Commit Graph

174 Commits

Author SHA1 Message Date
David Grayson
c046b23ea2 shared/runtime/pyexec: Don't allow Ctrl+C to interrupt frozen boot code.
Helps prevent the filesystem from getting formatted by mistake, among other
things.  For example, on a Pico board, entering Ctrl+D and Ctrl+C fast many
times will eventually wipe the filesystem (without warning or notice).

Further rationale: Ctrl+C is used a lot by automation scripts (eg mpremote)
and UI's (eg Mu, Thonny) to get the board into a known state.  If the board
is not responding for a short time then it's not possible to know if it's
just a slow start up (eg in _boot.py), or an infinite loop in the main
application.  The former should not be interrupted, but the latter should.
The only way to distinguish these two cases would be to wait "long enough",
and if there's nothing on the serial after "long enough" then assume it's
running the application and Ctrl+C should break out of it.  But defining
"long enough" is impossible for all the different boards and their possible
behaviour.  The solution in this commit is to make it so that frozen
start-up code cannot be interrupted by Ctrl+C.  That code then effectively
acts like normal C start-up code, which also cannot be interrupted.

Note: on the stm32 port this was never seen as an issue because all
start-up code is in C.  But now other ports start to put more things in
_boot.py and so this problem crops up.

Signed-off-by: David Grayson <davidegrayson@gmail.com>
2023-04-05 10:38:50 +10:00
Damien George
38e7b842c6 ports: Implement simple write polling for stdout.
This is a best-effort implementation of write polling.  It's difficult to
do correctly because if there are multiple output streams (eg UART and USB
CDC) then some may not be writeable while others are.  A full solution
should also have a return value from mp_hal_stdout_tx_strn(), returning the
number of bytes written to the stream(s).  That's also hard to define.

The renesas-ra and stm32 ports already implement a similar best-effort
mechanism for write polling.

Fixes issue #11026.

Signed-off-by: Damien George <damien@micropython.org>
2023-03-23 13:51:17 +11:00
robert-hh
be686e634e rp2: Allow disabling USB via MICROPY_HW_ENABLE_USBDEV config.
Previously, setting MICROPY_HW_ENABLE_USBDEV to 0 caused build errors.  The
change affects the nrf and samd ports as well, so MICROPY_HW_ENABLE_USBDEV
had to be explicitly enabled there.

The configuration options MICROPY_HW_ENABLE_USBDEV and
MICROPY_HW_ENABLE_UART_REPL are independent, and can be enabled or disabled
by a board.

Signed-off-by: Damien George <damien@micropython.org>
2023-03-20 22:33:45 +11:00
robert-hh
05bb26010e samd: Always provide the machine.RTC class.
Even if boards do not have a clock crystal.  In that case, the clock
quality will be very poor.

Always having machine.RTC means that the date/time can be set in a way that
is consistent with other ports.

This commit also removes the special code in modutime.c for devices without
the RTC class.

Signed-off-by: Damien George <damien@micropython.org>
2023-03-13 12:44:34 +11:00
iabdalkader
fb94ae48e9 samd/pendsv: Add MICROPY_BOARD_PENDSV_ENTRIES for board customisation. 2023-03-07 15:59:58 +11:00
Jim Mussared
69b93527d5 ports: Make BOARD default from BOARD_DIR in Makefile's.
This allows:

    $ make BOARD_DIR=path/to/board

to infer BOARD=board, rather than the previous behavior that required
additionally setting BOARD explicitly.

Also makes the same change for VARIANT_DIR -> VARIANT on Unix.

This work was funded through GitHub Sponsors.

Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Signed-off-by: Damien George <damien@micropython.org>
2023-02-23 09:47:08 +11:00
robert-hh
b110266897 samd/moduos: Add uos.urandom() using the phase-jitter rng.
This RNG passes many of the Diehard tests and also the AIS31 test suite.
The RNG is quite slow, delivering 200bytes/s.

