| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
| |
This removes the tcp_zero_copy interface, which is not supported by any
USRP.
|
| |
|
|
|
|
|
|
| |
Debian uses pkg-config without the libdpdk.so linker script. Use
the pkg-config file to grab the installed libraries and determine
what to link to.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
docs: Update DPDK docs with new parameters:
Parameter names have had their hyphens changed to underscores, and
the I/O CPU argument is now named after the lcores and reflects
the naming used by DPDK.
transport: Add new udp_dpdk_link, based atop the new APIs:
This link is tightly coupled with the DPDK I/O service. The link class
carries all the address information to communicate with the other
host, and it can send packets directly through the DPDK NIC ports.
However, for receiving packets, the I/O service must pull the packets
from the DMA queue and attach them to the appropriate link object.
The link object merely formats the frame_buff object underneath, which
is embedded in the rte_mbuf container. For get_recv_buff, the link
will pull buffers only from its internal queue (the one filled by the
I/O service).
transport: Add DPDK-specific I/O service:
The I/O service is split into two parts, the user threads and the
I/O worker threads. The user threads submit requests through
various appropriate queues, and the I/O threads perform all the
I/O on their behalf. This includes routing UDP packets to the
correct receiver and getting the MAC address of a destination (by
performing the ARP request and handling the ARP replies).
The DPDK context stores I/O services. The context spawns all I/O
services on init(), and I/O services can be fetched from the dpdk_ctx
object by using a port ID.
I/O service clients:
The clients have two lockless ring buffers. One is to get a buffer
from the I/O service; the other is to release a buffer back to the
I/O service. Threads sleeping on buffer I/O are kept in a separate
list from the service queue and are processed in the course of doing
RX or TX.
The list nodes are embedded in the dpdk_io_if, and the head of the
list is on the dpdk_io_service. The I/O service will transfer the
embedded wait_req to the list if it cannot acquire the mutex to
complete the condition for waking.
Co-authored-by: Martin Braun <martin.braun@ettus.com>
Co-authored-by: Ciro Nishiguchi <ciro.nishiguchi@ni.com>
Co-authored-by: Brent Stapleton <brent.stapleton@ettus.com>
|
|
|
|
| |
The DPDK files are left behind as a reference, for now.
|
|
|
|
|
|
|
| |
The offload_io_service executes another I/O service instance within an
offload thread, and provides synchronization mechanisms to communicate
with clients. Frame buffers are passed from the offload thread to the
client and back via single-producer, single-consumer queues.
|
|
|
|
|
|
|
| |
This commit removes all files and parts of files that are used by
proto-RFNoC only.
uhd: Fix include CMakeLists.txt, add missing files
|
| |
|
| |
|
|
|
|
|
|
|
| |
Now link instances must have the ability to report the corresponding
physical adapter that is used for the local side of the link. This
information can be used to help identify when multiple links share
the same adapter.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The inline_io_service connects transports to links without any
worker threads. Send operations go directly to the link, and recv
will perform the I/O as part of the get_recv_buffer() call.
The inline_io_service also supports muxed links natively. The receive
mux is entirely inline. There is no separate thread for the
inline_io_service, and that continues here. A queue is created for
each client of the mux, and packets are processed as they come in. If
a packet is to go up to a different client, the packet is queued up
for later. When that client attempts to recv(), the queue is checked
first, and the attempts to receive from the link happen ONLY if no
packet was found.
Also add mock transport to test I/O service APIs. Tests I/O service
construction and some basic packet transmision. One case will also
uses a single link that is shared between the send and recv transports.
That link is muxed between two compatible but different transports.
|
|
|
|
| |
Updating all SPDX license identifiers to include "-or-later"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add configuration sections to the UHD config file for NIC entries. Keys
are based on MAC addresses, and the entries beneath the section describe
which CPU and I/O thread to use for the NIC and its IPv4 address.
Make ring sizes configurable for uhd-dpdk. Ring size is now an argument
for packet buffers. Note that the maximum number of available buffers
is still determined at init!
Add ability to receive broadcasts to uhd-dpdk. This is controllable by
a boolean in the sockarg during socket creation. dpdk_zero_copy will
filter broadcast packets out.
Add dpdk_simple transport (to mirror udp_simple). This transport allows
receiving from broadcast addresses, but it only permits one outstanding
buffer at a time.
