. -[ Note that the parameters of netconsole targets that were specified/created -from the boot/module option are not exposed via this interface, and hence -cannot be modified dynamically. ] To include this feature, select CONFIG_NETCONSOLE_DYNAMIC when building the netconsole module (or kernel, if netconsole is built-in). @@ -155,6 +152,25 @@ You can also update the local interface dynamically. This is especially useful if you want to use interfaces that have newly come up (and may not have existed when netconsole was loaded / initialized). +Netconsole targets defined at boot time (or module load time) with the +`netconsole=` param are assigned the name `cmdline<index>`. For example, the +first target in the parameter is named `cmdline0`. You can control and modify +these targets by creating configfs directories with the matching name. + +Let's suppose you have two netconsole targets defined at boot time:: + + netconsole=4444@10.0.0.1/eth1,9353@10.0.0.2/12:34:56:78:9a:bc;4444@10.0.0.1/eth1,9353@10.0.0.3/12:34:56:78:9a:bc + +You can modify these targets in runtime by creating the following targets:: + + mkdir cmdline0 + cat cmdline0/remote_ip + 10.0.0.2 + + mkdir cmdline1 + cat cmdline1/remote_ip + 10.0.0.3 + Extended console: ================= diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst index 215ebc9275..60993cb56b 100644 --- a/Documentation/networking/page_pool.rst +++ b/Documentation/networking/page_pool.rst @@ -58,7 +58,9 @@ a page will cause no race conditions is enough. .. kernel-doc:: include/net/page_pool/helpers.h :identifiers: page_pool_put_page page_pool_put_full_page - page_pool_recycle_direct page_pool_dev_alloc_pages + page_pool_recycle_direct page_pool_free_va + page_pool_dev_alloc_pages page_pool_dev_alloc_frag + page_pool_dev_alloc page_pool_dev_alloc_va page_pool_get_dma_addr page_pool_get_dma_dir .. kernel-doc:: net/core/page_pool.c diff --git a/Documentation/networking/pktgen.rst b/Documentation/networking/pktgen.rst index 1225f0f63f..c945218946 100644 --- a/Documentation/networking/pktgen.rst +++ b/Documentation/networking/pktgen.rst @@ -178,6 +178,7 @@ Examples:: IPSEC # IPsec encapsulation (needs CONFIG_XFRM) NODE_ALLOC # node specific memory allocation NO_TIMESTAMP # disable timestamping + SHARED # enable shared SKB pgset 'flag ![name]' Clear a flag to determine behaviour. Note that you might need to use single quote in interactive mode, so that your shell wouldn't expand @@ -288,6 +289,16 @@ To avoid breaking existing testbed scripts for using AH type and tunnel mode, you can use "pgset spi SPI_VALUE" to specify which transformation mode to employ. +Disable shared SKB +================== +By default, SKBs sent by pktgen are shared (user count > 1). +To test with non-shared SKBs, remove the "SHARED" flag by simply setting:: + + pg_set "flag !SHARED" + +However, if the "clone_skb" or "burst" parameters are configured, the skb +still needs to be held by pktgen for further access. Hence the skb must be +shared. Current commands and configuration options ========================================== @@ -357,6 +368,7 @@ Current commands and configuration options IPSEC NODE_ALLOC NO_TIMESTAMP + SHARED spi (ipsec) diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst index 92c9fb46d6..03ae19a689 100644 --- a/Documentation/networking/scaling.rst +++ b/Documentation/networking/scaling.rst @@ -105,6 +105,48 @@ a separate CPU. For interrupt handling, HT has shown no benefit in initial tests, so limit the number of queues to the number of CPU cores in the system. +Dedicated RSS contexts +~~~~~~~~~~~~~~~~~~~~~~ + +Modern NICs support creating multiple co-existing RSS configurations +which are selected based on explicit matching rules. This can be very +useful when application wants to constrain the set of queues receiving +traffic for e.g. a particular destination port or IP address. +The example below shows how to direct all traffic to TCP port 22 +to queues 0 and 1. + +To create an additional RSS context use:: + + # ethtool -X eth0 hfunc toeplitz context new + New RSS context