Commit Graph

3817 Commits

Author SHA1 Message Date
Trent Piepho 92f0469711 esp32/uart: Make compatible with sclk type change in ESP-IDF 5.3.
This type changes when they add LP-UART support for the ESP32-C6 in the dev
version of ESP-IDF 5.3.

Signed-off-by: Trent Piepho <tpiepho@gmail.com>
2023-11-23 11:51:06 +11:00
Trent Piepho f72a7dde18 esp32/uart: Preserve console UART clock, fix UART console with DFS.
In commit 7c929d44 the console UART was changed to use the UART HAL.
Starting the UART HAL will change the UART clock from whatever it was
already configured at to UART_SCLK_DEFAULT.  There is no "initialize at
existing settings" option.

This clock doesn't work with DFS.

The ESP-IDF code already takes this into account, and when DFS is enabled
it will configure the console UART to use the correct platform-specific
clock that will work with DFS.

The UART HAL init undoes this and sets it back to default.

This change will query the clock before the HAL init, then use the HAL
function to restore it back.  Thus keeping the clock at the "correct"
value, which depends on platform, DFS status, and so on.

The clock frequency will be found using the UART driver function ESP-IDF
code uses for this.  The existing code hard-coded a path that worked if the
clock was the APB clock and would fail otherwise.

The UART_NUM_0 define is removed because driver/uart.h already provides
this same macro.

Signed-off-by: Trent Piepho <tpiepho@gmail.com>
2023-11-23 11:49:08 +11:00
Damien George a85c3c45a6 esp32/boards/ESP32_GENERIC: Reduce size of D2WD variant to fit in flash.
Signed-off-by: Damien George <damien@micropython.org>
2023-11-23 10:39:12 +11:00
Angus Gratton a800ed5ae3 docs/library/esp: Correct the description of esp.osdebug().
The behaviour described in the docs was not correct for either port.

This work was funded through GitHub Sponsors.

Signed-off-by: Angus Gratton <angus@redyak.com.au>
2023-11-22 16:48:35 +11:00
Angus Gratton 917b56137f esp32/boards/sdkconfig.base: Fix increasing log level via esp.osdebug().
At some point the config changed such that no messages above Error level
were compiled into the final binary.

Fixes issue #12815.

This work was funded through GitHub Sponsors.

Signed-off-by: Angus Gratton <angus@redyak.com.au>
2023-11-22 16:48:15 +11:00
Angus Gratton fce8d9fd55 esp32/modsocket: Try garbage collection if the socket limit is reached.
If the hard socket limit (default 16) is reached then it's possible that
socket allocation fails but garbage collection would allow it to succeed.

Perform a GC pass and try again before giving up, similar to the logic
elsewhere in MicroPython that tries a GC pass before raising MemoryError.

This work was funded through GitHub Sponsors.

Signed-off-by: Angus Gratton <angus@redyak.com.au>
2023-11-20 19:16:16 +11:00
Angus Gratton 57cce79a46 esp32/modsocket: Implement socket connect timeout.
LWIP doesn't implement a timeout for blocking connect(), and such a timeout
is not required by POSIX.  However, CPython will use the socket timeout for
blocking connect on most platforms.  The "principle of least surprise"
suggests we should support it on ESP32 as well (not to mention it's
useful!).

This provides the additional improvement that external exceptions (like
KeyboardInterrupt) are now handled immediately if they happen during
connect().  Previously Ctrl-C would not terminate a blocking connect until
connect() returned, but now it will.

Fixes issue #8326.

This work was funded through GitHub Sponsors.

Signed-off-by: Angus Gratton <angus@redyak.com.au>
2023-11-20 18:48:25 +11:00
Sebastian Romero 6117aa686f renesas-ra/boards/ARDUINO_PORTENTA_C33: Fix incorrect I2C pins.
Also change the number of the interface to 0 as it's connected to IIC0.

