nuttx/net/devif/devif_iobsend.c

118 lines
3.2 KiB
C
Raw Normal View History

/****************************************************************************
* net/devif/devif_iobsend.c
*
* SPDX-License-Identifier: Apache-2.0
*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership. The
* ASF licenses this file to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance with the
* License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
* License for the specific language governing permissions and limitations
* under the License.
*
****************************************************************************/
/****************************************************************************
* Included Files
****************************************************************************/
#include <nuttx/config.h>
#include <string.h>
#include <assert.h>
#include <debug.h>
#include <errno.h>
#include <nuttx/mm/iob.h>
#include <nuttx/net/netdev.h>
#ifdef CONFIG_MM_IOB
/****************************************************************************
* Public Functions
****************************************************************************/
/****************************************************************************
* Name: devif_iob_send
*
* Description:
* Called from socket logic in response to a xmit or poll request from the
* the network interface driver.
*
* This is identical to calling devif_send() except that the data is
2014-06-24 03:38:10 +02:00
* in an I/O buffer chain, rather than a flat buffer.
*
* Assumptions:
* Called with the network locked.
*
****************************************************************************/
int devif_iob_send(FAR struct net_driver_s *dev, FAR struct iob_s *iob,
unsigned int len, unsigned int offset,
unsigned int target_offset)
{
int ret;
net/l2/l3/l4: add support of iob offload 1. Add new config CONFIG_NET_LL_GUARDSIZE to isolation of l2 stack, which will benefit l3(IP) layer for multi-MAC(l2) implementation, especially in some NICs such as celluler net driver. new configuration options: CONFIG_NET_LL_GUARDSIZE CONFIG_NET_LL_GUARDSIZE will reserved l2 buffer header size of network buffer to isolate the L2/L3 (MAC/IP) data on network layer, which will be beneficial to L3 network layer protocol transparent transmission and forwarding ------------------------------------------------------------ Layout of frist iob entry: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- iob | Reserved | io_len | ------------------------------------------------- ------------------------------------------------------------- Layout of different NICs implementation: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- Ethernet | Reserved | ETH_HDRLEN | io_len | ---------------------------------|--------------- 8021Q | Reserved | ETH_8021Q_HDRLEN | io_len | ---------------------------------|--------------- ipforward | Reserved | io_len | ------------------------------------------------- -------------------------------------------------------------------- 2. Support iob offload to l2 driver to avoid unnecessary memory copy Support send/receive iob vectors directly between the NICs and l3/l4 stack to avoid unnecessary memory copies, especially on hardware that supports Scatter/gather, which can greatly improve performance. new interface to support iob offload: ------------------------------------------ | IOB version | original | |----------------------------------------| | devif_iob_poll() | devif_poll() | | ... | ... | ------------------------------------------ -------------------------------------------------------------------- 1> NIC hardware support Scatter/gather transfer TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | dev->d_iob: | --------------- --------------- io_data iob1 | | | iob3 | | | \ --------------- --------------- --------------- | --------------- | iob0 | | | | iob2 | | | | --------------- | --------------- | \ | / / \ | / / ---------------------------------------------- NICs io vector | | | | | | | | | | ---------------------------------------------- RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to each iobs) -------------------------------------------------------------------- 2> CONFIG_IOB_BUFSIZE is greater than MTU: TX: "(CONFIG_IOB_BUFSIZE) > (MAX_NETDEV_PKTSIZE + CONFIG_NET_GUARDSIZE + CONFIG_NET_LL_GUARDSIZE)" tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | "NIC"_send() (dev->d_iob->io_data[CONFIG_NET_LL_GUARDSIZE - NET_LL_HDRLEN(dev)]) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to io_data) -------------------------------------------------------------------- 3> Compatible with all old flat buffer