diff options
Diffstat (limited to 'Documentation/networking')
| -rw-r--r-- | Documentation/networking/bonding.txt | 6 | ||||
| -rw-r--r-- | Documentation/networking/can.txt | 237 | ||||
| -rw-r--r-- | Documentation/networking/dm9000.txt | 2 | ||||
| -rw-r--r-- | Documentation/networking/ieee802154.txt | 76 | ||||
| -rw-r--r-- | Documentation/networking/ip-sysctl.txt | 18 | ||||
| -rw-r--r-- | Documentation/networking/ipv6.txt | 37 | ||||
| -rw-r--r-- | Documentation/networking/l2tp.txt | 2 | ||||
| -rw-r--r-- | Documentation/networking/mac80211-injection.txt | 28 | ||||
| -rw-r--r-- | Documentation/networking/netdevices.txt | 2 | ||||
| -rw-r--r-- | Documentation/networking/operstates.txt | 3 | ||||
| -rw-r--r-- | Documentation/networking/packet_mmap.txt | 140 | ||||
| -rw-r--r-- | Documentation/networking/phonet.txt | 2 | ||||
| -rw-r--r-- | Documentation/networking/regulatory.txt | 2 |
13 files changed, 463 insertions, 92 deletions
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 08762750f12..d5181ce9ff6 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -221,7 +221,7 @@ ad_select - Any slave's 802.3ad association state changes - - The bond's adminstrative state changes to up + - The bond's administrative state changes to up count or 2 @@ -369,7 +369,7 @@ fail_over_mac When this policy is used in conjuction with the mii monitor, devices which assert link up prior to being able to actually transmit and receive are particularly - susecptible to loss of the gratuitous ARP, and an + susceptible to loss of the gratuitous ARP, and an appropriate updelay setting may be required. follow or 2 @@ -1794,7 +1794,7 @@ target to query. generally referred to as "trunk failover." This is a feature of the switch that causes the link state of a particular switch port to be set down (or up) when the state of another switch port goes down (or up). -It's purpose is to propogate link failures from logically "exterior" ports +Its purpose is to propagate link failures from logically "exterior" ports to the logically "interior" ports that bonding is able to monitor via miimon. Availability and configuration for trunk failover varies by switch, but this can be a viable alternative to the ARP monitor when using diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt index 2035bc4932f..cd79735013f 100644 --- a/Documentation/networking/can.txt +++ b/Documentation/networking/can.txt @@ -36,10 +36,15 @@ This file contains 6.2 local loopback of sent frames 6.3 CAN controller hardware filters 6.4 The virtual CAN driver (vcan) - 6.5 currently supported CAN hardware - 6.6 todo + 6.5 The CAN network device driver interface + 6.5.1 Netlink interface to set/get devices properties + 6.5.2 Setting the CAN bit-timing + 6.5.3 Starting and stopping the CAN network device + 6.6 supported CAN hardware - 7 Credits + 7 Socket CAN resources + + 8 Credits ============================================================================ @@ -234,6 +239,8 @@ solution for a couple of reasons: the user application using the common CAN filter mechanisms. Inside this filter definition the (interested) type of errors may be selected. The reception of error frames is disabled by default. + The format of the CAN error frame is briefly decribed in the Linux + header file "include/linux/can/error.h". 4. How to use Socket CAN ------------------------ @@ -327,7 +334,7 @@ solution for a couple of reasons: return 1; } - /* paraniod check ... */ + /* paranoid check ... */ if (nbytes < sizeof(struct can_frame)) { fprintf(stderr, "read: incomplete CAN frame\n"); return 1; @@ -605,61 +612,213 @@ solution for a couple of reasons: removal of vcan network devices can be managed with the ip(8) tool: - Create a virtual CAN network interface: - ip link add type vcan + $ ip link add type vcan - Create a virtual CAN network interface with a specific name 'vcan42': - ip link add dev vcan42 type vcan + $ ip link add dev vcan42 type vcan - Remove a (virtual CAN) network interface 'vcan42': - ip link del vcan42 - - The tool 'vcan' from the SocketCAN SVN repository on BerliOS is obsolete. - - Virtual CAN network device creation in older Kernels: - In Linux Kernel versions < 2.6.24 the vcan driver creates 4 vcan - netdevices at module load time by default. This value can be changed - with the module parameter 'numdev'. E.g. 