When PWM constructor was created without specifying a device or setting
both freq and duty rate, it was not tagged as used, and further calls to
get a PWM object may get the same PWM device assigned.
Fixes#13494.
Signed-off-by: robert-hh <robert@hammelrath.com>
Exceptions in pin interrupt handlers would end up crashing MicroPython with
a "FATAL: uncaught exception".
In addition, MicroPython would get stuck trying to output this error
message, or generally any print output from inside a pin interrupt handler,
through the UART after the first character, so that only "F" was visible.
The reason was a matching interrupt priority between the running pin
interrupt and the UARTE interrupt signaling completion of the output
operation. Fix that by increasing the UARTE interrupt priority.
Code taken from the stm32 port and adapted.
Signed-off-by: Christian Walther <cwalther@gmx.ch>
Under some circumstances, after a hard reset, the low-frequency clock would
not be running. This caused time.ticks_ms() to return 0, time.sleep_ms()
to get stuck, and other misbehavior. A soft reboot would return it to a
working state.
The cause was a race condition that was hit when the bootloader would
itself turn LFCLK on, but turn it off again shortly before launching the
main application (this apparently happens with the Adafruit bootloader
from https://github.com/fanoush/ds-d6/tree/master/micropython). Stopping
the clock is an asynchronous operation and it continues running for a short
time after the stop command is given. When MicroPython checked whether to
start it by looking at the LFCLKSTAT register (nrf_clock_lf_is_running)
during that time, it would mistakenly not be started again. What
MicroPython should be looking at is not whether the clock is running at
this time, but whether a start/stop command has been given, which is
indicated by the LFCLKRUN register (nrf_clock_lf_start_task_status_get).
It is not clearly documented, but empirically LFCLKRUN is not just set when
the LFCLKSTART task is triggered, but also cleared when the LFCLKSTOP task
is triggered, which is exactly what we need.
The matter is complicated by the fact that the nRF52832 has an anomaly
(see [errata](https://infocenter.nordicsemi.com/topic/errata_nRF52832_Rev3/ERR/nRF52832/Rev3/latest/anomaly_832_132.html?cp=5_2_1_0_1_33))
where starting the LFCLK will not work between 66µs and 138µs after it last
stopped. Apply a workaround for that. See nrfx_clock_lfclk_start() in
micropython/lib/nrfx/drivers/src/nrfx_clock.c for reference, but we are not
using that because it also does other things and makes the code larger.
Signed-off-by: Christian Walther <cwalther@gmx.ch>
It destroys a few manual alignments, but these seem minor compared to
the benefit of automated code style consistency.
Signed-off-by: Christian Walther <cwalther@gmx.ch>
Trying to use an external board definition according to
https://github.com/micropython/micropython-example-boards on the nrf port
failed with "Invalid BOARD specified". Replacing all ocurrences of
"boards/$(BOARD)" with "$(BOARD_DIR)" following the example of
stm32/Makefile fixes that.
Signed-off-by: Christian Walther <cwalther@gmx.ch>
If the heap allocation fails we will crash if we continue, so at least we
can show a clear error message so one can figure out memory allocation was
the problem (instead of just seeing some arbitrary null pointer error
later).
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
This commit adds a pyscript variant for use in https://pyscript.net/.
The configuration is:
- No ASYNCIFY, in order to keep the WASM size down and have good
performance.
- MICROPY_CONFIG_ROM_LEVEL_FULL_FEATURES to enable most features.
- Custom manifest that includes many of the python-stdlib libraries.
- MICROPY_GC_SPLIT_HEAP_AUTO to increase GC heap size instead of doing a
collection when memory is exhausted. This is needed because ASYNCIFY is
disabled. Instead the GC collection is run at the top-level before
executing any Python code.
- No MICROPY_VARIANT_ENABLE_JS_HOOK because there is no asynchronous
keyboard input to interrupt a running script.
Signed-off-by: Damien George <damien@micropython.org>
With this commit, `interpreter.runPythonAsync(code)` can now be used to run
Python code that uses `await` at the top level. That will yield up to
JavaScript and produce a thenable, which the JavaScript runtime can then
resume. Also implemented is the ability for Python code to await on
JavaScript promises/thenables. For example, outer JavaScript code can
await on `runPythonAsync(code)` which then runs Python code that does
`await js.fetch(url)`. The entire chain of calls will be suspended until
the fetch completes.
