diff options
Diffstat (limited to 'Documentation/networking')
26 files changed, 852 insertions, 1465 deletions
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index 415154a487d0..c6beb5f1637f 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -10,8 +10,6 @@ LICENSE.qlge - GPLv2 for QLogic Linux qlge NIC Driver LICENSE.qlcnic - GPLv2 for QLogic Linux qlcnic NIC Driver -Makefile - - Makefile for docsrc. PLIP.txt - PLIP: The Parallel Line Internet Protocol device driver README.ipw2100 @@ -74,6 +72,8 @@ dns_resolver.txt - The DNS resolver module allows kernel servies to make DNS queries. driver.txt - Softnet driver issues. +ena.txt + - info on Amazon's Elastic Network Adapter (ENA) e100.txt - info on Intel's EtherExpress PRO/100 line of 10/100 boards e1000.txt diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile deleted file mode 100644 index 4c5d7c485439..000000000000 --- a/Documentation/networking/Makefile +++ /dev/null @@ -1 +0,0 @@ -subdir-y := timestamping diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt index 1b5e7a7f2185..ccf94677b240 100644 --- a/Documentation/networking/batman-adv.txt +++ b/Documentation/networking/batman-adv.txt @@ -32,7 +32,7 @@ compatible interfaces. Once found, it will create subfolders in the /sys directories of each supported interface, e.g. # ls /sys/class/net/eth0/batman_adv/ -# iface_status mesh_iface +# elp_interval iface_status mesh_iface throughput_override If an interface does not have the "batman_adv" subfolder it prob- ably is not supported. Not supported interfaces are: loopback, @@ -43,10 +43,15 @@ new interfaces to verify the compatibility. There is no need to reload the module if you plug your USB wifi adapter into your ma- chine after batman advanced was initially loaded. -To activate a given interface simply write "bat0" into its -"mesh_iface" file inside the batman_adv subfolder: +The batman-adv soft-interface can be created using the iproute2 +tool "ip" -# echo bat0 > /sys/class/net/eth0/batman_adv/mesh_iface +# ip link add name bat0 type batadv + +To activate a given interface simply attach it to the "bat0" +interface + +# ip link set dev eth0 master bat0 Repeat this step for all interfaces you wish to add. Now batman starts using/broadcasting on this/these interface(s). @@ -56,27 +61,29 @@ By reading the "iface_status" file you can check its status: # cat /sys/class/net/eth0/batman_adv/iface_status # active -To deactivate an interface you have to write "none" into its -"mesh_iface" file: +To deactivate an interface you have to detach it from the +"bat0" interface: -# echo none > /sys/class/net/eth0/batman_adv/mesh_iface +# ip link set dev eth0 nomaster All mesh wide settings can be found in batman's own interface folder: # ls /sys/class/net/bat0/mesh/ -#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 +# aggregated_ogms fragmentation isolation_mark routing_algo +# ap_isolation gw_bandwidth log_level vlan0 +# bonding gw_mode multicast_mode +# bridge_loop_avoidance gw_sel_class network_coding +# distributed_arp_table hop_penalty orig_interval There is a special folder for debugging information: # ls /sys/kernel/debug/batman_adv/bat0/ -# bla_backbone_table log transtable_global -# bla_claim_table originators transtable_local -# gateways socket +# bla_backbone_table log neighbors transtable_local +# bla_claim_table mcast_flags originators +# dat_cache nc socket +# gateways nc_nodes transtable_global Some of the files contain all sort of status information regard- ing the mesh network. For example, you can view the table of @@ -154,13 +161,16 @@ file in debugfs The additional debug output is by default disabled. It can be en- abled during run time. Following log_levels are defined: -0 - All debug output disabled -1 - Enable messages related to routing / flooding / broadcasting -2 - Enable messages related to route added / changed / deleted -4 - Enable messages related to translation table operations -8 - Enable messages related to bridge loop avoidance -16 - Enable messaged related to DAT, ARP snooping and parsing -31 - Enable all messages + 0 - All debug output disabled + 1 - Enable messages related to routing / flooding / broadcasting + 2 - Enable messages related to route added / changed / deleted + 4 - Enable messages related to translation table operations + 8 - Enable messages related to bridge loop avoidance + 16 - Enable messages related to DAT, ARP snooping and parsing + 32 - Enable messages related to network coding + 64 - Enable messages related to multicast +128 - Enable messages related to throughput meter +255 - Enable all messages The debug output can be changed at runtime using the file /sys/class/net/bat0/mesh/log_level. e.g. diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index f20c884c048a..63912ef34606 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -67,13 +67,14 @@ Note that DSA does not currently create network interfaces for the "cpu" and Switch tagging protocols ------------------------ -DSA currently supports 4 different tagging protocols, and a tag-less mode as +DSA currently supports 5 different tagging protocols, and a tag-less mode as well. The different protocols are implemented in: net/dsa/tag_trailer.c: Marvell's 4 trailer tag mode (legacy) net/dsa/tag_dsa.c: Marvell's original DSA tag net/dsa/tag_edsa.c: Marvell's enhanced DSA tag net/dsa/tag_brcm.c: Broadcom's 4 bytes tag +net/dsa/tag_qca.c: Qualcomm's 2 bytes tag The exact format of the tag protocol is vendor specific, but in general, they all contain something which: @@ -227,9 +228,9 @@ to address individual switches in the tree. dsa_switch: structure describing a switch device in the tree, referencing a dsa_switch_tree as a backpointer, slave network devices, master network device, -and a reference to the backing dsa_switch_driver +and a reference to the backing dsa_switch_ops -dsa_switch_driver: structure referencing function pointers, see below for a full +dsa_switch_ops: structure referencing function pointers, see below for a full description. Design limitations @@ -357,10 +358,10 @@ regular HWMON devices in /sys/class/hwmon/. Driver development ================== -DSA switch drivers need to implement a dsa_switch_driver structure which will +DSA switch drivers need to implement a dsa_switch_ops structure which will contain the various members described below. -register_switch_driver() registers this dsa_switch_driver in its internal list +register_switch_driver() registers this dsa_switch_ops in its internal list of drivers to probe for. unregister_switch_driver() does the exact opposite. Unless requested differently by setting the priv_size member accordingly, DSA @@ -379,7 +380,7 @@ Switch configuration buses, return a non-NULL string - setup: setup function for the switch, this function is responsible for setting - up the dsa_switch_driver private structure with all it needs: register maps, + up the dsa_switch_ops private structure with all it needs: register maps, interrupts, mutexes, locks etc.. This function is also expected to properly configure the switch to separate all network interfaces from each other, that is, they should be isolated by the switch hardware itself, typically by creating @@ -584,6 +585,29 @@ of DSA, would be the its port-based VLAN, used by the associated bridge device. function that the driver has to call for each MAC address known to be behind the given port. A switchdev object is used to carry the VID and FDB info. +- port_mdb_prepare: bridge layer function invoked when the bridge prepares the + installation of a multicast database entry. If the operation is not supported, + this function should return -EOPNOTSUPP to inform the bridge code to fallback + to a software implementation. No hardware setup must be done in this function. + See port_fdb_add for this and details. + +- port_mdb_add: bridge layer function invoked when the bridge wants to install + a multicast database entry, the switch hardware should be programmed with the + specified address in the specified VLAN ID in the forwarding database + associated with this VLAN ID. + +Note: VLAN ID 0 corresponds to the port private database, which, in the context +of DSA, would be the its port-based VLAN, used by the associated bridge device. + +- port_mdb_del: bridge layer function invoked when the bridge wants to remove a + multicast database entry, the switch hardware should be programmed to delete + the specified MAC address from the specified VLAN ID if it was mapped into + this port forwarding database. + +- port_mdb_dump: bridge layer function invoked with a switchdev callback + function that the driver has to call for each MAC address known to be behind + the given port. A switchdev object is used to carry the VID and MDB info. + TODO ==== diff --git a/Documentation/networking/ena.txt b/Documentation/networking/ena.txt new file mode 100644 index 000000000000..2b4b6f57e549 --- /dev/null +++ b/Documentation/networking/ena.txt @@ -0,0 +1,305 @@ +Linux kernel driver for Elastic Network Adapter (ENA) family: +============================================================= + +Overview: +========= +ENA is a networking interface designed to make good use of modern CPU +features and system architectures. + +The ENA device exposes a lightweight management interface with a +minimal set of memory mapped registers and extendable command set +through an Admin Queue. + +The driver supports a range of ENA devices, is link-speed independent +(i.e., the same driver is used for 10GbE, 25GbE, 40GbE, etc.), and has +a negotiated and extendable feature set. + +Some ENA devices support SR-IOV. This driver is used for both the +SR-IOV Physical Function (PF) and Virtual Function (VF) devices. + +ENA devices enable high speed and low overhead network traffic +processing by providing multiple Tx/Rx queue pairs (the maximum number +is advertised by the device via the Admin Queue), a dedicated MSI-X +interrupt vector per Tx/Rx queue pair, adaptive interrupt moderation, +and CPU cacheline optimized data placement. + +The ENA driver supports industry standard TCP/IP offload features such +as checksum offload and TCP transmit segmentation offload (TSO). +Receive-side scaling (RSS) is supported for multi-core scaling. + +The ENA driver and its corresponding devices implement health +monitoring mechanisms such as watchdog, enabling the device and driver +to recover in a manner transparent to the application, as well as +debug logs. + +Some of the ENA devices support a working mode called Low-latency +Queue (LLQ), which saves several more microseconds. + +Supported PCI vendor ID/device IDs: +=================================== +1d0f:0ec2 - ENA PF +1d0f:1ec2 - ENA PF with LLQ support +1d0f:ec20 - ENA VF +1d0f:ec21 - ENA VF with LLQ support + +ENA Source Code Directory Structure: +==================================== +ena_com.[ch] - Management communication layer. This layer is + responsible for the handling all the management + (admin) communication between the device and the + driver. +ena_eth_com.[ch] - Tx/Rx data path. +ena_admin_defs.h - Definition of ENA management interface. +ena_eth_io_defs.h - Definition of ENA data path interface. +ena_common_defs.h - Common definitions for ena_com layer. +ena_regs_defs.h - Definition of ENA PCI memory-mapped (MMIO) registers. +ena_netdev.[ch] - Main Linux kernel driver. +ena_syfsfs.