Commit Graph

33 Commits

Author SHA1 Message Date
Zhe Weng
1cf3147626 net/netdev: Avoid hardcoded guardsize when using d_iob
Signed-off-by: Zhe Weng <wengzhe@xiaomi.com>
2023-01-18 14:41:07 +08:00
chao an
82d67b201a net/offload: add offload support for pkt/arp
1. add offload support for pkt/arp
2. Reset the d_buf to NULL if d_iob has released

Signed-off-by: chao an <anchao@xiaomi.com>
2022-12-04 01:34:30 +08:00
chao an
34d2cde8a8 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>
2022-12-03 11:47:04 +08:00
Petro Karashchenko
b3cd9090d1 drivers/net: make sure that net driver d_buf is 16-bit aligned
Signed-off-by: Petro Karashchenko <petro.karashchenko@gmail.com>
2022-08-05 22:21:37 +08:00
Gregory Nutt
04c9079954 Back in 2007, an early network implementation was developed for NuttX. This early development was inspired largely by uIP 1.0 and recognition of that was noted in the then BSD license headers. Over the next 14 years, a new, much more advanced, original network was developed for NuttX. However, some references to Adam Dunkels were still present in the file headers.
Because of this, it will take some time to detangle the licensing under net/.  Many new features, original features were added to the NuttX network.  Clearly, any references to Adam Dunkels in the files that implement these new features that have no counterpart in uIP 1.0 are errors.

This PR removes the references and converts the license headers to Apache 2.0 where possible.  The affected files include only (1) the implementation of IPv6 (including neighbor support under ICMPv6) and (2) Raw sockets.  Neither of these features are present in uIP 1.0 and the licenses can be freely updated.
2021-09-17 21:49:44 -05:00
Gregory Nutt
7409f57d40 net/pkt: Fix inconsistent use of FAR
Also run all .c and .h files through nxstyle (with -m 0)
2020-02-13 15:10:34 +08:00
Gregory Nutt
69056d4053 net/: The value ERROR should never be returned from internal OS functions. That is reserved for returning values to appliations with the errno value set. Within the OS, errors are returned with a negated errno value ALWAYS. 2019-02-14 15:38:36 -06:00
Gregory Nutt
1fd9eb6069 net/pkt: pkt_input() should not report an error using the nerr() macro when the PKT tap does not need the packet. That is not an error. Use ninfo() instead. 2018-11-16 13:48:30 -06:00
Xiang Xiao
eb31dc69ac net/: Remove the unnecessary arp.h inclusion 2018-11-09 14:01:12 -06:00
Gregory Nutt
88130a996a net/: Fixes for more coding standard issues detected by nxstyle. 2018-10-29 18:00:30 -06:00
Gregory Nutt
b54ffe858a Standardization of some function headers. 2018-03-13 09:52:27 -06:00
Gregory Nutt
7cf88d7dbd Make sure that labeling is used consistently in all function headers. 2018-02-01 10:00:02 -06:00
Gregory Nutt
0b2a4eb4bd Networking: A little more wording changes related to interrupts vs. events 2017-08-29 15:08:38 -06:00
Gregory Nutt
d7c90ae71b Update and move ieee802154.h socket header file. Fix some comments in net/pkt. 2017-08-18 07:08:02 -06:00
Gregory Nutt
799b2d5671 Update comments. 2017-07-17 07:14:12 -06:00
Gregory Nutt
2a751068e6 Without lowsyslog() *llerr() is not useful. Eliminate and replace with *err(). 2016-06-20 12:44:38 -06:00
Gregory Nutt
f4fcdcdb4d net/: Change some *err() message to *info() messages if what was a *dbg() message does not indicate and error condition. 2016-06-11 17:37:21 -06:00
Gregory Nutt
e99301d7c2 Rename *lldbg to *llerr 2016-06-11 14:55:27 -06:00
Gregory Nutt
2c95fef501 Remove some empty code section comments 2016-02-26 07:35:55 -06:00
Gregory Nutt
0fb035f76b Standardize some naming in code section comments 2016-02-21 18:09:04 -06:00
Gregory Nutt
cb9e27c3b0 Standardize naming used for public data and function groupings 2015-10-02 16:30:35 -06:00
Gregory Nutt
88a0e82934 Networking: Remove field d_sndata from the device structure. It is the same as d_appdata and unnecessary 2015-01-17 05:59:13 -06:00
Gregory Nutt
73f3ecf7e2 NET: Rename network interrupt event flags more appropriately: TCP_, UDP_, ICMP_, or PKT_ vs UIP_ 2014-07-06 17:22:02 -06:00
Gregory Nutt
9e87ab90b8 NET: Move private definitions from include/nuttx/net/arp.h to net/arp/arp.h 2014-07-06 11:05:28 -06:00
Gregory Nutt
0bb153b8cb Remove all inclusion of uip.h 2014-07-04 16:58:22 -06:00
Gregory Nutt
5790c94ba3 Rename net/uip to net/devif. Rename uip/uip.h to devif/devif.h 2014-06-28 18:07:02 -06:00
Gregory Nutt
fce2a79abd Rename uip_driver_s net_driver_s 2014-06-27 16:48:12 -06:00
Gregory Nutt
e1091251e6 NET: Move statistcs from uip.h to new netstats.h to remove nasty circular inclusion problem. 2014-06-26 09:32:39 -06:00
Gregory Nutt
579ee6f573 Clean-up packet socket naming 2014-06-25 10:34:52 -06:00
Gregory Nutt
621097b6c8 Rename ip_eth_hdr to eth_hdr_s 2014-06-25 09:57:52 -06:00
Gregory Nutt
5d1f8180d4 Move the remaining files from include/nuttx/net/uip to include/nuttx/net; Rename *_internal.h header files in net/ to just *.h 2014-06-24 10:14:15 -06:00
Gregory Nutt
37646044ac Move include/nuttx/net/uip/uip-arch.h to include/nuttx/net/netdev.h 2014-06-24 09:28:44 -06:00
Gregory Nutt
e46ff63eb8 Move Packet files from net/uip to net/pkt 2014-06-18 11:02:52 -06:00