'modprobe vcan numdev=8' - - 6.5 currently supported CAN hardware + $ ip link del vcan42 + + 6.5 The CAN network device driver interface + + The CAN network device driver interface provides a generic interface + to setup, configure and monitor CAN network devices. The user can then + configure the CAN device, like setting the bit-timing parameters, via + the netlink interface using the program "ip" from the "IPROUTE2" + utility suite. The following chapter describes briefly how to use it. + Furthermore, the interface uses a common data structure and exports a + set of common functions, which all real CAN network device drivers + should use. Please have a look to the SJA1000 or MSCAN driver to + understand how to use them. The name of the module is can-dev.ko. + + 6.5.1 Netlink interface to set/get devices properties + + The CAN device must be configured via netlink interface. The supported + netlink message types are defined and briefly described in + "include/linux/can/netlink.h". CAN link support for the program "ip" + of the IPROUTE2 utility suite is avaiable and it can be used as shown + below: + + - Setting CAN device properties: + + $ ip link set can0 type can help + Usage: ip link set DEVICE type can + [ bitrate BITRATE [ sample-point SAMPLE-POINT] ] | + [ tq TQ prop-seg PROP_SEG phase-seg1 PHASE-SEG1 + phase-seg2 PHASE-SEG2 [ sjw SJW ] ] + + [ loopback { on | off } ] + [ listen-only { on | off } ] + [ triple-sampling { on | off } ] + + [ restart-ms TIME-MS ] + [ restart ] + + Where: BITRATE := { 1..1000000 } + SAMPLE-POINT := { 0.000..0.999 } + TQ := { NUMBER } + PROP-SEG := { 1..8 } + PHASE-SEG1 := { 1..8 } + PHASE-SEG2 := { 1..8 } + SJW := { 1..4 } + RESTART-MS := { 0 | NUMBER } + + - Display CAN device details and statistics: + + $ ip -details -statistics link show can0 + 2: can0: <NOARP,UP,LOWER_UP,ECHO> mtu 16 qdisc pfifo_fast state UP qlen 10 + link/can + can <TRIPLE-SAMPLING> state ERROR-ACTIVE restart-ms 100 + bitrate 125000 sample_point 0.875 + tq 125 prop-seg 6 phase-seg1 7 phase-seg2 2 sjw 1 + sja1000: tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1 + clock 8000000 + re-started bus-errors arbit-lost error-warn error-pass bus-off + 41 17457 0 41 42 41 + RX: bytes packets errors dropped overrun mcast + 140859 17608 17457 0 0 0 + TX: bytes packets errors dropped carrier collsns + 861 112 0 41 0 0 + + More info to the above output: + + "<TRIPLE-SAMPLING>" + Shows the list of selected CAN controller modes: LOOPBACK, + LISTEN-ONLY, or TRIPLE-SAMPLING. + + "state ERROR-ACTIVE" + The current state of the CAN controller: "ERROR-ACTIVE", + "ERROR-WARNING", "ERROR-PASSIVE", "BUS-OFF" or "STOPPED" + + "restart-ms 100" + Automatic restart delay time. If set to a non-zero value, a + restart of the CAN controller will be triggered automatically + in case of a bus-off condition after the specified delay time + in milliseconds. By default it's off. + + "bitrate 125000 sample_point 0.875" + Shows the real bit-rate in bits/sec and the sample-point in the + range 0.000..0.999. If the calculation of bit-timing parameters + is enabled in the kernel (CONFIG_CAN_CALC_BITTIMING=y), the + bit-timing can be defined by setting the "bitrate" argument. + Optionally the "sample-point" can be specified. By default it's + 0.000 assuming CIA-recommended sample-points. + + "tq 125 prop-seg 6 phase-seg1 7 phase-seg2 2 sjw 1" + Shows the time quanta in ns, propagation segment, phase buffer + segment 1 and 2 and the synchronisation jump width in units of + tq. They allow to define the CAN bit-timing in a hardware + independent format as proposed by the Bosch CAN 2.0 spec (see + chapter 8 of http://www.semiconductors.bosch.de/pdf/can2spec.pdf). + + "sja1000: tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1 + clock 8000000" + Shows the bit-timing constants of the CAN controller, here the + "sja1000". The minimum and maximum values of the time segment 1 + and 2, the synchronisation jump width in units of tq, the + bitrate pre-scaler and the CAN system clock