See the commit a00c9d56db for a detailed description of the problem, a
regression introduced in 26d503298.
Same approach here as the linked fix for rp2 (applied unconditionally here
as this port only supports USB-CDC for stdin/stdout).
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>
Fixes undefined behavior when calling vfs_posix_file_ioctl with
MP_STREAM_CLOSE as request because that casts away the constness and
assigns -1 to the object's fd member.
Fixes issue #12670.
Signed-off-by: stijn <stijn@ignitron.net>
Similar to 3883f29485 where this change was
implemented for threads: when the Bluetooth IRQ handler is called the
thread state is not not zero-initialized and thus we need to manually set
this to NULL.
Fixes issue #12239.
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
This adds the sync version of the LoRa driver (and the base WL55 driver).
Adds +13.6kiB (212.6 -> 226.2). Limit for this board is 232kiB.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
If you have a variable frequency and pulse width, and you want to optimize
pulse resolution, then you must do a calculation beforehand to ensure you
normalize the array to keep all list values within bound. That calculation
requires RMT.source_freq(), RMT.clock_div(), and this 32767 constant.
Signed-off-by: Mark Blakeney <mark.blakeney@bullet-systems.net>
To create an esp32.RMT() instance with an optimum (i.e. highest resolution)
clock_div is currently awkward because you need to know the source clock
frequency to calculate the best clock_div, but unfortunately that is only
currently available as an source_freq() method on the instance after you
have already created it. So RMT.source_freq() should really be a class
method, not an instance method. This change is backwards compatible for
existing code because you can still reference that function from an
instance, or now also, from the class.
Signed-off-by: Mark Blakeney <mark.blakeney@bullet-systems.net>
Previously the TinyUSB task was run in the ISR immediately after the
interrupt handler. This approach gives very similar performance (no change
in CDC throughput tests) but reduces the amount of time spent in the ISR,
and allows TinyUSB callbacks to run in thread mode.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
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>
dcd_event_handler() is called from the IRQ when a new DCD event is queued
for processing by the TinyUSB thread mode task. This lets us queue the
handler to run immediately when MicroPython resumes.
Currently this relies on a linker --wrap hack to work, but a PR has been
submitted to TinyUSB to allow the function to be called inline from
dcd_event_handler() itself.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Speeds up importing files from mounted filesystem.
Also fix the return code for invalid / unsupported ioctl requests.
Signed-off-by: Andrew Leech <andrew.leech@planetinnovation.com.au>
Add a .ico file with common icon image size, created from
vector-logo-2.png, and embed it into the resulting executable.
Signed-off-by: stijn <stijn@ignitron.net>
This is a code factoring to have the Python bindings in one location, and
all the ports use those same bindings. At this stage only esp32 implements
this class, so the code for the bindings comes from that port.
The documentation is also updated to reflect the esp32's behaviour of
ADCBlock.connect().
Signed-off-by: Damien George <damien@micropython.org>
This handles the case where an empty bytes/bytearray/str could pass in
NULL as the str argument (with length zero). This would result in UB in
strncmp. Even though our bare-metal implementation of strncmp handles
this, best to avoid it for when we're using system strncmp.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
C99 says that strncmp has UB for either string being NULL, so the
current behavior is technically correct, but it's an easy fix to handle
this case correctly.
7.1.4: "unless explicitly stated otherwise in the detailed
description... if an argument to a function has ...null pointer.. the
behavior is undefined".
7.21.1: "Unless explicitly stated otherwise in the description of a
particular function in this subclause, pointer arguments on such a call
shall still have valid values, as described in 7.1.4".
Also make the same change for the minimal version in bare-arm/lib.c.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Remove port-specific test directories and excluded tests from
tinytest-codegen, and let it read said information from an external file.
This way tinytest-codegen is not limited to always generate tests for the
`qemu-arm` target.
This allows having port-specific test directory and excluded tests for more
than one QEMU bare-metal target.
The `qemu-arm` port Makefile was modified to work with the generator
changes and a tests profile file was added to said port.
Signed-off-by: Alessandro Gatti <a.gatti@frob.it>
Changing the baudrate requires a complete re-configuration of the Sercom
device, which is put into a separate rather large function. This new
machine_uart_set_baudrate() function will be useful for future drivers such
as Bluetooth.
Signed-off-by: robert-hh <robert@hammelrath.com>
Fixes are:
- Only emit ADC table entries for pins that aren't cpu-hidden
(i.e. ignore `X,-Y` rows).
