Prior to this commit there is a potential deadlock in
mp_thread_begin_atomic_section(), when obtaining the atomic_mutex, in the
following situation:
- main thread calls mp_thread_begin_atomic_section() (for whatever reason,
doesn't matter)
- the second core is running so the main thread grabs the mutex via the
call mp_thread_mutex_lock(&atomic_mutex, 1), and this succeeds
- before the main thread has a chance to run save_and_disable_interrupts()
a USB IRQ comes in and the main thread jumps off to process this IRQ
- that USB processing triggers a call to the dcd_event_handler() wrapper
from commit bcbdee2357
- that then calls mp_sched_schedule_node()
- that then attempts to obtain the atomic section, calling
mp_thread_begin_atomic_section()
- that call then blocks trying to obtain atomic_mutex
- core0 is now deadlocked on itself, because the main thread has the mutex
but the IRQ handler (which preempted the main thread) is blocked waiting
for the mutex, which will never be free
The solution in this commit is to use mutex enter/exit functions that also
atomically disable/restore interrupts.
Fixes issues #12980 and #13288.
Signed-off-by: Damien George <damien@micropython.org>
Using the multicore lockout feature in the general atomic section makes it
much more difficult to get correct.
Signed-off-by: Damien George <damien@micropython.org>
This commit implements fairly complete support for the DMA controller in
the rp2 series of microcontrollers. It provides a class for accessing the
DMA channels through a high-level, Pythonic interface, and functions for
setting and manipulating the DMA channel configurations.
Creating an instance of the rp2.DMA class claims one of the processor's DMA
channels. A sensible, per-channel default value for the ctrl register can
be fetched from the DMA.pack_ctrl() function, and the components of this
register can be set via keyword arguments to pack_ctrl().
The read, write, count and ctrl attributes of the DMA class provide
read/write access to the respective registers of the DMA controller. The
config() method allows any or all of these values to be set simultaneously
and adds a trigger keyword argument to allow the setup to immediately be
triggered. The read and write attributes (or keywords in config()) accept
either actual addresses or any object that supports the buffer interface.
The active() method provides read/write control of the channel's activity,
allowing the user to start and stop the channel and test if it is running.
Standard MicroPython interrupt handlers are supported through the irq()
method and the channel can be released either by deleting it and allowing
it to be garbage-collected or with the explicit close() method.
Direct, unfettered access to the DMA controllers registers is provided
through a proxy memoryview() object returned by the DMA.registers attribute
that maps directly onto the memory-mapped registers. This is necessary for
more fine-grained control and is helpful for allowing chaining of DMA
channels.
As a simple example, using DMA to do a fast memory copy just needs:
src = bytearray(32*1024)
dest = bytearray(32*1024)
dma = rp2.DMA()
dma.config(read=src, write=dest, count=len(src) // 4,
ctrl=dma.pack_ctrl(), trigger=True)
# Wait for completion
while dma.active():
pass
This API aims to strike a balance between simplicity and comprehensiveness.
Signed-off-by: Nicko van Someren <nicko@nicko.org>
Signed-off-by: Damien George <damien@micropython.org>
MicroPython code may rely on the return value of sys.stdout.buffer.write()
to reflect the number of bytes actually written. While in most scenarios a
write() operation is successful, there are cases where it fails, leading to
data loss. This problem arises because, currently, write() merely returns
the number of bytes it was supposed to write, without indication of
failure.
One scenario where write() might fail, is where USB is used and the
receiving end doesn't read quickly enough to empty the receive buffer. In
that case, write() on the MicroPython side can timeout, resulting in the
loss of data without any indication, a behavior observed notably in
communication between a Pi Pico as a client and a Linux host using the ACM
driver.
A complex issue arises with mp_hal_stdout_tx_strn() when it involves
multiple outputs, such as USB, dupterm and hardware UART. The challenge is
in handling cases where writing to one output is successful, but another
fails, either fully or partially. This patch implements the following
solution:
mp_hal_stdout_tx_strn() attempts to write len bytes to all of the possible
destinations for that data, and returns the minimum successful write
length.