frequency in Hz. + These constants could be used for user-defined (non-standard) + bit-timing calculation algorithms in user-space. + + "re-started bus-errors arbit-lost error-warn error-pass bus-off" + Shows the number of restarts, bus and arbitration lost errors, + and the state changes to the error-warning, error-passive and + bus-off state. RX overrun errors are listed in the "overrun" + field of the standard network statistics. + + 6.5.2 Setting the CAN bit-timing + + The CAN bit-timing parameters can always be defined in a hardware + independent format as proposed in the Bosch CAN 2.0 specification + specifying the arguments "tq", "prop_seg", "phase_seg1", "phase_seg2" + and "sjw": + + $ ip link set canX type can tq 125 prop-seg 6 \ + phase-seg1 7 phase-seg2 2 sjw 1 + + If the kernel option CONFIG_CAN_CALC_BITTIMING is enabled, CIA + recommended CAN bit-timing parameters will be calculated if the bit- + rate is specified with the argument "bitrate": + + $ ip link set canX type can bitrate 125000 + + Note that this works fine for the most common CAN controllers with + standard bit-rates but may *fail* for exotic bit-rates or CAN system + clock frequencies. Disabling CONFIG_CAN_CALC_BITTIMING saves some + space and allows user-space tools to solely determine and set the + bit-timing parameters. The CAN controller specific bit-timing + constants can be used for that purpose. They are listed by the + following command: + + $ ip -details link show can0 + ... + sja1000: clock 8000000 tseg1 1..16 tseg2 1..8 sjw 1..4 brp 1..64 brp-inc 1 + + 6.5.3 Starting and stopping the CAN network device + + A CAN network device is started or stopped as usual with the command + "ifconfig canX up/down" or "ip link set canX up/down". Be aware that + you *must* define proper bit-timing parameters for real CAN devices + before you can start it to avoid error-prone default settings: + + $ ip link set canX up type can bitrate 125000 + + A device may enter the "bus-off" state if too much 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.: + + $ ip link set canX type can restart-ms 100 + + Alternatively, the application may realize the "bus-off" condition + by monitoring CAN error frames and do a restart when appropriate with + the command: + + $ ip link set canX type can restart + + Note that a restart will also create a CAN error frame (see also + chapter 3.4). - On the project website http://developer.berlios.de/projects/socketcan - there are different drivers available: + 6.6 Supported CAN hardware - vcan: Virtual CAN interface driver (if no real hardware is available) - sja1000: Philips SJA1000 CAN controller (recommended) - i82527: Intel i82527 CAN controller - mscan: Motorola/Freescale CAN controller (e.g. inside SOC MPC5200) - ccan: CCAN controller core (e.g. inside SOC h7202) - slcan: For a bunch of CAN adaptors that are attached via a - serial line ASCII protocol (for serial / USB adaptors) + 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 + (see chapter 7) there might be further drivers available, also for + older kernel versions. - Additionally the different CAN adaptors (ISA/PCI/PCMCIA/USB/Parport) - from PEAK Systemtechnik support the CAN netdevice driver model - since Linux driver v6.0: http://www.peak-system.com/linux/index.htm +7. Socket CAN resources +----------------------- - Please check the Mailing Lists on the berlios OSS project website. + 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: - 6.6 todo + http://developer.berlios.de/projects/socketcan - The configuration interface for CAN network drivers is still an open - issue that has not been finalized in the socketcan project. Also the - idea of having a library module (candev.ko) that holds functions - that are needed by all CAN netdevices is not ready to ship. - Your contribution is welcome. + 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. -7. Credits +8. Credits ---------- - Oliver Hartkopp (PF_CAN core, filters, drivers, bcm) + Oliver Hartkopp (PF_CAN core, filters, drivers, bcm, SJA1000 driver) Urs Thuermann (PF_CAN core, kernel integration, socket interfaces, raw, vcan) Jan Kizka (RT-SocketCAN core, Socket-API