is 1 + +Kernel reports back the ID of the allocated context (the default, always +present RSS context has ID of 0). The new context can be queried and +modified using the same APIs as the default context:: + + # ethtool -x eth0 context 1 + RX flow hash indirection table for eth0 with 13 RX ring(s): + 0: 0 1 2 3 4 5 6 7 + 8: 8 9 10 11 12 0 1 2 + [...] + # ethtool -X eth0 equal 2 context 1 + # ethtool -x eth0 context 1 + RX flow hash indirection table for eth0 with 13 RX ring(s): + 0: 0 1 0 1 0 1 0 1 + 8: 0 1 0 1 0 1 0 1 + [...] + +To make use of the new context direct traffic to it using an n-tuple +filter:: + + # ethtool -N eth0 flow-type tcp6 dst-port 22 context 1 + Added rule with ID 1023 + +When done, remove the context and the rule:: + + # ethtool -N eth0 delete 1023 + # ethtool -X eth0 context 1 delete + RPS: Receive Packet Steering ============================ diff --git a/Documentation/networking/sfp-phylink.rst b/Documentation/networking/sfp-phylink.rst index 55b65f607a..8054d33f44 100644 --- a/Documentation/networking/sfp-phylink.rst +++ b/Documentation/networking/sfp-phylink.rst @@ -200,10 +200,12 @@ this documentation. when the in-band link state changes - otherwise the link will never come up. - The :c:func:`validate` method should mask the supplied supported mask, - and ``state->advertising`` with the supported ethtool link modes. - These are the new ethtool link modes, so bitmask operations must be - used. For an example, see ``drivers/net/ethernet/marvell/mvneta.c``. + The :c:func:`mac_get_caps` method is optional, and if provided should + return the phylink MAC capabilities that are supported for the passed + ``interface`` mode. In general, there is no need to implement this method. + Phylink will use these capabilities in combination with permissible + capabilities for ``interface`` to determine the allowable ethtool link + modes. The :c:func:`mac_link_state` method is used to read the link state from the MAC, and report back the settings that the MAC is currently diff --git a/Documentation/networking/smc-sysctl.rst b/Documentation/networking/smc-sysctl.rst index 6d8acdbe9b..769149d987 100644 --- a/Documentation/networking/smc-sysctl.rst +++ b/Documentation/networking/smc-sysctl.rst @@ -44,18 +44,16 @@ smcr_testlink_time - INTEGER wmem - INTEGER Initial size of send buffer used by SMC sockets. - The default value inherits from net.ipv4.tcp_wmem[1]. The minimum value is 16KiB and there is no hard limit for max value, but only allowed 512KiB for SMC-R and 1MiB for SMC-D. - Default: 16K + Default: 64KiB rmem - INTEGER Initial size of receive buffer (RMB) used by SMC sockets. - The default value inherits from net.ipv4.tcp_rmem[1]. The minimum value is 16KiB and there is no hard limit for max value, but only allowed 512KiB for SMC-R and 1MiB for SMC-D. - Default: 128K + Default: 64KiB diff --git a/Documentation/networking/tcp_ao.rst b/Documentation/networking/tcp_ao.rst new file mode 100644 index 0000000000..8a58321acc --- /dev/null +++ b/Documentation/networking/tcp_ao.rst @@ -0,0 +1,444 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================================== +TCP Authentication Option Linux implementation (RFC5925) +======================================================== + +TCP Authentication Option (TCP-AO) provides a TCP extension aimed at verifying +segments between trusted peers. It adds a new TCP header option with +a Message Authentication Code (MAC). MACs are produced from the content +of a TCP segment using a hashing function with a password known to both peers. +The intent of TCP-AO is to deprecate TCP-MD5 providing better security, +key rotation and support for variety of hashing algorithms. + +1. Introduction +=============== + +.. table:: Short and Limited Comparison of TCP-AO and TCP-MD5 + + +----------------------+------------------------+-----------------------+ + | | TCP-MD5 | TCP-AO | + +======================+========================+=======================+ + |Supported hashing |MD5 |Must support HMAC-SHA1 | + |algorithms |(cryptographically