[ch] - Sysfs files. +ena_ethtool.c - ethtool callbacks. +ena_pci_id_tbl.h - Supported device IDs. + +Management Interface: +===================== +ENA management interface is exposed by means of: +- PCIe Configuration Space +- Device Registers +- Admin Queue (AQ) and Admin Completion Queue (ACQ) +- Asynchronous Event Notification Queue (AENQ) + +ENA device MMIO Registers are accessed only during driver +initialization and are not involved in further normal device +operation. + +AQ is used for submitting management commands, and the +results/responses are reported asynchronously through ACQ. + +ENA introduces a very small set of management commands with room for +vendor-specific extensions. Most of the management operations are +framed in a generic Get/Set feature command. + +The following admin queue commands are supported: +- Create I/O submission queue +- Create I/O completion queue +- Destroy I/O submission queue +- Destroy I/O completion queue +- Get feature +- Set feature +- Configure AENQ +- Get statistics + +Refer to ena_admin_defs.h for the list of supported Get/Set Feature +properties. + +The Asynchronous Event Notification Queue (AENQ) is a uni-directional +queue used by the ENA device to send to the driver events that cannot +be reported using ACQ. AENQ events are subdivided into groups. Each +group may have multiple syndromes, as shown below + +The events are: + Group Syndrome + Link state change - X - + Fatal error - X - + Notification Suspend traffic + Notification Resume traffic + Keep-Alive - X - + +ACQ and AENQ share the same MSI-X vector. + +Keep-Alive is a special mechanism that allows monitoring of the +device's health. The driver maintains a watchdog (WD) handler which, +if fired, logs the current state and statistics then resets and +restarts the ENA device and driver. A Keep-Alive event is delivered by +the device every second. The driver re-arms the WD upon reception of a +Keep-Alive event. A missed Keep-Alive event causes the WD handler to +fire. + +Data Path Interface: +==================== +I/O operations are based on Tx and Rx Submission Queues (Tx SQ and Rx +SQ correspondingly). Each SQ has a completion queue (CQ) associated +with it. + +The SQs and CQs are implemented as descriptor rings in contiguous +physical memory. + +The ENA driver supports two Queue Operation modes for Tx SQs: +- Regular mode + * In this mode the Tx SQs reside in the host's memory. The ENA + device fetches the ENA Tx descriptors and packet data from host + memory. +- Low Latency Queue (LLQ) mode or "push-mode". + * In this mode the driver pushes the transmit descriptors and the + first 128 bytes of the packet directly to the ENA device memory + space. The rest of the packet payload is fetched by the + device. For this operation mode, the driver uses a dedicated PCI + device memory BAR, which is mapped with write-combine capability. + +The Rx SQs support only the regular mode. + +Note: Not all ENA devices support LLQ, and this feature is negotiated + with the device upon initialization. If the ENA device does not + support LLQ mode, the driver falls back to the regular mode. + +The driver supports multi-queue for both Tx and Rx. This has various +benefits: +- Reduced CPU/thread/process contention on a given Ethernet interface. +- Cache miss rate on completion is reduced, particularly for data + cache lines that hold the sk_buff structures. +- Increased process-level parallelism when handling received packets. +- Increased data cache hit rate, by steering kernel processing of + packets to the CPU, where the application thread consuming the + packet is running. +- In hardware interrupt re-direction. + +Interrupt Modes: +================ +The driver assigns a single MSI-X vector per queue pair (for both Tx +and Rx directions). The driver assigns an additional dedicated MSI-X vector +for management (for ACQ and AENQ). + +Management interrupt registration is performed when the Linux kernel +probes the adapter, and it is de-registered when the adapter is +removed. I/O queue interrupt registration is performed when the Linux +interface of the adapter is opened, and it is de-registered when the +interface is closed. + +The management interrupt is named: + ena-mgmnt@pci:<PCI domain:bus:slot.function> +and for each queue pair, an interrupt is named: + <interface name>-Tx-Rx-<queue index> + +The ENA device operates in auto-mask and auto-clear interrupt +modes. That is, once MSI-X is delivered to the host, its Cause bit is +automatically cleared and the interrupt is masked. The interrupt is +unmasked by the driver after NAPI processing is complete. + +Interrupt Moderation: +===================== +ENA driver and device can operate in conventional or adaptive interrupt +moderation mode. + +In conventional mode the driver instructs device to postpone interrupt +posting according to static interrupt delay value. The interrupt delay +value can be configured through ethtool(8). The following ethtool +parameters are supported by the driver: tx-usecs, rx-usecs + +In adaptive interrupt moderation mode the interrupt delay value is +updated by the driver dynamically and adjusted every NAPI cycle +according to the traffic nature. + +By default ENA driver applies adaptive coalescing on Rx traffic and +conventional coalescing on Tx traffic. + +Adaptive coalescing can be switched on/off through ethtool(8) +adaptive_rx on|off parameter. + +The driver chooses interrupt delay value according to the number of +bytes and packets received between interrupt unmasking and interrupt +posting. The driver uses interrupt delay table that subdivides the +range of received bytes/packets into 5 levels and assigns interrupt +delay value to each level. + +The user can enable/disable adaptive moderation, modify the interrupt +delay table and restore its default values through sysfs. + +The rx_copybreak is initialized by default to ENA_DEFAULT_RX_COPYBREAK +and can be configured by the ETHTOOL_STUNABLE command of the +SIOCETHTOOL ioctl. + +SKB: +The driver-allocated SKB for frames received from Rx handling using +NAPI context. The allocation method depends on the size of the packet. +If the frame length is larger than rx_copybreak, napi_get_frags() +is used, otherwise netdev_alloc_skb_ip_align() is used, the buffer +content is copied (by CPU) to the SKB, and the buffer is recycled. + +Statistics: +=========== +The user can obtain ENA device and driver statistics using ethtool. +The driver can collect regular or extended statistics (including +per-queue stats) from the device. + +In addition the driver logs the stats to syslog upon device reset. + +MTU: +==== +The driver supports an arbitrarily large MTU with a maximum that is +negotiated with the device. The driver configures MTU using the +SetFeature command (ENA_ADMIN_MTU property). The user can change MTU +via ip(8) and similar legacy tools. + +Stateless Offloads: +=================== +The ENA driver supports: +- TSO over IPv4/IPv6 +- TSO with ECN +- IPv4 header checksum offload +- TCP/UDP over IPv4/IPv6 checksum offloads + +RSS: +==== +- The ENA device supports RSS that allows flexible Rx traffic + steering. +- Toeplitz and CRC32 hash functions are supported. +- Different combinations of L2/L3/L4 fields can be configured as + inputs for hash functions. +- The driver configures RSS settings using the AQ SetFeature command + (ENA_ADMIN_RSS_HASH_FUNCTION, ENA_ADMIN_RSS_HASH_INPUT and + ENA_ADMIN_RSS_REDIRECTION_TABLE_CONFIG properties). +- If the NETIF_F_RXHASH flag is set, the 32-bit result of the hash + function delivered in the Rx CQ descriptor is set in the received + SKB. +- The user can provide a hash key, hash function, and configure the + indirection table through ethtool(8). + +DATA PATH: +========== +Tx: +--- +end_start_xmit() is called by the stack. This function does the following: +- Maps data buffers (skb->data and frags). +- Populates ena_buf for the push buffer (if the driver and device are + in push mode.) +- Prepares ENA bufs for the remaining frags. +- Allocates a new request ID from the empty req_id ring. The request + ID is the index of the packet in the Tx info. This is used for + out-of-order TX completions. +- Adds the packet to the proper place in the Tx ring. +- Calls ena_com_prepare_tx(), an ENA communication layer that converts + the ena_bufs to ENA descriptors (and adds meta ENA descriptors as + needed.) + * This function also copies the ENA descriptors and the push buffer + to the Device memory space (if in push mode.) +- Writes doorbell to the ENA device. +- When the ENA device finishes sending the packet, a completion + interrupt is raised. +- The interrupt handler schedules NAPI. +- The ena_clean_tx_irq() function is called. This function handles the + completion descriptors generated by the ENA, with a single + completion descriptor per completed packet. + * req_id is retrieved from the completion descriptor. The tx_info of + the packet is retrieved via the req_id. The data buffers are + unmapped and req_id is returned to the empty req_id ring. + * The function stops when the completion descriptors are completed or + the budget is reached. + +Rx: +--- +- When a packet is received from the ENA device. +- The interrupt handler schedules NAPI. +- The ena_clean_rx_irq() function is called. This function calls + ena_rx_pkt(), an ENA communication layer function, which returns the + number of descriptors used for a new unhandled packet, and zero if + no new packet is found. +- Then it calls the ena_clean_rx_irq() function. +- ena_eth_rx_skb() checks packet length: + * If the packet is small (len < rx_copybreak), the driver allocates + a SKB for the new packet, and copies the packet payload into the + SKB data buffer. + - In this way the original data buffer is not passed to the stack + and is reused for future Rx packets. + * Otherwise the function unmaps the Rx buffer, then allocates the + new SKB structure and hooks the Rx buffer to the SKB frags. +- The new SKB is updated with the necessary information (protocol, + checksum hw verify result, etc.), and then passed to the network + stack, using the NAPI interface function napi_gro_receive(). diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt index aa69ccc481db..c4114346f054 100644 --- a/Documentation/networking/ieee802154.txt +++ b/Documentation/networking/ieee802154.txt @@ -4,20 +4,20 @@ Introduction ============ -The IEEE 802.15.4 working group focuses on standardization of bottom -two layers: Medium Access Control (MAC) and Physical (PHY). And there +The IEEE 802.15.4 working group focuses on standardization of the bottom +two layers: Medium Access Control (MAC) and Physical access (PHY). And there are mainly two options available for upper layers: - ZigBee - proprietary protocol from the ZigBee Alliance - 6LoWPAN - IPv6 networking over low rate personal area networks -The linux-wpan project goal is to provide a complete implementation +The goal of the Linux-wpan is to provide a complete implementation of the IEEE 802.15.4 and 6LoWPAN protocols. IEEE 802.15.4 is a stack of protocols for organizing Low-Rate Wireless Personal Area Networks. The stack is composed of three main parts: - IEEE 802.15.4 layer; We have chosen 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 + the generic Linux networking stack to transfer IEEE 802.15.4 data + messages and a special protocol over netlink for configuration/management - MAC - provides access to shared channel and reliable data delivery - PHY - represents device drivers @@ -33,15 +33,13 @@ include/net/af_ieee802154.h header or in the special header in the userspace package (see either http://wpan.cakelab.org/ or the git tree at https://github.com/linux-wpan/wpan-tools). -One can use SOCK_RAW for passing raw data towards device xmit function. YMMV. - 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. + exports a management (e.g. 