NICs TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll(devif_poll_callback()) devif_poll_callback() /* new interface, gather iobs to flat buffer */ / \ / \ devif_poll("NIC"_txpoll) "NIC"_send()(dev->d_buf) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | netdev_input() /* new interface, Scatter/gather flat/iob buffer */ | | pkt/ipv[4|6]_input()/... | | NICs io vector receive(Orignal flat buffer) 3. Iperf passthrough on NuttX simulator: ------------------------------------------------- | Protocol | Server | Client | | |-----------------------------------------------| | TCP | 813 | 834 | Mbits/sec | | TCP(Offload) | 1720 | 1100 | Mbits/sec | | UDP | 22 | 757 | Mbits/sec | | UDP(Offload) | 25 | 1250 | Mbits/sec | ------------------------------------------------- Signed-off-by: chao an <anchao@xiaomi.com>
2022-11-23 12:39:40 +01:00
if (dev == NULL)
{
ret = -ENODEV;
goto errout;
}
if (len == 0)
{
ret = -EINVAL;
goto errout;
}
net/l2/l3/l4: add support of iob offload 1. Add new config CONFIG_NET_LL_GUARDSIZE to isolation of l2 stack, which will benefit l3(IP) layer for multi-MAC(l2) implementation, especially in some NICs such as celluler net driver. new configuration options: CONFIG_NET_LL_GUARDSIZE CONFIG_NET_LL_GUARDSIZE will reserved l2 buffer header size of network buffer to isolate the L2/L3 (MAC/IP) data on network layer, which will be beneficial to L3 network layer protocol transparent transmission and forwarding ------------------------------------------------------------ Layout of frist iob entry: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- iob | Reserved | io_len | ------------------------------------------------- ------------------------------------------------------------- Layout of different NICs implementation: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- Ethernet | Reserved | ETH_HDRLEN | io_len | ---------------------------------|--------------- 8021Q | Reserved | ETH_8021Q_HDRLEN | io_len | ---------------------------------|--------------- ipforward | Reserved | io_len | ------------------------------------------------- -------------------------------------------------------------------- 2. Support iob offload to l2 driver to avoid unnecessary memory copy Support send/receive iob vectors directly between the NICs and l3/l4 stack to avoid unnecessary memory copies, especially on hardware that supports Scatter/gather, which can greatly improve performance. new interface to support iob offload: ------------------------------------------ | IOB version | original | |----------------------------------------| | devif_iob_poll() | devif_poll() | | ... | ... | ------------------------------------------ -------------------------------------------------------------------- 1> NIC hardware support Scatter/gather transfer TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | dev->d_iob: | --------------- --------------- io_data iob1 | | | iob3 | | | \ --------------- --------------- --------------- | --------------- | iob0 | | | | iob2 | | | | --------------- | --------------- | \ | / / \ | / / ---------------------------------------------- NICs io vector | | | | | | | | | | ---------------------------------------------- RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to each iobs) -------------------------------------------------------------------- 2> CONFIG_IOB_BUFSIZE is greater than MTU: TX: "(CONFIG_IOB_BUFSIZE) > (MAX_NETDEV_PKTSIZE + CONFIG_NET_GUARDSIZE + CONFIG_NET_LL_GUARDSIZE)" tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | "NIC"_send() (dev->d_iob->io_data[CONFIG_NET_LL_GUARDSIZE - NET_LL_HDRLEN(dev)]) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to io_data) -------------------------------------------------------------------- 3> Compatible with all old flat buffer NICs TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll(devif_poll_callback()) devif_poll_callback() /* new interface, gather iobs to flat buffer */ / \ / \ devif_poll("NIC"_txpoll) "NIC"_send()(dev->d_buf) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | netdev_input() /* new interface, Scatter/gather flat/iob buffer */ | | pkt/ipv[4|6]_input()/... | | NICs io vector receive(Orignal flat buffer) 3. Iperf passthrough on NuttX simulator: ------------------------------------------------- | Protocol | Server | Client | | |-----------------------------------------------| | TCP | 813 | 834 | Mbits/sec | | TCP(Offload) | 1720 | 1100 | Mbits/sec | | UDP | 22 | 757 | Mbits/sec | | UDP(Offload) | 25 | 1250 | Mbits/sec | ------------------------------------------------- Signed-off-by: chao an <anchao@xiaomi.com>
2022-11-23 12:39:40 +01:00