The implementation of this is complicated by several factors:
- multiple outputs may be enabled or disabled at compiled time
- multiple outputs may be enabled or disabled at runtime
- mp_os_dupterm_tx_strn() is one such output, optionally containing
multiple additional outputs
- each of these outputs may or may not be able to report success
- each of these outputs may or may not be able to report partial writes
As a result, there's no single strategy that fits all ports, necessitating
unique logic for each instance of mp_hal_stdout_tx_strn().
Note that addressing sys.stdout.write() is more complex due to its data
modification process ("cooked" output), and it remains unchanged in this
patch. Developers who are concerned about accurate return values from
write operations should use sys.stdout.buffer.write().
This patch might disrupt some existing code, but it's also expected to
resolve issues, considering that the peculiar return value behavior of
sys.stdout.buffer.write() is not well-documented and likely not widely
known. Therefore, it's improbable that much existing code relies on the
previous behavior.
Signed-off-by: Maarten van der Schrieck <maarten@thingsconnected.nl>
Add new board Silicognition RP2040-Shim, RP2040 with 4 MB of flash
and W5500 drivers included and configured by default for use with
the Silicognition PoE-FeatherWing.
Co-authored-by: Matt Trentini <matt.trentini@gmail.com>
Signed-off-by: Patrick Van Oosterwijck <patrick@silicognition.com>
Some boards have multiple options for these pins, and they don't want to
allow users to initialize a port without explicitly specifying pin numbers.
Signed-off-by: Paul Grayson <paul@pololu.com>
Previously this was not set, so potential for race conditions in interrupt
handlers this didn't issue SEV. (Which is currently all of them, as far as
I can see.)
Eventually we might be able to augment the interrupt handlers that wake the
main thread to call SEV, and leave the others as-is to suspend the CPU
slightly faster, but this will solve the issue for now.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
This commit changes all uses in the rp2 port, and drivers that are
optionally supported by that port.
The old MICROPY_EVENT_POLL_HOOK and MICROPY_EVENT_POLL_HOOK_FAST macros are
no longer used for rp2 builds and are removed (C user code will need to be
changed to suit).
Also take the opportunity to change some timeouts that used 64-bit
arithmetic to 32-bit, to hopefully claw back a little code size.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
This commit fixes all known floating-point bugs with the pico-sdk. There
are two things going on here:
- Use a custom pico float component so that the pico-sdk doesn't include
its math functions, and then provide our own from lib/libm.
- Provide a wrapper for __aeabi_fadd to fix the infinity addition bug.
Prior to this commit, the following tests failed on the rp2 port: cmath_fun
float_parse math_domain math_domain_special math_fun_special. With this
commit, all these tests pass.
Thanks to @projectgus for how to approach this fix.
Signed-off-by: Damien George <damien@micropython.org>
All ports using this common configuration already enable time/date
validation, so this commit is a no-op change.
Signed-off-by: Damien George <damien@micropython.org>
Also move MICROPY_PY_PENDSV_ENTER/REENTER/EXIT to mphalport.h, for ports
where these are not already there.
This helps separate the hardware implementation of these macros from the
MicroPython configuration (eg for renesas-ra and stm32, the IRQ static
inline helper functions can now be moved to irq.h).
Signed-off-by: Damien George <damien@micropython.org>
The ports esp32, mimxrt, rp2 and samd all shared exactly the same
implementation of machine.disable_irq() and machine.enable_irq(),
implemented in terms of MICROPY_{BEGIN,END}_ATOMIC_SECTION. This commit
factors these implementations into extmod/modmachine.c.
The cc3200, esp8266, nrf, renesas-ra and stm32 ports do not yet use this
common implementation.