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. @@ -106,7 +104,7 @@ Fake drivers In addition there is a driver available which simulates a real device with SoftMAC (fakelb - IEEE 802.15.4 loopback driver) interface. This option -provides possibility to test and debug stack without usage of real hardware. +provides a possibility to test and debug the stack without usage of real hardware. See sources in drivers/net/ieee802154 folder for more details. @@ -125,17 +123,15 @@ to support the IPv6 minimum MTU requirement [RFC2460], and stateless header compression for IPv6 datagrams (LOWPAN_HC1 and LOWPAN_HC2) to reduce the relatively large IPv6 and UDP headers down to (in the best case) several bytes. -In Semptember 2011 the standard update was published - [RFC6282]. +In September 2011 the standard update was published - [RFC6282]. It deprecates HC1 and HC2 compression and defines IPHC encoding format which is used in this Linux implementation. All the code related to 6lowpan you may find in files: net/6lowpan/* and net/ieee802154/6lowpan/* -To setup 6lowpan interface you need (busybox release > 1.17.0): -1. Add IEEE802.15.4 interface and initialize PANid; +To setup a 6LoWPAN interface you need: +1. Add IEEE802.15.4 interface and set channel and PAN ID; 2. Add 6lowpan interface by command like: # ip link add link wpan0 name lowpan0 type lowpan -3. Set MAC (if needs): - # ip link set lowpan0 address de:ad:be:ef:ca:fe:ba:be -4. Bring up 'lowpan0' interface +3. Bring up 'lowpan0' interface diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 9ae929395b24..7dd65c9cf707 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -575,32 +575,33 @@ tcp_syncookies - BOOLEAN unconditionally generation of syncookies. tcp_fastopen - INTEGER - Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data - in the opening SYN packet. To use this feature, the client application - must use sendmsg() or sendto() with MSG_FASTOPEN flag rather than - connect() to perform a TCP handshake automatically. + Enable TCP Fast Open (RFC7413) to send and accept data in the opening + SYN packet. - The values (bitmap) are - 1: Enables sending data in the opening SYN on the client w/ MSG_FASTOPEN. - 2: Enables TCP Fast Open on the server side, i.e., allowing data in - a SYN packet to be accepted and passed to the application before - 3-way hand shake finishes. - 4: Send data in the opening SYN regardless of cookie availability and - without a cookie option. - 0x100: Accept SYN data w/o validating the cookie. - 0x200: Accept data-in-SYN w/o any cookie option present. - 0x400/0x800: Enable Fast Open on all listeners regardless of the - TCP_FASTOPEN socket option. The two different flags designate two - different ways of setting max_qlen without the TCP_FASTOPEN socket - option. + The client support is enabled by flag 0x1 (on by default). The client + then must use sendmsg() or sendto() with the MSG_FASTOPEN flag, + rather than connect() to send data in SYN. - Default: 1 + The server support is enabled by flag 0x2 (off by default). Then + either enable for all listeners with another flag (0x400) or + enable individual listeners via TCP_FASTOPEN socket option with + the option value being the length of the syn-data backlog. - Note that the client & server side Fast Open flags (1 and 2 - respectively) must be also enabled before the rest of flags can take - effect. + The values (bitmap) are + 0x1: (client) enables sending data in the opening SYN on the client. + 0x2: (server) enables the server support, i.e., allowing data in + a SYN packet to be accepted and passed to the + application before 3-way handshake finishes. + 0x4: (client) send data in the opening SYN regardless of cookie + availability and without a cookie option. + 0x200: (server) accept data-in-SYN w/o any cookie option present. + 0x400: (server) enable all listeners to support Fast Open by + default without explicit TCP_FASTOPEN socket option. + + Default: 0x1 - See include/net/tcp.h and the code for more details. + Note that that additional client or server features are only + effective if the basic support (0x1 and 0x2) are enabled respectively. tcp_syn_retries - INTEGER Number of times initial SYNs for an active TCP connection attempt @@ -609,8 +610,13 @@ tcp_syn_retries - INTEGER with the current initial RTO of 1second. With this the final timeout for an active TCP connection attempt will happen after 127seconds. -tcp_timestamps - BOOLEAN - Enable timestamps as defined in RFC1323. +tcp_timestamps - INTEGER +Enable timestamps as defined in RFC1323. + 0: Disabled. + 1: Enable timestamps as defined in RFC1323 and use random offset for + each connection rather than only using the current time. + 2: Like 1, but without random offsets. + Default: 1 tcp_min_tso_segs - INTEGER Minimal number of segments per TSO frame. @@ -966,6 +972,21 @@ igmp_qrv - INTEGER Default: 2 (as specified by RFC2236 8.1) Minimum: 1 (as specified by RFC6636 4.5) +force_igmp_version - INTEGER + 0 - (default) No enforcement of a IGMP version, IGMPv1/v2 fallback + allowed. Will back to IGMPv3 mode again if all IGMPv1/v2 Querier + Present timer expires. + 1 - Enforce to use IGMP version 1. Will also reply IGMPv1 report if + receive IGMPv2/v3 query. + 2 - Enforce to use IGMP version 2. Will fallback to IGMPv1 if receive + IGMPv1 query message. Will reply report if receive IGMPv3 query. + 3 - Enforce to use IGMP version 3. The same react with default 0. + + Note: this is not the same with force_mld_version because IGMPv3 RFC3376 + Security Considerations does not have clear description that we could + ignore other version messages completely as MLDv2 RFC3810. So make + this value as default 0 is recommended. + conf/interface/* changes special settings per interface (where "interface" is the name of your network interface) @@ -1713,6 +1734,15 @@ drop_unsolicited_na - BOOLEAN By default this is turned off. +enhanced_dad - BOOLEAN + Include a nonce option in the IPv6 neighbor solicitation messages used for + duplicate address detection per RFC7527. A received DAD NS will only signal + a duplicate address if the nonce is different. This avoids any false + detection of duplicates due to loopback of the NS messages that we send. + The nonce option will be sent on an interface unless both of + conf/{all,interface}/enhanced_dad are set to FALSE. + Default: TRUE + icmp/*: ratelimit - INTEGER Limit the maximal rates for sending ICMPv6 packets. diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt index 14422f8fcdc4..24196cef7c91 100644 --- a/Documentation/networking/ipvlan.txt +++ b/Documentation/networking/ipvlan.txt @@ -22,7 +22,7 @@ The driver can be built into the kernel (CONFIG_IPVLAN=y) or as a module There are no module parameters for this driver and it can be configured using IProute2/ip utility. - ip link add link <master-dev> <slave-dev> type ipvlan mode { l2 | L3 } + ip link add link <master-dev> <slave-dev> type ipvlan mode { l2 | l3 | l3s } e.g. ip link add link ipvl0 eth0 type ipvlan mode l2 @@ -48,6 +48,11 @@ master device for the L2 processing and routing from that instance will be used before packets are queued on the outbound device. In this mode the slaves will not receive nor can send multicast / broadcast traffic. +4.3 L3S mode: + This is very similar to the L3 mode except that iptables (conn-tracking) +works in this mode and hence it is L3-symmetric (L3s). This will have slightly less +performance but that shouldn't matter since you are choosing this mode over plain-L3 +mode to make conn-tracking work. 5. What to choose (macvlan vs. ipvlan)? These two devices are very similar in many regards and the specific use diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt index 4650a00ed012..9bc271cdc9a8 100644 --- a/Documentation/networking/l2tp.txt +++ b/Documentation/networking/l2tp.txt @@ -177,10 +177,10 @@ setsockopt on the PPPoX socket to set a debug mask. The following debug mask bits are available: -PPPOL2TP_MSG_DEBUG verbose debug (if compiled in) -PPPOL2TP_MSG_CONTROL userspace - kernel interface -PPPOL2TP_MSG_SEQ sequence numbers handling -PPPOL2TP_MSG_DATA data packets +L2TP_MSG_DEBUG verbose debug (if compiled in) +L2TP_MSG_CONTROL userspace - kernel interface +L2TP_MSG_SEQ sequence numbers handling +L2TP_MSG_DATA data packets If enabled, files under a l2tp debugfs directory can be used to dump kernel state about L2TP tunnels and sessions. To access it, the diff --git a/Documentation/networking/mac80211_hwsim/README b/Documentation/networking/mac80211_hwsim/README index 24ac91d56698..3566a725d19c 100644 --- a/Documentation/networking/mac80211_hwsim/README +++ b/Documentation/networking/mac80211_hwsim/README @@ -60,7 +60,7 @@ modprobe mac80211_hwsim hostapd hostapd.conf # Run wpa_supplicant (station) for wlan1 -wpa_supplicant -Dwext -iwlan1 -c wpa_supplicant.conf +wpa_supplicant -Dnl80211 -iwlan1 -c wpa_supplicant.conf More test cases are available in hostap.git: diff --git a/Documentation/networking/netconsole.txt b/Documentation/networking/netconsole.txt index 30409a36e95d..296ea00fd3eb 100644 --- a/Documentation/networking/netconsole.txt +++ b/Documentation/networking/netconsole.txt @@ -200,7 +200,7 @@ priority messages to the console. You can change this at runtime using: or by specifying "debug" on the kernel command line at boot, to send all kernel messages to the console. A specific value for this parameter can also be set using the "loglevel" kernel boot option. See the -dmesg(8) man page and Documentation/kernel-parameters.txt for details. +dmesg(8) man page and Documentation/admin-guide/kernel-parameters.rst for details. Netconsole was designed to be as instantaneous as possible, to enable the logging of even the most critical kernel bugs. It works diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt index 0fe1c6e0dbcd..247a30ba8e17 100644 --- a/Documentation/networking/netdev-FAQ.txt +++ b/Documentation/networking/netdev-FAQ.txt @@ -29,8 +29,8 @@ A: There are always two trees (git repositories) in play. Both are driven Linus, and net-next is where the new code goes for the future release. You can find the trees here: - http://git.kernel.org/?p=linux/kernel/git/davem/net.git - http://git.kernel.org/?p=linux/kernel/git/davem/net-next.git + https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git + https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git Q: How often do changes from these trees make it to the mainline Linus tree? @@ -76,7 +76,7 @@ Q: So where are we now in this cycle? A: Load the mainline (Linus) page here: - http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git + https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git and note the top of the "tags" section. If it is rc1, it is early in the dev cycle. If it was tagged rc7 a week ago, then a release @@ -123,7 +123,7 @@ A: Normally Greg Kroah-Hartman collects stable commits himself, but It contains the patches which Dave has selected, but not yet handed off to Greg. If Greg already has the patch, then it will be here: - http://git.kernel.org/cgit/linux/kernel/git/stable/stable-queue.git + https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git A quick way to find whether the patch is in this stable-queue is to simply clone the repo, and then git grep the mainline commit ID, e.g. @@ -136,14 +136,14 @@ A: Normally Greg Kroah-Hartman collects stable commits himself, but Q: I see a network patch and I think it should be backported to stable. Should I request it via "stable@vger.kernel.org" like the references in - the kernel's Documentation/stable_kernel_rules.txt file say? + the kernel's Documentation/process/stable-kernel-rules.rst file say? A: No, not for networking. Check the stable queues as per above 1st to see if it is already queued. If not, then send a mail to netdev, listing the upstream commit ID and why you think it should be a stable candidate. Before you jump to go do the above, do note that the normal stable rules - in Documentation/stable_kernel_rules.txt still apply. So you need to + in Documentation/process/stable-kernel-rules.rst still apply. So you need to explicitly indicate why it is a critical fix and exactly what users are impacted. In addition, you need to convince yourself that you _really_ think it has been overlooked, vs. having been considered and rejected. @@ -165,7 +165,7 @@ A: No. See above answer. In short, if you think it really belongs in If you think there is some valid information relating to it being in stable that does _not_ belong in the commit log, then use the three - dash marker line as described in Documentation/SubmittingPatches to + dash marker line as described in Documentation/process/submitting-patches.rst to temporarily embed that information into the patch that you send. Q: Someone said that the comment style and coding convention is different @@ -220,5 +220,5 @@ A: Attention to detail. Re-read your own work as if you were the If it is your first patch, mail it to yourself so you can test apply it to an unpatched tree to confirm infrastructure didn't mangle it. - Finally, go back and read Documentation/SubmittingPatches to be + Finally, go back and read Documentation/process/submitting-patches.rst to be sure you are not repeating some common mistake documented there. diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt index 4fb51d32fccc..497d668288f9 100644 --- a/Documentation/networking/nf_conntrack-sysctl.txt +++ b/Documentation/networking/nf_conntrack-sysctl.txt @@ -33,24 +33,6 @@ nf_conntrack_events - BOOLEAN If this option is enabled, the connection tracking code will provide userspace with connection tracking events via ctnetlink. -nf_conntrack_events_retry_timeout - INTEGER (seconds) - default 15 - - This option is only relevant when "reliable connection tracking - events" are used. Normally, ctnetlink is "lossy", that is, - events are normally dropped when userspace