#ifndef CONFIG_NET_IPFRAG
if (len > NETDEV_PKTSIZE(dev) - NET_LL_HDRLEN(dev) - target_offset)
{
ret = -EMSGSIZE;
goto errout;
}
#endif
net/l2/l3/l4: add support of iob offload 1. Add new config CONFIG_NET_LL_GUARDSIZE to isolation of l2 stack, which will benefit l3(IP) layer for multi-MAC(l2) implementation, especially in some NICs such as celluler net driver. new configuration options: CONFIG_NET_LL_GUARDSIZE CONFIG_NET_LL_GUARDSIZE will reserved l2 buffer header size of network buffer to isolate the L2/L3 (MAC/IP) data on network layer, which will be beneficial to L3 network layer protocol transparent transmission and forwarding ------------------------------------------------------------ Layout of frist iob entry: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- iob | Reserved | io_len | ------------------------------------------------- ------------------------------------------------------------- Layout of different NICs implementation: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- Ethernet | Reserved | ETH_HDRLEN | io_len | ---------------------------------|--------------- 8021Q | Reserved | ETH_8021Q_HDRLEN | io_len | ---------------------------------|--------------- ipforward | Reserved | io_len | ------------------------------------------------- -------------------------------------------------------------------- 2. Support iob offload to l2 driver to avoid unnecessary memory copy Support send/receive iob vectors directly between the NICs and l3/l4 stack to avoid unnecessary memory copies, especially on hardware that supports Scatter/gather, which can greatly improve performance. new interface to support iob offload: ------------------------------------------ | IOB version | original | |----------------------------------------| | devif_iob_poll() | devif_poll() | | ... | ... | ------------------------------------------ -------------------------------------------------------------------- 1> NIC hardware support Scatter/gather transfer TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | dev->d_iob: | --------------- --------------- io_data iob1 | | | iob3 | | | \ --------------- --------------- --------------- | --------------- | iob0 | | | | iob2 | | | | --------------- | --------------- | \ | / / \ | / / ---------------------------------------------- NICs io vector | | | | | | | | | | ---------------------------------------------- RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to each iobs) -------------------------------------------------------------------- 2> CONFIG_IOB_BUFSIZE is greater than MTU: TX: "(CONFIG_IOB_BUFSIZE) > (MAX_NETDEV_PKTSIZE + CONFIG_NET_GUARDSIZE + CONFIG_NET_LL_GUARDSIZE)" tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | "NIC"_send() (dev->d_iob->io_data[CONFIG_NET_LL_GUARDSIZE - NET_LL_HDRLEN(dev)]) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to io_data) -------------------------------------------------------------------- 3> Compatible with all old flat buffer NICs TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll(devif_poll_callback()) devif_poll_callback() /* new interface, gather iobs to flat buffer */ / \ / \ devif_poll("NIC"_txpoll) "NIC"_send()(dev->d_buf) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | netdev_input() /* new interface, Scatter/gather flat/iob buffer */ | | pkt/ipv[4|6]_input()/... | | NICs io vector receive(Orignal flat buffer) 3. Iperf passthrough on NuttX simulator: ------------------------------------------------- | Protocol | Server | Client | | |-----------------------------------------------| | TCP | 813 | 834 | Mbits/sec | | TCP(Offload) | 1720 | 1100 | Mbits/sec | | UDP | 22 | 757 | Mbits/sec | | UDP(Offload) | 25 | 1250 | Mbits/sec | ------------------------------------------------- Signed-off-by: chao an <anchao@xiaomi.com>
2022-11-23 12:39:40 +01:00
/* Append the send buffer after device buffer */
if (len > iob_navail(false) * CONFIG_IOB_BUFSIZE)
net/l2/l3/l4: add support of iob offload 1. Add new config CONFIG_NET_LL_GUARDSIZE to isolation of l2 stack, which will benefit l3(IP) layer for multi-MAC(l2) implementation, especially in some NICs such as celluler net driver. new configuration options: CONFIG_NET_LL_GUARDSIZE CONFIG_NET_LL_GUARDSIZE will reserved l2 buffer header size of network buffer to isolate the L2/L3 (MAC/IP) data on network layer, which will be beneficial to L3 network layer protocol transparent transmission and forwarding ------------------------------------------------------------ Layout of frist iob entry: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- iob | Reserved | io_len | ------------------------------------------------- ------------------------------------------------------------- Layout