reconciliation) - Wolfgang Grandegger (RT-SocketCAN core & drivers, Raw Socket-API reviews) + Wolfgang Grandegger (RT-SocketCAN core & drivers, Raw Socket-API reviews, + CAN device driver interface, MSCAN driver) Robert Schwebel (design reviews, PTXdist integration) Marc Kleine-Budde (design reviews, Kernel 2.6 cleanups, drivers) Benedikt Spranger (reviews) Thomas Gleixner (LKML reviews, coding style, posting hints) - Andrey Volkov (kernel subtree structure, ioctls, mscan driver) + Andrey Volkov (kernel subtree structure, ioctls, MSCAN driver) Matthias Brukner (first SJA1000 CAN netdevice implementation Q2/2003) Klaus Hitschler (PEAK driver integration) Uwe Koppe (CAN netdevices with PF_PACKET approach) Michael Schulze (driver layer loopback requirement, RT CAN drivers review) + Pavel Pisa (Bit-timing calculation) + Sascha Hauer (SJA1000 platform driver) + Sebastian Haas (SJA1000 EMS PCI driver) + Markus Plessing (SJA1000 EMS PCI driver) + Per Dalen (SJA1000 Kvaser PCI driver) + Sam Ravnborg (reviews, coding style, kbuild help) diff --git a/Documentation/networking/dm9000.txt b/Documentation/networking/dm9000.txt index 65df3dea556..5552e2e575c 100644 --- a/Documentation/networking/dm9000.txt +++ b/Documentation/networking/dm9000.txt @@ -129,7 +129,7 @@ PHY Link state polling ---------------------- The driver keeps track of the link state and informs the network core -about link (carrier) availablilty. This is managed by several methods +about link (carrier) availability. This is managed by several methods depending on the version of the chip and on which PHY is being used. For the internal PHY, the original (and currently default) method is diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt new file mode 100644 index 00000000000..a0280ad2edc --- /dev/null +++ b/Documentation/networking/ieee802154.txt @@ -0,0 +1,76 @@ + + Linux IEEE 802.15.4 implementation + + +Introduction +============ + +The Linux-ZigBee project goal is to provide complete implementation +of IEEE 802.15.4 / ZigBee / 6LoWPAN protocols. IEEE 802.15.4 is a stack +of protocols for organizing Low-Rate Wireless Personal Area Networks. + +Currently only IEEE 802.15.4 layer is implemented. We have choosen +to use plain Berkeley socket API, the generic Linux networking stack +to transfer IEEE 802.15.4 messages and a special protocol over genetlink +for configuration/management + + +Socket API +========== + +int sd = socket(PF_IEEE802154, SOCK_DGRAM, 0); +..... + +The address family, socket addresses etc. are defined in the +include/net/ieee802154/af_ieee802154.h header or in the special header +in our userspace package (see either linux-zigbee sourceforge download page +or git tree at git://linux-zigbee.git.sourceforge.net/gitroot/linux-zigbee). + +One can use SOCK_RAW for passing raw data towards device xmit function. YMMV. + + +MLME - MAC Level Management +============================ + +Most of IEEE 802.15.4 MLME interfaces are directly mapped on netlink commands. +See the include/net/ieee802154/nl802154.h header. Our userspace tools package +(see above) provides CLI configuration utility for radio interfaces and simple +coordinator for IEEE 802.15.4 networks as an example users of MLME protocol. + + +Kernel side +============= + +Like with WiFi, there are several types of devices implementing IEEE 802.15.4. +1) 'HardMAC'. The MAC layer is implemented in the device itself, the device + exports MLME and data API. +2) 'SoftMAC' or just radio. These types of devices are just radio transceivers + possibly with some kinds of acceleration like automatic CRC computation and + comparation, automagic ACK handling, address matching, etc. + +Those types of devices require different approach to be hooked into Linux kernel. + + +HardMAC +======= + +See the header include/net/ieee802154/netdevice.h. You have to implement Linux +net_device, with .type = ARPHRD_IEEE802154. Data is exchanged with socket family +code via plain sk_buffs. The control block of sk_buffs will contain additional +info as described in the struct ieee802154_mac_cb. + +To hook the MLME interface you have to populate the ml_priv field of your +net_device with a pointer to struct