listeners can't keep up. - - Userspace can request "reliable event mode". When this mode is - active, the conntrack will only be destroyed after the event was - delivered. If event delivery fails, the kernel periodically - re-tries to send the event to userspace. - - This is the maximum interval the kernel should use when re-trying - to deliver the destroy event. - - A higher number means there will be fewer delivery retries and it - will take longer for a backlog to be processed. - nf_conntrack_expect_max - INTEGER Maximum size of expectation table. Default value is nf_conntrack_buckets / 256. Minimum is 1. @@ -80,10 +62,13 @@ nf_conntrack_generic_timeout - INTEGER (seconds) protocols. nf_conntrack_helper - BOOLEAN - 0 - disabled - not 0 - enabled (default) + 0 - disabled (default) + not 0 - enabled Enable automatic conntrack helper assignment. + If disabled it is required to set up iptables rules to assign + helpers to connections. See the CT target description in the + iptables-extensions(8) man page for further information. nf_conntrack_icmp_timeout - INTEGER (seconds) default 30 @@ -111,6 +96,17 @@ nf_conntrack_max - INTEGER Size of connection tracking table. Default value is nf_conntrack_buckets value * 4. +nf_conntrack_default_on - BOOLEAN + 0 - don't register conntrack in new net namespaces + 1 - register conntrack in new net namespaces (default) + + This controls wheter newly created network namespaces have connection + tracking enabled by default. It will be enabled automatically + regardless of this setting if the new net namespace requires + connection tracking, e.g. when NAT rules are created. + This setting is only visible in initial user namespace, it has no + effect on existing namespaces. + nf_conntrack_tcp_be_liberal - BOOLEAN 0 - disabled (default) not 0 - enabled diff --git a/Documentation/networking/phy.txt b/Documentation/networking/phy.txt index 7ab9404a8412..16f90d817224 100644 --- a/Documentation/networking/phy.txt +++ b/Documentation/networking/phy.txt @@ -65,6 +65,83 @@ The MDIO bus drivers/net/ethernet/freescale/fsl_pq_mdio.c and an associated DTS file for one of the users. (e.g. "git grep fsl,.*-mdio arch/powerpc/boot/dts/") +(RG)MII/electrical interface considerations + + The Reduced Gigabit Medium Independent Interface (RGMII) is a 12-pin + electrical signal interface using a synchronous 125Mhz clock signal and several + data lines. Due to this design decision, a 1.5ns to 2ns delay must be added + between the clock line (RXC or TXC) and the data lines to let the PHY (clock + sink) have enough setup and hold times to sample the data lines correctly. The + PHY library offers different types of PHY_INTERFACE_MODE_RGMII* values to let + the PHY driver and optionally the MAC driver, implement the required delay. The + values of phy_interface_t must be understood from the perspective of the PHY + device itself, leading to the following: + + * PHY_INTERFACE_MODE_RGMII: the PHY is not responsible for inserting any + internal delay by itself, it assumes that either the Ethernet MAC (if capable + or the PCB traces) insert the correct 1.5-2ns delay + + * PHY_INTERFACE_MODE_RGMII_TXID: the PHY should insert an internal delay + for the transmit data lines (TXD[3:0]) processed by the PHY device + + * PHY_INTERFACE_MODE_RGMII_RXID: the PHY should insert an internal delay + for the receive data lines (RXD[3:0]) processed by the PHY device + + * PHY_INTERFACE_MODE_RGMII_ID: the PHY should insert internal delays for + both transmit AND receive data lines from/to the PHY device + + Whenever possible, use the PHY side RGMII delay for these reasons: + + * PHY devices may offer sub-nanosecond granularity in how they allow a + receiver/transmitter side delay (e.g: 0.5, 1.0, 1.5ns) to be specified. Such + precision may be required to account for differences in PCB trace lengths + + * PHY devices are typically qualified for a large range of applications + (industrial, medical, automotive...), and they provide a constant and + reliable delay across temperature/pressure/voltage ranges + + * PHY device drivers in PHYLIB being reusable by nature, being able to + configure correctly a specified delay enables more designs with similar delay + requirements to be operate correctly + + For cases where the PHY is not capable of providing this delay, but the + Ethernet MAC driver is capable of doing so, the correct phy_interface_t value + should be PHY_INTERFACE_MODE_RGMII, and the Ethernet MAC driver should be + configured correctly in order to provide the required transmit and/or receive + side delay from the perspective of the PHY device. Conversely, if the Ethernet + MAC driver looks at the phy_interface_t value, for any other mode but + PHY_INTERFACE_MODE_RGMII, it should make sure that the MAC-level delays are + disabled. + + In case neither the Ethernet MAC, nor the PHY are capable of providing the + required delays, as defined per the RGMII standard, several options may be + available: + + * Some SoCs may offer a pin pad/mux/controller capable of configuring a given + set of pins'strength, delays, and voltage; and it may be a suitable + option to insert the expected 2ns RGMII delay. + + * Modifying the PCB design to include a fixed delay (e.g: using a specifically + designed serpentine), which may not require software configuration at all. + +Common problems with RGMII delay mismatch + + When there is a RGMII delay mismatch between the Ethernet MAC and the PHY, this + will most likely result in the clock and data line signals to be unstable when + the PHY or MAC take a snapshot of these signals to translate them into logical + 1 or 0 states and reconstruct the data being transmitted/received. Typical + symptoms include: + + * Transmission/reception partially works, and there is frequent or occasional + packet loss observed + + * Ethernet MAC may report some or all packets ingressing with a FCS/CRC error, + or just discard them all + + * Switching to lower speeds such as 10/100Mbits/sec makes the problem go away + (since there is enough setup/hold time in that case) + + Connecting to a PHY Sometime during startup, the network driver needs to establish a connection @@ -127,8 +204,9 @@ Letting the PHY Abstraction Layer do Everything values pruned from them which don't make sense for your controller (a 10/100 controller may be connected to a gigabit capable PHY, so you would need to mask off SUPPORTED_1000baseT*). See include/linux/ethtool.h for definitions - for these bitfields. Note that you should not SET any bits, or the PHY may - get put into an unsupported state. + for these bitfields. Note that you should not SET any bits, except the + SUPPORTED_Pause and SUPPORTED_AsymPause bits (see below), or the PHY may get + put into an unsupported state. Lastly, once the controller is ready to handle network traffic, you call phy_start(phydev). This tells the PAL that you are ready, and configures the @@ -139,6 +217,19 @@ Letting the PHY Abstraction Layer do Everything When you want to disconnect from the network (even if just briefly), you call phy_stop(phydev). +Pause frames / flow control + + The PHY does not participate directly in flow control/pause frames except by + making sure that the SUPPORTED_Pause and SUPPORTED_AsymPause bits are set in + MII_ADVERTISE to indicate towards the link partner that the Ethernet MAC + controller supports such a thing. Since flow control/pause frames generation + involves the Ethernet MAC driver, it is recommended that this driver takes care + of properly indicating advertisement and support for such features by setting + the SUPPORTED_Pause and SUPPORTED_AsymPause bits accordingly. This can be done + either before or after phy_connect() and/or as a result of implementing the + ethtool::set_pauseparam feature. + + Keeping Close Tabs on the PAL It is possible that the PAL's built-in state machine needs a little help to @@ -251,39 +342,8 @@ Writing a PHY driver PHY_BASIC_FEATURES, but you can look in include/mii.h for other features. - Each driver consists of a number of function pointers: - - soft_reset: perform a PHY software reset - config_init: configures PHY into a sane state after a reset. - For instance, a Davicom PHY requires descrambling disabled. - 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 - aneg_done: Determines the auto-negotiation result - read_status: Reads the current speed/duplex/negotiation settings - ack_interrupt: Clear a pending interrupt - did_interrupt: Checks if the PHY generated an interrupt - config_intr: Enable or disable interrupts - remove: Does any driver take-down - ts_info: Queries about the HW timestamping status - match_phy_device: used for Clause 45 capable PHYs to match devices - in package and ensure they are compatible - hwtstamp: Set the PHY HW timestamping configuration - rxtstamp: Requests a receive timestamp at the PHY level for a 'skb' - txtsamp: Requests a transmit timestamp at the PHY level for a 'skb' - set_wol: Enable Wake-on-LAN at the PHY level - get_wol: Get the Wake-on-LAN status at the PHY level - link_change_notify: called to inform the core is about to change the - link state, can be used to work around bogus PHY between state changes - read_mmd_indirect: Read PHY MMD indirect register - write_mmd_indirect: Write PHY MMD indirect register - module_info: Get the size and type of an EEPROM contained in an plug-in - module - module_eeprom: Get EEPROM information of a plug-in module - get_sset_count: Get number of strings sets that get_strings will count - get_strings: Get strings from requested objects (statistics) - get_stats: Get the extended statistics from the PHY device + Each driver consists of a number of function pointers, documented + in include/linux/phy.h under the phy_driver structure. Of these, only config_aneg and read_status are required to be assigned by the driver code. The rest are optional. Also, it is @@ -347,3 +407,22 @@ Board Fixups The stubs set one of the two matching criteria, and set the other one to match anything. + When phy_register_fixup() or *_for_uid()/*_for_id() is called at module, + unregister fixup and free allocate memory are required. + + Call one of following function before unloading module. + + int phy_unregister_fixup(const char *phy_id, u32 phy_uid, u32 phy_uid_mask); + int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); + int phy_register_fixup_for_id(const char *phy_id); + +Standards + + IEEE Standard 802.3: CSMA/CD Access Method and Physical Layer Specifications, Section Two: + http://standards.ieee.org/getieee802/download/802.3-2008_section2.pdf + + RGMII v1.3: + http://web.archive.org/web/20160303212629/http://www.hp.com/rnd/pdfs/RGMIIv1_3.pdf + + RGMII v2.0: + http://web.archive.org/web/20160303171328/http://www.hp.com/rnd/pdfs/RGMIIv2_0_final_hp.pdf diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index 70c926ae212d..1b63bbc6b94f 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -725,7 +725,8 @@ The kernel interface functions are as follows: (*) End a client call. - void rxrpc_kernel_end_call(struct rxrpc_call *call); + void rxrpc_kernel_end_call(struct socket *sock, + struct rxrpc_call *call); This is used to end a previously begun call. The user_call_ID is expunged from AF_RXRPC's knowledge and will not be seen again in association with @@ -733,7 +734,9 @@ The kernel interface functions are as follows: (*) Send data through a call. - int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, + int rxrpc_kernel_send_data(struct socket *sock, + struct rxrpc_call *call, + struct msghdr *msg, size_t len); This is used to supply either the request part of a client call or the @@ -745,9 +748,42 @@ The kernel interface functions are as follows: The msg must not specify a destination address, control data or any flags other than MSG_MORE. len is the total amount of data to transmit. + (*) Receive data from a call. + + int rxrpc_kernel_recv_data(struct socket *sock, + struct rxrpc_call *call, + void *buf, + size_t size, + size_t *_offset, + bool want_more, + u32 *_abort) + + This is used to receive data from either the reply part of a client call + or the request part of a service call. buf and size specify how much + data is desired and where to store it. *_offset is added on to buf and + subtracted from size internally; the amount copied into the buffer is + added to *_offset before returning. + + want_more