diff options
Diffstat (limited to 'Documentation')
25 files changed, 1115 insertions, 137 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-net-mesh b/Documentation/ABI/testing/sysfs-class-net-mesh index 0baa657b18c4..4793d3dff6af 100644 --- a/Documentation/ABI/testing/sysfs-class-net-mesh +++ b/Documentation/ABI/testing/sysfs-class-net-mesh @@ -68,6 +68,14 @@ Description: Defines the penalty which will be applied to an originator message's tq-field on every hop. +What: /sys/class/net/<mesh_iface>/mesh/isolation_mark +Date: Nov 2013 +Contact: Antonio Quartulli <antonio@meshcoding.com> +Description: + Defines the isolation mark (and its bitmask) which + is used to classify clients as "isolated" by the + Extended Isolation feature. + What: /sys/class/net/<mesh_iface>/mesh/network_coding Date: Nov 2012 Contact: Martin Hundeboll <martin@hundeboll.net> diff --git a/Documentation/cgroups/net_cls.txt b/Documentation/cgroups/net_cls.txt index 9face6bb578a..ec182346dea2 100644 --- a/Documentation/cgroups/net_cls.txt +++ b/Documentation/cgroups/net_cls.txt @@ -6,6 +6,8 @@ tag network packets with a class identifier (classid). The Traffic Controller (tc) can be used to assign different priorities to packets from different cgroups. +Also, Netfilter (iptables) can use this tag to perform +actions on such packets. Creating a net_cls cgroups instance creates a net_cls.classid file. This net_cls.classid value is initialized to 0. @@ -32,3 +34,6 @@ tc class add dev eth0 parent 10: classid 10:1 htb rate 40mbit - creating traffic class 10:1 tc filter add dev eth0 parent 10: protocol ip prio 10 handle 1: cgroup + +configuring iptables, basic example: +iptables -A OUTPUT -m cgroup ! --cgroup 0x100001 -j DROP diff --git a/Documentation/devicetree/bindings/net/allwinner,sun7i-a20-gmac.txt b/Documentation/devicetree/bindings/net/allwinner,sun7i-a20-gmac.txt new file mode 100644 index 000000000000..ea4d752389a2 --- /dev/null +++ b/Documentation/devicetree/bindings/net/allwinner,sun7i-a20-gmac.txt @@ -0,0 +1,27 @@ +* Allwinner GMAC ethernet controller + +This device is a platform glue layer for stmmac. +Please see stmmac.txt for the other unchanged properties. + +Required properties: + - compatible: Should be "allwinner,sun7i-a20-gmac" + - clocks: Should contain the GMAC main clock, and tx clock + The tx clock type should be "allwinner,sun7i-a20-gmac-clk" + - clock-names: Should contain the clock names "stmmaceth", + and "allwinner_gmac_tx" + +Optional properties: +- phy-supply: phandle to a regulator if the PHY needs one + +Examples: + + gmac: ethernet@01c50000 { + compatible = "allwinner,sun7i-a20-gmac"; + reg = <0x01c50000 0x10000>, + <0x01c20164 0x4>; + interrupts = <0 85 1>; + interrupt-names = "macirq"; + clocks = <&ahb_gates 49>, <&gmac_tx>; + clock-names = "stmmaceth", "allwinner_gmac_tx"; + phy-mode = "mii"; + }; diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt b/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt new file mode 100644 index 000000000000..ee3723beb701 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt @@ -0,0 +1,25 @@ +* Microchip MCP251X stand-alone CAN controller device tree bindings + +Required properties: + - compatible: Should be one of the following: + - "microchip,mcp2510" for MCP2510. + - "microchip,mcp2515" for MCP2515. + - reg: SPI chip select. + - clocks: The clock feeding the CAN controller. + - interrupt-parent: The parent interrupt controller. + - interrupts: Should contain IRQ line for the CAN controller. + +Optional properties: + - vdd-supply: Regulator that powers the CAN controller. + - xceiver-supply: Regulator that powers the CAN transceiver. + +Example: + can0: can@1 { + compatible = "microchip,mcp2515"; + reg = <1>; + clocks = <&clk24m>; + interrupt-parent = <&gpio4>; + interrupts = <13 0x2>; + vdd-supply = <®5v0>; + xceiver-supply = <®5v0>; + }; diff --git a/Documentation/devicetree/bindings/net/davinci_emac.txt b/Documentation/devicetree/bindings/net/davinci_emac.txt index bad381faf036..ca0911a20e8b 100644 --- a/Documentation/devicetree/bindings/net/davinci_emac.txt +++ b/Documentation/devicetree/bindings/net/davinci_emac.txt @@ -12,8 +12,6 @@ Required properties: - ti,davinci-ctrl-ram-size: size of control module ram - ti,davinci-rmii-en: use RMII - ti,davinci-no-bd-ram: has the emac controller BD RAM -- phy-handle: Contains a phandle to an Ethernet PHY. - if not, davinci_emac driver defaults to 100/FULL - interrupts: interrupt mapping for the davinci emac interrupts sources: 4 sources: <Receive Threshold Interrupt Receive Interrupt @@ -21,6 +19,8 @@ Required properties: Miscellaneous Interrupt> Optional properties: +- phy-handle: Contains a phandle to an Ethernet PHY. + If absent, davinci_emac driver defaults to 100/FULL. - local-mac-address : 6 bytes, mac address Example (enbw_cmc board): diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt index 85de6107b98f..58307d0931c8 100644 --- a/Documentation/devicetree/bindings/net/phy.txt +++ b/Documentation/devicetree/bindings/net/phy.txt @@ -19,6 +19,7 @@ Optional Properties: specifications. If neither of these are specified, the default is to assume clause 22. The compatible list may also contain other elements. +- max-speed: Maximum PHY supported speed (10, 100, 1000...) Example: diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index eba0e5e59ebe..9d92d42140f2 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -12,7 +12,6 @@ Required properties: property - phy-mode: String, operation mode of the PHY interface. Supported values are: "mii", "rmii", "gmii", "rgmii". -- snps,phy-addr phy address to connect to. - snps,reset-gpio gpio number for phy reset. - snps,reset-active-low boolean flag to indicate if phy reset is active low. - snps,reset-delays-us is triplet of delays @@ -30,6 +29,11 @@ Required properties: Optional properties: - mac-address: 6 bytes, mac address +- resets: Should contain a phandle to the STMMAC reset signal, if any +- reset-names: Should contain the reset signal name "stmmaceth", if a + reset phandle is given +- max-frame-size: Maximum Transfer Unit (IEEE defined MTU), rather + than the maximum frame size. Examples: @@ -40,5 +44,6 @@ Examples: interrupts = <24 23>; interrupt-names = "macirq", "eth_wake_irq"; mac-address = [000000000000]; /* Filled in by U-Boot */ + max-frame-size = <3800>; phy-mode = "gmii"; }; diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt index 89490beb3c0b..58e49042fc20 100644 --- a/Documentation/networking/batman-adv.txt +++ b/Documentation/networking/batman-adv.txt @@ -66,11 +66,10 @@ All mesh wide settings can be found in batman's own interface folder: # ls /sys/class/net/bat0/mesh/ -# aggregated_ogms gw_bandwidth log_level -# ap_isolation gw_mode orig_interval -# bonding gw_sel_class routing_algo -# bridge_loop_avoidance hop_penalty fragmentation - +#aggregated_ogms distributed_arp_table gw_sel_class orig_interval +#ap_isolation fragmentation hop_penalty routing_algo +#bonding gw_bandwidth isolation_mark vlan0 +#bridge_loop_avoidance gw_mode log_level There is a special folder for debugging information: diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 2cdb8b66caa9..5cdb22971d19 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -657,7 +657,8 @@ primary one slave is preferred over another, e.g., when one slave has higher throughput than another. - The primary option is only valid for active-backup mode. + The primary option is only valid for active-backup(1), + balance-tlb (5) and balance-alb (6) mode. primary_reselect @@ -853,6 +854,14 @@ resend_igmp This option was added for bonding version 3.7.0. +lp_interval + + Specifies the number of seconds between instances where the bonding + driver sends learning packets to each slaves peer switch. + + The valid range is 1 - 0x7fffffff; the default value is 1. This Option + has effect only in balance-tlb and balance-alb modes. + 3. Configuring Bonding Devices ============================== diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt index 4c072414eadb..f3089d423515 100644 --- a/Documentation/networking/can.txt +++ b/Documentation/networking/can.txt @@ -2,21 +2,20 @@ can.txt -Readme file for the Controller