Signed-off-by: Damien George <damien@micropython.org>
This commit improves the webassembly port by adding:
- Proxying of Python objects to JavaScript with a PyProxy type that lives
on the JavaScript side. PyProxy implements JavaScript Proxy traps such
as has, get, set and ownKeys, to make Python objects have functionality
on the JavaScript side.
- Proxying of JavaScript objects to Python with a JsProxy type that lives
on the Python side. JsProxy passes through calls, attributes,
subscription and iteration from Python to JavaScript.
- A top-level API on the JavaScript side to construct a MicroPython
interpreter instance via `loadMicroPython()`. That function returns an
object that can be used to execute Python code, access the Python globals
dict, access the Emscripten filesystem, and other things. This API is
based on the API provided by Pyodide (https://pyodide.org/). As part of
this, the top-level file is changed from `micropython.js` to
`micropython.mjs`.
- A Python `js` module which can be used to access all JavaScript-side
symbols, for example the DOM when run within a browser.
- A Python `jsffi` module with various helper functions like
`create_proxy()` and `to_js()`.
- A dedenting lexer which automatically dedents Python source code if every
non-empty line in that source starts with a common whitespace prefix.
This is very helpful when Python source code is indented within a string
within HTML or JavaScript for formatting reasons.
Signed-off-by: Damien George <damien@micropython.org>
This commit cleans up and generalises the Makefile, adds support for
variants (following the unix port) and adds the "standard" variant as the
default variant.
Signed-off-by: Damien George <damien@micropython.org>
When enabled the GC will not reclaim any memory on a call to
`gc_collect()`. Instead it will grow the heap.
Signed-off-by: Damien George <damien@micropython.org>
This workaround makes sure that all ringbuf functions that may be called
from an ISR are placed in IRAM. See
https://github.com/espressif/esp-idf/issues/13378
Note that this means that all esp32-og builds get non-ISR ringbuf functions
placed in flash now, whereas previously it was just the spiram variant.
This might be a good thing (e.g. free up some IRAM for native/viper).
Fixes issue #14005.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The C-based SPI flash driver is needed because the
`_copy_file_to_raw_filesystem()` function must copy from a filesystem (eg
FAT) to another part of flash, and the same C code must be used for both
reading (from FAT) and writing (to flash).
Signed-off-by: Damien George <damien@micropython.org>
This is enabled by default if MBOOT_FSLOAD is enabled, although a board
can explicitly disable it by `#define MBOOT_VFS_RAW (0)`.
Signed-off-by: Damien George <damien@micropython.org>
Add `pop()`, `appendleft()`, and `extend()` methods, support iteration
and indexing, and initializing from an existing sequence.
Iteration and indexing (subscription) have independent configuration flags
to enable them. They are enabled by default at the same level that
collections.deque is enabled (the extra features level).
Also add tests for checking new behavior.
Signed-off-by: Damien George <damien@micropython.org>
This provides a MicroPython-specific berkeley-db configuration in
extmod/berkeley-db/berkeley_db_config_port.h, and cleans up the include
path for this library.
Fixes issue #13092.
Signed-off-by: Damien George <damien@micropython.org>
Previously USB was always enabled, but this created some conflicts when
adding guards to other files on other ports.
Note the configuration with USB disabled hasn't been tested and probably
won't build or run without further work.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Disabled by default, but enabled on all boards that previously had
`MICROPY_PY_MACHINE_BARE_METAL_FUNCS` enabled.
Signed-off-by: Damien George <damien@micropython.org>
Added a 4MiB flash partitioning variant for ESP32S3: adds support for 4MiB
discrete flash boards or ESP32-S3FH4R2 with embedded 4MiB flash based ones.
Tested on the waveshare ESP32-S3 Mini w/ESP32-S3FH4R2.
Signed-off-by: Stanislav Ponomarev <me@stasponomarev.com>
If the `timeout_char` parameter is not given, we should still configure the
UART to ensure the UART is always initialized consistently. So the default
of 0 gets applied correctly, or if, for example, the baudrate was changed
the char timeout isn't still based on the old baudrate causing weird
behaviour, etc.