ieee802154_mlme_ops instance. All fields are +required. + +We provide an example of simple HardMAC driver at drivers/ieee802154/fakehard.c + + +SoftMAC +======= + +We are going to provide intermediate layer impelementing IEEE 802.15.4 MAC +in software. This is currently WIP. + +See header include/net/ieee802154/mac802154.h and several drivers in +drivers/ieee802154/ diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index b121c5db707..8be76235fe6 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -168,7 +168,16 @@ tcp_dsack - BOOLEAN Allows TCP to send "duplicate" SACKs. tcp_ecn - BOOLEAN - Enable Explicit Congestion Notification in TCP. + Enable Explicit Congestion Notification (ECN) in TCP. ECN is only + used when both ends of the TCP flow support it. It is useful to + avoid losses due to congestion (when the bottleneck router supports + ECN). + Possible values are: + 0 disable ECN + 1 ECN enabled + 2 Only server-side ECN enabled. If the other end does + not support ECN, behavior is like with ECN disabled. + Default: 2 tcp_fack - BOOLEAN Enable FACK congestion avoidance and fast retransmission. @@ -1048,6 +1057,13 @@ disable_ipv6 - BOOLEAN address. Default: FALSE (enable IPv6 operation) + When this value is changed from 1 to 0 (IPv6 is being enabled), + it will dynamically create a link-local address on the given + interface and start Duplicate Address Detection, if necessary. + + When this value is changed from 0 to 1 (IPv6 is being disabled), + it will dynamically delete all address on the given interface. + accept_dad - INTEGER Whether to accept DAD (Duplicate Address Detection). 0: Disable DAD diff --git a/Documentation/networking/ipv6.txt b/Documentation/networking/ipv6.txt index 268e5c103dd..9fd7e21296c 100644 --- a/Documentation/networking/ipv6.txt +++ b/Documentation/networking/ipv6.txt @@ -33,3 +33,40 @@ disable A reboot is required to enable IPv6. +autoconf + + Specifies whether to enable IPv6 address autoconfiguration + on all interfaces. This might be used when one does not wish + for addresses to be automatically generated from prefixes + received in Router Advertisements. + + The possible values and their effects are: + + 0 + IPv6 address autoconfiguration is disabled on all interfaces. + + Only the IPv6 loopback address (::1) and link-local addresses + will be added to interfaces. + + 1 + IPv6 address autoconfiguration is enabled on all interfaces. + + This is the default value. + +disable_ipv6 + + Specifies whether to disable IPv6 on all interfaces. + This might be used when no IPv6 addresses are desired. + + The possible values and their effects are: + + 0 + IPv6 is enabled on all interfaces. + + This is the default value. + + 1 + IPv6 is disabled on all interfaces. + + No IPv6 addresses will be added to interfaces. + diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt index 2451f551c50..63214b280e0 100644 --- a/Documentation/networking/l2tp.txt +++ b/Documentation/networking/l2tp.txt @@ -158,7 +158,7 @@ Sample Userspace Code } return 0; -Miscellanous +Miscellaneous ============ The PPPoL2TP driver was developed as part of the OpenL2TP project by diff --git a/Documentation/networking/mac80211-injection.txt b/Documentation/networking/mac80211-injection.txt index 84906ef3ed6..b30e81ad530 100644 --- a/Documentation/networking/mac80211-injection.txt +++ b/Documentation/networking/mac80211-injection.txt @@ -12,38 +12,22 @@ following format: The radiotap format is discussed in ./Documentation/networking/radiotap-headers.txt. -Despite 13 radiotap argument types are currently defined, most only make sense +Despite many radiotap parameters being currently defined, most only make sense to appear on received packets. The following information is parsed from the radiotap headers and used to control injection: - * IEEE80211_RADIOTAP_RATE - - rate in 500kbps units, automatic if invalid or not present - - - * IEEE80211_RADIOTAP_ANTENNA - - antenna to use, automatic if not present - - - * IEEE80211_RADIOTAP_DBM_TX_POWER - - transmit power in dBm, automatic if not present - - * IEEE80211_RADIOTAP_FLAGS IEEE80211_RADIOTAP_F_FCS: FCS will be removed and recalculated IEEE80211_RADIOTAP_F_WEP: frame