should be true if further data will be required after this is + satisfied and false if this is the last item of the receive phase. + + There are three normal returns: 0 if the buffer was filled and want_more + was true; 1 if the buffer was filled, the last DATA packet has been + emptied and want_more was false; and -EAGAIN if the function needs to be + called again. + + If the last DATA packet is processed but the buffer contains less than + the amount requested, EBADMSG is returned. If want_more wasn't set, but + more data was available, EMSGSIZE is returned. + + If a remote ABORT is detected, the abort code received will be stored in + *_abort and ECONNABORTED will be returned. + (*) Abort a call. - void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code); + void rxrpc_kernel_abort_call(struct socket *sock, + struct rxrpc_call *call, + u32 abort_code); This is used to abort a call if it's still in an abortable state. The abort code specified will be placed in the ABORT message sent. @@ -820,47 +856,6 @@ The kernel interface functions are as follows: Other errors may be returned if the call had been aborted (-ECONNABORTED) or had timed out (-ETIME). - (*) Record the delivery of a data message. - - void rxrpc_kernel_data_consumed(struct rxrpc_call *call, - struct sk_buff *skb); - - This is used to record a data message as having been consumed and to - update the ACK state for the call. The message must still be passed to - rxrpc_kernel_free_skb() for disposal by the caller. - - (*) Free a message. - - void rxrpc_kernel_free_skb(struct sk_buff *skb); - - This is used to free a non-DATA socket buffer intercepted from an AF_RXRPC - socket. - - (*) Determine if a data message is the last one on a call. - - bool rxrpc_kernel_is_data_last(struct sk_buff *skb); - - This is used to determine if a socket buffer holds the last data message - to be received for a call (true will be returned if it does, false - if not). - - The data message will be part of the reply on a client call and the - request on an incoming call. In the latter case there will be more - messages, but in the former case there will not. - - (*) Get the abort code from an abort message. - - u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb); - - This is used to extract the abort code from a remote abort message. - - (*) Get the error number from a local or network error message. - - int rxrpc_kernel_get_error_number(struct sk_buff *skb); - - This is used to extract the error number from a message indicating either - a local error occurred or a network error occurred. - (*) Allocate a null key for doing anonymous security. struct key *rxrpc_get_null_key(const char *keyname); @@ -868,6 +863,13 @@ The kernel interface functions are as follows: This is used to allocate a null RxRPC key that can be used to indicate anonymous security for a particular domain. + (*) Get the peer address of a call. + + void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call, + struct sockaddr_rxrpc *_srx); + + This is used to find the remote peer address of a call. + ======================= CONFIGURABLE PARAMETERS diff --git a/Documentation/networking/seg6-sysctl.txt b/Documentation/networking/seg6-sysctl.txt new file mode 100644 index 000000000000..bdbde23b19cb --- /dev/null +++ b/Documentation/networking/seg6-sysctl.txt @@ -0,0 +1,18 @@ +/proc/sys/net/conf/<iface>/seg6_* variables: + +seg6_enabled - BOOL + Accept or drop SR-enabled IPv6 packets on this interface. + + Relevant packets are those with SRH present and DA = local. + + 0 - disabled (default) + not 0 - enabled + +seg6_require_hmac - INTEGER + Define HMAC policy for ingress SR-enabled packets on this interface. + + -1 - Ignore HMAC field + 0 - Accept SR packets without HMAC, validate SR packets with HMAC + 1 - Drop SR packets without HMAC, validate SR packets with HMAC + + Default is 0. diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt index e226f8925c9e..2bb07078f535 100644 --- a/Documentation/networking/stmmac.txt +++ b/Documentation/networking/stmmac.txt @@ -28,8 +28,6 @@ CONFIG_STMMAC_PCI: is to enable the pci driver. 2) Driver parameters list: debug: message level (0: no output, 16: all); phyaddr: to manually provide the physical address to the PHY device; - dma_rxsize: DMA rx ring size; - dma_txsize: DMA tx ring size; buf_sz: DMA buffer size; tc: control the HW FIFO threshold; watchdog: transmit timeout (in milliseconds); @@ -40,31 +38,31 @@ CONFIG_STMMAC_PCI: is to enable the pci driver. 3) Command line options Driver parameters can be also passed in command line by using: - stmmaceth=dma_rxsize:128,dma_txsize:512 + stmmaceth=watchdog:100,chain_mode=1 4) Driver information and notes 4.1) Transmit process The xmit method is invoked when the kernel needs to transmit a packet; it sets -the descriptors in the ring and informs the DMA engine that there is a packet +the descriptors in the ring and informs the DMA engine, that there is a packet ready to be transmitted. By default, the driver sets the NETIF_F_SG bit in the features field of the -net_device structure enabling the scatter-gather feature. This is true on +net_device structure, enabling the scatter-gather feature. This is true on chips and configurations where the checksum can be done in hardware. -Once the controller has finished transmitting the packet, napi will be +Once the controller has finished transmitting the packet, timer will be scheduled to release the transmit resources. 4.2) Receive process When one or more packets are received, an interrupt happens. The interrupts -are not queued so the driver has to scan all the descriptors in the ring during +are not queued, so the driver has to scan all the descriptors in the ring during the receive process. -This is based on NAPI so the interrupt handler signals only if there is work +This is based on NAPI, so the interrupt handler signals only if there is work to be done, and it exits. Then the poll method will be scheduled at some future point. The incoming packets are stored, by the DMA, in a list of pre-allocated socket buffers in order to avoid the memcpy (zero-copy). -4.3) Interrupt Mitigation +4.3) Interrupt mitigation The driver is able to mitigate the number of its DMA interrupts using NAPI for the reception on chips older than the 3.50. New chips have an HW RX-Watchdog used for this mitigation. @@ -88,19 +86,20 @@ the list, hence creating the explicit chaining in the descriptor itself, whereas such explicit chaining is not possible in RING mode. 4.5.1) Extended descriptors - The extended descriptors give us information about the Ethernet payload - when it is carrying PTP packets or TCP/UDP/ICMP over IP. - These are not available on GMAC Synopsys chips older than the 3.50. - At probe time the driver will decide if these can be actually used. - This support also is mandatory for PTPv2 because the extra descriptors - are used for saving the hardware timestamps and Extended Status. +The extended descriptors give us information about the Ethernet payload +when it is carrying PTP packets or TCP/UDP/ICMP over IP. +These are not available on GMAC Synopsys chips older than the 3.50. +At probe time the driver will decide if these can be actually used. +This support also is mandatory for PTPv2 because the extra descriptors +are used for saving the hardware timestamps and Extended Status. 4.6) Ethtool support Ethtool is supported. For example, driver statistics (including RMON), internal errors can be taken using: - # ethtool -S ethX command + # ethtool -S ethX +command 4.7) Jumbo and Segmentation Offloading Jumbo frames are supported and tested for the GMAC. @@ -153,8 +152,10 @@ Where: o dma_cfg: internal DMA parameters o pbl: the Programmable Burst Length is maximum number of beats to be transferred in one DMA transaction. - GMAC also enables the 4xPBL by default. - o fixed_burst/mixed_burst/burst_len + GMAC also enables the 4xPBL by default. (8xPBL for GMAC 3.50 and newer) + o txpbl/rxpbl: GMAC and newer supports independent DMA pbl for tx/rx. + o pblx8: Enable 8xPBL (4xPBL for core rev < 3.50). Enabled by default. + o fixed_burst/mixed_burst/aal o clk_csr: fixed CSR Clock range selection. o has_gmac: uses the GMAC core. o enh_desc: if sets the MAC will use the enhanced descriptor structure. @@ -206,16 +207,24 @@ tuned according to the HW capabilities. struct stmmac_dma_cfg { int pbl; + int txpbl; + int rxpbl; + bool pblx8; int fixed_burst; - int burst_len_supported; + int mixed_burst; + bool aal; }; Where: - o pbl: Programmable Burst Length + o pbl: Programmable Burst Length (tx and rx) + o txpbl: Transmit Programmable Burst Length. Only for GMAC and newer. + If set, DMA tx will use this value rather than pbl. + o rxpbl: Receive Programmable Burst Length. Only for GMAC and newer. + If set, DMA rx will use this value rather than pbl. + o pblx8: Enable 8xPBL (4xPBL for core rev < 3.50). Enabled by default. o fixed_burst: program the DMA to use the fixed burst mode - o burst_len: this is the value we put in the register - supported values are provided as macros in - linux/stmmac.h header file. + o mixed_burst: program the DMA to use the mixed burst mode + o aal: Address-Aligned Beats --- @@ -275,11 +284,11 @@ Please see the following document: Documentation/devicetree/bindings/net/stmmac.txt 4.11) This is a summary of the content of some relevant files: - o stmmac_main.c: to implement the main network device driver; - o stmmac_mdio.c: to provide mdio functions; - o stmmac_pci: this the PCI driver; - o stmmac_platform.c: this the platform driver (OF supported) - o stmmac_ethtool.c: to implement the ethtool support; + o stmmac_main.c: implements the main network device driver; + o stmmac_mdio.c: provides MDIO functions; + o stmmac_pci: this is the PCI driver; + o stmmac_platform.c: this the platform driver (OF supported); + o stmmac_ethtool.c: implements the ethtool support; o stmmac.h: private driver structure; o common.h: common definitions and VFTs; o mmc_core.c/mmc.h: Management MAC Counters; @@ -381,12 +390,12 @@ In addition to the basic timestamp features mentioned in IEEE 1588-2002 Timestamps, new GMAC cores support the advanced timestamp features. IEEE 1588-2008 that can be enabled when configure the Kernel. -8) SGMII/RGMII supports +8) SGMII/RGMII support New GMAC devices provide own way to manage RGMII/SGMII. This information is available at run-time by looking at the HW capability register. This means that the stmmac can manage -auto-negotiation and link status w/o using the PHYLIB stuff +auto-negotiation and link status w/o using the PHYLIB stuff. In fact, the HW provides a subset of extended registers to restart the ANE, verify Full/Half duplex mode and Speed. -Also thanks to these registers it is possible to look at the +Thanks to these registers, it is possible to look at the Auto-negotiated Link Parter Ability. diff --git a/Documentation/networking/strparser.txt b/Documentation/networking/strparser.txt new file mode 100644 index 000000000000..a0bf573dfa61 --- /dev/null +++ b/Documentation/networking/strparser.txt @@ -0,0 +1,136 @@ +Stream Parser +------------- + +The stream parser (strparser) is a utility that parses messages of an +application layer protocol running over a TCP connection. The stream +parser works in conjunction with an upper layer in the kernel to provide +kernel support for application layer messages. For instance, Kernel +Connection Multiplexor (KCM) uses the Stream Parser to parse messages +using a BPF program. + +Interface +--------- + +The API includes a context structure, a set of callbacks, utility +functions, and a data_ready function. The callbacks include +a parse_msg function that is called to perform parsing (e.g. +BPF parsing in case of KCM), and a rcv_msg function that is called +when a full message has been completed. + +A stream parser can be instantiated for a TCP connection. This is done +by: + +strp_init(struct strparser *strp, struct sock *csk, + struct strp_callbacks *cb) + +strp is a struct of type strparser that is allocated by the upper layer. +csk is the TCP socket associated with the stream parser. Callbacks are +called by the stream parser. + +Callbacks +--------- + +There are four callbacks: + +int (*parse_msg)(struct strparser *strp, struct sk_buff *skb); + + parse_msg is called to determine the length of the next message + in the stream. The upper