Area Network Protocol Family (aka Socket CAN) +Readme file for the Controller Area Network Protocol Family (aka SocketCAN) This file contains - 1 Overview / What is Socket CAN + 1 Overview / What is SocketCAN 2 Motivation / Why using the socket API - 3 Socket CAN concept + 3 SocketCAN concept 3.1 receive lists 3.2 local loopback of sent frames - 3.3 network security issues (capabilities) - 3.4 network problem notifications + 3.3 network problem notifications - 4 How to use Socket CAN + 4 How to use SocketCAN 4.1 RAW protocol sockets with can_filters (SOCK_RAW) 4.1.1 RAW socket option CAN_RAW_FILTER 4.1.2 RAW socket option CAN_RAW_ERR_FILTER @@ -34,7 +33,7 @@ This file contains 4.3 connected transport protocols (SOCK_SEQPACKET) 4.4 unconnected transport protocols (SOCK_DGRAM) - 5 Socket CAN core module + 5 SocketCAN core module 5.1 can.ko module params 5.2 procfs content 5.3 writing own CAN protocol modules @@ -51,20 +50,20 @@ This file contains 6.6 CAN FD (flexible data rate) driver support 6.7 supported CAN hardware - 7 Socket CAN resources + 7 SocketCAN resources 8 Credits ============================================================================ -1. Overview / What is Socket CAN +1. Overview / What is SocketCAN -------------------------------- The socketcan package is an implementation of CAN protocols (Controller Area Network) for Linux. CAN is a networking technology which has widespread use in automation, embedded devices, and automotive fields. While there have been other CAN implementations -for Linux based on character devices, Socket CAN uses the Berkeley +for Linux based on character devices, SocketCAN uses the Berkeley socket API, the Linux network stack and implements the CAN device drivers as network interfaces. The CAN socket API has been designed as similar as possible to the TCP/IP protocols to allow programmers, @@ -74,7 +73,7 @@ sockets. 2. Motivation / Why using the socket API ---------------------------------------- -There have been CAN implementations for Linux before Socket CAN so the +There have been CAN implementations for Linux before SocketCAN so the question arises, why we have started another project. Most existing implementations come as a device driver for some CAN hardware, they are based on character devices and provide comparatively little @@ -89,10 +88,10 @@ the CAN controller requires employment of another device driver and often the need for adaption of large parts of the application to the new driver's API. -Socket CAN was designed to overcome all of these limitations. A new +SocketCAN was designed to overcome all of these limitations. A new protocol family has been implemented which provides a socket interface to user space applications and which builds upon the Linux network -layer, so to use all of the provided queueing functionality. A device +layer, enabling use all of the provided queueing functionality. A device driver for CAN controller hardware registers itself with the Linux network layer as a network device, so that CAN frames from the controller can be passed up to the network layer and on to the CAN @@ -146,15 +145,15 @@ solution for a couple of reasons: providing an API for device drivers to register with. However, then it would be no more difficult, or may be even easier, to use the networking framework provided by the Linux kernel, and this is what - Socket CAN does. + SocketCAN does. The use of the networking framework of the Linux kernel is just the natural and most appropriate way to implement CAN for Linux. -3. Socket CAN concept +3. SocketCAN concept --------------------- - As described in chapter 2 it is the main goal of Socket CAN to + As described in chapter 2 it is the main goal of SocketCAN to provide a socket interface to user space applications which builds upon the Linux network layer. In contrast to the commonly known TCP/IP and ethernet networking, the CAN bus is a broadcast-only(!) @@ -168,11 +167,11 @@ solution for a couple of reasons: The network transparent access of multiple applications leads to the problem that different applications may be interested in the same - CAN-IDs from the same CAN network interface. The Socket CAN core + CAN-IDs from the same CAN network interface. The SocketCAN core module - which implements the protocol family CAN - provides several high efficient receive lists for this reason. If e.g. a user space application opens a CAN RAW socket, the raw protocol module itself - requests the (range of) CAN-IDs from the Socket CAN core that are + requests the (range of) CAN-IDs from the SocketCAN core that are requested by the user. The subscription and unsubscription of CAN-IDs can be done for specific CAN interfaces or for all(!) known CAN interfaces with the can_rx_(un)register() functions provided to @@ -217,21 +216,7 @@ solution for a couple of reasons: * = you really like to have this when you're running analyser tools like 'candump' or 'cansniffer' on the (same) node. - 3.3 network security issues (capabilities) - - The Controller Area Network is a local field bus transmitting only - broadcast messages without any routing and security concepts. - In the majority of cases the user application has to deal with - raw CAN frames. Therefore it might be reasonable NOT to restrict - the CAN access only to the user root, as known from other networks. - Since the currently implemented CAN_RAW and CAN_BCM sockets can only - send and receive frames to/from CAN interfaces it does not affect - security of others networks to allow all users to access the CAN. - To enable non-root users to access CAN_RAW and CAN_BCM protocol - sockets the Kconfig options CAN_RAW_USER and/or CAN_BCM_USER may be - selected at kernel compile time. - - 3.4 network problem notifications + 3.3 network problem notifications The use of the CAN bus may lead to several problems on the physical and media access control layer. Detecting and logging of these lower @@ -251,11 +236,11 @@ solution for a couple of reasons: by default. The format of the CAN error message frame is briefly described in the Linux header file "include/linux/can/error.h". -4. How to use Socket CAN +4. How to use SocketCAN ------------------------ Like TCP/IP, you first need to open a socket for communicating over a - CAN network. Since Socket CAN implements a new protocol family, you + CAN network. Since SocketCAN implements a new protocol family, you need to pass PF_CAN as the first argument to the socket(2) system call. Currently, there are two CAN protocols to choose from, the raw socket protocol and the broadcast manager (BCM). So to open a socket, @@ -286,8 +271,8 @@ solution for a couple of reasons: }; The alignment of the (linear) payload data[] to a 64bit boundary - allows the user to define own structs and unions to easily access the - CAN payload. There is no given byteorder on the CAN bus by + allows the user to define their own structs and unions to easily access + the CAN payload. There is no given byteorder on the CAN bus by default. A read(2) system call on a CAN_RAW socket transfers a struct can_frame to the user space. @@ -479,7 +464,7 @@ solution for a couple of reasons: setsockopt(s, SOL_CAN_RAW, CAN_RAW_FILTER, NULL, 0); - To set the filters to zero filters is quite obsolete as not read + To set the filters to zero filters is quite obsolete as to not read data causes the raw socket to discard the received CAN frames. But having this 'send only' use-case we may remove the receive list in the Kernel to save a little (really a very little!) CPU usage. @@ -814,17 +799,17 @@ solution for a couple of reasons: 4.4 unconnected transport protocols (SOCK_DGRAM) -5. Socket CAN core module +5. SocketCAN core module ------------------------- - The Socket CAN core module implements the protocol family + The SocketCAN core module implements the protocol family PF_CAN. CAN protocol modules are loaded by the core module at runtime. The core module provides an interface for CAN protocol modules to subscribe needed CAN IDs (see chapter 3.1). 