Signed-off-by: Damien George <damien@micropython.org>
Minor changes for consistency are:
- nrf gains: unique_id(), freq() [they do nothing]
- samd: deepsleep() now resets after calling lightsleep()
- esp32: lightsleep()/deepsleep() no longer take kw arg "sleep", instead
it's positional to match others. also, passing 0 here will now do a 0ms
sleep instead of acting like nothing was passed.
reset_cause() no longer takes any args (before it would just ignore them)
- mimxrt: freq() with an argument and lightsleep() both raise
NotImplementedError
Signed-off-by: Damien George <damien@micropython.org>
And use it in all ports. The ports are unchanged, except esp8266 which now
just returns None from this function instead of the time elapsed (to match
other ports), and qemu-arm which gains this function.
Signed-off-by: Damien George <damien@micropython.org>
This is a code factoring to have the dict for the machine module in one
location, and all the ports use that same dict. The machine.soft_reset()
function implementation is also factored because it's the same for all
ports that did already implement it. Eventually more functions/bindings
can be factored.
All ports remain functionally the same, except:
- cc3200 port: gains soft_reset, mem8, mem16, mem32, Signal; loses POWER_ON
(which was a legacy constant, replaced long ago by PWRON_RESET)
- nrf port: gains Signal
- qemu-arm port: gains soft_reset
- unix port: gains soft_reset
- zephyr port: gains soft_reset, mem8, mem16, mem32
Signed-off-by: Damien George <damien@micropython.org>
best_effort_wfe_or_timeout() already calls time_reached() and returns the
result of it, so no need to call it again.
Signed-off-by: Damien George <damien@micropython.org>
This commit changes the Arduino board identifiers to correspond to their
official names. This helps to identify boards at runtime. At the moment
the Arduino Portenta H7 is reported as PORTENTA which is unfortunate as now
there is another Portenta board (Portenta C33) supported in MicroPython.
Also made the other identifiers for flash and network name consistent,
removed the incorrectly used MICROPY_PY_SYS_PLATFORM identifiers, and added
missing MICROPY_PY_NETWORK_HOSTNAME_DEFAULT identifiers.
Boards affected:
- stm32: ARDUINO_PORTENTA_H7, ARDUINO_GIGA, ARDUINO_NICLA_VISION
- renesas-ra: ARDUINO_PORTENTA_C33
- esp32: ARDUINO_NANO_ESP32
- rp2: ARDUINO_NANO_RP2040_CONNECT
Signed-off-by: Sebastian Romero <s.romero@arduino.cc>
Change the rp2 and renesas-ra ports to use the helper function.
Saves copy-pasta, at the small cost of one more function call in the
firmware (if not using LTO).
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
The recent change in bcbdee2357 means that
TinyUSB can no longer be run from within a soft (or hard) IRQ handler, ie
when the scheduler is locked. That means that Python code that calls
`print(...)` from within a scheduled function may block indefinitely if the
USB CDC buffers are full.
This commit fixes that problem by explicitly running the TinyUSB stack when
waiting within stdio tx/rx functions.
Signed-off-by: Damien George <damien@micropython.org>
This change:
- Has a small code size reduction.
- Should slightly improve overall performance. The old hook code
seemed to use between 0.1% and 1.6% of the total CPU time doing no-op
calls even when no USB work was required.
- USB performance is mostly the same, there is a small increase in
latency for some workloads that seems to because sometimes the hook
usbd_task() is called at the right time to line up with the next USB host
request. This only happened semi-randomly due to the timing of the hook.
Improving the wakeup latency by switching rp2 to tickless WFE allows the
usbd_task() to run in time for the next USB host request almost always,
improving performance and more than offsetting this impact.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
The main motivation for doing this was to reduce the latency when the
system is woken by a USB interrupt. The best_effort_wfe_or_timeout()
function calls into the pico-sdk dynamic timer framework which sets up a
new dynamic timer instance each time, and then has to tear it down before
continuing after a WFE.
Testing Python interrupt latency, it seems to be improved by about 12us
(from average of 46us to 34us running a Pin IRQ). C-based "scheduled
nodes" should see even lower latency.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
This patch ensures that integer channel numbers passed to the ADC
constructor (including temperature sensor) are interpreted as raw
channel numbers, and not cause any GPIO pins to be initialized.