- Only use the P channels on H7.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
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>
Update rtc, machine and powerctrl drivers to support STM32H5 sleep
modes. This makes RTC alarm wakeup working from lightsleep() and
deepsleep().
Changes:
- Determine start reason for machine.reset_cause() in modmachine.c.
- Add proper interrupt clear code in rtc.c.
- Add wakeup functionality in powerctrl_enter_stop_mode(). Remember
and restore voltage scaling level. Restart HSI48 if it was on before
entering sleep mode.
- Clear DBGMCU_CR in SystemClock_Config() as for other variants.
Otherwise debug flags prevent entering sleep mode.
Implementation Notes:
- rtc.c: EXTI_RTSTR1 bits are not present for H5. Code sequence from
G0/G4/L4/WB/WL would be invalid. RTSTR is only defined for external
(GPIO) interrupts. Maybe this is also true for other STM32 variants.
- powerctrl_enter_stop_mode() uses complicated, nested conditionals
to select STM32 variants. To make code slightly better readable,
comment have been added. A non-nested, #if/#elif sequence would
make the code more readable. I leave this to the original authors.
Signed-off-by: Rene Straub <rene@see5.ch>
This fixes the case where e.g.
struct foo_t {
mp_obj_t x;
uint16_t y;
char buf[];
};
will have `sizeof(struct foo_t)==8`, but `offsetof(struct foo_t, buf)==6`.
When computing the size to allocate for `m_new_obj_var` we need to use
offsetof to avoid over-allocating. This is important especially when it
might cause it to spill over into another GC block.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Set the position of new line tokens as the end of the preceding line
instead of the beginning of the next line. This is done by first moving
the pointer to the end of the current line to skip any whitespace, record
the position for the token, then finaly skip any other line and whitespace.
The previous behavior was to skip every new line and whitespace, including
the indent of the next line, before recording the token position.
(Note that both lex->emit_dent and lex->nested_bracket_level equal 0 if
had_physical_newline == true, which allows simplifying the if-logic for
MP_TOKEN_NEWLINE.)
And update the cmd_parsetree.py test expected output, because the position
of the new-line token has changed.
Fixes issue #12792.
Signed-off-by: Mathieu Serandour <mathieu.serandour@numworks.fr>
It's not worth the effort to update these ports to use boardgen.py, but
put a note just in case anyone uses this as a reference for a new port.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This removes previously unused functionality to generate pins_ad_const.h,
as well as the unused handling of pin AF in machine_pin.c.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Minor change to remove support for using numeric IDs for machine.Pin. This
was previously based on the index of the pin in the board csv, but this is
different (and incompatible) with other ports.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This replaces the previous make-pin-table.py with an implementation based
on boardgen.py.
- MICROPY_PY_MACHINE_PIN_BOARD_CPU macro is removed. This isn't optional
on other ports, so no need for it to be optional on SAMD.
- pin_af_table is removed, and lookups just search the cpu dict instead
(this saves N*wordsize bytes of firmware size to have this extra table).
- pins.csv is now BOARD,CPU to match other ports.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This fixes the H7 af.csv files to include the dual-pad information, by
listing the ADCs supported on the _C pad with a C_ADC prefix.
Minimal change to make-pins.py to ignore these entries. This will be
implemented later to emit constants (similar to ADC.CORE_TEMP) to access
these channels.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Requires additions to tools/boardgen.py for stm32 pin generation.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This is now consistent with other ports.
Also renamed `pin_{board/cpu}_pins_locals_dict` to
`machine_pin_{board/cpu}_pins_locals_dict`.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Changes are:
- Pad all cells to make them easier to read.
- Ensure all files have exactly 19 columns (Port,Pin,AF0-15,ADC)
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Fixes are:
- Comment out lines in pins.csv that do not have valid CPU pins.
It's useful to keep these in the file as "documentation" but in order to
make make-pins.py stricter they need to be commented out.
- Fix some typos (missing P prefix) in pins.csv.
This resulted in some missing board pins.
- Fix some typos in af.csv files.
Some typos of "ADC" and some other that were previously ignored.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
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>
Angus Gratton
Damien George
stijn
Daniël van de Giessen
Jim Mussared
Mark Blakeney
robert-hh
Andrew Leech
Andrew Leech
Alessandro Gatti
iabdalkader
Maarten van der Schrieck
Rene Straub
Mathieu Serandour