weak)|(chosen-prefix attacks)| + | | |and CMAC-AES-128 (only | + | | |side-channel attacks). | + | | |May support any hashing| + | | |algorithm. | + +----------------------+------------------------+-----------------------+ + |Length of MACs (bytes)|16 |Typically 12-16. | + | | |Other variants that fit| + | | |TCP header permitted. | + +----------------------+------------------------+-----------------------+ + |Number of keys per |1 |Many | + |TCP connection | | | + +----------------------+------------------------+-----------------------+ + |Possibility to change |Non-practical (both |Supported by protocol | + |an active key |peers have to change | | + | |them during MSL) | | + +----------------------+------------------------+-----------------------+ + |Protection against |No |Yes: ignoring them | + |ICMP 'hard errors' | |by default on | + | | |established connections| + +----------------------+------------------------+-----------------------+ + |Protection against |No |Yes: pseudo-header | + |traffic-crossing | |includes TCP ports. | + |attack | | | + +----------------------+------------------------+-----------------------+ + |Protection against |No |Sequence Number | + |replayed TCP segments | |Extension (SNE) and | + | | |Initial Sequence | + | | |Numbers (ISNs) | + +----------------------+------------------------+-----------------------+ + |Supports |Yes |No. ISNs+SNE are needed| + |Connectionless Resets | |to correctly sign RST. | + +----------------------+------------------------+-----------------------+ + |Standards |RFC 2385 |RFC 5925, RFC 5926 | + +----------------------+------------------------+-----------------------+ + + +1.1 Frequently Asked Questions (FAQ) with references to RFC 5925 +---------------------------------------------------------------- + +Q: Can either SendID or RecvID be non-unique for the same 4-tuple +(srcaddr, srcport, dstaddr, dstport)? + +A: No [3.1]:: + + >> The IDs of MKTs MUST NOT overlap where their TCP connection + identifiers overlap. + +Q: Can Master Key Tuple (MKT) for an active connection be removed? + +A: No, unless it's copied to Transport Control Block (TCB) [3.1]:: + + It is presumed that an MKT affecting a particular connection cannot + be destroyed during an active connection -- or, equivalently, that + its parameters are copied to an area local to the connection (i.e., + instantiated) and so changes would affect only new connections. + +Q: If an old MKT needs to be deleted, how should it be done in order +to not remove it for an active connection? (As it can be still in use +at any moment later) + +A: Not specified by RFC 5925, seems to be a problem for key management +to ensure that no one uses such MKT before trying to remove it. + +Q: Can an old MKT exist forever and be used by another peer? + +A: It can, it's a key management task to decide when to remove an old key [6.1]:: + + Deciding when to start using a key is a performance issue. Deciding + when to remove an MKT is a security issue. Invalid MKTs are expected + to be removed. TCP-AO provides no mechanism to coordinate their removal, + as we consider this a key management operation. + +also [6.1]:: + + The only way to avoid reuse of previously used MKTs is to remove the MKT + when it is no longer considered permitted. + +Linux TCP-AO will try its best to prevent you from removing a key that's +being used, considering it a key management failure. But since keeping +an outdated key may become a security issue and as a peer may +unintentionally prevent the removal of an old key by always setting +it as RNextKeyID - a forced key removal mechanism is provided, where +userspace has to supply KeyID to use instead of the one that's being removed +and the kernel will atomically delete the old key, even if the peer is +still requesting it. There are no guarantees for force-delete as the peer +may yet not have the new key - the TCP connection may just break. +Alternatively, one may choose to shut down the socket. + +Q: What happens when a packet is received on a new connection with no known +MKT's RecvID? + +A: RFC 5925 specifies that by default it is accepted with a warning logged, but +the behaviour can be configured by the user [7.5.1.a]:: + + If the segment is a SYN, then this is the first segment of a new + connection. Find the matching MKT for this segment, using the segment's + socket pair and its TCP-AO KeyID, matched against the MKT's TCP connection + identifier and the MKT's RecvID. + + i. If there is no matching MKT, remove TCP-AO from the segment. + Proceed with further TCP handling of the segment. + NOTE: this presumes that connections that do not match any MKT + should be silently accepted, as noted in Section 7.3. + +[7.3]:: + + >> A TCP-AO implementation MUST allow for configuration of the behavior + of segments with TCP-AO but that do not match an MKT. The initial default + of this configuration SHOULD be to silently accept such connections. + If this is not the desired case, an MKT can be included to match such + connections, or the connection can indicate that TCP-AO is required. + Alternately, the configuration can be changed to discard segments with + the AO option not matching an MKT. + +[10.2.b]:: + + Connections not matching any MKT do not require TCP-AO. Further, incoming + segments with TCP-AO are not discarded solely because they include + the option, provided they do not match any MKT. + +Note that Linux TCP-AO implementation differs in this aspect. Currently, TCP-AO +segments with unknown key signatures are discarded with warnings logged. + +Q: Does the RFC imply centralized kernel key management in any way? +(i.e. that a key on all connections MUST be rotated at the same time?) + +A: Not specified. MKTs can be managed in userspace, the only relevant part to +key changes is [7.3]:: + + >> All TCP segments MUST be checked against the set of MKTs for matching + TCP connection identifiers. + +Q: What happens when RNextKeyID requested by a peer is unknown? Should +the connection be reset? + +A: It should not, no action needs to be performed [7.5.2.e]:: + + ii. If they differ, determine whether the RNextKeyID MKT is ready. + + 1. If the MKT corresponding to the segment’s socket pair and RNextKeyID + is not available, no action is required (RNextKeyID of a received + segment needs to match the MKT’s SendID). + +Q: How current_key is set and when does it change? It is a user-triggered +change, or is it by a request from the remote peer? Is it set by the user +explicitly, or by a matching rule? + +A: current_key is set by RNextKeyID [6.1]:: + + Rnext_key is changed only by manual user intervention or MKT management + protocol operation. It is not manipulated by TCP-AO. Current_key is updated + by TCP-AO when processing received TCP segments as discussed in the segment + processing description in Section 7.5. Note that the algorithm allows + the current_key to change to a new MKT, then change back to a previously + used MKT (known as "backing up"). This can occur during an MKT change when + segments are received out of order, and is considered a feature of TCP-AO, + because reordering does not result in drops. + +[7.5.2.e.ii]:: + + 2. If the matching MKT corresponding to the segment’s socket pair and + RNextKeyID is available: + + a. Set current_key to the RNextKeyID MKT. + +Q: If both peers have multiple MKTs matching the connection's socket pair +(with different KeyIDs), how should the sender/receiver pick KeyID to use? + +A: Some mechanism should pick the "desired" MKT [3.3]:: + + Multiple MKTs may match a single outgoing segment, e.g., when MKTs + are being changed. Those MKTs cannot have conflicting IDs (as noted + elsewhere), and some mechanism must determine which MKT to use for each + given outgoing segment. + + >> An outgoing TCP segment MUST match at most one desired MKT, indicated + by the segment’s socket pair. The segment MAY match multiple MKTs, provided + that exactly one MKT is indicated as desired. Other information in + the segment MAY be used to determine the desired MKT when multiple MKTs + match; such information MUST NOT include values in any TCP option fields. + +Q: Can TCP-MD5 connection migrate to TCP-AO (and vice-versa): + +A: No [1]:: + + TCP MD5-protected connections cannot be migrated to TCP-AO because TCP MD5 + does not support any changes to a connection’s security algorithm + once established. + +Q: If all MKTs are removed on a connection, can it become a non-TCP-AO signed +connection? + +A: [7.5.2] doesn't have the same choice as SYN packet handling in [7.5.1.i] +that would allow accepting segments without a sign (which would be insecure). +While switching to non-TCP-AO connection is not prohibited directly, it seems +what the RFC means. Also, there's a requirement for TCP-AO connections to +always have one current_key [3.3]:: + + TCP-AO requires that every protected TCP segment match exactly one MKT. + +[3.3]:: + + >> An incoming TCP segment including TCP-AO MUST match exactly one MKT, + indicated solely by the segment’s socket pair and its TCP-AO KeyID. + +[4.4]:: + + One or more MKTs. These are the MKTs that match this connection’s + socket pair. + +Q: Can a non-TCP-AO connection become a TCP-AO-enabled one? + +A: No: for already established non-TCP-AO connection it would be impossible +to switch using TCP-AO as the traffic key generation requires the initial +sequence numbers. Paraphrasing, starting using TCP-AO would require +re-establishing the TCP connection. + +2. In-kernel MKTs database vs database in userspace +=================================================== + +Linux TCP-AO support is implemented using ``setsockopt()s``, in a similar way +to TCP-MD5. It means that a userspace application that wants to use TCP-AO +should perform ``setsockopt()`` on a TCP socket when it wants to add, +remove or rotate MKTs. This approach moves the key management responsibility +to userspace as well as decisions on corner cases, i.e. what to do if +the peer doesn't respect RNextKeyID; moving more code to userspace, especially +responsible for the policy decisions. Besides, it's flexible and scales well +(with less locking needed than in the case of an in-kernel database). One also +should keep in mind that mainly intended users are BGP processes, not any +random applications, which means that compared to IPsec tunnels, +no transparency is really needed and modern BGP daemons already have +``setsockopt()s`` for TCP-MD5 support. + +.. table:: Considered pros and cons of the approaches + + +----------------------+------------------------+-----------------------+ + | | ``setsockopt()`` | in-kernel DB | + +======================+========================+=======================+ + | Extendability | ``setsockopt()`` | Netlink messages are | + | | commands should be | simple and extendable | + | | extendable syscalls | | + +----------------------+------------------------+-----------------------+ + | Required userspace | BGP or any application | could be transparent | + | changes | that wants TCP-AO needs| as tunnels, providing | + | | to perform | something like | + | | ``setsockopt()s`` | ``ip tcpao add key`` | + | | and do key management | (delete/show/rotate) | + +----------------------+------------------------+-----------------------+ + |MKTs removal or adding| harder for userspace | harder for kernel | + +----------------------+------------------------+-----------------------+ + | Dump-ability | ``getsockopt()`` | Netlink .dump() | + | | | callback | + +----------------------+------------------------+-----------------------+ + | Limits on kernel | equal | + | resources/memory | | + +----------------------+------------------------+-----------------------+ + | Scalability | contention on | contention on | + | | ``TCP_LISTEN`` sockets | the whole database | + +----------------------+------------------------+-----------------------+ + | Monitoring & warnings| ``TCP_DIAG`` | same Netlink socket | + +----------------------+------------------------+-----------------------+ + | Matching of MKTs | half-problem: only | hard | + | | listen sockets | | + +----------------------+------------------------+-----------------------+ + + +3. uAPI +======= + +Linux provides a