Tested on boards with and without a crystal.
2023-02-21 23:17:44 +11:00
robert-hh
4160ec087b samd/mcu: Set the SAMD21 us-counter to 2 MHz for better resolution.
It turned out that the result of calling ticks_us() was always either odd
or even, depending on some internal state during boot.  So the us-counter
was set to a 2 MHz input and the result shifted by 1.  The counting period
is still long enough, since internally a (now) 63 bit value is used for us.
2023-02-21 23:17:12 +11:00
robert-hh
76cf98c35b samd/mcu: Implement a hardware seed for the SAMD21 random module.
By using the phase jitter between the DFLL48M clock and the FDPLL96M clock.
Even if both use the same reference source, they have a different jitter.
SysTick is driven by FDPLL96M, the us counter by DFLL48M.  As a random
source, the us counter is read out on every SysTick and the value is used
to accumulate a simple multiply, add and xor register.  According to tests
it creates about 30 bit random bit-flips per second.  That mechanism will
pass quite a few RNG tests, has a suitable frequency distribution and
serves better than just the time after boot to seed the PRNG.
2023-02-21 23:15:29 +11:00
robert-hh
7e0b1bc95d samd/mcu: Use the FDPLL96M clock for the SAMD21 CPU.
Allowing to increase the clock a little bit to 54Mhz.  Not much of a gain,
but useful for generating a RNG entropy source from the jitter between
DFLL48M and FDPLL96M.
2023-02-21 23:15:00 +11:00
robert-hh
60ab556385 samd/mcu: Rework the comments in clock_config.c.
For more clarity. clock_config.c is not overly readable, so comments are
important.
2023-02-21 23:14:45 +11:00
robert-hh
c3afafd1ec samd/boards: Clean up comments and some pins in pins.csv files.
Remove two SPARKFUN_SAMD51_THINGS_PLUS pin definitions.  There were
definitions of TXD and RXD, but these pins do not exist on the board.  They
were only shown in the schematics.

Also remove any reference to LED_.  This is just a text change, no
functional change.
2023-02-21 23:13:01 +11:00
robert-hh
4598b89ce9 samd: Add Pin.board and Pin.cpu classes to Pin.
For compatibility with other ports.  Code increase up to ~1250 bytes for
SAMD21.  The feature is configurable via MICROPY_PY_MACHINE_PIN_BOARD_CPU
in case flash memory is tight.
2023-02-17 17:27:21 +11:00
robert-hh
de1f1dd164 shared/runtime/softtimer: Use consistently the same clock source.
Before, both uwTick and mp_hal_ticks_ms() were used as clock source.  That
assumes, that these two are synchronous and start with the same value,
which may be not the case for all ports.  If the lag between uwTick and
mp_hal_ticks_ms() is larger than the timer interval, the timer would either
rush up until the times are synchronous, or not start until uwTick wraps
over.

As suggested by @dpgeorge, MICROPY_SOFT_TIMER_TICKS_MS is now used in
softtimer.c, which has to be defined in a port's mpconfigport.h with
the variable that holds the SysTick counter.

Note that it's not possible to switch everything in softtimer.c to use
mp_hal_ticks_ms() because the logic in SysTick_Handler that schedules
soft_timer_handler() uses (eg on mimxrt) the uwTick variable directly
(named systick_ms there), and mp_hal_ticks_ms() uses a different source
timer.  Thus it is made fully configurable.
2023-02-16 12:59:48 +11:00
David Lechner
3446d440f6 shared/runtime/gchelper: Drop cpu directive from ARM asm helpers.
This drops the `.cpu` directive from the ARM gchelper_*.s files.  Having
this directive breaks the linker when targeting older CPUs (e.g. `-mthumb
-mthumb-interwork` for `-mcpu=arm7tdmi`).  The actual target CPU should be
determined by the compiler options.

The exact CPU doesn't actually matter, but rather the supported assembly
instruction set.  So the files are renamed to *_thumb1.s and *thumb2.s to
indicate the instruction set support instead of the CPU support.