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
Prior to this commit, the pin defined for power would be used by the
esp_idf driver to reset the PHY. That worked, but sometimes the MDIO
configuration started before the power was fully settled, leading to an
error.
With the change in this commit, the power for the PHY is independently
enabled in network_lan.c with a 100ms delay to allow the power to settle.
A separate define for a reset pin is provided, even if the PHY reset
pin is rarely connected.
Fixes issue #14013.
Signed-off-by: robert-hh <robert@hammelrath.com>
On these targets it's possible to enter the bootloader by setting a bit in
an RTC register before resetting.
Structure it in a way that a board can still provide a custom bootloader
handler. The handler here will be the default if none is provided, for any
board based on the supported targets.
Signed-off-by: Trent Piepho <tpiepho@gmail.com>
Currently only the Arduino Nano ESP32 defines a machine.bootloader handler
for ESP32. All other boards will intentionally hang.
There is no error message, nor is a NotImplementedError raised. There's no
indication if Micropython has crashed, or if the bootloader was entered but
USB is not working, which is a real problem the ESP32 bootloader has. It's
not possible escape from this hang with ^C or any other means besides
physical access to the reset pin or the ability to cycle power.
Change this to only define an implementation of machine.bootloader() when
there is a handler for it.
Signed-off-by: Trent Piepho <tpiepho@gmail.com>
The new IDF v5.2 deprecated the task cleanup callback we use, so support
for the new option has been implemented in the previous commit. This also
requires a change in the sdkconfig, via a new variable
${SDKCONFIG_IDF_VERSION_SPECIFIC} which is used in all mpconfigboard.cmake
files to include an extra sdkconfig file based on the IDF version in use.
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
The legacy I2S "shim" is removed and replaced by the new I2S driver. The
new driver fixes a bug where mono audio plays only in one channel.
Application code size is reduced by 2672 bytes with this change. Tested on
ESP32, ESP32+spiram, ESP32-S3 using example code from
https://github.com/miketeachman/micropython-i2s-examples
Signed-off-by: Mike Teachman <mike.teachman@gmail.com>
Adds Dx and Ax named pins for Arduino Gigi, Arduino Nicla Vision and
Arduino Portenta H7. The analog pins include the dual-pad _C pins.
Signed-off-by: Sebastian Romero <s.romero@arduino.cc>
This commit adds support for the dual-analog-pads on STM32H7 parts. These
pads/pins are called PA0_C/PA1_C/PC2_C/PC3_C in the datasheet. They each
have an analog switch that can optionally connect them to their normal pin
(eg PA0). When the switch is open, the normal and _C pin are independent
pins/pads.
The approach taken in this commit to make these _C pins available to Python
is:
- put them in their own, independent row in the stm32h7_af.csv definition
file, with only the ADC column defined (they are separate machine.Pin
entities, and doing it this way keeps make-pins.py pretty clean)
- allow a board to reference these pins in the board's pins.csv file by the
name PA0_C etc (so a board can alias them, for example)
- these pins (when enabled in pins.csv) now become available like any other
machine.Pin through both machine.Pin.board and machine.Pin.cpu
- BUT these _C pins have a separate pin type which doesn't have any
methods, because they don't have any functionality
- these _C pins can be used with machine.ADC to construct the appropriate
ADC object, either by passing the string as machine.ADC("PA0_C") or by
passing the object as machine.ADC(machine.Pin.cpu.PA0_C)
- if a board defines both the normal and _C pin (eg both PA0 and PA0_C) in
pins.csv then it must not define the analog switch to be closed (this is
a sanity check for the build, because it doesn't make sense to close the
switch and have two separate pins)
Signed-off-by: Damien George <damien@micropython.org>
This new DMA API corrects possible cache coherency issues on chips with
D-Cache, when working with buffers at arbitrary memory locations (i.e.
supplied by Python code).
The API is used by SPI to fix an issue with corrupt data when reading from
SPI using DMA in certain cases. A regression test is included (it depends
on external hardware connection).