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
The FIFO reports not only the bytes read, but also 4 error bits. These were
not checked, leading to NUL value read in case of break and possible
garbage bytes being written on parity/framing error.
This patch addresses the issue that NUL bytes are incorrectly read on
break, and at least provides the boilerplate code and comments for error
handling, that may be implemented in the future.
Signed-off-by: Maarten van der Schrieck <maarten@thingsconnected.nl>
For now, this implements the functionality required for esp32 and rp2,
including support for numeric pins, rp2 alternate functions, and rp2
extended pins.
This also updates the rp2 port to use the same structure for pins.h and
pins.csv as for esp32, and moves the pin definitions directly into the
table (rather than having a table of pointers), which is a small code size
improvement.
Support for "hidden" pins in pins.csv is added (matching the stm32
implementation).
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
All ports now use `--board-csv`, `--prefix`, `--output-souce`,
`--output-header` and no longer write to stdout. This matches the esp32
implementation.
Ports that have an AF input use `--af-csv` (to match `--board-csv`).
Any additional output files are now prefixed with `output-` (e.g.
`--output-af-const`).
Default arguments are removed (all makefiles should always specify all
arguments, using default values is likely an error).
Replaced the `af-defs-cmp-strings` and `hdr-obj-decls` args for stm32 with
just `mboot-mode`. Previously they were set on the regular build, now the
logic is reversed so mboot sets it.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
It's not supported on all ports, adds complexity to the build to generate
pins_af.py, and can mostly be replicated just by printing the pin objects.
Remove support for generating pins_af.py from all ports (nrf, stm32,
renesas-ra, mimxrt, rp2).
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Also remove af-const header, as this is left over from the STM32 version
and unused.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This updates a small number of files that change with ruff-format's (vs
black's) rules.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This provides a way to enable features and changes slated for MicroPython
2.x, by running `make MICROPY_PREVIEW_VERSION_2=1`. Also supported for
the cmake ports (except Zephyr).
This is an alternative to having a 2.x development branch (or equivalently,
keeping a 1.x release branch). Any feature or change that needs to be
"hidden" until 2.x can use this flag (either in the Makefile or the
preprocessor).
A good example is changing function arguments or other public API features,
in particular to aid in improving consistency between ports.
When `MICROPY_PREVIEW_VERSION_2` is enabled, the REPL banner is amended to
say "MicroPython (with v2.0 preview) vX.Y.Z", and sys.implementation gets a
new field `_v2` set to `True`.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The contents of machine_mem.h, machine_i2c.h and machine_spi.h have been
moved into extmod/modmachine.h.
Signed-off-by: Damien George <damien@micropython.org>
The contents of machine_bitstream.h, machine_pinbase.h, machine_pulse.h and
machine_signal.h have been moved into extmod/modmachine.h.
Signed-off-by: Damien George <damien@micropython.org>
The machine_i2c_type, machine_spi_type and machine_timer_type symbols are
already declared in extmod/modmachine.h and should not be declared anywhere
else.
Also move declarations of machine_pin_type and machine_rtc_type to the
common header in extmod.
Signed-off-by: Damien George <damien@micropython.org>
This is a code factoring to have the Python bindings in one location, and
all the ports use those same bindings. For all ports except the two listed
below there is no functional change.
The nrf port has UART.sendbreak() removed, but this method previously did
nothing.
The zephyr port has the following methods added:
- UART.init(): supports setting timeout and timeout_char.
- UART.deinit(): does nothing, just returns None.
- UART.flush(): raises OSError(EINVAL) because it's not implemented.
- UART.any() and UART.txdone(): raise NotImplementedError.
Signed-off-by: Damien George <damien@micropython.org>
No functional change, just code factoring to have the Python bindings in
one location, and all the ports use those same bindings.
Signed-off-by: Damien George <damien@micropython.org>
This factors the basic top-level I2S class code from the ports into
extmod/machine_i2s.c:
- I2S class definition and method table.
- The init and deinit method wrappers.
- The make_new code.
Further factoring will follow.
Signed-off-by: Damien George <damien@micropython.org>
Damien George