Signed-off-by: David Lechner <david@pybricks.com>
2023-01-28 15:51:38 +11:00
Jim Mussared
6d460d33dc samd/boards/SEEED_XIAO: Rename to SEEED_XIAO_SAMD21.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
2022-12-15 14:18:44 +11:00
robert-hh
17ab2f671b samd: Support entering bootloader via USB CDC 1200bps touch. 2022-12-14 12:50:04 +11:00
robert-hh
e69313f89c samd: Add a vref=num option to the ADC and DAC constructor.
ADC: The argument of vref=num is an integer. Values for num are:

    SAMD21:
    0  INT1V   1.0V voltage reference
    1  INTVCC0 1/1.48 Analog voltage supply
    2  INTVCC1 1/2 Analog voltage supply (only for VDDANA > 2.0V)
    3  VREFA   External reference
    4  VREFB   External reference

    SAMD51:
    0  INTREF  internal bandgap reference
    1  INTVCC1 Analog voltage supply
    2  INTVCC0 1/2 Analog voltage supply (only for VDDANA > 2.0v)
    3  AREFA   External reference A
    4  AREFB   External reference B
    5  AREFC   External reference C (ADC1 only)

DAC: The argument of vref=num is an integer. Suitable values:

    SAMD21:
    0  INT1V   Internal voltage reference
    1  VDDANA  Analog voltage supply
    2  VREFA   External reference

    SAMD51:
    0  INTREF Internal bandgap reference
    1  VDDANA Analog voltage supply
    2  VREFAU Unbuffered external voltage reference (not buffered in DAC)
    4  VREFAB Buffered external voltage reference (buffered in DAC).
2022-12-14 12:48:24 +11:00
robert-hh
a73dcb3d22 samd/machine_uart: Fix uart.deinit() and save some RAM.
Changes in this commit:
- Do not deinit IRQ when uart.deinit() is called with an inactive object.
- Remove using it for the finaliser.  There is another machanism for soft
  reset, and it is not needed otherwise.
- Do not tag the UART buffers with MP_STATE_PORT, it is not required.
2022-12-14 12:46:20 +11:00
robert-hh
f78dd25a2c samd/machine_uart: Check the UART TX pin assignment.
Check, if TX is at Pad 0 (SAMD51), or Pad 0 or 2 (SAMD21).
2022-12-14 12:45:51 +11:00
robert-hh
5b1fd8802a samd/machine_uart: Simplify machine_uart_any() and machine_uart_read().
Remove the call to uart_drain_rx_fifo().  It is not required, and may cause
a race condition.
2022-12-14 12:43:34 +11:00
robert-hh
4199f986ad samd/machine_uart: Fix IRQ flag setting and clearing.
Clearing the DRE flag for the transmit interrupt at the end of a
uart.write() also cleared the RXC flag disabling the receive interrupt.

This commit also changes the flag set/clear mechanism in the driver for SPI
as well, even if it did not cause a problem there.  But at least it saves a
few bytes of code.
2022-12-14 12:42:34 +11:00
robert-hh
fcd1788937 samd: Avoid under-/overflow in I2C and SPI baudrate calculations.
Applies to both SPI and I2C.  The underflow caused high baudrate settings
resulting in the lowest possible baudrate.  The overflow resulted in
erratic baudrates, not just the lowest possible.
2022-12-14 12:41:42 +11:00
robert-hh
43fc133dbd samd/mpconfigport: Use __WFE() in MICROPY_EVENT_POLL_HOOK.
Like WFI, WFE also responds to a hardware interrupt, and using WFE speeds
up at least spi.read().  Power consumption at an idle REPL is unchanged.
2022-12-14 12:40:22 +11:00
robert-hh
3cc359c204 samd/mpconfigport: Support MICROPY_HW_SOFTSPI_MIN_DELAY.
Bringing the SoftSPI baudrate up to about 500 kHz.
2022-12-14 12:39:54 +11:00
Jim Mussared
f34eedeb1b samd/Makefile: Set MPY_CROSS_FLAGS.
Otherwise this port will be unable to freeze `@native`/`@viper` code.

Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
2022-11-17 22:10:41 +11:00
Jim Mussared
92c35efb63 samd: Move MCU-specific CFLAGS to mpconfigmcu.mk.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
2022-11-17 22:10:40 +11:00
robert-hh
ca63ead2d8 samd/mphalport: Add a timeout to mp_hal_stdout_tx_strn().
If USB CDC is connected and the board sends data, but the host does not
receive the data, the device locks up.  This is fixed in this commit by
having a timeout of 500ms, after which time the transmission is skipped.
2022-11-09 11:15:24 +11:00
robert-hh
9d0aefe719 samd/boards/SEEED_WIO_TERMINAL: Enable using the 32kHz crystal.
That was missing from the configuration.
2022-11-08 23:26:24 +11:00
robert-hh
fadfc30547 samd/README: Update README to reflect recent changes to the port.
Most of the content of README.md became obsolete and was replaced by the
documentation of MicroPython.  Instead, README.md now shows build
instructions like the other ports.
2022-11-08 23:25:39 +11:00
robert-hh
144e5ec645 samd/mcu/samd51: Use an additional manifest.py for SAMD51 boards.
Including the uasyncio scripts and the drivers for DHT, DS18x20 and
onewire.  The uasyncio scripts need about 8k of flash and are not included
for the SAMD21 boards by default.
2022-11-08 23:22:26 +11:00
Damien George
6643b4f0cc samd/machine_timer: Use extmod version of machine.Timer.
Signed-off-by: Damien George <damien@micropython.org>
2022-10-27 14:45:24 +11:00
robert-hh
fcccfc176b samd/modmachine: Add machine.softreset().
For consistency with other ports.
2022-10-25 23:49:52 +11:00
robert-hh
a1eebc507e samd/machine_spi: Register SerCom objects as root pointers.
Protect SerCom (UART, SPI, I2C) objects from getting freed by the GC when
they go out of scope without being deinitialized.  Otherwise the ISR of a
Sercom may access an invalid data structure.
2022-10-25 23:48:37 +11:00
robert-hh
d74215a313 samd/machine_spi: Implement spi.deinit() and simplify sercom_deinit_all.
The sercom_deinit_all() function does not need the object pointers.
2022-10-25 23:46:00 +11:00
robert-hh
9c2bc379f1 samd/machine_uart: Use a finaliser to tidy up UART on soft reset.
And use the common sercom_table, saving a few bytes of RAM.
2022-10-25 23:44:49 +11:00
robert-hh
474233c250 samd/machine_pwm: Serialize fast update of PWM settings.
Any update of freq or duty_cycle requires the previous PWM cycle to be
finished.  Otherwise the new settings are not accepted.

Other changes in this commit:
- Report the set duty cycles even when the PWM is not yet started.
- pwm.freq(0) stops the pwm device, instead of raising an expception.
- Clear the duty cycle value cache on soft reset.
2022-10-25 23:42:14 +11:00
robert-hh
ac1e31267b samd/boards: Rework the pins.csv files.
Changes are:
- Remove the LED_Pxxx definitions from pins.csv, now that the LED class is
  gone.
- Remove the '-' lines.
- Add default lines for USB and SWCLK, SWDIO.
2022-10-25 23:40:28 +11:00
robert-hh
a6760bd4ef samd/modmachine: Replace the LED class by the Signal class.
It simplifies and improves the code.  The LED_Pxxx lines of the board.csv
lines can still be used, but will be taken as Pin definitions.
2022-10-25 23:39:41 +11:00
robert-hh
4d38ab652e samd: Make ADC, DAC, PWM, SPI objects consistent in how they print out.
All of ADC, DAC, Pin, PWM and SPI looked different before this change.
2022-10-25 23:36:01 +11:00
robert-hh
e5cf3fab95 samd/machine_pin: Change the pin handling and naming/numbering.
Pin numbers are now the MCU port numbers in the range:

    PA0..PA31:  0..31
    PB0..PB31: 32..63
    PC0..PC31: 64..95
    PD0..PD31: 96..127

Pins can be denoted by the GPIO port number, the name as defined in
pins.csv or a string in the form Pxnn, like "PA16" or "PD03".

The pins.c and pins.h files are now obsolete.  The pin objects are part of
the AF table.

As result of a simplification, the code now supports using pin names or
numbers instead of pin objects for modules like UART, SPI, PWM, I2C, ADC,
pininfo.
2022-10-25 23:34:07 +11:00
robert-hh
e7aa9700ca samd/boards/SEEED_WIO_TERMINAL: Declare more pins for SEEED WIO board.
Defining all pins from the external 40 Pin connector, and some internal
pins like the one for SD and LCD.
2022-10-25 23:28:34 +11:00
robert-hh
e33db80a59 samd/clock_config: Extend the SAMD51 us-counter to 60 bit.
This removes the difference in the time.ticks_us() range between SAMD21 and
SAMD51.