Signed-off-by: Sebastian Romero <s.romero@arduino.cc>
2023-11-17 15:40:33 +11:00
Sebastian Romero 6f0193335a ports: Fix incorrect identifiers on Arduino boards.
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>
2023-11-17 15:24:15 +11:00
Damien George 92741a3438 stm32/boards/STM32H573I_DK: Enable the SD card.
Signed-off-by: Damien George <damien@micropython.org>
2023-11-17 14:17:49 +11:00
Damien George c34941109f stm32/sdcard: Add SD card support for H5 MCUs.
Signed-off-by: Damien George <damien@micropython.org>
2023-11-17 14:17:37 +11:00
Rene Straub 0cc100be2c stm32/boards/NUCLEO_H563ZI: Add new NUCLEO-H563ZI board definition.
Configuration:
- Clock is HSE, CPU runs at 250MHz.
- REPL on USB and UART connected to the ST-Link interface.
- Storage is configured for internal flash memory.
- Three LEDs and one user button.
- Ethernet is enabled.

Signed-off-by: Rene Straub <rene@see5.ch>
2023-11-17 13:53:01 +11:00
ThomHPL 70feb123bf stm32/boards/NUCLEO_F446RE: Add UARTs 1, 3 and 4.
Signed-off-by: ThomHPL <thomas.herpoel@gmail.com>
2023-11-17 13:43:11 +11:00
Peter Züger a23dbdca79 stm32: Add optional lwip loopback support.
MICROPY_PY_LWIP_LOOPBACK must be set at the make level to enable this.

Signed-off-by: Peter Züger <zueger.peter@icloud.com>
2023-11-17 13:37:04 +11:00
Andrew Leech 37c1c5fa49 stm32/mpu: Enable STM32WB mpu use to support qspi flash.
Signed-off-by: Andrew Leech <andrew.leech@planetinnovation.com.au>
2023-11-17 13:17:13 +11:00
Angus Gratton 8b1980ad45 samd: Use unique id for USB serial number.
Replaces the previous all-zeroes "TODO" serial number.

Requires refactoring the low-level unique_id routine out from modmachine.c.

This work was funded through GitHub Sponsors.

Signed-off-by: Angus Gratton <angus@redyak.com.au>
2023-11-16 15:03:09 +11:00
Angus Gratton f567a9255a shared/tinyusb: Add a helper for hex string conversion.
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>
2023-11-16 14:59:48 +11:00
Angus Gratton 5e3f0e7f85 samd: Switch to shared TinyUSB implementation.
Functionality and code size don't really change, but removes port-specific
code in favour of shared code.

(The MSC implemented in shared/tinyusb depends on some functions in the
pico-sdk, so this change doesn't make this available for samd.)

This work was funded through GitHub Sponsors.

Signed-off-by: Angus Gratton <angus@redyak.com.au>
2023-11-16 14:54:29 +11:00
Angus Gratton 033361da4a samd/mphalport: Run TinyUSB stack while waiting for CDC input/output.
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>
2023-11-10 08:04:26 +11:00
Damien George a00c9d56db rp2/mphalport: Run TinyUSB stack while waiting for CDC input/output.
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>
2023-11-09 17:56:58 +11:00
Damien George d46dc5e173 shared/tinyusb: Expose mp_usbd_task as a public function.
Signed-off-by: Damien George <damien@micropython.org>
2023-11-09 17:56:58 +11:00
Jim Mussared af52e1ff24 stm32/boards/NUCLEO_WL55: Freeze LoRa driver.
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>
2023-11-09 14:47:53 +11:00
Mark Blakeney 2888c5b230 esp32/esp32_rmt: Add RMT.PULSE_MAX constant.
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>
2023-11-09 13:51:52 +11:00
Mark Blakeney fbb7c32040 esp32/esp32_rmt: Change RMT.source_freq() to class method.
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>
2023-11-09 13:51:47 +11:00
robert-hh f07f90f1ab mimxrt/boards/OLIMEX_RT1010: Adjust the UART pin assignment.
Olimex asked for that, getting a UART at the UEXT1 connector as well.