layer must implement this function. It + should parse the sk_buff as containing the headers for the + next application layer messages in the stream. + + The skb->cb in the input skb is a struct strp_rx_msg. Only + the offset field is relevant in parse_msg and gives the offset + where the message starts in the skb. + + The return values of this function are: + + >0 : indicates length of successfully parsed message + 0 : indicates more data must be received to parse the message + -ESTRPIPE : current message should not be processed by the + kernel, return control of the socket to userspace which + can proceed to read the messages itself + other < 0 : Error is parsing, give control back to userspace + assuming that synchronization is lost and the stream + is unrecoverable (application expected to close TCP socket) + + In the case that an error is returned (return value is less than + zero) the stream parser will set the error on TCP socket and wake + it up. If parse_msg returned -ESTRPIPE and the stream parser had + previously read some bytes for the current message, then the error + set on the attached socket is ENODATA since the stream is + unrecoverable in that case. + +void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb); + + rcv_msg is called when a full message has been received and + is queued. The callee must consume the sk_buff; it can + call strp_pause to prevent any further messages from being + received in rcv_msg (see strp_pause below). This callback + must be set. + + The skb->cb in the input skb is a struct strp_rx_msg. This + struct contains two fields: offset and full_len. Offset is + where the message starts in the skb, and full_len is the + the length of the message. skb->len - offset may be greater + then full_len since strparser does not trim the skb. + +int (*read_sock_done)(struct strparser *strp, int err); + + read_sock_done is called when the stream parser is done reading + the TCP socket. The stream parser may read multiple messages + in a loop and this function allows cleanup to occur when existing + the loop. If the callback is not set (NULL in strp_init) a + default function is used. + +void (*abort_parser)(struct strparser *strp, int err); + + This function is called when stream parser encounters an error + in parsing. The default function stops the stream parser for the + TCP socket and sets the error in the socket. The default function + can be changed by setting the callback to non-NULL in strp_init. + +Functions +--------- + +The upper layer calls strp_tcp_data_ready when data is ready on the lower +socket for strparser to process. This should be called from a data_ready +callback that is set on the socket. + +strp_stop is called to completely stop stream parser operations. This +is called internally when the stream parser encounters an error, and +it is called from the upper layer when unattaching a TCP socket. + +strp_done is called to unattach the stream parser from the TCP socket. +This must be called after the stream processor has be stopped. + +strp_check_rcv is called to check for new messages on the socket. This +is normally called at initialization of the a stream parser instance +of after strp_unpause. + +Statistics +---------- + +Various counters are kept for each stream parser for a TCP socket. +These are in the strp_stats structure. strp_aggr_stats is a convenience +structure for accumulating statistics for multiple stream parser +instances. save_strp_stats and aggregate_strp_stats are helper functions +to save and aggregate statistics. + +Message assembly limits +----------------------- + +The stream parser provide mechanisms to limit the resources consumed by +message assembly. + +A timer is set when assembly starts for a new message. The message +timeout is taken from rcvtime for the associated TCP socket. If the +timer fires before assembly completes the stream parser is aborted +and the ETIMEDOUT error is set on the TCP socket. + +Message length is limited to the receive buffer size of the associated +TCP socket. If the length returned by parse_msg is greater than +the socket buffer size then the stream parser is aborted with +EMSGSIZE error set on the TCP socket. Note that this makes the +maximum size of receive skbuffs for a socket with a stream parser +to be 2*sk_rcvbuf of the TCP socket. diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 31c39115834d..2bbac05ab9e2 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -283,15 +283,10 @@ be sent to the port netdev for processing by the bridge driver. The bridge should not reflood the packet to the same ports the device flooded, otherwise there will be duplicate packets on the wire. -To avoid duplicate packets, the device/driver should mark a packet as already -forwarded using skb->offload_fwd_mark. The same mark is set on the device -ports in the domain using dev->offload_fwd_mark. If the skb->offload_fwd_mark -is non-zero and matches the forwarding egress port's dev->skb_mark, the kernel -will drop the skb right before transmit on the egress port, with the -understanding that the device already forwarded the packet on same egress port. -The driver can use switchdev_port_fwd_mark_set() to set a globally unique mark -for port's dev->offload_fwd_mark, based on the port's parent ID (switch ID) and -a group ifindex. +To avoid duplicate packets, the switch driver should mark a packet as already +forwarded by setting the skb->offload_fwd_mark bit. The bridge driver will mark +the skb using the ingress bridge port's mark and prevent it from being forwarded +through any bridge port with the same mark. It is possible for the switch device to not handle flooding and push the packets up to the bridge driver for flooding. This is not ideal as the number @@ -319,30 +314,29 @@ the kernel, with the device doing the FIB lookup and forwarding. The device does a longest prefix match (LPM) on FIB entries matching route prefix and forwards the packet to the matching FIB entry's nexthop(s) egress ports. -To program the device, the driver implements support for -SWITCHDEV_OBJ_IPV[4|6]_FIB object using switchdev_port_obj_xxx ops. -switchdev_port_obj_add is used for both adding a new FIB entry to the device, -or modifying an existing entry on the device. +To program the device, the driver has to register a FIB notifier handler +using register_fib_notifier. The following events are available: +FIB_EVENT_ENTRY_ADD: used for both adding a new FIB entry to the device, + or modifying an existing entry on the device. +FIB_EVENT_ENTRY_DEL: used for removing a FIB entry +FIB_EVENT_RULE_ADD, FIB_EVENT_RULE_DEL: used to propagate FIB rule changes -XXX: Currently, only SWITCHDEV_OBJ_ID_IPV4_FIB objects are supported. +FIB_EVENT_ENTRY_ADD and FIB_EVENT_ENTRY_DEL events pass: -SWITCHDEV_OBJ_ID_IPV4_FIB object passes: - - struct switchdev_obj_ipv4_fib { /* IPV4_FIB */ + struct fib_entry_notifier_info { + struct fib_notifier_info info; /* must be first */ u32 dst; int dst_len; struct fib_info *fi; u8 tos; u8 type; - u32 nlflags; u32 tb_id; - } ipv4_fib; + u32 nlflags; + }; to add/modify/delete IPv4 dst/dest_len prefix on table tb_id. The *fi structure holds details on the route and route's nexthops. *dev is one of the -port netdevs mentioned in the routes next hop list. If the output port netdevs -referenced in the route's nexthop list don't all have the same switch ID, the -driver is not called to add/modify/delete the FIB entry. +port netdevs mentioned in the route's next hop list. Routes offloaded to the device are labeled with "offload" in the ip route listing: @@ -360,6 +354,8 @@ listing: 12.0.0.4 via 11.0.0.9 dev sw1p2 proto zebra metric 20 offload 192.168.0.0/24 dev eth0 proto kernel scope link src 192.168.0.15 +The "offload" flag is set in case at least one device offloads the FIB entry. + XXX: add/mod/del IPv6 FIB API Nexthop Resolution diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 671cccf0dcd2..96f50694a748 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -182,6 +182,16 @@ SOF_TIMESTAMPING_OPT_TSONLY: the timestamp even if sysctl net.core.tstamp_allow_data is 0. This option disables SOF_TIMESTAMPING_OPT_CMSG. +SOF_TIMESTAMPING_OPT_STATS: + + Optional stats that are obtained along with the transmit timestamps. + It must be used together with SOF_TIMESTAMPING_OPT_TSONLY. When the + transmit timestamp is available, the stats are available in a + separate control message of type SCM_TIMESTAMPING_OPT_STATS, as a + list of TLVs (struct nlattr) of types. These stats allow the + application to associate various transport layer stats with + the transmit timestamps, such as how long a certain block of + data was limited by peer's receiver window. New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate diff --git a/Documentation/networking/timestamping/.gitignore b/Documentation/networking/timestamping/.gitignore deleted file mode 100644 index 9e69e982fb38..000000000000 --- a/Documentation/networking/timestamping/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -timestamping -txtimestamp -hwtstamp_config diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile deleted file mode 100644 index 8c20dfaa4d6e..000000000000 --- a/Documentation/networking/timestamping/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# To compile, from the source root -# -# make headers_install -# make M=documentation - -# List of programs to build -hostprogs-y := hwtstamp_config timestamping txtimestamp - -# Tell kbuild to always build the programs -always := $(hostprogs-y) - -HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include -HOSTCFLAGS_txtimestamp.o += -I$(objtree)/usr/include -HOSTCFLAGS_hwtstamp_config.o += -I$(objtree)/usr/include diff --git a/Documentation/networking/timestamping/hwtstamp_config.c b/Documentation/networking/timestamping/hwtstamp_config.c deleted file mode 100644 index e8b685a7f15f..000000000000 --- a/Documentation/networking/timestamping/hwtstamp_config.c +++ /dev/null @@ -1,134 +0,0 @@ -/* 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/networking/timestamping/timestamping.c b/Documentation/networking/timestamping/timestamping.c deleted file mode 100644 index 5cdfd743447b..000000000000 --- a/Documentation/networking/timestamping/timestamping.c +++ /dev/null @@ -1,528 +0,0 @@ -/* - * This program demonstrates how the various time stamping features in - * the Linux kernel work. It emulates the behavior of a PTP - * implementation in stand-alone master mode by sending PTPv1 Sync - * multicasts once every second. It looks for similar packets, but - * beyond that doesn't actually implement PTP. - * - * Outgoing packets are time stamped with SO_TIMESTAMPING with or - * without hardware support. - * - * Incoming packets are time stamped with SO_TIMESTAMPING with or - * without hardware support, SIOCGSTAMP[NS] (per-socket time stamp) and - * SO_TIMESTAMP[NS]. - * - * Copyright (C) 2009 Intel Corporation. - * Author: Patrick Ohly <patrick.ohly@intel.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <stdio.h> -#include <stdlib.h> -#include <errno.h> -#include <string.h> - -#include <sys/time.h> -#include <sys/socket.h> -#include <sys/select.h> -#include <sys/ioctl.h> -#include <arpa/inet.h> -#include <net/if.h> - -#include <asm/types.h> -#include <linux/net_tstamp.h> -#include <linux/errqueue.h> - -#ifndef SO_TIMESTAMPING -# define SO_TIMESTAMPING 37 -# define SCM_TIMESTAMPING SO_TIMESTAMPING -#endif - -#ifndef SO_TIMESTAMPNS -# define SO_TIMESTAMPNS 35 -#endif - -#ifndef SIOCGSTAMPNS -# define SIOCGSTAMPNS 0x8907 -#endif - -#ifndef SIOCSHWTSTAMP -# define SIOCSHWTSTAMP 0x89b0 -#endif - -static void usage(const char *error) -{ - if (error) - printf("invalid option: %s\n", error); - printf("timestamping interface option*\n\n" - "Options:\n" - " IP_MULTICAST_LOOP - looping outgoing multicasts\n" - " SO_TIMESTAMP - normal software time stamping, ms resolution\n" - " SO_TIMESTAMPNS - more accurate software time stamping\n" - " SOF_TIMESTAMPING_TX_HARDWARE - hardware time stamping of outgoing packets\n" - " SOF_TIMESTAMPING_TX_SOFTWARE - software fallback for outgoing packets\n" - " SOF_TIMESTAMPING_RX_HARDWARE - hardware time stamping of incoming packets\n" - " SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n" - " SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n" - " SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n" - " SIOCGSTAMP - check last socket time stamp\n" - " SIOCGSTAMPNS - more accurate socket time stamp\n"); - exit(1); -} - -static void bail(const char *error) -{ - printf("%s: %s\n", error, strerror(errno)); - exit(1); -} - -static const unsigned char sync[] = { - 0x00, 0x01, 0x00, 0x01, - 0x5f, 0x44, 0x46, 0x4c, - 0x54, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, - 0x01, 0x01, - - /* fake uuid */ - 0x00, 0x01, - 0x02, 0x03, 0x04, 0x05, - - 0x00, 0x01, 0x00, 0x37, - 0x00, 0x00, 0x00, 0x08, - 0x00, 0x00, 0x00, 0x00, - 0x49, 0x05, 0xcd, 0x01, - 0x29, 0xb1, 0x8d, 0xb0, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x01, - - /* fake uuid */ - 0x00, 0x01, - 0x02, 0x03, 0x04, 0x05, - - 0x00, 0x00, 0x00, 0x37, - 0x00, 0x00, 0x00, 0x04, - 0x44, 0x46, 0x4c, 0x54, - 0x00, 0x00, 0xf0, 0x60, - 0x00, 0x01, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x01, - 0x00, 0x00, 0xf0, 0x60, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x04, - 0x44, 0x46, 0x4c, 0x54, - 0x00, 0x01, - - /* fake uuid */ - 0x00, 0x01, - 0x02, 0x03, 0x04, 0x05, - - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00 -}; - -static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len) -{ - struct timeval now; - int res; - - res = sendto(sock, sync, sizeof(sync), 0, - addr, addr_len); - gettimeofday(&now, 0); - if (res < 0) - printf("%s: %s\n", "send", strerror(errno)); - else - printf("%ld.