will be encrypted if key available IEEE80211_RADIOTAP_F_FRAG: frame will be fragmented if longer than the - current fragmentation threshold. Note that - this flag is only reliable when software - fragmentation is enabled) + current fragmentation threshold. + The injection code can also skip all other currently defined radiotap fields facilitating replay of captured radiotap headers directly. -Here is an example valid radiotap header defining these three parameters +Here is an example valid radiotap header defining some parameters 0x00, 0x00, // <-- radiotap version 0x0b, 0x00, // <- radiotap header length @@ -72,8 +56,8 @@ interface), along the following lines: ... r = pcap_inject(ppcap, u8aSendBuffer, nLength); -You can also find sources for a complete inject test applet here: +You can also find a link to a complete inject application here: -http://penumbra.warmcat.com/_twk/tiki-index.php?page=packetspammer +http://wireless.kernel.org/en/users/Documentation/packetspammer Andy Green <andy@warmcat.com> diff --git a/Documentation/networking/netdevices.txt b/Documentation/networking/netdevices.txt index a2ab6a0b116..87b3d15f523 100644 --- a/Documentation/networking/netdevices.txt +++ b/Documentation/networking/netdevices.txt @@ -74,7 +74,7 @@ dev->hard_start_xmit: for this and return NETDEV_TX_LOCKED when the spin lock fails. The locking there should also properly protect against set_multicast_list. Note that the use of NETIF_F_LLTX is deprecated. - Dont use it for new drivers. + Don't use it for new drivers. Context: Process with BHs disabled or BH (timer), will be called with interrupts disabled by netconsole. diff --git a/Documentation/networking/operstates.txt b/Documentation/networking/operstates.txt index c9074f9b78b..1a77a3cfae5 100644 --- a/Documentation/networking/operstates.txt +++ b/Documentation/networking/operstates.txt @@ -38,9 +38,6 @@ ifinfomsg::if_flags & IFF_LOWER_UP: ifinfomsg::if_flags & IFF_DORMANT: Driver has signaled netif_dormant_on() -These interface flags can also be queried without netlink using the -SIOCGIFFLAGS ioctl. - TLV IFLA_OPERSTATE contains RFC2863 state of the interface in numeric representation: diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index 07c53d59603..a22fd85e379 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -4,16 +4,18 @@ This file documents the CONFIG_PACKET_MMAP option available with the PACKET socket interface on 2.4 and 2.6 kernels. This type of sockets is used for -capture network traffic with utilities like tcpdump or any other that uses -the libpcap library. - -You can find the latest version of this document at +capture network traffic with utilities like tcpdump or any other that needs +raw access to network interface. +You can find the latest version of this document at: http://pusa.uv.es/~ulisses/packet_mmap/ -Please send me your comments to +Howto can be found at: + http://wiki.gnu-log.net (packet_mmap) +Please send your comments to Ulisses Alonso Camaró <uaca@i.hate.spam.alumni.uv.es> + Johann Baudy <johann.baudy@gnu-log.net> ------------------------------------------------------------------------------- + Why use PACKET_MMAP @@ -25,19 +27,24 @@ to capture each packet, it requires two if you want to get packet's timestamp (like libpcap always does). In the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size -configurable circular buffer mapped in user space. This way reading packets just -needs to wait for them, most of the time there is no need to issue a single -system call. By using a shared buffer between the kernel and the user -also has the benefit of minimizing packet copies. - -It's fine to use PACKET_MMAP to improve the performance of the capture process, -but it isn't everything. At least, if you are capturing at high speeds (this -is relative to the cpu speed), you should check if the device driver of your -network interface card supports some sort of interrupt load mitigation or -(even better) if it supports NAPI, also make sure it is enabled. +configurable circular buffer mapped in user space that can be used to either +send or receive packets. This way reading packets just needs to wait for them, +most of the