5.1 can.ko module params - - stats_timer: To calculate the Socket CAN core statistics + - stats_timer: To calculate the SocketCAN core statistics (e.g. current/maximum frames per second) this 1 second timer is invoked at can.ko module start time by default. This timer can be disabled by using stattimer=0 on the module commandline. @@ -833,7 +818,7 @@ solution for a couple of reasons: 5.2 procfs content - As described in chapter 3.1 the Socket CAN core uses several filter + As described in chapter 3.1 the SocketCAN core uses several filter lists to deliver received CAN frames to CAN protocol modules. These receive lists, their filters and the count of filter matches can be checked in the appropriate receive list. All entries contain the @@ -860,15 +845,15 @@ solution for a couple of reasons: Additional procfs files in /proc/net/can - stats - Socket CAN core statistics (rx/tx frames, match ratios, ...) + stats - SocketCAN core statistics (rx/tx frames, match ratios, ...) reset_stats - manual statistic reset - version - prints the Socket CAN core version and the ABI version + version - prints the SocketCAN core version and the ABI version 5.3 writing own CAN protocol modules To implement a new protocol in the protocol family PF_CAN a new protocol has to be defined in include/linux/can.h . - The prototypes and definitions to use the Socket CAN core can be + The prototypes and definitions to use the SocketCAN core can be accessed by including include/linux/can/core.h . In addition to functions that register the CAN protocol and the CAN device notifier chain there are functions to subscribe CAN @@ -1105,7 +1090,7 @@ solution for a couple of reasons: $ ip link set canX up type can bitrate 125000 - A device may enter the "bus-off" state if too much errors occurred on + A device may enter the "bus-off" state if too many errors occurred on the CAN bus. Then no more messages are received or sent. An automatic bus-off recovery can be enabled by setting the "restart-ms" to a non-zero value, e.g.: @@ -1125,7 +1110,7 @@ solution for a couple of reasons: CAN FD capable CAN controllers support two different bitrates for the arbitration phase and the payload phase of the CAN FD frame. Therefore a - second bittiming has to be specified in order to enable the CAN FD bitrate. + second bit timing has to be specified in order to enable the CAN FD bitrate. Additionally CAN FD capable CAN controllers support up to 64 bytes of payload. The representation of this length in can_frame.can_dlc and @@ -1150,21 +1135,16 @@ solution for a couple of reasons: 6.7 Supported CAN hardware Please check the "Kconfig" file in "drivers/net/can" to get an actual - list of the support CAN hardware. On the Socket CAN project website + list of the support CAN hardware. On the SocketCAN project website (see chapter 7) there might be further drivers available, also for older kernel versions. -7. Socket CAN resources +7. SocketCAN resources ----------------------- - You can find further resources for Socket CAN like user space tools, - support for old kernel versions, more drivers, mailing lists, etc. - at the BerliOS OSS project website for Socket CAN: - - http://developer.berlios.de/projects/socketcan - - If you have questions, bug fixes, etc., don't hesitate to post them to - the Socketcan-Users mailing list. But please search the archives first. + The Linux CAN / SocketCAN project ressources (project site / mailing list) + are referenced in the MAINTAINERS file in the Linux source tree. + Search for CAN NETWORK [LAYERS|DRIVERS]. 8. Credits ---------- diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index cdb3e40b9d14..a06b48d2f5cc 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -1,49 +1,563 @@ -filter.txt: Linux Socket Filtering -Written by: Jay Schulist <jschlst@samba.org> +Linux Socket Filtering aka Berkeley Packet Filter (BPF) +======================================================= Introduction -============ - - Linux Socket Filtering is derived from the Berkeley -Packet Filter. There are some distinct differences between -the BSD and Linux Kernel Filtering. - -Linux Socket Filtering (LSF) allows a user-space program to -attach a filter onto any socket and allow or disallow certain -types of data to come through the socket. LSF follows exactly -the same filter code structure as the BSD Berkeley Packet Filter -(BPF), so referring to the BSD bpf.4 manpage is very helpful in -creating filters. - -LSF is much simpler than BPF. One does not have to worry about -devices or anything like that. You simply create your filter -code, send it to the kernel via the SO_ATTACH_FILTER option and -if your filter code passes the kernel check on it, you then -immediately begin filtering data on that socket. - -You can also detach filters from your socket via the -SO_DETACH_FILTER option. This will probably not be used much -since when you close a socket that has a filter on it the -filter is automagically removed. The other less common case -may be adding a different filter on the same socket where you had another -filter that is still running: the kernel takes care of removing -the old one and placing your new one in its place, assuming your -filter has passed the checks, otherwise if it fails the old filter -will remain on that socket. - -SO_LOCK_FILTER option allows to lock the filter attached to a -socket. Once set, a filter cannot be removed or changed. This allows -one process to setup a socket, attach a filter, lock it then drop -privileges and be assured that the filter will be kept until the -socket is closed. - -Examples -======== - -Ioctls- -setsockopt(sockfd, SOL_SOCKET, SO_ATTACH_FILTER, &Filter, sizeof(Filter)); -setsockopt(sockfd, SOL_SOCKET, SO_DETACH_FILTER, &value, sizeof(value)); -setsockopt(sockfd, SOL_SOCKET, SO_LOCK_FILTER, &value, sizeof(value)); - -See the BSD bpf.4 manpage and the BSD Packet Filter paper written by -Steven McCanne and Van Jacobson of Lawrence Berkeley Laboratory. +------------ + +Linux Socket Filtering (LSF) is derived from the Berkeley Packet Filter. +Though there are some distinct differences between the BSD and Linux +Kernel filtering, but when we speak of BPF or LSF in Linux context, we +mean the very same mechanism of filtering in the Linux kernel. + +BPF allows a user-space program to attach a filter onto any socket and +allow or disallow certain types of data to come through the socket. LSF +follows exactly the same filter code structure as BSD's BPF, so referring +to the BSD bpf.4 manpage is very helpful in creating filters. + +On Linux, BPF is much simpler than on BSD. One does not have to worry +about devices or anything like that. You simply create your filter code, +send it to the kernel via the SO_ATTACH_FILTER option and if your filter +code passes the kernel check on it, you then immediately begin filtering +data on that socket. + +You can also detach filters from your socket via the SO_DETACH_FILTER +option. This will probably not be used much since when you close a socket +that has a filter on it the filter is automagically removed. The other +less common case may be adding a different filter on the same socket where +you had another filter that is still running: the kernel takes care of +removing the old one and placing your new one in its place, assuming your +filter has passed the checks, otherwise if it fails the old filter will +remain on that socket. + +SO_LOCK_FILTER option allows to lock the filter attached to a socket. Once +set, a filter cannot be removed or changed. This allows one process to +setup a socket, attach a filter, lock it then drop privileges and be +assured that the filter will be kept until the socket is closed. + +The biggest user of this construct might be libpcap. Issuing a high-level +filter command like `tcpdump -i em1 port 22` passes through the libpcap +internal compiler that generates a structure that can eventually be loaded +via SO_ATTACH_FILTER to the kernel. `tcpdump -i em1 port 22 -ddd` +displays what is being placed into this structure. + +Although we were only speaking about sockets here, BPF in Linux is used +in many more places. There's xt_bpf for netfilter, cls_bpf in the kernel +qdisc layer, SECCOMP-BPF (SECure COMPuting [1]), and lots of other places +such as team driver, PTP code, etc where BPF is being