Signed-off-by: robert-hh <robert@hammelrath.com>
2023-11-09 13:41:44 +11:00
Angus Gratton 26d5032980 samd: Switch TinyUSB to run via a scheduled task.
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>
2023-11-09 12:30:04 +11:00
Angus Gratton bcbdee2357 rp2: Change to use TinyUSB dcd_event_handler hook.
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>
2023-11-09 12:28:28 +11:00
stijn 958c6d917d windows: Use the MicroPython logo as application icon.
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>
2023-11-07 17:22:52 +11:00
Damien George 03eae48847 extmod/machine_adc_block: Factor esp32 ADCBlock bindings to common code.
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>
2023-11-07 16:44:35 +11:00
Jim Mussared 9be0623d4c shared/libc/string0: Don't deref args for n==0 case.
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>
2023-11-07 16:01:50 +11:00
Alessandro Gatti bea6ff82fa tools/tinytest-codegen.py: Externalise tests list.
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>
2023-11-07 15:53:27 +11:00
robert-hh c35cc63366 samd/pin_af: Fix a typo in a conditional compile.
Thanks to @ricksorensen for finding it.

Signed-off-by: robert-hh <robert@hammelrath.com>
2023-11-06 11:11:18 +11:00
robert-hh 59afeb056a samd/machine_uart: Add machine_uart_set_baudrate() function.
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>
2023-11-06 11:10:11 +11:00
robert-hh 2c1f238205 samd/mpconfigport: Set MICROPY_USE_INTERNAL_ERRNO to 1.
Without this, error codes can be misleading.

Signed-off-by: robert-hh <robert@hammelrath.com>
2023-11-06 11:09:16 +11:00
Jim Mussared 47ed06bda2 stm32/boards/make-pins.py: Only support ADC1-3.
e.g. The STM32G4 includes ADC4 & ADC5 which is not currently supported
by the stm32 driver.

Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
2023-11-05 08:33:49 +11:00
robert-hh ae3b1cfab1 mimxrt/modmachine: Fix settings for the MIMXRT1170 board.
These were not changed with commit c0b64a3f2 for using tools/boardgen.py.

Signed-off-by: robert-hh <robert@hammelrath.com>
2023-11-05 08:30:18 +11:00
Jim Mussared 09c9c8ac30 stm32/boards/stm32g474_af.csv: Fix final row ADC column.
The original file was missing a trailing , on the final row.

Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
2023-11-04 11:00:06 +11:00
Jim Mussared c028f956fc stm32/boards/stm32f4x9_af.csv: Fix DCMI_VSYNC.
This incorrectly had a `(1)` on the end.

Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
2023-11-04 09:01:40 +11:00
Jim Mussared 841422817e stm32/boards/make-pins.py: Fix H7 ADC generation.
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>
2023-11-03 19:34:54 +11:00
Angus Gratton 8c432ea2d4 rp2: Remove 1ms timeout to make idle waiting tickless.
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>
2023-11-03 18:26:51 +11:00
iabdalkader b41055a5a3 rp2/machine_adc: Refactor channel/pin validation code.
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>
2023-11-03 18:20:31 +11:00
Maarten van der Schrieck d95f5aa011 rp2/machine_uart: Fix handling of serial break condition.
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>
2023-11-03 17:33:28 +11:00
Rene Straub 47ea831c0e stm32: Add STM32H5 support for sleep mode.
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>
2023-11-03 17:14:05 +11:00
iabdalkader e5014a4d79 stm32: Add configuration options for analog switches.
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
2023-11-03 16:27:10 +11:00
Jim Mussared b6a9778484 py/misc: Change sizeof to offsetof for variable-length alloc.
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>
2023-11-03 16:03:18 +11:00
Jim Mussared 6ef9b29f88 {cc3200,nrf}/boards/make-pins.py: Add a note about tools/boardgen.py.
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>
2023-11-03 14:18:54 +11:00
Jim Mussared 1f804e03f6 renesas-ra/boards/make-pins.py: Update to use tools/boardgen.py.
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>
2023-11-03 14:18:54 +11:00
Jim Mussared c0b64a3f23 mimxrt/boards/make-pins.py: Update to use tools/boardgen.py.
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>
2023-11-03 14:18:54 +11:00
Jim Mussared 4d568a5bd7 samd/boards/make-pins.py: Update to use tools/boardgen.py.
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>
2023-11-03 14:18:32 +11:00
Jim Mussared ff6c2adfd7 stm32/boards/make-pins.py: Add initial support for H7 dual-pad pins.
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>
2023-11-03 14:18:32 +11:00