time there is no need to issue a single system call. Concerning +transmission, multiple packets can be sent through one system call to get the +highest bandwidth. +By using a shared buffer between the kernel and the user also has the benefit +of minimizing packet copies. + +It's fine to use PACKET_MMAP to improve the performance of the capture and +transmission process, but it isn't everything. At least, if you are capturing +at high speeds (this is relative to the cpu speed), you should check if the +device driver of your network interface card supports some sort of interrupt +load mitigation or (even better) if it supports NAPI, also make sure it is +enabled. For transmission, check the MTU (Maximum Transmission Unit) used and +supported by devices of your network. -------------------------------------------------------------------------------- -+ How to use CONFIG_PACKET_MMAP ++ How to use CONFIG_PACKET_MMAP to improve capture process -------------------------------------------------------------------------------- From the user standpoint, you should use the higher level libpcap library, which @@ -57,7 +64,7 @@ the low level details or want to improve libpcap by including PACKET_MMAP support. -------------------------------------------------------------------------------- -+ How to use CONFIG_PACKET_MMAP directly ++ How to use CONFIG_PACKET_MMAP directly to improve capture process -------------------------------------------------------------------------------- From the system calls stand point, the use of PACKET_MMAP involves @@ -66,6 +73,7 @@ the following process: [setup] socket() -------> creation of the capture socket setsockopt() ---> allocation of the circular buffer (ring) + option: PACKET_RX_RING mmap() ---------> mapping of the allocated buffer to the user process @@ -97,13 +105,75 @@ also the mapping of the circular buffer in the user process and the use of this buffer. -------------------------------------------------------------------------------- ++ How to use CONFIG_PACKET_MMAP directly to improve transmission process +-------------------------------------------------------------------------------- +Transmission process is similar to capture as shown below. + +[setup] socket() -------> creation of the transmission socket + setsockopt() ---> allocation of the circular buffer (ring) + option: PACKET_TX_RING + bind() ---------> bind transmission socket with a network interface + mmap() ---------> mapping of the allocated buffer to the + user process + +[transmission] poll() ---------> wait for free packets (optional) + send() ---------> send all packets that are set as ready in + the ring + The flag MSG_DONTWAIT can be used to return + before end of transfer. + +[shutdown] close() --------> destruction of the transmission socket and + deallocation of all associated resources. + +Binding the socket to your network interface is mandatory (with zero copy) to +know the header size of frames used in the circular buffer. + +As capture, each frame contains two parts: + + -------------------- +| struct tpacket_hdr | Header. It contains the status of +| | of this frame +|--------------------| +| data buffer | +. . Data that will be sent over the network interface. +. . + -------------------- + + bind() associates the socket to your network interface thanks to + sll_ifindex parameter of struct sockaddr_ll. + + Initialization example: + + struct sockaddr_ll my_addr; + struct ifreq s_ifr; + ... + + strncpy (s_ifr.ifr_name, "eth0", sizeof(s_ifr.ifr_name)); + + /* get interface index of eth0 */ + ioctl(this->socket, SIOCGIFINDEX, &s_ifr); + + /* fill sockaddr_ll struct to prepare binding */ + my_addr.sll_family = AF_PACKET; + my_addr.sll_protocol = ETH_P_ALL; + my_addr.sll_ifindex = s_ifr.ifr_ifindex; + + /* bind socket to eth0 */ + bind(this->socket, (struct sockaddr *)&my_addr, sizeof(struct sockaddr_ll)); + + A complete tutorial is available at: http://wiki.gnu-log.net/ + +-------------------------------------------------------------------------------- + PACKET_MMAP settings -------------------------------------------------------------------------------- To setup PACKET_MMAP from user level code is