diff options
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/devicetree/bindings/net/apm-xgene-enet.txt | 3 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt | 45 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/macb.txt | 1 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/xilinx_gmii2rgmii.txt | 35 | ||||
| -rw-r--r-- | Documentation/networking/00-INDEX | 2 | ||||
| -rw-r--r-- | Documentation/networking/batman-adv.txt | 17 | ||||
| -rw-r--r-- | Documentation/networking/dsa/dsa.txt | 10 | ||||
| -rw-r--r-- | Documentation/networking/ena.txt | 305 | ||||
| -rw-r--r-- | Documentation/networking/ip-sysctl.txt | 45 | ||||
| -rw-r--r-- | Documentation/networking/strparser.txt | 136 | ||||
| -rw-r--r-- | Documentation/networking/switchdev.txt | 13 |
11 files changed, 569 insertions, 43 deletions
diff --git a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt index e41b2d59ca7f..f591ab782dbc 100644 --- a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt +++ b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt @@ -47,6 +47,9 @@ Optional properties: Valid values are between 0 to 7, that maps to 273, 589, 899, 1222, 1480, 1806, 2147, 2464 ps Default value is 2, which corresponds to 899 ps +- rxlos-gpios: Input gpio from SFP+ module to indicate availability of + incoming signal. + Example: menetclk: menetclk { diff --git a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt index 30d487597ecb..fb40891ee606 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt +++ b/Documentation/devicetree/bindings/net/brcm,bcm7445-switch-v4.0.txt @@ -6,9 +6,13 @@ Required properties: - reg: addresses and length of the register sets for the device, must be 6 pairs of register addresses and lengths - interrupts: interrupts for the devices, must be two interrupts +- #address-cells: must be 1, see dsa/dsa.txt +- #size-cells: must be 0, see dsa/dsa.txt + +Deprecated binding required properties: + - dsa,mii-bus: phandle to the MDIO bus controller, see dsa/dsa.txt - dsa,ethernet: phandle to the CPU network interface controller, see dsa/dsa.txt -- #size-cells: must be 0 - #address-cells: must be 2, see dsa/dsa.txt Subnodes: @@ -48,6 +52,45 @@ switch_top@f0b00000 { ethernet_switch@0 { compatible = "brcm,bcm7445-switch-v4.0"; #size-cells = <0>; + #address-cells = <1>; + reg = <0x0 0x40000 + 0x40000 0x110 + 0x40340 0x30 + 0x40380 0x30 + 0x40400 0x34 + 0x40600 0x208>; + reg-names = "core", "reg", intrl2_0", "intrl2_1", + "fcb, "acb"; + interrupts = <0 0x18 0 + 0 0x19 0>; + brcm,num-gphy = <1>; + brcm,num-rgmii-ports = <2>; + brcm,fcb-pause-override; + brcm,acb-packets-inflight; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + label = "gphy"; + reg = <0>; + }; + }; + }; +}; + +Example using the old DSA DeviceTree binding: + +switch_top@f0b00000 { + compatible = "simple-bus"; + #size-cells = <1>; + #address-cells = <1>; + ranges = <0 0xf0b00000 0x40804>; + + ethernet_switch@0 { + compatible = "brcm,bcm7445-switch-v4.0"; + #size-cells = <0>; #address-cells = <2>; reg = <0x0 0x40000 0x40000 0x110 diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index b5a42df4c928..1506e948610c 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -21,6 +21,7 @@ Required properties: - clock-names: Tuple listing input clock names. Required elements: 'pclk', 'hclk' Optional elements: 'tx_clk' + Optional elements: 'rx_clk' applies to cdns,zynqmp-gem - clocks: Phandles to input clocks. Optional properties for PHY child node: diff --git a/Documentation/devicetree/bindings/net/xilinx_gmii2rgmii.txt b/Documentation/devicetree/bindings/net/xilinx_gmii2rgmii.txt new file mode 100644 index 000000000000..038dda48b8e6 --- /dev/null +++ b/Documentation/devicetree/bindings/net/xilinx_gmii2rgmii.txt @@ -0,0 +1,35 @@ +XILINX GMIITORGMII Converter Driver Device Tree Bindings +-------------------------------------------------------- + +The Gigabit Media Independent Interface (GMII) to Reduced Gigabit Media +Independent Interface (RGMII) core provides the RGMII between RGMII-compliant +Ethernet physical media devices (PHY) and the Gigabit Ethernet controller. +This core can be used in all three modes of operation(10/100/1000 Mb/s). +The Management Data Input/Output (MDIO) interface is used to configure the +Speed of operation. This core can switch dynamically between the three +Different speed modes by configuring the conveter register through mdio write. + +This converter sits between the ethernet MAC and the external phy. +MAC <==> GMII2RGMII <==> RGMII_PHY + +For more details about mdio please refer phy.txt file in the same directory. + +Required properties: +- compatible : Should be "xlnx,gmii-to-rgmii-1.0" +- reg : The ID number for the phy, usually a small integer +- phy-handle : Should point to the external phy device. + See ethernet.txt file in the same directory. + +Example: + mdio { + #address-cells = <1>; + #size-cells = <0>; + phy: ethernet-phy@0 { + ...... + }; + gmiitorgmii: gmiitorgmii@8 { + compatible = "xlnx,gmii-to-rgmii-1.0"; + reg = <8>; + phy-handle = <&phy>; + }; + }; diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index 415154a487d0..a7697783ac4c 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -74,6 +74,8 @@ 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/batman-adv.txt b/Documentation/networking/batman-adv.txt index 1b5e7a7f2185..8a8d3d96f6c6 100644 --- a/Documentation/networking/batman-adv.txt +++ b/Documentation/networking/batman-adv.txt @@ -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). @@ -56,10 +61,10 @@ 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 diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index f20c884c048a..a4e55c76d371 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -227,9 +227,9 @@ 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 +357,10 @@ 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 +379,7 @@ 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 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/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 9ae929395b24..3db8c67d2c8d 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 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..44235e83799b 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 |