Fix IP checksum handling in UHD-DPDK.
TX checksums were not being calculated in the NIC, and in RX, the check
for IP checksums allowed values of zero (reported as none). Now packets
with bad IP checksums will be dropped.
|
|
|
|
|
| |
This transport is based on uhd-dpdk, and it includes a global context
that must be initialized prior to creating any dpdk_zero_copy objects.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Also updates our coding style file.
Ancient CMake versions required upper-case commands. Later command
names became case-insensitive. Now the preferred style is lower-case.
Run the following shell code (with GNU compliant sed):
cmake --help-command-list | grep -v "cmake version" | while read c; do
echo 's/\b'"$(echo $c | tr '[:lower:]' '[:upper:]')"'\(\s*\)(/'"$c"'\1(/g'
done > convert.sed \
&& git ls-files -z -- bootstrap '*.cmake' '*.cmake.in' \
'*CMakeLists.txt' | xargs -0 gsed -i -f convert.sed && rm convert.sed
(Make sure the backslashes don't get mangled!)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This library makes available a userspace network stack with a
socket-like interface for applications (except the sockets pass around
pointers to buffers and use the buffers directly--It's sockets + a
put/get for buffer management). Supported services are ARP and UDP.
Destinations can be unicast or broadcast. Multicast is not currently
supported.
The implementation has two driver layers. The upper layer runs within
the caller's context. The caller will make requests through lockless
ring buffers (including socket creation and packet transmission), and
the lower layer will implement the requests and provide a response.
Currently, the lower layer runs in a separate I/O thread, and the caller
will block until it receives a response.
The I/O thread's main body is in src/uhd_dpdk_driver.c. You'll find that
all I/O thread functions are prefixed by an underscore, and user thread
functions do not.
src/uhd_dpdk.c is used to initialize uhd-dpdk and bring up the network
interfaces.
src/uhd_dpdk_fops.c and src/uhd_dpdk_udp.c are for network services.
The test is a benchmark of a flow control loop using a certain made-up
protocol with credits and sequence number tracking.
|
| |
|
|
|
|
|
|
|
| |
All copyright is now attributed to "Ettus Research, a National
Instruments company".
SPDX headers were also updated to latest version 3.0.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
This adds a zero copy transport using the liberio library.
Currently supported API version for liberio is 0.3, this might
still very much break, since the library is still in development.
So far nobody uses it UHD so we might as well merge it.
Signed-off-by: Alex Williams <alex.williams@ni.com>
Signed-off-by: Moritz Fischer <moritz.fischer@ettus.com>
|
| |
|
|
|
|
|
|
|
| |
- Can be used to share a single zero_copy_if object with multiple
streams
- Allows creating of virtual streams that are indistinguishable
from low-level streams
|
| |
|
| |
|
|
|
|
|
|
|
|
|
|
| |
All device-specific CMake components are now registered in one place,
before the host/lib/ subdirs are sourced. This way, there are no
cyclic dependencies.
This solves the issue where ENABLE_X300=Off could disable USB, but
preserves the fix where ENABLE_X300=Off would still build some X300
codes.
|
| |
|
|
|
|
|
|
| |
set LibUHD to required
* If required component's dependencies aren't met, CMake will throw an error unless user specifically disables it
|
|
|
|
|
|
| |
Our VRT routines have the option to switch, on the fly, between
VRLP and CHDR. This adds new CHDR-specific (un-)packers, which
can only work with CHDR.
|
| |
|
|
|
|
| |
* since its only used internally in b100
|
| |
|
| |
|
| |
|
| |
|
|
|
|
|
| |
Using cmake's recommended conventions for find scripts.
Find script also handles different library name for freebsd.
|
|
|
|
|
|
| |
Once the send buffer size is increased,
there appears to be no performance advantage.
I would rather not have extra implementations.
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|
|
|
|
|
| |
for features
implemented different ifdefs in the cpp files
|
|
|
|
|
|
|
| |
Reimplemented simple udp transport with one impl class.
Moved wait for ready/select implementation into common header.
Important note on select, timeval should have usecs < 1 second
or it may error on some platforms. Fixed in this implementation.
|
|
|
|
| |
the source
|
|
|
|
|
|
|
|
| |
the buffers are reusable and the overhead is reduced (nothing to malloc)
also removed the zero_copy.cpp (not needed anymore)
need to test on device...
|