set of ``setsockopt()s`` and ``getsockopt()s`` that let +userspace manage TCP-AO on a per-socket basis. In order to add/delete MKTs +``TCP_AO_ADD_KEY`` and ``TCP_AO_DEL_KEY`` TCP socket options must be used +It is not allowed to add a key on an established non-TCP-AO connection +as well as to remove the last key from TCP-AO connection. + +``setsockopt(TCP_AO_DEL_KEY)`` command may specify ``tcp_ao_del::current_key`` ++ ``tcp_ao_del::set_current`` and/or ``tcp_ao_del::rnext`` ++ ``tcp_ao_del::set_rnext`` which makes such delete "forced": it +provides userspace a way to delete a key that's being used and atomically set +another one instead. This is not intended for normal use and should be used +only when the peer ignores RNextKeyID and keeps requesting/using an old key. +It provides a way to force-delete a key that's not trusted but may break +the TCP-AO connection. + +The usual/normal key-rotation can be performed with ``setsockopt(TCP_AO_INFO)``. +It also provides a uAPI to change per-socket TCP-AO settings, such as +ignoring ICMPs, as well as clear per-socket TCP-AO packet counters. +The corresponding ``getsockopt(TCP_AO_INFO)`` can be used to get those +per-socket TCP-AO settings. + +Another useful command is ``getsockopt(TCP_AO_GET_KEYS)``. One can use it +to list all MKTs on a TCP socket or use a filter to get keys for a specific +peer and/or sndid/rcvid, VRF L3 interface or get current_key/rnext_key. + +To repair TCP-AO connections ``setsockopt(TCP_AO_REPAIR)`` is available, +provided that the user previously has checkpointed/dumped the socket with +``getsockopt(TCP_AO_REPAIR)``. + +A tip here for scaled TCP_LISTEN sockets, that may have some thousands TCP-AO +keys, is: use filters in ``getsockopt(TCP_AO_GET_KEYS)`` and asynchronous +delete with ``setsockopt(TCP_AO_DEL_KEY)``. + +Linux TCP-AO also provides a bunch of segment counters that can be helpful +with troubleshooting/debugging issues. Every MKT has good/bad counters +that reflect how many packets passed/failed verification. +Each TCP-AO socket has the following counters: +- for good segments (properly signed) +- for bad segments (failed TCP-AO verification) +- for segments with unknown keys +- for segments where an AO signature was expected, but wasn't found +- for the number of ignored ICMPs + +TCP-AO per-socket counters are also duplicated with per-netns counters, +exposed with SNMP. Those are ``TCPAOGood``, ``TCPAOBad``, ``TCPAOKeyNotFound``, +``TCPAORequired`` and ``TCPAODroppedIcmps``. + +RFC 5925 very permissively specifies how TCP port matching can be done for +MKTs:: + + TCP connection identifier. A TCP socket pair, i.e., a local IP + address, a remote IP address, a TCP local port, and a TCP remote port. + Values can be partially specified using ranges (e.g., 2-30), masks + (e.g., 0xF0), wildcards (e.g., "*"), or any other suitable indication. + +Currently Linux TCP-AO implementation doesn't provide any TCP port matching. +Probably, port ranges are the most flexible for uAPI, but so far +not implemented. + +4. ``setsockopt()`` vs ``accept()`` race +======================================== + +In contrast with TCP-MD5 established connection which has just one key, +TCP-AO connections may have many keys, which means that accepted connections +on a listen socket may have any amount of keys as well. As copying all those +keys on a first properly signed SYN would make the request socket bigger, that +would be undesirable. Currently, the implementation doesn't copy keys +to request sockets, but rather look them up on the "parent" listener socket. + +The result is that when userspace removes TCP-AO keys, that may break +not-yet-established connections on request sockets as well as not removing +keys from sockets that were already established, but not yet ``accept()``'ed, +hanging in the accept queue. + +The reverse is valid as well: if userspace adds a new key for a peer on +a listener socket, the established sockets in accept queue won't +have the new keys. + +At this moment, the resolution for the two races: +``setsockopt(TCP_AO_ADD_KEY)`` vs ``accept()`` +and ``setsockopt(TCP_AO_DEL_KEY)`` vs ``accept()`` is delegated to userspace. +This means that it's expected that userspace would check the MKTs on the socket +that was returned by ``accept()`` to verify that any key rotation that +happened on listen socket is reflected on the newly established connection. + +This is a similar "do-nothing" approach to TCP-MD5 from the kernel side and +may be changed later by introducing new flags to ``tcp_ao_add`` +and ``tcp_ao_del``. + +Note that this race is rare for it needs TCP-AO key rotation to happen +during the 3-way handshake for the new TCP connection. + +5. Interaction with TCP-MD5 +=========================== + +A TCP connection can not migrate between TCP-AO and TCP-MD5 options. The +established sockets that have either AO or MD5 keys are restricted for +adding keys of the other option. + +For listening sockets the picture is different: BGP server may want to receive +both TCP-AO and (deprecated) TCP-MD5 clients. As a result, both types of keys +may be added to TCP_CLOSED or TCP_LISTEN sockets. It's not allowed to add +different types of keys for the same peer. + +6. SNE Linux implementation +=========================== + +RFC 5925 [6.2] describes the algorithm of how to extend TCP sequence numbers +with SNE. In short: TCP has to track the previous sequence numbers and set +sne_flag when the current SEQ number rolls over. The flag is cleared when +both current and previous SEQ numbers cross 0x7fff, which is 32Kb. + +In times when sne_flag is set, the algorithm compares SEQ for each packet with +0x7fff and if it's higher than 32Kb, it assumes that the packet should be +verified with SNE before the increment. As a result, there's +this [0; 32Kb] window, when packets with (SNE - 1) can be accepted. + +Linux implementation simplifies this a bit: as the network stack already tracks +the first SEQ byte that ACK is wanted for (snd_una) and the next SEQ byte that +is wanted (rcv_nxt) - that's enough information for a rough estimation +on where in the 4GB SEQ number space both sender and receiver are. +When they roll over to zero, the corresponding SNE gets incremented. + +tcp_ao_compute_sne() is called for each TCP-AO segment. It compares SEQ numbers +from the segment with snd_una or rcv_nxt and fits the result into a 2GB window around them, +detecting SEQ numbers rolling over. That simplifies the code a lot and only +requires SNE numbers to be stored on every TCP-AO socket. + +The 2GB window at first glance seems much more permissive compared to +RFC 5926. But that is only used to pick the correct SNE before/after +a rollover. It allows more TCP segment replays, but yet all regular +TCP checks in tcp_sequence() are applied on the verified segment. +So, it trades a bit more permissive acceptance of replayed/retransmitted +segments for the simplicity of the algorithm and what seems better behaviour +for large TCP windows. + +7. Links +======== + +RFC 5925 The TCP Authentication Option + https://www.rfc-editor.org/rfc/pdfrfc/rfc5925.txt.pdf + +RFC 5926 Cryptographic Algorithms for the TCP Authentication Option (TCP-AO) + https://www.rfc-editor.org/rfc/pdfrfc/rfc5926.txt.pdf + +Draft "SHA-2 Algorithm for the TCP Authentication Option (TCP-AO)" + https://datatracker.ietf.org/doc/html/draft-nayak-tcp-sha2-03 + +RFC 2385 Protection of BGP Sessions via the TCP MD5 Signature Option + https://www.rfc-editor.org/rfc/pdfrfc/rfc2385.txt.pdf + +:Author: Dmitry Safonov <dima@arista.com> diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst index 25ce72af81..205696780b 100644 --- a/Documentation/networking/xdp-rx-metadata.rst +++ b/Documentation/networking/xdp-rx-metadata.rst @@ -105,6 +105,13 @@ bpf_tail_call Adding programs that access metadata kfuncs to the ``BPF_MAP_TYPE_PROG_ARRAY`` is currently not supported. +Supported Devices +================= + +It is possible to query which kfunc the particular netdev implements via +netlink. See ``xdp-rx-metadata-features`` attribute set in +``Documentation/netlink/specs/netdev.yaml``. + Example ======= |