aboutsummaryrefslogtreecommitdiffstats
path: root/host/lib/include
Commit message (Collapse)AuthorAgeFilesLines
* uhdlib: Add dpdk_zero_copy.hppAlex Williams2019-05-211-0/+45
| | | | | dpdk_zero_copy.hpp was referenced in multiple places using relative paths. Let's throw it in uhdlib for easy access.
* transport: Make dpdk_simple subclass udp_simpleAlex Williams2019-05-211-27/+14
| | | | With the same APIs, this will make it easier to add support for X310.
* include: max287x: Fix conversion warningMartin Braun2019-03-051-1/+1
|
* lib: fix includes for boost::noncopyableMichael Dickens2019-02-112-0/+7
| | | | | | | - expert_nodes.hpp: fix to work with BOOST_VERSION < 105600, since UHD still supports Boost 1.53.00. - gpio_atr_3000.hpp: requires boost::noncopyable header, so replicate that (now) in export_nodes.hpp.
* RFNoC: Prevent unnecessary FC ACK packetsmichael-west2019-01-311-2/+3
| | | | | | | | Avoid sending flow control ACK packets for lossless transports. Add 'send_no_fc_acks' device argument to explicitly prevent flow control ACK packets from being sent. Signed-off-by: michael-west <michael.west@ettus.com>
* mpmd,transport,prefs: Add xport_mgr for dpdk_zero_copyAlex Williams2019-01-254-7/+235
| | | | | | | | | | | | | | | | | | | | | | | 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.
* math: Replace boost::*::{lcm,gcd}() with portable versionsMartin Braun2019-01-182-6/+4
| | | | | | Boost changed the lcm() and gcd() functions in Boost 1.67. This creates portable UHD versions to be used instead. They use various Boost versions under the hood conditionally.
* formatting: preparing for uhd::math cleanupBrent Stapleton2019-01-182-370/+450
| | | | Formatting files that will be touched in upcoming changes to uhd::math
* formatting: remove vim hints in headersBrent Stapleton2019-01-166-6/+0
| | | | | Remove trailing vim hints in header files. This functionality will be replaced by clang-format.
* uhd: skip formatting misc arrays, maps, etc.Brent Stapleton2019-01-161-0/+2
| | | | | | Various data structures are nicely formatted to be human-readable. clang-format makes these structures harder to read, so we can skip formatting these sections.
* transport: Move uhd-dpdk header to uhdlibAlex Williams2019-01-151-0/+0
|
* transport: Add blocking recv calls to uhd-dpdkAlex Williams2019-01-151-2/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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.
* uhd-dpdk: Add ARP responder, set MTU, and clean up APIAlex Williams2019-01-151-2/+2
| | | | | | | | | | | | 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.
* rpc,mpmd: replace all set_timeout() to new apiTrung Tran2019-01-141-5/+0
| | | | | Using new rpc client new API that ensure atomic setting of timeout on each rpc call.
* utils:rpc: set rpc timeout during rpc callTrung Tran2019-01-141-3/+120
| | | | | | | | | | | | | The current implementation of the UHD RPC client has a timeout that is being accessed non-atomically. Many calls follow the pattern: 1. set_timeout(value) 2. request_rpc() 3. set_timeout(default) which is not atomic. Other concurrent calls on the same rpc client may change the timeout value; leads to unexpected behavior These new set of function will, instead, handle setting and re-setting the timeout atomically in the RPC request.
* lib: experts: fixup for including Boost headerMartin Braun2019-01-091-0/+2
| | | | | | Header wasn't included until Boost 1.56. Fixes 5c012cad7858 ("lib: experts: Add potentially missing but...")
* lib: experts: Add potentially missing but sometimes inferred includeMartin Braun2019-01-091-0/+1
| | | | | This adds an include for boost/core/noncopyable.hpp. Without it, builds would potentially fail on Boost 1.69++.
* TwinRX: Fix tuningMichael West2019-01-021-7/+4
| | | | | - Set SPI clock back to 3 MHz - Fix returned frequency for ADF5355 (rev A and B boards)
* radio_ctrl_impl: move continuous_streaming to protected.Ryan Marlow2018-12-191-1/+1
|
* TwinRX: Enable phase resync on ADF535xmichael-west2018-12-101-17/+9
|
* TwinRX: Tuning improvementsmichael-west2018-12-101-10/+8
| | | | | | - Added delay for VTUNE calibration as per ADF5355 and ADF5356 data sheets - Increased SPI clock to 10 MHz - Removed write to register 10 during tuning of ADF5356 to match ADF5355 code and reduce tune time
* cmake: Update coding style to use lowercase commandsMartin Braun2018-11-141-1/+1
| | | | | | | | | | | | | | | | | 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!)