%06ld: sent %d bytes\n", - (long)now.tv_sec, (long)now.tv_usec, - res); -} - -static void printpacket(struct msghdr *msg, int res, - char *data, - int sock, int recvmsg_flags, - int siocgstamp, int siocgstampns) -{ - struct sockaddr_in *from_addr = (struct sockaddr_in *)msg->msg_name; - struct cmsghdr *cmsg; - struct timeval tv; - struct timespec ts; - struct timeval now; - - gettimeofday(&now, 0); - - printf("%ld.%06ld: received %s data, %d bytes from %s, %zu bytes control messages\n", - (long)now.tv_sec, (long)now.tv_usec, - (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", - res, - inet_ntoa(from_addr->sin_addr), - msg->msg_controllen); - for (cmsg = CMSG_FIRSTHDR(msg); - cmsg; - cmsg = CMSG_NXTHDR(msg, cmsg)) { - printf(" cmsg len %zu: ", cmsg->cmsg_len); - switch (cmsg->cmsg_level) { - case SOL_SOCKET: - printf("SOL_SOCKET "); - switch (cmsg->cmsg_type) { - case SO_TIMESTAMP: { - struct timeval *stamp = - (struct timeval *)CMSG_DATA(cmsg); - printf("SO_TIMESTAMP %ld.%06ld", - (long)stamp->tv_sec, - (long)stamp->tv_usec); - break; - } - case SO_TIMESTAMPNS: { - struct timespec *stamp = - (struct timespec *)CMSG_DATA(cmsg); - printf("SO_TIMESTAMPNS %ld.%09ld", - (long)stamp->tv_sec, - (long)stamp->tv_nsec); - break; - } - case SO_TIMESTAMPING: { - struct timespec *stamp = - (struct timespec *)CMSG_DATA(cmsg); - printf("SO_TIMESTAMPING "); - printf("SW %ld.%09ld ", - (long)stamp->tv_sec, - (long)stamp->tv_nsec); - stamp++; - /* skip deprecated HW transformed */ - stamp++; - printf("HW raw %ld.%09ld", - (long)stamp->tv_sec, - (long)stamp->tv_nsec); - break; - } - default: - printf("type %d", cmsg->cmsg_type); - break; - } - break; - case IPPROTO_IP: - printf("IPPROTO_IP "); - switch (cmsg->cmsg_type) { - case IP_RECVERR: { - struct sock_extended_err *err = - (struct sock_extended_err *)CMSG_DATA(cmsg); - printf("IP_RECVERR ee_errno '%s' ee_origin %d => %s", - strerror(err->ee_errno), - err->ee_origin, -#ifdef SO_EE_ORIGIN_TIMESTAMPING - err->ee_origin == SO_EE_ORIGIN_TIMESTAMPING ? - "bounced packet" : "unexpected origin" -#else - "probably SO_EE_ORIGIN_TIMESTAMPING" -#endif - ); - if (res < sizeof(sync)) - printf(" => truncated data?!"); - else if (!memcmp(sync, data + res - sizeof(sync), - sizeof(sync))) - printf(" => GOT OUR DATA BACK (HURRAY!)"); - break; - } - case IP_PKTINFO: { - struct in_pktinfo *pktinfo = - (struct in_pktinfo *)CMSG_DATA(cmsg); - printf("IP_PKTINFO interface index %u", - pktinfo->ipi_ifindex); - break; - } - default: - printf("type %d", cmsg->cmsg_type); - break; - } - break; - default: - printf("level %d type %d", - cmsg->cmsg_level, - cmsg->cmsg_type); - break; - } - printf("\n"); - } - - if (siocgstamp) { - if (ioctl(sock, SIOCGSTAMP, &tv)) - printf(" %s: %s\n", "SIOCGSTAMP", strerror(errno)); - else - printf("SIOCGSTAMP %ld.%06ld\n", - (long)tv.tv_sec, - (long)tv.tv_usec); - } - if (siocgstampns) { - if (ioctl(sock, SIOCGSTAMPNS, &ts)) - printf(" %s: %s\n", "SIOCGSTAMPNS", strerror(errno)); - else - printf("SIOCGSTAMPNS %ld.%09ld\n", - (long)ts.tv_sec, - (long)ts.tv_nsec); - } -} - -static void recvpacket(int sock, int recvmsg_flags, - int siocgstamp, int siocgstampns) -{ - char data[256]; - struct msghdr msg; - struct iovec entry; - struct sockaddr_in from_addr; - struct { - struct cmsghdr cm; - char control[512]; - } control; - int res; - - memset(&msg, 0, sizeof(msg)); - msg.msg_iov = &entry; - msg.msg_iovlen = 1; - entry.iov_base = data; - entry.iov_len = sizeof(data); - msg.msg_name = (caddr_t)&from_addr; - msg.msg_namelen = sizeof(from_addr); - msg.msg_control = &control; - msg.msg_controllen = sizeof(control); - - res = recvmsg(sock, &msg, recvmsg_flags|MSG_DONTWAIT); - if (res < 0) { - printf("%s %s: %s\n", - "recvmsg", - (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", - strerror(errno)); - } else { - printpacket(&msg, res, data, - sock, recvmsg_flags, - siocgstamp, siocgstampns); - } -} - -int main(int argc, char **argv) -{ - int so_timestamping_flags = 0; - int so_timestamp = 0; - int so_timestampns = 0; - int siocgstamp = 0; - int siocgstampns = 0; - int ip_multicast_loop = 0; - char *interface; - int i; - int enabled = 1; - int sock; - struct ifreq device; - struct ifreq hwtstamp; - struct hwtstamp_config hwconfig, hwconfig_requested; - struct sockaddr_in addr; - struct ip_mreq imr; - struct in_addr iaddr; - int val; - socklen_t len; - struct timeval next; - - if (argc < 2) - usage(0); - interface = argv[1]; - - for (i = 2; i < argc; i++) { - if (!strcasecmp(argv[i], "SO_TIMESTAMP")) - so_timestamp = 1; - else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS")) - so_timestampns = 1; - else if (!strcasecmp(argv[i], "SIOCGSTAMP")) - siocgstamp = 1; - else if (!strcasecmp(argv[i], "SIOCGSTAMPNS")) - siocgstampns = 1; - else if (!strcasecmp(argv[i], "IP_MULTICAST_LOOP")) - ip_multicast_loop = 1; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE; - else - usage(argv[i]); - } - - sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP); - if (sock < 0) - bail("socket"); - - memset(&device, 0, sizeof(device)); - strncpy(device.ifr_name, interface, sizeof(device.ifr_name)); - if (ioctl(sock, SIOCGIFADDR, &device) < 0) - bail("getting interface IP address"); - - memset(&hwtstamp, 0, sizeof(hwtstamp)); - strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name)); - hwtstamp.ifr_data = (void *)&hwconfig; - memset(&hwconfig, 0, sizeof(hwconfig)); - hwconfig.tx_type = - (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ? - HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - hwconfig.rx_filter = - (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ? - HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE; - hwconfig_requested = hwconfig; - if (ioctl(sock, SIOCSHWTSTAMP, &hwtstamp) < 0) { - if ((errno == EINVAL || errno == ENOTSUP) && - hwconfig_requested.tx_type == HWTSTAMP_TX_OFF && - hwconfig_requested.rx_filter == HWTSTAMP_FILTER_NONE) - printf("SIOCSHWTSTAMP: disabling hardware time stamping not possible\n"); - else - bail("SIOCSHWTSTAMP"); - } - printf("SIOCSHWTSTAMP: tx_type %d requested, got %d; rx_filter %d requested, got %d\n", - hwconfig_requested.tx_type, hwconfig.tx_type, - hwconfig_requested.rx_filter, hwconfig.rx_filter); - - /* bind to PTP port */ - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = htons(319 /* PTP event port */); - if (bind(sock, - (struct sockaddr *)&addr, - sizeof(struct sockaddr_in)) < 0) - bail("bind"); - - /* set multicast group for outgoing packets */ - inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */ - addr.sin_addr = iaddr; - imr.imr_multiaddr.s_addr = iaddr.s_addr; - imr.imr_interface.s_addr = - ((struct sockaddr_in *)&device.ifr_addr)->sin_addr.s_addr; - if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_IF, - &imr.imr_interface.s_addr, sizeof(struct in_addr)) < 0) - bail("set multicast"); - - /* join multicast group, loop our own packet */ - if (setsockopt(sock, IPPROTO_IP, IP_ADD_MEMBERSHIP, - &imr, sizeof(struct ip_mreq)) < 0) - bail("join multicast group"); - - if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_LOOP, - &ip_multicast_loop, sizeof(enabled)) < 0) { - bail("loop multicast"); - } - - /* set socket options for time stamping */ - if (so_timestamp && - setsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, - &enabled, sizeof(enabled)) < 0) - bail("setsockopt SO_TIMESTAMP"); - - if (so_timestampns && - setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, - &enabled, sizeof(enabled)) < 0) - bail("setsockopt SO_TIMESTAMPNS"); - - if (so_timestamping_flags && - setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, - &so_timestamping_flags, - sizeof(so_timestamping_flags)) < 0) - bail("setsockopt SO_TIMESTAMPING"); - - /* request IP_PKTINFO for debugging purposes */ - if (setsockopt(sock, SOL_IP, IP_PKTINFO, - &enabled, sizeof(enabled)) < 0) - printf("%s: %s\n", "setsockopt IP_PKTINFO", strerror(errno)); - - /* verify socket options */ - len = sizeof(val); - if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, &val, &len) < 0) - printf("%s: %s\n", "getsockopt SO_TIMESTAMP", strerror(errno)); - else - printf("SO_TIMESTAMP %d\n", val); - - if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, &val, &len) < 0) - printf("%s: %s\n", "getsockopt SO_TIMESTAMPNS", - strerror(errno)); - else - printf("SO_TIMESTAMPNS %d\n", val); - - if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) { - printf("%s: %s\n", "getsockopt SO_TIMESTAMPING", - strerror(errno)); - } else { - printf("SO_TIMESTAMPING %d\n", val); - if (val != so_timestamping_flags) - printf(" not the expected value %d\n", - so_timestamping_flags); - } - - /* send packets forever every five seconds */ - gettimeofday(&next, 0); - next.tv_sec = (next.tv_sec + 1) / 5 * 5; - next.tv_usec = 0; - while (1) { - struct timeval now; - struct timeval delta; - long delta_us; - int res; - fd_set readfs, errorfs; - - gettimeofday(&now, 0); - delta_us = (long)(next.tv_sec - now.tv_sec) * 1000000 + - (long)(next.tv_usec - now.tv_usec); - if (delta_us > 0) { - /* continue waiting for timeout or data */ - delta.tv_sec = delta_us / 1000000; - delta.tv_usec = delta_us % 1000000; - - FD_ZERO(&readfs); - FD_ZERO(&errorfs); - FD_SET(sock, &readfs); - FD_SET(sock, &errorfs); - printf("%ld.%06ld: select %ldus\n", - (long)now.tv_sec, (long)now.tv_usec, - delta_us); - res = select(sock + 1, &readfs, 0, &errorfs, &delta); - gettimeofday(&now, 0); - printf("%ld.%06ld: select returned: %d, %s\n", - (long)now.tv_sec, (long)now.tv_usec, - res, - res < 0 ? strerror(errno) : "success"); - if (res > 0) { - if (FD_ISSET(sock, &readfs)) - printf("ready for reading\n"); - if (FD_ISSET(sock, &errorfs)) - printf("has error\n"); - recvpacket(sock, 0, - siocgstamp, - siocgstampns); - recvpacket(sock, MSG_ERRQUEUE, - siocgstamp, - siocgstampns); - } - } else { - /* write one packet */ - sendpacket(sock, - (struct sockaddr *)&addr, - sizeof(addr)); - next.tv_sec += 5; - continue; - } - } - - return 0; -} diff --git a/Documentation/networking/timestamping/txtimestamp.c b/Documentation/networking/timestamping/txtimestamp.c deleted file mode 100644 index 5df07047ca86..000000000000 --- a/Documentation/networking/timestamping/txtimestamp.c +++ /dev/null @@ -1,549 +0,0 @@ -/* - * Copyright 2014 Google Inc. - * Author: willemb@google.com (Willem de Bruijn) - * - * Test software tx timestamping, including - * - * - SCHED, SND and ACK timestamps - * - RAW, UDP and TCP - * - IPv4 and IPv6 - * - various packet sizes (to test GSO and TSO) - * - * Consult the command line arguments for help on running - * the various testcases. - * - * This test requires a dummy TCP server. - * A simple `nc6 [-u] -l -p $DESTPORT` will do - * - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#define _GNU_SOURCE - -#include <arpa/inet.h> -#include <asm/types.h> -#include <error.h> -#include <errno.h> -#include <inttypes.h> -#include <linux/errqueue.h> -#include <linux/if_ether.h> -#include <linux/net_tstamp.h> -#include <netdb.h> -#include <net/if.h> -#include <netinet/in.h> -#include <netinet/ip.h> -#include <netinet/udp.h> -#include <netinet/tcp.h> -#include <netpacket/packet.h> -#include <poll.h> -#include <stdarg.h> -#include <stdbool.