of different NICs implementation: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- Ethernet | Reserved | ETH_HDRLEN | io_len | ---------------------------------|--------------- 8021Q | Reserved | ETH_8021Q_HDRLEN | io_len | ---------------------------------|--------------- ipforward | Reserved | io_len | ------------------------------------------------- -------------------------------------------------------------------- 2. Support iob offload to l2 driver to avoid unnecessary memory copy Support send/receive iob vectors directly between the NICs and l3/l4 stack to avoid unnecessary memory copies, especially on hardware that supports Scatter/gather, which can greatly improve performance. new interface to support iob offload: ------------------------------------------ | IOB version | original | |----------------------------------------| | devif_iob_poll() | devif_poll() | | ... | ... | ------------------------------------------ -------------------------------------------------------------------- 1> NIC hardware support Scatter/gather transfer TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | dev->d_iob: | --------------- --------------- io_data iob1 | | | iob3 | | | \ --------------- --------------- --------------- | --------------- | iob0 | | | | iob2 | | | | --------------- | --------------- | \ | / / \ | / / ---------------------------------------------- NICs io vector | | | | | | | | | | ---------------------------------------------- RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to each iobs) -------------------------------------------------------------------- 2> CONFIG_IOB_BUFSIZE is greater than MTU: TX: "(CONFIG_IOB_BUFSIZE) > (MAX_NETDEV_PKTSIZE + CONFIG_NET_GUARDSIZE + CONFIG_NET_LL_GUARDSIZE)" tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | "NIC"_send() (dev->d_iob->io_data[CONFIG_NET_LL_GUARDSIZE - NET_LL_HDRLEN(dev)]) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to io_data) -------------------------------------------------------------------- 3> Compatible with all old flat buffer NICs TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll(devif_poll_callback()) devif_poll_callback() /* new interface, gather iobs to flat buffer */ / \ / \ devif_poll("NIC"_txpoll) "NIC"_send()(dev->d_buf) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | netdev_input() /* new interface, Scatter/gather flat/iob buffer */ | | pkt/ipv[4|6]_input()/... | | NICs io vector receive(Orignal flat buffer) 3. Iperf passthrough on NuttX simulator: ------------------------------------------------- | Protocol | Server | Client | | |-----------------------------------------------| | TCP | 813 | 834 | Mbits/sec | | TCP(Offload) | 1720 | 1100 | Mbits/sec | | UDP | 22 | 757 | Mbits/sec | | UDP(Offload) | 25 | 1250 | Mbits/sec | ------------------------------------------------- Signed-off-by: chao an <anchao@xiaomi.com>
2022-11-23 12:39:40 +01:00
{
ret = -ENOMEM;
goto errout;
}
net/l2/l3/l4: add support of iob offload 1. Add new config CONFIG_NET_LL_GUARDSIZE to isolation of l2 stack, which will benefit l3(IP) layer for multi-MAC(l2) implementation, especially in some NICs such as celluler net driver. new configuration options: CONFIG_NET_LL_GUARDSIZE CONFIG_NET_LL_GUARDSIZE will reserved l2 buffer header size of network buffer to isolate the L2/L3 (MAC/IP) data on network layer, which will be beneficial to L3 network layer protocol transparent transmission and forwarding ------------------------------------------------------------ Layout of frist iob entry: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- iob | Reserved | io_len | ------------------------------------------------- ------------------------------------------------------------- Layout of different NICs implementation: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- Ethernet | Reserved | ETH_HDRLEN | io_len | ---------------------------------|--------------- 8021Q | Reserved | ETH_8021Q_HDRLEN | io_len | ---------------------------------|--------------- ipforward | Reserved | io_len | ------------------------------------------------- -------------------------------------------------------------------- 2. Support iob offload to l2 driver to avoid unnecessary memory copy Support send/receive iob vectors directly between the NICs and l3/l4 stack to avoid unnecessary memory copies, especially on hardware that supports Scatter/gather, which can greatly improve performance. new interface to support iob offload: ------------------------------------------ | IOB version | original | |----------------------------------------| | devif_iob_poll() | devif_poll() | | ... | ... | ------------------------------------------ -------------------------------------------------------------------- 1> NIC hardware support Scatter/gather transfer TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | dev->d_iob: | --------------- --------------- io_data iob1 | | | iob3 | | | \ --------------- --------------- --------------- | --------------- | iob0 | | | | iob2 | | | | --------------- | --------------- | \ | / / \ | / / ---------------------------------------------- NICs io vector | | | | | | | | | | ---------------------------------------------- RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to each iobs) -------------------------------------------------------------------- 2> CONFIG_IOB_BUFSIZE is greater than MTU: TX: "(CONFIG_IOB_BUFSIZE) > (MAX_NETDEV_PKTSIZE + CONFIG_NET_GUARDSIZE + CONFIG_NET_LL_GUARDSIZE)" tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | "NIC"_send() (dev->d_iob->io_data[CONFIG_NET_LL_GUARDSIZE - NET_LL_HDRLEN(dev)]) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to io_data) -------------------------------------------------------------------- 3> Compatible with all old flat buffer NICs TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll(devif_poll_callback()) devif_poll_callback() /* new interface, gather iobs to flat buffer */ / \ / \ devif_poll("NIC"_txpoll) "NIC"_send()(dev->d_buf) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | netdev_input() /* new interface, Scatter/gather flat/iob buffer */ | | pkt/ipv[4|6]_input()/... | | NICs io vector receive(Orignal flat buffer) 3. Iperf passthrough on NuttX simulator: ------------------------------------------------- | Protocol | Server | Client | | |-----------------------------------------------| | TCP | 813 | 834 | Mbits/sec | | TCP(Offload) | 1720 | 1100 | Mbits/sec | | UDP | 22 | 757 | Mbits/sec | | UDP(Offload) | 25 | 1250 | Mbits/sec | ------------------------------------------------- Signed-off-by: chao an <anchao@xiaomi.com>
2022-11-23 12:39:40 +01:00
/* Clone the iob to target device buffer */
net/l2/l3/l4: add support of iob offload 1. Add new config CONFIG_NET_LL_GUARDSIZE to isolation of l2 stack, which will benefit l3(IP) layer for multi-MAC(l2) implementation, especially in some NICs such as celluler net driver. new configuration options: CONFIG_NET_LL_GUARDSIZE CONFIG_NET_LL_GUARDSIZE will reserved l2 buffer header size of network buffer to isolate the L2/L3 (MAC/IP) data on network layer, which will be beneficial to L3 network layer protocol transparent transmission and forwarding ------------------------------------------------------------ Layout of frist iob entry: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- iob | Reserved | io_len | ------------------------------------------------- ------------------------------------------------------------- Layout of different NICs implementation: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- Ethernet | Reserved | ETH_HDRLEN | io_len | ---------------------------------|--------------- 8021Q | Reserved | ETH_8021Q_HDRLEN | io_len | ---------------------------------|--------------- ipforward | Reserved | io_len | ------------------------------------------------- -------------------------------------------------------------------- 2. Support iob offload to l2 driver to avoid unnecessary memory copy Support send/receive iob vectors directly between the NICs and l3/l4 stack to avoid unnecessary memory copies, especially on hardware that supports Scatter/gather, which can greatly improve performance. new interface to support iob offload: ------------------------------------------ | IOB version | original | |----------------------------------------| | devif_iob_poll() | devif_poll() | | ... | ... | ------------------------------------------ -------------------------------------------------------------------- 1> NIC hardware support Scatter/gather transfer TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | dev->d_iob: | --------------- --------------- io_data iob1 | | | iob3 | | | \ --------------- --------------- --------------- | --------------- | iob0 | | | | iob2 | | | | --------------- | --------------- | \ | / / \ | / / ---------------------------------------------- NICs io vector | | | | | | | | | | ---------------------------------------------- RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to each iobs) -------------------------------------------------------------------- 2> CONFIG_IOB_BUFSIZE is greater than MTU: TX: "(CONFIG_IOB_BUFSIZE) > (MAX_NETDEV_PKTSIZE + CONFIG_NET_GUARDSIZE + CONFIG_NET_LL_GUARDSIZE)" tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | "NIC"_send() (dev->d_iob->io_data[CONFIG_NET_LL_GUARDSIZE - NET_LL_HDRLEN(dev)]) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to io_data) -------------------------------------------------------------------- 3> Compatible with all old flat buffer NICs TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll(devif_poll_callback()) devif_poll_callback() /* new interface, gather iobs to flat buffer */ / \ / \ devif_poll("NIC"_txpoll) "NIC"_send()(dev->d_buf) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | netdev_input() /* new interface, Scatter/gather flat/iob buffer */ | | pkt/ipv[4|6]_input()/... | | NICs io vector receive(Orignal flat buffer) 3. Iperf passthrough on NuttX simulator: ------------------------------------------------- | Protocol | Server | Client | | |-----------------------------------------------| | TCP | 813 | 834 | Mbits/sec | | TCP(Offload) | 1720 | 1100 | Mbits/sec | | UDP | 22 | 757 | Mbits/sec | | UDP(Offload) | 25 | 1250 | Mbits/sec | ------------------------------------------------- Signed-off-by: chao an <anchao@xiaomi.com>
2022-11-23 12:39:40 +01:00
ret = iob_clone_partial(iob, len, offset, dev->d_iob,
target_offset, false, false);
if (ret != OK)
net/l2/l3/l4: add support of iob offload 1. Add new config CONFIG_NET_LL_GUARDSIZE to isolation of l2 stack, which will benefit l3(IP) layer for multi-MAC(l2) implementation, especially in some NICs such as celluler net driver. new configuration options: CONFIG_NET_LL_GUARDSIZE CONFIG_NET_LL_GUARDSIZE will reserved l2 buffer header size of network buffer to isolate the L2/L3 (MAC/IP) data on network layer, which will be beneficial to L3 network layer protocol transparent transmission and forwarding ------------------------------------------------------------ Layout of frist iob entry: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- iob | Reserved | io_len | ------------------------------------------------- ------------------------------------------------------------- Layout of different NICs implementation: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- Ethernet | Reserved | ETH_HDRLEN | io_len | ---------------------------------|--------------- 8021Q | Reserved | ETH_8021Q_HDRLEN | io_len | ---------------------------------|--------------- ipforward | Reserved | io_len | ------------------------------------------------- -------------------------------------------------------------------- 2. Support iob offload to l2 driver to avoid unnecessary memory copy Support send/receive iob vectors directly between the NICs and l3/l4 stack to avoid unnecessary memory copies, especially on hardware that supports Scatter/gather, which can greatly improve performance. new interface to support iob offload: ------------------------------------------ | IOB version | original | |----------------------------------------| | devif_iob_poll() | devif_poll() | | ... | ... | ------------------------------------------ -------------------------------------------------------------------- 1> NIC hardware support Scatter/gather transfer TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | dev->d_iob: | --------------- --------------- io_data iob1 | | | iob3 | | | \ --------------- --------------- --------------- | --------------- | iob0 | | | | iob2 | | | | --------------- | --------------- | \ | / / \ | / / ---------------------------------------------- NICs io vector | | | | | | | | | | ---------------------------------------------- RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to each iobs) -------------------------------------------------------------------- 2> CONFIG_IOB_BUFSIZE is greater than MTU: TX: "(CONFIG_IOB_BUFSIZE) > (MAX_NETDEV_PKTSIZE + CONFIG_NET_GUARDSIZE + CONFIG_NET_LL_GUARDSIZE)" tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | "NIC"_send() (dev->d_iob->io_data[CONFIG_NET_LL_GUARDSIZE - NET_LL_HDRLEN(dev)]) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to io_data) -------------------------------------------------------------------- 3> Compatible with all old flat buffer NICs TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll(devif_poll_callback()) devif_poll_callback() /* new interface, gather iobs to flat buffer */ / \ / \ devif_poll("NIC"_txpoll) "NIC"_send()(dev->d_buf) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | netdev_input() /* new interface, Scatter/gather flat/iob buffer */ | | pkt/ipv[4|6]_input()/... | | NICs io vector receive(Orignal flat buffer) 3. Iperf passthrough on NuttX simulator: ------------------------------------------------- | Protocol | Server | Client | | |-----------------------------------------------| | TCP | 813 | 834 | Mbits/sec | | TCP(Offload) | 1720 | 1100 | Mbits/sec | | UDP | 22 | 757 | Mbits/sec | | UDP(Offload) | 25 | 1250 | Mbits/sec | ------------------------------------------------- Signed-off-by: chao an <anchao@xiaomi.com>