* Test: Add unit test for eeprom_utilsmichael-west2018-10-251-1/+1
|
* X300: Prevent duplicate MAC and IP addresses from being programmed in MBMichael West2018-10-251-0/+80
| | | | EEPROM
* twinrx: revise adf5356 frac2 register calculationMark Meserve2018-10-171-1/+1
| | | | | - If FRAC2 isn't exactly FRAC1 at certain frequencies, drifting spurs can be seen in the spectrum
* lmx2592: add spur dodgingMark Meserve2018-10-171-1/+4
|
* uhd: rfnoc: add async message handlerTrung Tran2018-09-143-3/+191
|
* radio_ctrl: add disable time stampTrung Tran2018-09-141-0/+2
|
* uhd-dpdk: Add DPDK-based sockets-like libraryAlex Williams2018-08-291-0/+249
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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.
* lib: Improve constrained_device_args_tMartin Braun2018-08-101-2/+14
| | | | | - Add default parser helper - Allow _enforce_discrete() for str_arg
* rfnoc: dma_fifo: Added a more robust flush mechanismAshish Chaudhari2018-08-031-1/+1
| | | | | | | | | - The flushing mechanism now looks similar to that in noc_shell - Make use of new flush bit in FIFO control register - Restrict using the clear bit only after flushing to ensure no partial packets are introduced in the stream. (clear immediately empties out FIFOs) - Changes are backwards compatible with older FPGAs
* b100: Move fifo_ctrl_excelsior to b100 subdirMartin Braun2018-07-311-51/+0
| | | | | This device is the only one using it, and no one will ever use it going forward.
* Device3: Change packet-based flow control to byte-based flow controlMartin Braun2018-07-251-1/+1
|
* mpm: initial commit of E320 codeBrent Stapleton2018-07-181-0/+6
| | | | Co-authored-by: Sugandha Gupta <sugandha.gupta@ettus.com>
* fixup! e300: merge files from rfnoc-develMartin Braun2018-07-061-0/+3
|
* e300: merge files from rfnoc-develTrung N Tran2018-06-291-7/+0
| | | | This disables the ability to do "network mode" on the E310.
* *_dsp_core: Update frequency when updating ratesVidush2018-06-212-0/+4
| | | | | Since the frequency shifter is set to a relative rate, it needs to be updated when changing the sampling rate.
* ad9361: Add API to set 1R1T/2R2T timing modesSugandha Gupta2018-06-151-0/+3
| | | | | LVDS interface can support both timing modes 1R1T/2R2T The API sets the required bit in catalina registers.
* uhd: Added LMX2592 driverDerek Kozel2018-05-031-0/+55
|
* lib: Purge all references to boost::this_thread::sleep()Martin Braun2018-04-301-5/+6
| | | | Replace with std::this_thread::sleep_for().
* Removed unecessary == operation.Vidush2018-04-301-3/+3
|
* Changed method to check for channel in _tx_streamer_active & rx_streamer_active.Vidush2018-04-301-4/+4
|
* lib: Change check_radio_config() to iterate over channels, not radios.Vidush2018-04-301-5/+8
|
* fixup! rfnoc: ctrl_iface cleanupmichael-west2018-04-301-1/+1
|
* ad9361: Fix bandwidth warnings and rangesVidush2018-04-271-3/+3
| | | | | | | Allows full bandwidth range to user. Reviewed-by: Michael West <michael.west@ettus.com> Reviewed-by: Martin Braun <martin.braun@ettus.com>
* ad936x: De-boostify ad936x_manager, minor cleanupMartin Braun2018-04-262-3/+4
| | | | | | | - Remove all use of boost::bind and boost::function - Demote some log messages to DEBUG - Change some formatting to match coding guidelines - B2xx/E310: Match changes in loopback function
* lib: move atomic.hpp and system_time.hpp to uhdlibMartin Braun2018-04-063-2/+2
|
* DDC/DUC: switch CORDIC -> DDS for all relevant variable namesRyan Marlow2018-03-222-0/+2
| | | | - Bump compat number for DDC/DUC to 2.0
* lib: add auto_timer profiling utilityPatrick Sisterhen2018-03-161-0/+137
| | | | | Note: This tool is not considered done, complete, unchangeable, or anything other than experimental.
* rfnoc: ctrl_iface cleanupMartin Braun2018-03-162-44/+61
| | | | | | | | | | - ctrl_iface is now longer a wb_iface. All it can do now is send command packets, and receive responses to those. - ctrl_iface does not store command time or tick rate - wb_iface_adapter is no longer a set of functors, but a wrapper around ctrl_iface. Command times are stored once, in the block. - DMA FIFO and radio block controllers have an easier time getting access to a timed_wb_iface
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-26 19:20:57 +0000