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <sys/ioctl.h> -#include <sys/select.h> -#include <sys/socket.h> -#include <sys/time.h> -#include <sys/types.h> -#include <time.h> -#include <unistd.h> - -/* command line parameters */ -static int cfg_proto = SOCK_STREAM; -static int cfg_ipproto = IPPROTO_TCP; -static int cfg_num_pkts = 4; -static int do_ipv4 = 1; -static int do_ipv6 = 1; -static int cfg_payload_len = 10; -static bool cfg_show_payload; -static bool cfg_do_pktinfo; -static bool cfg_loop_nodata; -static uint16_t dest_port = 9000; - -static struct sockaddr_in daddr; -static struct sockaddr_in6 daddr6; -static struct timespec ts_prev; - -static void __print_timestamp(const char *name, struct timespec *cur, - uint32_t key, int payload_len) -{ - if (!(cur->tv_sec | cur->tv_nsec)) - return; - - fprintf(stderr, " %s: %lu s %lu us (seq=%u, len=%u)", - name, cur->tv_sec, cur->tv_nsec / 1000, - key, payload_len); - - if ((ts_prev.tv_sec | ts_prev.tv_nsec)) { - int64_t cur_ms, prev_ms; - - cur_ms = (long) cur->tv_sec * 1000 * 1000; - cur_ms += cur->tv_nsec / 1000; - - prev_ms = (long) ts_prev.tv_sec * 1000 * 1000; - prev_ms += ts_prev.tv_nsec / 1000; - - fprintf(stderr, " (%+" PRId64 " us)", cur_ms - prev_ms); - } - - ts_prev = *cur; - fprintf(stderr, "\n"); -} - -static void print_timestamp_usr(void) -{ - struct timespec ts; - struct timeval tv; /* avoid dependency on -lrt */ - - gettimeofday(&tv, NULL); - ts.tv_sec = tv.tv_sec; - ts.tv_nsec = tv.tv_usec * 1000; - - __print_timestamp(" USR", &ts, 0, 0); -} - -static void print_timestamp(struct scm_timestamping *tss, int tstype, - int tskey, int payload_len) -{ - const char *tsname; - - switch (tstype) { - case SCM_TSTAMP_SCHED: - tsname = " ENQ"; - break; - case SCM_TSTAMP_SND: - tsname = " SND"; - break; - case SCM_TSTAMP_ACK: - tsname = " ACK"; - break; - default: - error(1, 0, "unknown timestamp type: %u", - tstype); - } - __print_timestamp(tsname, &tss->ts[0], tskey, payload_len); -} - -/* TODO: convert to check_and_print payload once API is stable */ -static void print_payload(char *data, int len) -{ - int i; - - if (!len) - return; - - if (len > 70) - len = 70; - - fprintf(stderr, "payload: "); - for (i = 0; i < len; i++) - fprintf(stderr, "%02hhx ", data[i]); - fprintf(stderr, "\n"); -} - -static void print_pktinfo(int family, int ifindex, void *saddr, void *daddr) -{ - char sa[INET6_ADDRSTRLEN], da[INET6_ADDRSTRLEN]; - - fprintf(stderr, " pktinfo: ifindex=%u src=%s dst=%s\n", - ifindex, - saddr ? inet_ntop(family, saddr, sa, sizeof(sa)) : "unknown", - daddr ? inet_ntop(family, daddr, da, sizeof(da)) : "unknown"); -} - -static void __poll(int fd) -{ - struct pollfd pollfd; - int ret; - - memset(&pollfd, 0, sizeof(pollfd)); - pollfd.fd = fd; - ret = poll(&pollfd, 1, 100); - if (ret != 1) - error(1, errno, "poll"); -} - -static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len) -{ - struct sock_extended_err *serr = NULL; - struct scm_timestamping *tss = NULL; - struct cmsghdr *cm; - int batch = 0; - - for (cm = CMSG_FIRSTHDR(msg); - cm && cm->cmsg_len; - cm = CMSG_NXTHDR(msg, cm)) { - if (cm->cmsg_level == SOL_SOCKET && - cm->cmsg_type == SCM_TIMESTAMPING) { - tss = (void *) CMSG_DATA(cm); - } else if ((cm->cmsg_level == SOL_IP && - cm->cmsg_type == IP_RECVERR) || - (cm->cmsg_level == SOL_IPV6 && - cm->cmsg_type == IPV6_RECVERR)) { - serr = (void *) CMSG_DATA(cm); - if (serr->ee_errno != ENOMSG || - serr->ee_origin != SO_EE_ORIGIN_TIMESTAMPING) { - fprintf(stderr, "unknown ip error %d %d\n", - serr->ee_errno, - serr->ee_origin); - serr = NULL; - } - } else if (cm->cmsg_level == SOL_IP && - cm->cmsg_type == IP_PKTINFO) { - struct in_pktinfo *info = (void *) CMSG_DATA(cm); - print_pktinfo(AF_INET, info->ipi_ifindex, - &info->ipi_spec_dst, &info->ipi_addr); - } else if (cm->cmsg_level == SOL_IPV6 && - cm->cmsg_type == IPV6_PKTINFO) { - struct in6_pktinfo *info6 = (void *) CMSG_DATA(cm); - print_pktinfo(AF_INET6, info6->ipi6_ifindex, - NULL, &info6->ipi6_addr); - } else - fprintf(stderr, "unknown cmsg %d,%d\n", - cm->cmsg_level, cm->cmsg_type); - - if (serr && tss) { - print_timestamp(tss, serr->ee_info, serr->ee_data, - payload_len); - serr = NULL; - tss = NULL; - batch++; - } - } - - if (batch > 1) - fprintf(stderr, "batched %d timestamps\n", batch); -} - -static int recv_errmsg(int fd) -{ - static char ctrl[1024 /* overprovision*/]; - static struct msghdr msg; - struct iovec entry; - static char *data; - int ret = 0; - - data = malloc(cfg_payload_len); - if (!data) - error(1, 0, "malloc"); - - memset(&msg, 0, sizeof(msg)); - memset(&entry, 0, sizeof(entry)); - memset(ctrl, 0, sizeof(ctrl)); - - entry.iov_base = data; - entry.iov_len = cfg_payload_len; - msg.msg_iov = &entry; - msg.msg_iovlen = 1; - msg.msg_name = NULL; - msg.msg_namelen = 0; - msg.msg_control = ctrl; - msg.msg_controllen = sizeof(ctrl); - - ret = recvmsg(fd, &msg, MSG_ERRQUEUE); - if (ret == -1 && errno != EAGAIN) - error(1, errno, "recvmsg"); - - if (ret >= 0) { - __recv_errmsg_cmsg(&msg, ret); - if (cfg_show_payload) - print_payload(data, cfg_payload_len); - } - - free(data); - return ret == -1; -} - -static void do_test(int family, unsigned int opt) -{ - char *buf; - int fd, i, val = 1, total_len; - - if (family == AF_INET6 && cfg_proto != SOCK_STREAM) { - /* due to lack of checksum generation code */ - fprintf(stderr, "test: skipping datagram over IPv6\n"); - return; - } - - total_len = cfg_payload_len; - if (cfg_proto == SOCK_RAW) { - total_len += sizeof(struct udphdr); - if (cfg_ipproto == IPPROTO_RAW) - total_len += sizeof(struct iphdr); - } - - buf = malloc(total_len); - if (!buf) - error(1, 0, "malloc"); - - fd = socket(family, cfg_proto, cfg_ipproto); - if (fd < 0) - error(1, errno, "socket"); - - if (cfg_proto == SOCK_STREAM) { - if (setsockopt(fd, IPPROTO_TCP, TCP_NODELAY, - (char*) &val, sizeof(val))) - error(1, 0, "setsockopt no nagle"); - - if (family == PF_INET) { - if (connect(fd, (void *) &daddr, sizeof(daddr))) - error(1, errno, "connect ipv4"); - } else { - if (connect(fd, (void *) &daddr6, sizeof(daddr6))) - error(1, errno, "connect ipv6"); - } - } - - if (cfg_do_pktinfo) { - if (family == AF_INET6) { - if (setsockopt(fd, SOL_IPV6, IPV6_RECVPKTINFO, - &val, sizeof(val))) - error(1, errno, "setsockopt pktinfo ipv6"); - } else { - if (setsockopt(fd, SOL_IP, IP_PKTINFO, - &val, sizeof(val))) - error(1, errno, "setsockopt pktinfo ipv4"); - } - } - - opt |= SOF_TIMESTAMPING_SOFTWARE | - SOF_TIMESTAMPING_OPT_CMSG | - SOF_TIMESTAMPING_OPT_ID; - if (cfg_loop_nodata) - opt |= SOF_TIMESTAMPING_OPT_TSONLY; - - if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, - (char *) &opt, sizeof(opt))) - error(1, 0, "setsockopt timestamping"); - - for (i = 0; i < cfg_num_pkts; i++) { - memset(&ts_prev, 0, sizeof(ts_prev)); - memset(buf, 'a' + i, total_len); - - if (cfg_proto == SOCK_RAW) { - struct udphdr *udph; - int off = 0; - - if (cfg_ipproto == IPPROTO_RAW) { - struct iphdr *iph = (void *) buf; - - memset(iph, 0, sizeof(*iph)); - iph->ihl = 5; - iph->version = 4; - iph->ttl = 2; - iph->daddr = daddr.sin_addr.s_addr; - iph->protocol = IPPROTO_UDP; - /* kernel writes saddr, csum, len */ - - off = sizeof(*iph); - } - - udph = (void *) buf + off; - udph->source = ntohs(9000); /* random spoof */ - udph->dest = ntohs(dest_port); - udph->len = ntohs(sizeof(*udph) + cfg_payload_len); - udph->check = 0; /* not allowed for IPv6 */ - } - - print_timestamp_usr(); - if (cfg_proto != SOCK_STREAM) { - if (family == PF_INET) - val = sendto(fd, buf, total_len, 0, (void *) &daddr, sizeof(daddr)); - else - val = sendto(fd, buf, total_len, 0, (void *) &daddr6, sizeof(daddr6)); - } else { - val = send(fd, buf, cfg_payload_len, 0); - } - if (val != total_len) - error(1, errno, "send"); - - /* wait for all errors to be queued, else ACKs arrive OOO */ - usleep(50 * 1000); - - __poll(fd); - - while (!recv_errmsg(fd)) {} - } - - if (close(fd)) - error(1, errno, "close"); - - free(buf); - usleep(400 * 1000); -} - -static void __attribute__((noreturn)) usage(const char *filepath) -{ - fprintf(stderr, "\nUsage: %s [options] hostname\n" - "\nwhere options are:\n" - " -4: only IPv4\n" - " -6: only IPv6\n" - " -h: show this message\n" - " -I: request PKTINFO\n" - " -l N: send N bytes at a time\n" - " -n: set no-payload option\n" - " -r: use raw\n" - " -R: use raw (IP_HDRINCL)\n" - " -p N: connect to port N\n" - " -u: use udp\n" - " -x: show payload (up to 70 bytes)\n", - filepath); - exit(1); -} - -static void parse_opt(int argc, char **argv) -{ - int proto_count = 0; - char c; - - while ((c = getopt(argc, argv, "46hIl:np:rRux")) != -1) { - switch (c) { - case '4': - do_ipv6 = 0; - break; - case '6': - do_ipv4 = 0; - break; - case 'I': - cfg_do_pktinfo = true; - break; - case 'n': - cfg_loop_nodata = true; - break; - case 'r': - proto_count++; - cfg_proto = SOCK_RAW; - cfg_ipproto = IPPROTO_UDP; - break; - case 'R': - proto_count++; - cfg_proto = SOCK_RAW; - cfg_ipproto = IPPROTO_RAW; - break; - case 'u': - proto_count++; - cfg_proto = SOCK_DGRAM; - cfg_ipproto = IPPROTO_UDP; - break; - case 'l': - cfg_payload_len = strtoul(optarg, NULL, 10); - break; - case 'p': - dest_port = strtoul(optarg, NULL, 10); - break; - case 'x': - cfg_show_payload = true; - break; - case 'h': - default: - usage(argv[0]); - } - } - - if (!cfg_payload_len) - error(1, 0, "payload may not be nonzero"); - if (cfg_proto != SOCK_STREAM && cfg_payload_len > 1472) - error(1, 0, "udp packet might exceed expected MTU"); - if (!do_ipv4 && !do_ipv6) - error(1, 0, "pass -4 or -6, not both"); - if (proto_count > 1) - error(1, 0, "pass -r, -R or -u, not multiple"); - - if (optind != argc - 1) - error(1, 0, "missing required hostname argument"); -} - -static void resolve_hostname(const char *hostname) -{ - struct addrinfo *addrs, *cur; - int have_ipv4 = 0, have_ipv6 = 0; - - if (getaddrinfo(hostname, NULL, NULL, &addrs)) - error(1, errno, "getaddrinfo"); - - cur = addrs; - while (cur && !have_ipv4 && !have_ipv6) { - if (!have_ipv4 && cur->ai_family == AF_INET) { - memcpy(&daddr, cur->ai_addr, sizeof(daddr)); - daddr.sin_port = htons(dest_port); - have_ipv4 = 1; - } - else if (!have_ipv6 && cur->ai_family == AF_INET6) { - memcpy(&daddr6, cur->ai_addr, sizeof(daddr6)); - daddr6.sin6_port = htons(dest_port); - have_ipv6 = 1; - } - cur = cur->ai_next; - } - if (addrs) - freeaddrinfo(addrs); - - do_ipv4 &= have_ipv4; - do_ipv6 &= have_ipv6; -} - -static void do_main(int family) -{ - fprintf(stderr, "family: %s\n", - family == PF_INET ? "INET" : "INET6"); - - fprintf(stderr, "test SND\n"); - do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE); - - fprintf(stderr, "test ENQ\n"); - do_test(family, SOF_TIMESTAMPING_TX_SCHED); - - fprintf(stderr, "test ENQ + SND\n"); - do_test(family, SOF_TIMESTAMPING_TX_SCHED | - SOF_TIMESTAMPING_TX_SOFTWARE); - - if (cfg_proto == SOCK_STREAM) { - fprintf(stderr, "\ntest ACK\n"); - do_test(family, SOF_TIMESTAMPING_TX_ACK); - - fprintf(stderr, "\ntest SND + ACK\n"); - do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_TX_ACK); - - fprintf(stderr, "\ntest ENQ + SND + ACK\n"); - do_test(family, SOF_TIMESTAMPING_TX_SCHED | - SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_TX_ACK); - } -} - -const char *sock_names[] = { NULL, "TCP", "UDP", "RAW" }; - -int main(int argc, char **argv) -{ - if (argc == 1) - usage(argv[0]); - - parse_opt(argc, argv); - resolve_hostname(argv[argc - 1]); - - fprintf(stderr, "protocol: %s\n", sock_names[cfg_proto]); - fprintf(stderr, "payload: %u\n", cfg_payload_len); - fprintf(stderr, "server port: %u\n", dest_port); - fprintf(stderr, "\n"); - - if (do_ipv4) - do_main(PF_INET); - if (do_ipv6) - do_main(PF_INET6); - - return 0; -} diff --git a/Documentation/networking/vortex.txt b/Documentation/networking/vortex.txt index 97282da82b75..ad3dead052a4 100644 --- a/Documentation/networking/vortex.txt +++ b/Documentation/networking/vortex.txt @@ -364,7 +364,7 @@ steps you should take: - The contents of your report will vary a lot depending upon the problem. If it's a kernel crash then you should refer to the - REPORTING-BUGS file. + admin-guide/reporting-bugs.rst file. But for most problems it is useful to provide the following: |