Explanation:
1) It's necessary to invalidate D-Cache after a DMA RX operation completes
in case the CPU reads (or speculatively reads) from the DMA RX region
during the operation. This seems to have been the root cause of issue
#13471 (only when src==dest for this case).
2) More generally, it is also necessary to temporarily mark the first and
last cache lines of a DMA RX operation as "uncached", in case the DMA
buffer shares this cache line with unrelated data. The CPU could
otherwise write the other data at any time during the DMA operation (for
example from an interrupt handler), creating a dirty cache line that's
inconsistent with the DMA result.
Fixes issue #13471.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
The existing MPU_CONFIG_DISABLE macro enables the MPU region but disables
all access to it.
The rename is necessary to support an MPU_CONFIG_DISABLE macro that
actually disables the MPU region entirely.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
With LAN8742, LAN8720, LAN83825 and DP83848 as possible options, and the
symbols PHY_LAN8720, PHY_LAN8742, PHY_DP83825 and PHY_DP8348. The default
is PHY_LAN8742 which is the existing behaviour.
The eth_init() parameters for the Portenta H7 board are set to phy_addr=0
and phy_type=LAN8742, which matches the previous defaults and the
schematics.
Tested with LAN8720 and DP83848 breakout boards at 10M Duplex and 100M
Duplex modes.
Signed-off-by: robert-hh <robert@hammelrath.com>
The default value is 0, which is compatible with the existing behaviour.
Implementing that required changes to eth.c as well. The value of phy_addr
is added to the eth_t data type.
Tested with a STM32F767 and a STM32H750 device.
Signed-off-by: robert-hh <robert@hammelrath.com>
The STATIC macro was introduced a very long time ago in commit
d5df6cd44a. The original reason for this was
to have the option to define it to nothing so that all static functions
become global functions and therefore visible to certain debug tools, so
one could do function size comparison and other things.
This STATIC feature is rarely (if ever) used. And with the use of LTO and
heavy inline optimisation, analysing the size of individual functions when
they are not static is not a good representation of the size of code when
fully optimised.
So the macro does not have much use and it's simpler to just remove it.
Then you know exactly what it's doing. For example, newcomers don't have
to learn what the STATIC macro is and why it exists. Reading the code is
also less "loud" with a lowercase static.
One other minor point in favour of removing it, is that it stops bugs with
`STATIC inline`, which should always be `static inline`.
Methodology for this commit was:
1) git ls-files | egrep '\.[ch]$' | \
xargs sed -Ei "s/(^| )STATIC($| )/\1static\2/"
2) Do some manual cleanup in the diff by searching for the word STATIC in
comments and changing those back.
3) "git-grep STATIC docs/", manually fixed those cases.
4) "rg -t python STATIC", manually fixed codegen lines that used STATIC.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
It's no longer supported by Emscripten (at least at 3.1.55). And it's not
needed when the output is WASM, which it is by default.
Signed-off-by: Damien George <damien@micropython.org>
Because `mpthreadport.h` is included by `mpthread.h`.
Also remove unnecessary include of `mpthreadport.h` in esp32's `main.c`.
Signed-off-by: Damien George <damien@micropython.org>
The patch enables SDRAM banks 1 and 2 to be accessible at 0xC0000000 and
0xD0000000 respectively (default mapping) or remapped to addresses
0x60000000 and 0x70000000.
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
This combines the argument parsing and checking for the machine.SPI.init()
and machine.SPI() interfaces.
The only real difference was unspecified arguments in init() mean to keep
the same value, while in new they get default values.
Behavior has changed for passing the "id" argument to init(). On other
ports this isn't allowed. But on esp32 it would change the SPI controller
of the static SPI instance to the new id. This results in multiple static
spi objects for the same controller and they would fight over which one has
inconsistent mpy vs esp-idf state. This has been changed to not allow "id"
with init(), like other ports.
In a few causes, a loop is used over arguments that are handled the same
way instead of cut & pasting the same stanza of code for each argument.
The init_internal function had a lot of arguments, which is not efficient
to pass. Pass the args mp_arg_val_t array instead as a single argument.
This reduced both the number of C lines and the compiled code size.
