| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
| |
This will make sure that the context holder for the liberio context is
destroyed when the last liberio transport is destroyed, and not on
termination of the program.
|
|
|
|
|
| |
dpdk_zero_copy.hpp was referenced in multiple places using relative
paths. Let's throw it in uhdlib for easy access.
|
|
|
|
| |
With the same APIs, this will make it easier to add support for X310.
|
|
|
|
|
|
|
|
|
|
| |
Occasionally, MPM would check its links before the kernel would report
link up, and it would then shave those ports off the CHDR link list
prematurely. This commit adds a second of wait to allow the kernel time
to respond.
It also includes some additional reporting of link status, since Intel
PMDs may report a misleading initial state upon bring-up.
|
|
|
|
|
|
| |
When using a buffer size smaller than recommended, a warning would be
printed with the wrong value (it would print the default value, not the
actual value).
|
|
|
|
|
| |
Some NICs were not enabling TX IP checksum offloads. This fixes that
issue.
|
|
|
|
| |
This was old code that wouldn't compile or run anymore.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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.
|
|
|
|
|
|
|
|
|
|
| |
Changed muxed_zero_copy_if to make each stream buffer the same number
of frames as the underlying transport and changed the size of the
underlying control transport for X300 and MPMD devices to match the
size of the command FIFO in order to prevent starvation of any single
control transport. Added some constants to remove hard coded values.
Signed-off-by: michael-west <michael.west@ettus.com>
|
|
|
|
|
|
|
|
| |
Boost changed the macros for endianness identification in 1.69, and the
deprecation warning is a pretty noisy one during compilation. This
abstracts away the Boost macro, so we have two UHD macros,
UHD_BIG_ENDIAN and UHD_LITTLE_ENDIAN. They indicate big and little
endian byte order.
|
|
|
|
|
|
| |
std::sleep_for causes issues with priority threading when running
examples in embedded mode on some devices (E310). boost::sleep_for does
not have this problem.
|
|
|
|
|
|
|
|
|
|
| |
This is a continuation of 967be2a4.
$ find host/lib/transport -iname *.hpp -o -iname *.cpp |\
xargs clang-format -i -style=file
Skipping host/lib/transport/nirio/ because of build errors.
$ git checkout host/lib/transport/nirio
|
| |
|
|
|
|
|
| |
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.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This adds an internal wait queue API to uhd-dpdk. Socket configuration
requests had their blocking calls re-implemented on top of this API, and
it is also used to service requests to wait on RX packets (w/ timeout).
The wait API involves a multi-producer, single-consumer queue per I/O
thread (waiter_ring), with a condition variable used for sleeping. The
data structure is shared between user thread and I/O thread, and because
timeouts make resource release time non-deterministic, we use reference
counting on the shared resource.
One reference is generated by the user thread and passed to the I/O
thread to consume. A user thread that still needs the data after waking
must get() another reference, to postpone the destruction of the
resource until it is done.
Timeouts are based on CLOCK_MONOTONIC. For recv, a timeout of 0
indicates blocking indefinitely, and a negative timeout indicates no
timeout is desired.
Also drop timeout for closing sockets in uhd-dpdk.
The timeout would allow a user thread to pre-empt the I/O thread's
cleanup process. The user thread would free data structures the I/O
thread still needed to function. Since this timeout is superfluous
anyway, let's just get rid of it.
Also add some more input checking and error reporting.
|
|
|
|
|
|
|
|
|
|
|
|
| |
Set MTU of Ethernet ports:
Some NICs (like the Mellanox ones) require this to work.
Add ARP responder to uhd-dpdk.
Clean up pending ARP request list when done:
Threads waiting for an ARP request to complete would be woken up when
the request completed, but they wouldn't get removed from the list of
pending requests. This fixes the issue.
|
| |
|
|
|
|
| |
This fixes a C4267 which pops up a lot when compiling UHD with MSVC.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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.
|
|
|
|
|
|
|
|
| |
By default, Boost.ASIO uses 'address_configured' mode for UDP endpoint
resolution, which "only return[s] IPv4 addresses if a non-loopback
IPv4 address is configured for the system". This changes the resolver
to use 'all_matching', which instead returns "all matching IPv6 and
IPv4 addresses".
|
|
|
|
|
|
| |
This is a common message that will always occur during device init when
there is no RIO device available. Because it looks like an error, it
confuses people and was thus reduced to TRACE.
|
|
|
|
|
|
|
| |
Ethernet buffering is now done so that most of the buffering is done in
the socket buffers and multiple frames are only used to support the
receive side offload of the socket I/O. Eliminates dropped packets at
high full duplex rates.
|
|
|
|
|
| |
This is to allow for num_recv_frames=1 and reduce conversions from ticks
to time_spec_t to improve critical path performance.
|
| |
|
| |
|
|
|
|
| |
Replace with std::this_thread::sleep_for().
|
| |
|
|
|
|
|
| |
Some uses of boost::posix_time were incorrect and would cause compiler
errors on Boost 1.67.
|
|
|
|
| |
This avoids having to redeclare the static const to avoid linker errors.
|
|
|
|
| |
Use std::this_thread::sleep_for() instead.
|
|
|
|
|
|
| |
Static const attributes were causing linker issues the way there were
being used, but they were only used in niusrprio_session.cpp and thus
could be factored out.
|
| |
|
|
|
|
|
| |
Note: When socket buffers are incorrectly size, a WARNING is still
printed.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
To avoid the proliferation of additional include directories and
multiple ways of including project-local headers, we now default to
moving all headers that are used across UHD into the uhdlib/
subdirectory.
Some #include statements were also reordered as they were modified for
closer compliance with the coding guidelines.
Internal cpp source files should now include files like this:
#include <uhdlib/rfnoc/ctrl_iface.hpp>
Reviewed-by: Ashish Chaudhari <ashish.chaudhari@ettus.com>
|
|
|
|
|
| |
- Reading line by line avoids loading the entire 25 MB bitstream into memory
since the MD5 hash usually occurs within the first 1% of the file stream
|
|
|
|
|
|
|
| |
All copyright is now attributed to "Ettus Research, a National
Instruments company".
SPDX headers were also updated to latest version 3.0.
|
| |
|
|
|
|
| |
Thanks to FX Coudert for suggesting this fix.
|
|
|
|
|
|
|
| |
Remove the redundant send/recv buffer_pools from nirio_zero_copy_impl
class as no one is using them.
Signed-off-by: Moritz Fischer <moritz.fischer@ettus.com>
|
|
|
|
|
|
|
| |
Check return value of liberio_chan_set_fixed_size() since it can fail,
and bad things happen if one just proceeds.
Signed-off-by: Moritz Fischer <moritz.fischer@ettus.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The timeout value passed in by UHD would get multiplied by USEC,
to convert from the UHD value in seconds to the liberio value in
microseconds.
The bug manifested itself by calling liberio_dequeue_buf() with a
timeout equivalent to 100s.
Fixes ed1c64c81 ('transport: Added liberio_zero_copy transport ...')
Signed-off-by: Moritz Fischer <moritz.fischer@ettus.com>
Cc: Alex Williams <alex.williams@ni.com>
|
|
|
|
|
|
|
| |
Remove stray tabs from liberio_zero_copy transport and clarify actual
code flow by fixing indent.
Signed-off-by: Moritz Fischer <moritz.fischer@ettus.com>
|
|
|
|
|
| |
- Remove multi-line log message for socket creation
- Include local addr and port in trace messages
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
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>
|
| |
|