used. + + [1] Documentation/prctl/seccomp_filter.txt + +Original BPF paper: + +Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new +architecture for user-level packet capture. In Proceedings of the +USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993 +Conference Proceedings (USENIX'93). USENIX Association, Berkeley, +CA, USA, 2-2. [http://www.tcpdump.org/papers/bpf-usenix93.pdf] + +Structure +--------- + +User space applications include <linux/filter.h> which contains the +following relevant structures: + +struct sock_filter { /* Filter block */ + __u16 code; /* Actual filter code */ + __u8 jt; /* Jump true */ + __u8 jf; /* Jump false */ + __u32 k; /* Generic multiuse field */ +}; + +Such a structure is assembled as an array of 4-tuples, that contains +a code, jt, jf and k value. jt and jf are jump offsets and k a generic +value to be used for a provided code. + +struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ + unsigned short len; /* Number of filter blocks */ + struct sock_filter __user *filter; +}; + +For socket filtering, a pointer to this structure (as shown in +follow-up example) is being passed to the kernel through setsockopt(2). + +Example +------- + +#include <sys/socket.h> +#include <sys/types.h> +#include <arpa/inet.h> +#include <linux/if_ether.h> +/* ... */ + +/* From the example above: tcpdump -i em1 port 22 -dd */ +struct sock_filter code[] = { + { 0x28, 0, 0, 0x0000000c }, + { 0x15, 0, 8, 0x000086dd }, + { 0x30, 0, 0, 0x00000014 }, + { 0x15, 2, 0, 0x00000084 }, + { 0x15, 1, 0, 0x00000006 }, + { 0x15, 0, 17, 0x00000011 }, + { 0x28, 0, 0, 0x00000036 }, + { 0x15, 14, 0, 0x00000016 }, + { 0x28, 0, 0, 0x00000038 }, + { 0x15, 12, 13, 0x00000016 }, + { 0x15, 0, 12, 0x00000800 }, + { 0x30, 0, 0, 0x00000017 }, + { 0x15, 2, 0, 0x00000084 }, + { 0x15, 1, 0, 0x00000006 }, + { 0x15, 0, 8, 0x00000011 }, + { 0x28, 0, 0, 0x00000014 }, + { 0x45, 6, 0, 0x00001fff }, + { 0xb1, 0, 0, 0x0000000e }, + { 0x48, 0, 0, 0x0000000e }, + { 0x15, 2, 0, 0x00000016 }, + { 0x48, 0, 0, 0x00000010 }, + { 0x15, 0, 1, 0x00000016 }, + { 0x06, 0, 0, 0x0000ffff }, + { 0x06, 0, 0, 0x00000000 }, +}; + +struct sock_fprog bpf = { + .len = ARRAY_SIZE(code), + .filter = code, +}; + +sock = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_ALL)); +if (sock < 0) + /* ... bail out ... */ + +ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf)); +if (ret < 0) + /* ... bail out ... */ + +/* ... */ +close(sock); + +The above example code attaches a socket filter for a PF_PACKET socket +in order to let all IPv4/IPv6 packets with port 22 pass. The rest will +be dropped for this socket. + +The setsockopt(2) call to SO_DETACH_FILTER doesn't need any arguments +and SO_LOCK_FILTER for preventing the filter to be detached, takes an +integer value with 0 or 1. + +Note that socket filters are not restricted to PF_PACKET sockets only, +but can also be used on other socket families. + +Summary of system calls: + + * setsockopt(sockfd, SOL_SOCKET, SO_ATTACH_FILTER, &val, sizeof(val)); + * setsockopt(sockfd, SOL_SOCKET, SO_DETACH_FILTER, &val, sizeof(val)); + * setsockopt(sockfd, SOL_SOCKET, SO_LOCK_FILTER, &val, sizeof(val)); + +Normally, most use cases for socket filtering on packet sockets will be +covered by libpcap in high-level syntax, so as an application developer +you should stick to that. libpcap wraps its own layer around all that. + +Unless i) using/linking to libpcap is not an option, ii) the required BPF +filters use Linux extensions that are not supported by libpcap's compiler, +iii) a filter might be more complex and not cleanly implementable with +libpcap's compiler, or iv) particular filter codes should be optimized +differently than libpcap's internal compiler does; then in such cases +writing such a filter "by hand" can be of an alternative. For example, +xt_bpf and cls_bpf users might have requirements that could result in +more complex filter code, or one that cannot be expressed with libpcap +(e.g. different return codes for various code paths). Moreover, BPF JIT +implementors may wish to manually write test cases and thus need low-level +access to BPF code as well. + +BPF engine and instruction set +------------------------------ + +Under tools/net/ there's a small helper tool called bpf_asm which can +be used to write low-level filters for example scenarios mentioned in the +previous section. Asm-like syntax mentioned here has been implemented in +bpf_asm and will be used for further explanations (instead of dealing with +less readable opcodes directly, principles are the same). The syntax is +closely modelled after Steven McCanne's and Van Jacobson's BPF paper. + +The BPF architecture consists of the following basic elements: + + Element Description + + A 32 bit wide accumulator + X 32 bit wide X register + M[] 16 x 32 bit wide misc registers aka "scratch memory + store", addressable from 0 to 15 + +A program, that is translated by bpf_asm into "opcodes" is an array that +consists of the following elements (as already mentioned): + + op:16, jt:8, jf:8, k:32 + +The element op is a 16 bit wide opcode that has a particular instruction +encoded. jt and jf are two 8 bit wide jump targets, one for condition +"jump if true", the other one "jump if false". Eventually, element k +contains a miscellaneous argument that can be interpreted in different +ways depending on the given instruction in op. + +The instruction set consists of load, store, branch, alu, miscellaneous +and return instructions that are also represented in bpf_asm syntax. This +table lists all bpf_asm instructions available resp. what their underlying +opcodes as defined in linux/filter.h stand for: + + Instruction Addressing mode Description + + ld 1, 2, 3, 4, 10 Load word into A + ldi 4 Load word into A + ldh 1, 2 Load half-word into A + ldb 1, 2 Load byte into A + ldx 3, 4, 5, 10 Load word into X + ldxi 4 Load word into X + ldxb 5 Load byte into X + + st 3 Store A into M[] + stx 3 Store X into M[] + + jmp 6 Jump to label + ja 6 Jump to label + jeq 7, 8 Jump on k == A + jneq 8 Jump on k != A + jne 8 Jump on k != A + jlt 8 Jump on k < A + jle 8 Jump on k <= A + jgt 7, 8 Jump on k > A + jge 7, 8 Jump on k >= A + jset 7, 8 Jump on k & A + + add 0, 4 A + <x> + sub 0, 4 A - <x> + mul 0, 4 A * <x> + div 0, 4 A / <x> + mod 0, 4 A % <x> + neg 0, 4 !A + and 0, 4 A & <x> + or 0, 4 A | <x> + xor 0, 4 A ^ <x> + lsh 0, 4 A << <x> + rsh 0, 4 A >> <x> + + tax Copy A into X + txa Copy X into A + + ret 4, 9 Return + +The next table shows addressing formats from the 2nd column: + + Addressing mode Syntax Description + + 0 x/%x Register X + 1 [k] BHW at byte offset k in the packet + 2 [x + k] BHW at the offset X + k in the packet + 3 M[k] Word at offset k in M[] + 4 #k Literal value stored in k + 5 4*([k]&0xf) Lower nibble * 4 at byte offset k in the packet + 6 L Jump label L + 7 #k,Lt,Lf Jump to Lt if true, otherwise jump to Lf + 8 #k,Lt Jump to Lt if predicate is true + 9 a/%a Accumulator A + 10 extension BPF extension + +The Linux kernel also has a couple of BPF extensions that are used along +with the class of load instructions by "overloading" the k argument with +a negative offset + a particular extension offset. The result of such BPF +extensions are loaded into A. + +Possible BPF extensions are shown in the following table: + + Extension Description + + len skb->len + proto skb->protocol + type skb->pkt_type + poff Payload start offset + ifidx skb->dev->ifindex + nla Netlink attribute of type X with offset A + nlan Nested Netlink attribute of type X with offset A + mark skb->mark + queue skb->queue_mapping + hatype skb->dev->type + rxhash skb->rxhash + cpu raw_smp_processor_id() + vlan_tci vlan_tx_tag_get(skb) + vlan_pr vlan_tx_tag_present(skb) + +These extensions can also be prefixed with '#'. +Examples for low-level BPF: + +** ARP packets: + + ldh [12] + jne #0x806, drop + ret #-1 + drop: ret #0 + +** IPv4 TCP packets: + + ldh [12] + jne #0x800, drop + ldb [23] + jneq #6, drop + ret #-1 + drop: ret #0 + +** (Accelerated) VLAN w/ id 10: + + ld vlan_tci + jneq #10, drop + ret #-1 + drop: ret #0 + +** SECCOMP filter example: + + ld [4] /* offsetof(struct seccomp_data, arch) */ + jne #0xc000003e, bad /* AUDIT_ARCH_X86_64 */ + ld [0] /* offsetof(struct seccomp_data, nr) */ + jeq #15, good /* __NR_rt_sigreturn */ + jeq #231, good /* __NR_exit_group */ + jeq #60, good /* __NR_exit */ + jeq #0, good /* __NR_read */ + jeq #1, good /* __NR_write */ + jeq #5, good /* __NR_fstat */ + jeq #9, good /* __NR_mmap */ + jeq #14, good /* __NR_rt_sigprocmask */ + jeq #13, good /* __NR_rt_sigaction */ + jeq #35, good /* __NR_nanosleep */ + bad: ret #0 /* SECCOMP_RET_KILL */ + good: ret #0x7fff0000 /* SECCOMP_RET_ALLOW */ + +The above example code can be placed into a file (here called "foo"), and +then be passed to the bpf_asm tool for generating opcodes, output that xt_bpf +and cls_bpf understands and can directly be loaded with. Example with above +ARP code: + +$ ./bpf_asm foo +4,40 0 0 12,21 0 1 2054,6 0 0 4294967295,6 0 0 0, + +In copy and paste C-like output: + +$ ./bpf_asm -c foo +{ 0x28, 0, 0, 0x0000000c }, +{ 0x15, 0, 1, 0x00000806 }, +{ 0x06, 0, 0, 0xffffffff }, +{ 0x06, 0, 0, 0000000000 }, + +In particular, as usage with xt_bpf or cls_bpf can result in more complex BPF +filters that might not be obvious at first, it's good to test filters before +attaching to a live system. For that purpose, there's a small tool called +bpf_dbg under tools/net/ in the kernel source directory. This debugger allows +for testing BPF filters against given pcap files, single stepping through the +BPF code on the pcap's packets and to do BPF machine register dumps. + +Starting bpf_dbg is trivial and just requires issuing: + +# ./bpf_dbg + +In case input and output do not equal stdin/stdout, bpf_dbg takes an +alternative stdin source as a first argument, and an alternative stdout +sink as a second one, e.g. `./bpf_dbg test_in.txt test_out.txt`. + +Other than that, a particular libreadline configuration can be set via +file "~/.bpf_dbg_init" and the command history is stored in the file +"~/.bpf_dbg_history". + +Interaction in bpf_dbg happens through a shell that also has auto-completion +support (follow-up example commands starting with '>' denote bpf_dbg shell). +The usual workflow would be to ... + +> load bpf 6,40 0 0 12,21 0 3 2048,48 0 0 23,21 0 1 1,6 0 0 65535,6 0 0 0 + Loads a BPF filter from standard output of bpf_asm, or transformed via + e.g. `tcpdump -iem1 -ddd port 22 | tr '\n' ','`. Note that for JIT + debugging (next section), this command creates a temporary socket and + loads the BPF code into the kernel. Thus, this will also be useful for + JIT developers. + +> load pcap foo.pcap + Loads standard tcpdump pcap file. + +> run [<n>] +bpf passes:1 fails:9 + Runs through all packets from a pcap to account how many passes and fails + the filter will generate. A limit of packets to traverse can be given. + +> disassemble +l0: ldh [12] +l1: jeq #0x800, l2, l5 +l2: ldb [23] +l3: jeq #0x1, l4, l5 +l4: ret #0xffff +l5: ret #0 + Prints out BPF code disassembly. + +> dump +/* { op, jt, jf, k }, */ +{ 0x28, 0, 0, 0x0000000c }, +{ 0x15, 0, 3, 0x00000800 }, +{ 0x30, 0, 0, 0x00000017 }, +{ 0x15, 0, 1, 0x00000001 }, +{ 0x06, 0, 0, 0x0000ffff }, +{ 0x06, 0, 0, 0000000000 }, + Prints out C-style BPF code dump. + +> breakpoint 0 +breakpoint at: l0: ldh [12] +> breakpoint 1 +breakpoint at: l1: jeq #0x800, l2, l5 + ... + Sets breakpoints at particular BPF instructions. Issuing a `run` command + will walk through the pcap file continuing from the current packet and + break when a breakpoint is being hit (another `run` will continue from + the currently active breakpoint executing next instructions): + + > run + -- register dump -- + pc: [0] <-- program counter + code: [40] jt[0] jf[0] k[12] <-- plain BPF code of current instruction + curr: l0: ldh [12] <-- disassembly of current instruction + A: [00000000][0] <-- content of A (hex, decimal) + X: [00000000][0] <-- content of X (hex, decimal) + M[0,15]: [00000000][0] <-- folded content of M (hex, decimal) + -- packet dump -- <-- Current packet from pcap (hex) + len: 42 + 0: 00 19 cb 55 55 a4 00 14 a4 43 78 69 08 06 00 01 + 16: 08 00 06 04 00 01 00 14 a4 43 78 69 0a 3b 01 26 + 32: 00 00 00 00 00 00 0a 3b 01 01 + (breakpoint) + > + +> breakpoint +breakpoints: 0 1 + Prints currently set breakpoints. + +> step [-<n>, +<n>] + Performs single stepping through the BPF program from the current pc + offset. Thus, on each step invocation, above register dump is issued. + This can go forwards and backwards in time, a plain `step` will break + on the next BPF instruction, thus +1. (No `run` needs to be issued here.) + +> select <n> + Selects a given packet from the pcap file to continue from. Thus, on + the next `run` or `step`, the BPF program is being evaluated against + the user pre-selected packet. Numbering starts just as in Wireshark + with index 1. + +> quit +# + Exits bpf_dbg. + +JIT compiler +------------ + +The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, PowerPC, +ARM and s390 and can be enabled through CONFIG_BPF_JIT. The JIT compiler is +transparently invoked for each attached filter from user space or for internal +kernel users if it has been previously enabled by root: + + echo 1 > /proc/sys/net/core/bpf_jit_enable + +For JIT developers, doing audits etc, each compile run can output the generated +opcode image into the kernel log via: + + echo 2 > /proc/sys/net/core/bpf_jit_enable + +Example output from dmesg: + +[ 3389.935842] flen=6 proglen=70 pass=3 image=ffffffffa0069c8f +[ 3389.935847] JIT code: 00000000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 68 +[ 3389.935849] JIT code: 00000010: 44 2b 4f 6c 4c 8b 87 d8 00 00 00 be 0c 00 00 00 +[ 3389.935850] JIT code: 00000020: e8 1d 94 ff e0 3d 00 08 00 00 75 16 be 17 00 00 +[ 3389.935851] JIT code: 00000030: 00 e8 28 94 ff e0 83 f8 01 75 07 b8 ff ff 00 00 +[ 3389.935852] JIT code: 00000040: eb 02 31 c0 c9 c3 + +In the kernel source tree under tools/net/, there's bpf_jit_disasm for +generating disassembly out of the kernel log's hexdump: + +# ./bpf_jit_disasm +70 bytes emitted from JIT compiler (pass:3, flen:6) +ffffffffa0069c8f + <x>: + 0: push %rbp + 1: mov %rsp,%rbp + 4: sub $0x60,%rsp + 8: mov %rbx,-0x8(%rbp) + c: mov 0x68(%rdi),%r9d + 10: sub 0x6c(%rdi),%r9d + 14: mov 0xd8(%rdi),%r8 + 1b: mov $0xc,%esi + 20: callq 0xffffffffe0ff9442 + 25: cmp $0x800,%eax + 2a: jne 0x0000000000000042 + 2c: mov $0x17,%esi + 31: callq 0xffffffffe0ff945e + 36: cmp $0x1,%eax + 39: jne 0x0000000000000042 + 3b: mov $0xffff,%eax + 40: jmp 0x0000000000000044 + 42: xor %eax,%eax + 44: leaveq + 45: retq + +Issuing option `-o` will "annotate" opcodes to resulting assembler +instructions, which can be very useful for JIT developers: + +# ./bpf_jit_disasm -o +70 bytes emitted from JIT compiler (pass:3, flen:6) +ffffffffa0069c8f + <x>: + 0: push %rbp + 55 + 1: mov %rsp,%rbp + 48 89 e5 + 4: sub $0x60,%rsp + 48 83 ec 60 + 8: mov %rbx,-0x8(%rbp) + 48 89 5d f8 + c: mov 0x68(%rdi),%r9d + 44 8b 4f 68 + 10: sub 0x6c(%rdi),%r9d + 44 2b 4f 6c + 14: mov 0xd8(%rdi),%r8 + 4c 8b 87 d8 00 00 00 + 1b: mov $0xc,%esi + be 0c 00 00 00 + 20: callq 0xffffffffe0ff9442 + e8 1d 94 ff e0 + 25: cmp $0x800,%eax + 3d 00 08 00 00 + 2a: jne 0x0000000000000042 + 75 16 + 2c: mov $0x17,%esi + be 17 00 00 00 + 31: callq 0xffffffffe0ff945e + e8 28 94 ff e0 + 36: cmp $0x1,%eax + 83 f8 01 + 39: jne 0x0000000000000042 + 75 07 + 3b: mov $0xffff,%eax + b8 ff ff 00 00 + 40: jmp 0x0000000000000044 + eb 02 + 42: xor %eax,%eax + 31 c0 + 44: leaveq + c9 + 45: retq + c3 + +For BPF JIT developers, bpf_jit_disasm, bpf_asm and bpf_dbg provides a useful +toolchain for developing and testing the kernel's JIT compiler. + +Misc +---- + +Also trinity, the Linux syscall fuzzer, has built-in support for BPF and +SECCOMP-BPF kernel fuzzing. + +Written by +---------- + +The document was written in the hope that it is found useful and in order +to give potential BPF hackers or security auditors a better overview of +the underlying architecture. + +Jay Schulist <jschlst@samba.org> +Daniel Borkmann <dborkman@redhat.com> diff --git a/Documentation/networking/i40evf.txt b/Documentation/networking/i40evf.txt new file mode 100644 index 000000000000..21e41271af79 --- /dev/null +++ b/Documentation/networking/i40evf.txt @@ -0,0 +1,47 @@ +Linux* Base Driver for Intel(R) Network Connection +================================================== + +Intel XL710 X710 Virtual Function Linux driver. +Copyright(c) 2013 Intel Corporation. + +Contents +======== + +- Identifying Your Adapter +- Known Issues/Troubleshooting +- Support + +This file describes the i40evf Linux* Base Driver for the Intel(R) XL710 +X710 Virtual Function. + +The i40evf driver supports XL710 and X710 virtual function devices that +can only be activated on kernels with CONFIG_PCI_IOV enabled. + +The guest OS loading the i40evf driver must support MSI-X interrupts. + +Identifying Your Adapter +======================== + +For more information on how to identify your adapter, go to the Adapter & +Driver ID Guide at: + + http://support.intel.com/support/go/network/adapter/idguide.htm + +Known Issues/Troubleshooting +============================ + + +Support +======= + +For general information, go to the Intel support website at: + + http://support.intel.com + +or the Intel Wired Networking project hosted by Sourceforge at: + + http://sourceforge.net/projects/e1000 + +If an issue is identified with the released source code on the supported +kernel with a supported adapter, email the specific information related +to the issue to e1000-devel@lists.sf.net diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 8a984e994e61..5de03740cdd5 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -15,17 +15,47 @@ ip_default_ttl - INTEGER forwarded) IP packets. Should be between 1 and 255 inclusive. Default: 64 (as recommended by RFC1700) -ip_no_pmtu_disc - BOOLEAN - Disable Path MTU Discovery. If enabled and a +ip_no_pmtu_disc - INTEGER + Disable Path MTU Discovery. If enabled in mode 1 and a fragmentation-required ICMP is received, the PMTU to this destination will be set to min_pmtu (see below). You will need to raise min_pmtu to the smallest interface MTU on your system manually if you want to avoid locally generated fragments. + + In mode 2 incoming Path MTU Discovery messages will be + discarded. Outgoing frames are handled the same as in mode 1, + implicitly setting IP_PMTUDISC_DONT on every created socket. + + Mode 3 is a hardend pmtu discover mode. The kernel will only + accept fragmentation-needed errors if the underlying protocol + can verify them besides a plain socket lookup. Current + protocols for which pmtu events will be honored are TCP, SCTP + and DCCP as they verify e.g. the sequence number or the + association. This mode should not be enabled globally but is + only intended to secure e.g. name servers in namespaces where + TCP path mtu must still work but path MTU information of other + protocols should be discarded. If enabled globally this mode + could break other protocols. + + Possible values: 0-3 Default: FALSE min_pmtu - INTEGER default 552 - minimum discovered Path MTU +ip_forward_use_pmtu - BOOLEAN + By default we don't trust protocol path MTUs while forwarding + because they could be easily forged and can lead to unwanted + fragmentation by the router. + You only need to enable this if you have user-space software + which tries to discover path mtus by itself and depends on the + kernel honoring this information. This is normally not the + case. + Default: 0 (disabled) + Possible values: + 0 - disabled + 1 - enabled + route/max_size - INTEGER Maximum number of routes allowed in the kernel. Increase this when using large numbers of interfaces and/or routes. @@ -160,6 +190,16 @@ tcp_app_win - INTEGER buffer. Value 0 is special, it means that nothing is reserved. Default: 31 +tcp_autocorking - BOOLEAN + Enable TCP auto corking : + When applications do consecutive small write()/sendmsg() system calls, + we try to coalesce these small writes as much as possible, to lower + total amount of sent packets. This is done if at least one prior + packet for the flow is waiting in Qdisc queues or device transmit + queue. Applications can still use TCP_CORK for optimal behavior + when they know how/when to uncork their sockets. + Default : 1 + tcp_available_congestion_control - STRING Shows the available congestion control choices that are registered. More congestion control algorithms may be available as modules, @@ -1078,6 +1118,21 @@ bindv6only - BOOLEAN Default: FALSE (as specified in RFC3493) +flowlabel_consistency - BOOLEAN + Protect the consistency (and unicity) of flow label. + You have to disable it to use IPV6_FL_F_REFLECT flag on the + flow label manager. + TRUE: enabled + FALSE: disabled + Default: TRUE + +anycast_src_echo_reply - BOOLEAN + Controls the use of anycast addresses as source addresses for ICMPv6 + echo reply + TRUE: enabled + FALSE: disabled + Default: FALSE + IPv6 Fragmentation: ip6frag_high_thresh - INTEGER diff --git a/Documentation/networking/ipsec.txt b/Documentation/networking/ipsec.txt new file mode 100644 index 000000000000..8dbc08b7e431 --- /dev/null +++ b/Documentation/networking/ipsec.txt @@ -0,0 +1,38 @@ + +Here documents known IPsec corner cases which need to be keep in mind when +deploy various IPsec configuration in real world production environment. + +1. IPcomp: Small IP packet won't get compressed at sender, and failed on + policy check on receiver. + +Quote from RFC3173: +2.2. Non-Expansion Policy + + If the total size of a compressed payload and the IPComp header, as + defined in section 3, is not smaller than the size of the original + payload, the IP datagram MUST be sent in the original non-compressed + form. To clarify: If an IP datagram is sent non-compressed, no + + IPComp header is added to the datagram. This policy ensures saving + the decompression processing cycles and avoiding incurring IP + datagram fragmentation when the expanded datagram is larger than the + MTU. + + Small IP datagrams are likely to expand as a result of compression. + Therefore, a numeric threshold should be applied before compression, + where IP datagrams of size smaller than the threshold are sent in the + original form without attempting compression. The numeric threshold + is implementation dependent. + +Current IPComp implementation is indeed by the book, while as in practice +when sending non-compressed packet to the peer(whether or not packet len +is smaller than the threshold or the compressed len is large than original +packet len), the packet is dropped when checking the policy as this packet +matches the selector but not coming from any XFRM layer, i.e., with no +security path. Such naked packet will not eventually make it to upper layer. +The result is much more wired to the user when ping peer with different +payload length. + +One workaround is try to set "level use" for each policy if user observed +above scenario. The consequence of doing so is small packet(uncompressed) +will skip policy checking on receiver side. diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index 8e48e3b14227..91ffe1d9e8ca 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -98,6 +98,11 @@ by the kernel. The destruction of the socket and all associated resources is done by a simple call to close(fd). +Similarly as without PACKET_MMAP, it is possible to use one socket +for capture and transmission. This can be done by mapping the +allocated RX and TX buffer ring with a single mmap() call. +See "Mapping and use of the circular buffer (ring)". + Next I will describe PACKET_MMAP settings and its constraints, also the mapping of the circular buffer in the user process and the use of this buffer. @@ -414,6 +419,19 @@ tp_block_size/tp_frame_size frames there will be a gap between the frames. This is because a frame cannot be spawn across two blocks. +To use one socket for capture and transmission, the mapping of both the +RX and TX buffer ring has to be done with one call to mmap: + + ... + setsockopt(fd, SOL_PACKET, PACKET_RX_RING, &foo, sizeof(foo)); + setsockopt(fd, SOL_PACKET, PACKET_TX_RING, &bar, sizeof(bar)); + ... + rx_ring = mmap(0, size * 2, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); + tx_ring = rx_ring + size; + +RX must be the first as the kernel maps the TX ring memory right +after the RX one. + At the beginning of each frame there is an status field (see struct tpacket_hdr). If this field is 0 means that the frame is ready to be used for the kernel, If not, there is a frame the user can read @@ -517,8 +535,6 @@ where 'tpacket_version' can be TPACKET_V1 (default), TPACKET_V2, TPACKET_V3. TPACKET_V1: - Default if not otherwise specified by setsockopt(2) - RX_RING, TX_RING available - - VLAN metadata information available for packets - (TP_STATUS_VLAN_VALID) TPACKET_V1 --> TPACKET_V2: - Made 64 bit clean due to unsigned long usage in TPACKET_V1 @@ -526,6 +542,13 @@ TPACKET_V1 --> TPACKET_V2: userspace and the like - Timestamp resolution in nanoseconds instead of microseconds - RX_RING, TX_RING available + - VLAN metadata information available for packets + (TP_STATUS_VLAN_VALID, TP_STATUS_VLAN_TPID_VALID), + in the tpacket2_hdr structure: + - TP_STATUS_VLAN_VALID bit being set into the tp_status field indicates + that the tp_vlan_tci field has valid VLAN TCI value + - TP_STATUS_VLAN_TPID_VALID bit being set into the tp_status field + indicates that the tp_vlan_tpid field has valid VLAN TPID value - How to switch to TPACKET_V2: 1. Replace struct tpacket_hdr by struct tpacket2_hdr 2. Query header len and save @@ -953,6 +976,27 @@ int main(int argc, char **argp) } ------------------------------------------------------------------------------- ++ PACKET_QDISC_BYPASS +------------------------------------------------------------------------------- + +If there is a requirement to load the network with many packets in a similar +fashion as pktgen does, you might set the following option after socket +creation: + + int one = 1; + setsockopt(fd, SOL_PACKET, PACKET_QDISC_BYPASS, &one, sizeof(one)); + +This has the side-effect, that packets sent through PF_PACKET will bypass the +kernel's qdisc layer and are forcedly pushed to the driver directly. Meaning, +packet are not buffered, tc disciplines are ignored, increased loss can occur +and such packets are also not visible to other PF_PACKET sockets anymore. So, +you have been warned; generally, this can be useful for stress testing various +components of a system. + +On default, PACKET_QDISC_BYPASS is disabled and needs to be explicitly enabled +on PF_PACKET sockets. + +------------------------------------------------------------------------------- + PACKET_TIMESTAMP ------------------------------------------------------------------------------- diff --git a/Documentation/networking/phy.txt b/Documentation/networking/phy.txt index d5b1a3935245..ebf270719402 100644 --- a/Documentation/networking/phy.txt +++ b/Documentation/networking/phy.txt @@ -255,7 +255,8 @@ Writing a PHY driver config_init: configures PHY into a sane state after a reset. For instance, a Davicom PHY requires descrambling disabled. - probe: Does any setup needed by the driver + probe: Allocate phy->priv, optionally refuse to bind. + PHY may not have been reset or had fixups run yet. suspend/resume: power management config_aneg: Changes the speed/duplex/negotiation settings read_status: Reads the current speed/duplex/negotiation settings diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt index 75e4fd708ccb..5a61a240a652 100644 --- a/Documentation/networking/pktgen.txt +++ b/Documentation/networking/pktgen.txt @@ -108,7 +108,9 @@ Examples: MPLS_RND, VID_RND, SVID_RND QUEUE_MAP_RND # queue map random QUEUE_MAP_CPU # queue map mirrors smp_processor_id() + IPSEC # Make IPsec encapsulation for packet + pgset spi SPI_VALUE Set specific SA used to transform packet. pgset "udp_src_min 9" set UDP source port min, If < udp_src_max, then cycle through the port range. @@ -177,6 +179,18 @@ Note when adding devices to a specific CPU there good idea to also assign /proc/irq/XX/smp_affinity so the TX-interrupts gets bound to the same CPU. as this reduces cache bouncing when freeing skb's. +Enable IPsec +============ +Default IPsec transformation with ESP encapsulation plus Transport mode +could be enabled by simply setting: + +pgset "flag IPSEC" +pgset "flows 1" + +To avoid breaking existing testbed scripts for using AH type and tunnel mode, +user could use "pgset spi SPI_VALUE" to specify which formal of transformation +to employ. + Current commands and configuration options ========================================== @@ -225,6 +239,7 @@ flag UDPDST_RND MACSRC_RND MACDST_RND + IPSEC dst_min dst_max diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt index 9551622d0a7b..356f791af574 100644 --- a/Documentation/networking/regulatory.txt +++ b/Documentation/networking/regulatory.txt @@ -159,10 +159,10 @@ struct ieee80211_regdomain mydriver_jp_regdom = { REG_RULE(2412-20, 2484+20, 40, 6, 20, 0), /* IEEE 802.11a, channels 34..48 */ REG_RULE(5170-20, 5240+20, 40, 6, 20, - NL80211_RRF_PASSIVE_SCAN), + NL80211_RRF_NO_IR), /* IEEE 802.11a, channels 52..64 */ REG_RULE(5260-20, 5320+20, 40, 6, 20, - NL80211_RRF_NO_IBSS | + NL80211_RRF_NO_IR| NL80211_RRF_DFS), } }; diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt index cdd916da838d..2090895b08d4 100644 --- a/Documentation/networking/stmmac.txt +++ b/Documentation/networking/stmmac.txt @@ -127,8 +127,9 @@ struct plat_stmmacenet_data { int riwt_off; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); - int (*init)(struct platform_device *pdev); - void (*exit)(struct platform_device *pdev); + void *(*setup)(struct platform_device *pdev); + int (*init)(struct platform_device *pdev, void *priv); + void (*exit)(struct platform_device *pdev, void *priv); void *custom_cfg; void *custom_data; void *bsp_priv; @@ -169,10 +170,13 @@ Where: o bus_setup: perform HW setup of the bus. For example, on some ST platforms this field is used to configure the AMBA bridge to generate more efficient STBus traffic. - o init/exit: callbacks used for calling a custom initialization; + o setup/init/exit: callbacks used for calling a custom initialization; this is sometime necessary on some platforms (e.g. ST boxes) where the HW needs to have set some PIO lines or system cfg - registers. + registers. setup should return a pointer to private data, + which will be stored in bsp_priv, and then passed to init and + exit callbacks. init/exit callbacks should not use or modify + platform data. o custom_cfg/custom_data: this is a custom configuration that can be passed while initializing the resources. o bsp_priv: another private pointer. diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 98097d8cb910..661d3c316a17 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -85,7 +85,7 @@ Filled in if SOF_TIMESTAMPING_SYS_HARDWARE is set. Requires support by the network device and will be empty without that support. -SIOCSHWTSTAMP: +SIOCSHWTSTAMP, SIOCGHWTSTAMP: Hardware time stamping must also be initialized for each device driver that is expected to do hardware time stamping. The parameter is defined in @@ -115,6 +115,10 @@ Only a processes with admin rights may change the configuration. User space is responsible to ensure that multiple processes don't interfere with each other and that the settings are reset. +Any process can read the actual configuration by passing this +structure to ioctl(SIOCGHWTSTAMP) in the same way. However, this has +not been implemented in all drivers. + /* possible values for hwtstamp_config->tx_type */ enum { /* @@ -157,7 +161,8 @@ DEVICE IMPLEMENTATION A driver which supports hardware time stamping must support the SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with -the actual values as described in the section on SIOCSHWTSTAMP. +the actual values as described in the section on SIOCSHWTSTAMP. It +should also support SIOCGHWTSTAMP. Time stamps for received packets must be stored in the skb. To get a pointer to the shared time stamp structure of the skb call skb_hwtstamps(). Then diff --git a/Documentation/networking/timestamping/.gitignore b/Documentation/networking/timestamping/.gitignore index 71e81eb2e22f..a380159765ce 100644 --- a/Documentation/networking/timestamping/.gitignore +++ b/Documentation/networking/timestamping/.gitignore @@ -1 +1,2 @@ timestamping +hwtstamp_config diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile index e79973443e9f..d934afc8306a 100644 --- a/Documentation/networking/timestamping/Makefile +++ b/Documentation/networking/timestamping/Makefile @@ -2,12 +2,13 @@ obj- := dummy.o # List of programs to build -hostprogs-y := timestamping +hostprogs-y := timestamping hwtstamp_config # Tell kbuild to always build the programs always := $(hostprogs-y) HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include +HOSTCFLAGS_hwtstamp_config.o += -I$(objtree)/usr/include clean: - rm -f timestamping + rm -f timestamping hwtstamp_config diff --git a/Documentation/networking/timestamping/hwtstamp_config.c b/Documentation/networking/timestamping/hwtstamp_config.c new file mode 100644 index 000000000000..e8b685a7f15f --- /dev/null +++ b/Documentation/networking/timestamping/hwtstamp_config.c @@ -0,0 +1,134 @@ +/* Test program for SIOC{G,S}HWTSTAMP + * Copyright 2013 Solarflare Communications + * Author: Ben Hutchings + */ + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <sys/socket.h> +#include <sys/ioctl.h> + +#include <linux/if.h> +#include <linux/net_tstamp.h> +#include <linux/sockios.h> + +static int +lookup_value(const char **names, int size, const char *name) +{ + int value; + + for (value = 0; value < size; value++) + if (names[value] && strcasecmp(names[value], name) == 0) + return value; + + return -1; +} + +static const char * +lookup_name(const char **names, int size, int value) +{ + return (value >= 0 && value < size) ? names[value] : NULL; +} + +static void list_names(FILE *f, const char **names, int size) +{ + int value; + + for (value = 0; value < size; value++) + if (names[value]) + fprintf(f, " %s\n", names[value]); +} + +static const char *tx_types[] = { +#define TX_TYPE(name) [HWTSTAMP_TX_ ## name] = #name + TX_TYPE(OFF), + TX_TYPE(ON), + TX_TYPE(ONESTEP_SYNC) +#undef TX_TYPE +}; +#define N_TX_TYPES ((int)(sizeof(tx_types) / sizeof(tx_types[0]))) + +static const char *rx_filters[] = { +#define RX_FILTER(name) [HWTSTAMP_FILTER_ ## name] = #name + RX_FILTER(NONE), + RX_FILTER(ALL), + RX_FILTER(SOME), + RX_FILTER(PTP_V1_L4_EVENT), + RX_FILTER(PTP_V1_L4_SYNC), + RX_FILTER(PTP_V1_L4_DELAY_REQ), + RX_FILTER(PTP_V2_L4_EVENT), + RX_FILTER(PTP_V2_L4_SYNC), + RX_FILTER(PTP_V2_L4_DELAY_REQ), + RX_FILTER(PTP_V2_L2_EVENT), + RX_FILTER(PTP_V2_L2_SYNC), + RX_FILTER(PTP_V2_L2_DELAY_REQ), + RX_FILTER(PTP_V2_EVENT), + RX_FILTER(PTP_V2_SYNC), + RX_FILTER(PTP_V2_DELAY_REQ), +#undef RX_FILTER +}; +#define N_RX_FILTERS ((int)(sizeof(rx_filters) / sizeof(rx_filters[0]))) + +static void usage(void) +{ + fputs("Usage: hwtstamp_config if_name [tx_type rx_filter]\n" + "tx_type is any of (case-insensitive):\n", + stderr); + list_names(stderr, tx_types, N_TX_TYPES); + fputs("rx_filter is any of (case-insensitive):\n", stderr); + list_names(stderr, rx_filters, N_RX_FILTERS); +} + +int main(int argc, char **argv) +{ + struct ifreq ifr; + struct hwtstamp_config config; + const char *name; + int sock; + + if ((argc != 2 && argc != 4) || (strlen(argv[1]) >= IFNAMSIZ)) { + usage(); + return 2; + } + + if (argc == 4) { + config.flags = 0; + config.tx_type = lookup_value(tx_types, N_TX_TYPES, argv[2]); + config.rx_filter = lookup_value(rx_filters, N_RX_FILTERS, argv[3]); + if (config.tx_type < 0 || config.rx_filter < 0) { + usage(); + return 2; + } + } + + sock = socket(AF_INET, SOCK_DGRAM, 0); + if (sock < 0) { + perror("socket"); + return 1; + } + + strcpy(ifr.ifr_name, argv[1]); + ifr.ifr_data = (caddr_t)&config; + + if (ioctl(sock, (argc == 2) ? SIOCGHWTSTAMP : SIOCSHWTSTAMP, &ifr)) { + perror("ioctl"); + return 1; + } + + printf("flags = %#x\n", config.flags); + name = lookup_name(tx_types, N_TX_TYPES, config.tx_type); + if (name) + printf("tx_type = %s\n", name); + else + printf("tx_type = %d\n", config.tx_type); + name = lookup_name(rx_filters, N_RX_FILTERS, config.rx_filter); + if (name) + printf("rx_filter = %s\n", name); + else + printf("rx_filter = %d\n", config.rx_filter); + + return 0; +} diff --git a/Documentation/s390/qeth.txt b/Documentation/s390/qeth.txt new file mode 100644 index 000000000000..74122ada9949 --- /dev/null +++ b/Documentation/s390/qeth.txt @@ -0,0 +1,50 @@ +IBM s390 QDIO Ethernet Driver + +HiperSockets Bridge Port Support + +Uevents + +To generate the events the device must be assigned a role of either +a primary or a secondary Bridge Port. For more information, see +"z/VM Connectivity, SC24-6174". + +When run on HiperSockets Bridge Capable Port hardware, and the state +of some configured Bridge Port device on the channel changes, a udev +event with ACTION=CHANGE is emitted on behalf of the corresponding +ccwgroup device. The event has the following attributes: + +BRIDGEPORT=statechange - indicates that the Bridge Port device changed + its state. + +ROLE={primary|secondary|none} - the role assigned to the port. + +STATE={active|standby|inactive} - the newly assumed state of the port. + +When run on HiperSockets Bridge Capable Port hardware with host address +notifications enabled, a udev event with ACTION=CHANGE is emitted. +It is emitted on behalf of the corresponding ccwgroup device when a host +or a VLAN is registered or unregistered on the network served by the device. +The event has the following attributes: + +BRIDGEDHOST={reset|register|deregister|abort} - host address + notifications are started afresh, a new host or VLAN is registered or + deregistered on the Bridge Port HiperSockets channel, or address + notifications are aborted. + +VLAN=numeric-vlan-id - VLAN ID on which the event occurred. Not included + if no VLAN is involved in the event. + +MAC=xx:xx:xx:xx:xx:xx - MAC address of the host that is being registered + or deregistered from the HiperSockets channel. Not reported if the + event reports the creation or destruction of a VLAN. + +NTOK_BUSID=x.y.zzzz - device bus ID (CSSID, SSID and device number). + +NTOK_IID=xx - device IID. + +NTOK_CHPID=xx - device CHPID. + +NTOK_CHID=xxxx - device channel ID. + +Note that the NTOK_* attributes refer to devices other than the one +connected to the system on which the OS is running. diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt index f866c72291bf..a445da098bc6 100644 --- a/Documentation/unaligned-memory-access.txt +++ b/Documentation/unaligned-memory-access.txt @@ -137,24 +137,34 @@ Code that causes unaligned access ================================= With the above in mind, let's move onto a real life example of a function -that can cause an unaligned memory access. The following function adapted +that can cause an unaligned memory access. The following function taken from include/linux/etherdevice.h is an optimized routine to compare two ethernet MAC addresses for equality. -unsigned int compare_ether_addr(const u8 *addr1, const u8 *addr2) +bool ether_addr_equal(const u8 *addr1, const u8 *addr2) { - const u16 *a = (const u16 *) addr1; - const u16 *b = (const u16 *) addr2; +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) | + ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4))); + + return fold == 0; +#else + const u16 *a = (const u16 *)addr1; + const u16 *b = (const u16 *)addr2; return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0; +#endif } -In the above function, the reference to a[0] causes 2 bytes (16 bits) to -be read from memory starting at address addr1. Think about what would happen -if addr1 was an odd address such as 0x10003. (Hint: it'd be an unaligned -access.) +In the above function, when the hardware has efficient unaligned access +capability, there is no issue with this code. But when the hardware isn't +able to access memory on arbitrary boundaries, the reference to a[0] causes +2 bytes (16 bits) to be read from memory starting at address addr1. + +Think about what would happen if addr1 was an odd address such as 0x10003. +(Hint: it'd be an unaligned access.) Despite the potential unaligned access problems with the above function, it -is included in the kernel anyway but is understood to only work on +is included in the kernel anyway but is understood to only work normally on 16-bit-aligned addresses. It is up to the caller to ensure this alignment or not use this function at all. This alignment-unsafe function is still useful as it is a decent optimization for the cases when you can ensure alignment, |