Summary of code size change: Two argument lists of 72 bytes are replaced
by a single shared 72 byte list. New shared argument parsing code is small
enough to be inlined, but is still efficient enough to shrink the overall
code size by 349 bytes of the three argument handlering functions.
add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-349 (-349)
Function old new delta
machine_hw_spi_make_new 255 203 -52
machine_hw_spi_init 122 67 -55
machine_hw_spi_init_internal 698 456 -242
Total: Before=1227667, After=1227318, chg -0.03%
add/remove: 2/0 grow/shrink: 0/2 up/down: 92/-144 (-52)
Data old new delta
spi_allowed_args - 72 +72
defaults$0 - 20 +20
allowed_args$1 240 168 -72
allowed_args$0 1080 1008 -72
Total: Before=165430, After=165378, chg -0.03%
add/remove: 0/0 grow/shrink: 0/0 up/down: 0/0 (0)
Signed-off-by: Trent Piepho <tpiepho@gmail.com>
The size of the flash varies among MCU variants. Instead of requiring a
build-time variable to configure this, compute it at runtime using the
special device information word accessible through the FLASH_SIZE macro.
This feature is currently only implemented for H5 MCUs, but can be extended
to others.
Signed-off-by: Damien George <damien@micropython.org>
Allows bytecode itself to be used instead of an mp_raw_code_t in the simple
and common cases of a bytecode function without any children.
This can be used to further reduce frozen code size, and has the potential
to optimise other areas like importing.
Signed-off-by: Damien George <damien@micropython.org>
The Python BLE IRQ handler will most likely run on the NimBLE task, so its
C stack must be large enough to accommodate reasonably complicated Python
code (eg a few call depths). So increase this stack size.
Also increase the headroom from 1024 to 2048 bytes. This is needed because
(1) the esp32 architecture uses a fair amount of stack in general; and (2)
by the time execution gets to setting the Python stack top via
`mp_stack_set_top()` in this interlock code, about 600 bytes of stack are
already used, which reduces the amount available for Python.
Fixes issue #12349.
Signed-off-by: Damien George <damien@micropython.org>
In case callbacks must run (eg a disconnect event happens during the
deinit) and the GIL must be obtained to run the callback.
Fixes part of issue #12349.
Signed-off-by: Damien George <damien@micropython.org>
PPP is not that commonly used, let it be turned off in the board config to
save space. It is still on by default.
On an basic ESP32-S3 build, turning off PPP with LWIP still on saves ~35 kB
of codend 4 kB of data.
text data bss dec hex filename
1321257 304296 2941433 4566986 45afca before-ppp-off.elf
1285101 299920 2810305 4395326 43113e after-ppp-off.elf
-------------------------------
-36156 -4376 -56
Note that the BSS segment size includes all NOBITS sections in ELF file.
Some of these are aligned to 64kB chunk sized dummy blocks, I think for
alignment to MMU boundaries, and these went down by 1 block each, so 128
kiB of BSS is not really part of the binary size reduction.
Signed-off-by: Trent Piepho <tpiepho@gmail.com>
For mimxrt, nrf, renesas-ra, rp2 and samd ports, this commit implements
similar behaviour to the stm32 port, where USB is only brought up after
boot.py completes execution.
Currently this doesn't add any useful functionality (and may break
workflows that depend on USB-CDC being live in boot.py), however it's a
precondition for more usable workflows with USB devices defined in
Python (allows setting up USB interfaces in boot.py before the device
enumerates for the first time).
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Obtaining the stack-top via a few function calls may yield a pointer which
is too deep within the stack. So require the user to obtain it from a
higher level (or via some other means).
Fixes issue #11781.
Signed-off-by: YAMAMOTO Takashi <yamamoto@midokura.com>
The current `ssl` module has quite a few differences to the CPython
implementation. This change moves the MicroPython variant to a new `tls`
module and provides a wrapper module for `ssl` (in micropython-lib).
Users who only rely on implemented comparible behavior can continue to use
`ssl`, while users that rely on non-compatible behavior should switch to
`tls`. Then we can make the facade in `ssl` more strictly adhere to
CPython.
Signed-off-by: Felix Dörre <felix@dogcraft.de>