done with a call like + - Capture process setsockopt(fd, SOL_PACKET, PACKET_RX_RING, (void *) &req, sizeof(req)) + - Transmission process + setsockopt(fd, SOL_PACKET, PACKET_TX_RING, (void *) &req, sizeof(req)) The most significant argument in the previous call is the req parameter, this parameter must to have the following structure: @@ -117,11 +187,11 @@ this parameter must to have the following structure: }; This structure is defined in /usr/include/linux/if_packet.h and establishes a -circular buffer (ring) of unswappable memory mapped in the capture process. +circular buffer (ring) of unswappable memory. Being mapped in the capture process allows reading the captured frames and related meta-information like timestamps without requiring a system call. -Captured frames are grouped in blocks. Each block is a physically contiguous +Frames are grouped in blocks. Each block is a physically contiguous region of memory and holds tp_block_size/tp_frame_size frames. The total number of blocks is tp_block_nr. Note that tp_frame_nr is a redundant parameter because @@ -336,6 +406,7 @@ 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 and the following flags apply: ++++ Capture process: from include/linux/if_packet.h #define TP_STATUS_COPY 2 @@ -391,6 +462,37 @@ packets are in the ring: It doesn't incur in a race condition to first check the status value and then poll for frames. + +++ Transmission process +Those defines are also used for transmission: + + #define TP_STATUS_AVAILABLE 0 // Frame is available + #define TP_STATUS_SEND_REQUEST 1 // Frame will be sent on next send() + #define TP_STATUS_SENDING 2 // Frame is currently in transmission + #define TP_STATUS_WRONG_FORMAT 4 // Frame format is not correct + +First, the kernel initializes all frames to TP_STATUS_AVAILABLE. To send a +packet, the user fills a data buffer of an available frame, sets tp_len to +current data buffer size and sets its status field to TP_STATUS_SEND_REQUEST. +This can be done on multiple frames. Once the user is ready to transmit, it +calls send(). Then all buffers with status equal to TP_STATUS_SEND_REQUEST are +forwarded to the network device. The kernel updates each status of sent +frames with TP_STATUS_SENDING until the end of transfer. +At the end of each transfer, buffer status returns to TP_STATUS_AVAILABLE. + + header->tp_len = in_i_size; + header->tp_status = TP_STATUS_SEND_REQUEST; + retval = send(this->socket, NULL, 0, 0); + +The user can also use poll() to check if a buffer is available: +(status == TP_STATUS_SENDING) + + struct pollfd pfd; + pfd.fd = fd; + pfd.revents = 0; + pfd.events = POLLOUT; + retval = poll(&pfd, 1, timeout); + -------------------------------------------------------------------------------- + THANKS -------------------------------------------------------------------------------- diff --git a/Documentation/networking/phonet.txt b/Documentation/networking/phonet.txt index 6a07e45d4a9..6e8ce09f9c7 100644 --- a/Documentation/networking/phonet.txt +++ b/Documentation/networking/phonet.txt @@ -36,7 +36,7 @@ Phonet packets have a common header as follows: On Linux, the link-layer header includes the pn_media byte (see below). The next 7 bytes are part of the network-layer header. -The device ID is split: the 6 higher-order bits consitute the device +The device ID is split: the 6 higher-order bits constitute the device address, while the 2 lower-order bits are used for multiplexing, as are the 8-bit object identifiers. As such, Phonet can be considered as a network layer with 6 bits of address space and 10 bits for transport diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt index dcf31648414..eaa1a25946c 100644 --- a/Documentation/networking/regulatory.txt +++ b/Documentation/networking/regulatory.txt @@ -89,7 +89,7 @@ added to this document when its support is enabled. Device drivers who provide their own built regulatory domain do not need a callback as the channels registered by them are the only ones that will be allowed and therefore *additional* -cannels cannot be enabled. +channels cannot be enabled. Example code - drivers hinting an alpha2: ------------------------------------------ |