2022-11-23 12:39:40 +01:00
{
netdev_iob_release(dev);
goto errout;
net/l2/l3/l4: add support of iob offload 1. Add new config CONFIG_NET_LL_GUARDSIZE to isolation of l2 stack, which will benefit l3(IP) layer for multi-MAC(l2) implementation, especially in some NICs such as celluler net driver. new configuration options: CONFIG_NET_LL_GUARDSIZE CONFIG_NET_LL_GUARDSIZE will reserved l2 buffer header size of network buffer to isolate the L2/L3 (MAC/IP) data on network layer, which will be beneficial to L3 network layer protocol transparent transmission and forwarding ------------------------------------------------------------ Layout of frist iob entry: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- iob | Reserved | io_len | ------------------------------------------------- ------------------------------------------------------------- Layout of different NICs implementation: iob_data (aligned by CONFIG_IOB_ALIGNMENT) | | io_offset(CONFIG_NET_LL_GUARDSIZE) | | ------------------------------------------------- Ethernet | Reserved | ETH_HDRLEN | io_len | ---------------------------------|--------------- 8021Q | Reserved | ETH_8021Q_HDRLEN | io_len | ---------------------------------|--------------- ipforward | Reserved | io_len | ------------------------------------------------- -------------------------------------------------------------------- 2. Support iob offload to l2 driver to avoid unnecessary memory copy Support send/receive iob vectors directly between the NICs and l3/l4 stack to avoid unnecessary memory copies, especially on hardware that supports Scatter/gather, which can greatly improve performance. new interface to support iob offload: ------------------------------------------ | IOB version | original | |----------------------------------------| | devif_iob_poll() | devif_poll() | | ... | ... | ------------------------------------------ -------------------------------------------------------------------- 1> NIC hardware support Scatter/gather transfer TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | dev->d_iob: | --------------- --------------- io_data iob1 | | | iob3 | | | \ --------------- --------------- --------------- | --------------- | iob0 | | | | iob2 | | | | --------------- | --------------- | \ | / / \ | / / ---------------------------------------------- NICs io vector | | | | | | | | | | ---------------------------------------------- RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to each iobs) -------------------------------------------------------------------- 2> CONFIG_IOB_BUFSIZE is greater than MTU: TX: "(CONFIG_IOB_BUFSIZE) > (MAX_NETDEV_PKTSIZE + CONFIG_NET_GUARDSIZE + CONFIG_NET_LL_GUARDSIZE)" tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll("NIC"_txpoll) callback() // "NIC"_txpoll | "NIC"_send() (dev->d_iob->io_data[CONFIG_NET_LL_GUARDSIZE - NET_LL_HDRLEN(dev)]) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | pkt/ipv[4/6]_input()/... | | NICs io vector receive(iov_base to io_data) -------------------------------------------------------------------- 3> Compatible with all old flat buffer NICs TX: tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4) / \ / \ devif_poll_[l3|l4]_connections() devif_iob_send() (nocopy:udp/icmp/...) / \ (copy:tcp) / \ devif_iob_poll(devif_poll_callback()) devif_poll_callback() /* new interface, gather iobs to flat buffer */ / \ / \ devif_poll("NIC"_txpoll) "NIC"_send()(dev->d_buf) RX: [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead) | | [tcp|udp|icmp|...]_ipv[4|6]_in()/... | | netdev_input() /* new interface, Scatter/gather flat/iob buffer */ | | pkt/ipv[4|6]_input()/... | | NICs io vector receive(Orignal flat buffer) 3. Iperf passthrough on NuttX simulator: ------------------------------------------------- | Protocol | Server | Client | | |-----------------------------------------------| | TCP | 813 | 834 | Mbits/sec | | TCP(Offload) | 1720 | 1100 | Mbits/sec | | UDP | 22 | 757 | Mbits/sec | | UDP(Offload) | 25 | 1250 | Mbits/sec | ------------------------------------------------- Signed-off-by: chao an <anchao@xiaomi.com>
2022-11-23 12:39:40 +01:00
}
dev->d_sndlen = len;
#ifdef CONFIG_NET_TCP_WRBUFFER_DUMP
/* Dump the outgoing device buffer */
lib_dumpbuffer("devif_iob_send", dev->d_appdata, len);
#endif
return dev->d_sndlen;
errout:
nerr("ERROR: devif_iob_send error: %d\n", ret);
return ret;
}
#endif /* CONFIG_MM_IOB */