The function mp_hal_ticks_us_64() is added and used for:
- SAMD51's mp_hal_ticks_us and mp_hal_delay_us().
  For SAMD21, keep the previous methods, which are faster.
- mp_hal_ticks_ms() and mp_hal_tick_ms_64(), which saves some bytes
  and removes a potential race condition every 50 days.

Also set the us-counter for SAMD51 to 16 MHz for a faster reading of the
microsecond value.

Note: With SAMD51, mp_hal_ticks_us_64() has a 60 bit range only, which is
still a long time (~36000 years).
2022-10-25 23:26:14 +11:00
robert-hh
fc9d66fac6 samd/machine_rtc: Add the machine.RTC class.
Methods implemented are:
- rtc.init(date)
- rtc.datetime([new_date])
- rtc.calibration(value)

The presence of this class can be controlled by MICROPY_PY_MACHINE_RTC.  If
the RTC module is used, the time module uses the RTC as well.

For boards without a 32kHz crystal, using RTC makes no sense, since it will
then use the ULP32K oscillator, which is not precise at all.  Therefore, it
will by default only be enabled for boards using a crystal, but can be
enabled in the respective mpconfigboard.h.
2022-10-25 23:20:09 +11:00
robert-hh
be31fde012 samd/mcu: Make some settings in mpconfigmcu.h conditional.
And set the default for MICROPY_PY_MATH as 1 for both MCU types.
2022-10-25 23:13:58 +11:00
robert-hh
2251cb774b samd/machine_uart: Implement uart.txdone() and uart.flush().
Using the stream method for uart.flush().

uart.txdone() returns True, if the uart not busy, False otherwise.

uart.flush() waits until all bytes have been transmitted or a timeout
triggers.  The timeout is determined by the buffer size and the baud rate.

Also fix two inconsistencies when not using txbuf:
- Report in ioctl as being writeable if there is room in the tx buffer,
  only if it is configured.
- Print the txbuf size if configured.
2022-10-25 23:11:57 +11:00
robert-hh
ddd41b8bbf samd/clock_config: Document the #defines use in init_clocks().
Which may be set in the respective mpconfigboard.h files.
2022-10-25 23:10:27 +11:00
robert-hh
f0399d35e4 samd/modmachine: Get the bootloader magic address from the lib.
Instead of being hard-coded, and then it works for all MCUs.

That fits except for a Sparkfun SAMD51 Thing Plus (known) bug, which uses
192k - 4 as magic address.  Therefore, that address is set as well to avoid
a problem when this bug is fixed by Sparkfun.
2022-10-25 23:09:04 +11:00
robert-hh
03075a6839 samd/modmachine: Implement machine.lightsleep().
Which just sets the CPU clock to 200kHz and switches the peripheral clock
off.  There are two modes:

    machine.lightsleep(duration_ms)

and

    machine.lightsleep()

In any mode any configured pin.irq() event will terminate the sleep.

Current consumption in lightsleep for some boards:
- 1.5 - 2.5 mA when supplied trough an active USB
  (Seeed XIAO w/o power LED, Adafruit ItsyBitsy)
- 0.8 - 2 mA when supplied through Gnd/+5V (Vusb)
  (Seeed XIAO w/o power LED, Adafruit ItsyBitsy)
- < 1 mA for SAMD51 when supplied trough a battery connector
  (Sparkfun Thing SAMD51 plus)

Related change: move the calls to SysTick_Config() into set_cpu_freq().  It
is required after each CPU freq change to have ticks_ms run at the proper
rate.
2022-10-25 23:07:27 +11:00
robert-hh
4c9e4c3310 samd/mcu/samd51: Enable FAT support for SAMD51.
Tested with a SD card connected to a SAMD51 board.  The SEEED WIO terminal
has a SD-Card reader built-in.

Also a side change to remove a few obsolete lines from Makefile.
2022-10-25 23:07:23 +11:00