GitLab

This is usually called on soft-reboot, a NIC can implement this to do any
necessary cleaning up (such as invalidating root pointers).
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>

Signed-off-by: Damien George <damien@micropython.org>

This adds tests for, eg, -inf + inf which should be nan.
Signed-off-by: Damien George <damien@micropython.org>

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>

The installation instructions for ESP32 TinyPICO board contained a typo
that used a non-standard baud rate 912600 instead of 921600.  This made the
upload command fail on some Windows computers.
Signed-off-by: Scott Zhao <zhaomh1998@outlook.com>

The user memory area - accessible by machine.RTC.memory() -- will now
survive most reboot causes.  A power-on reset (also caused by the EN pin on
some boards) will clean the memory.  When this happens, the magic number
not found in the user memory will cause initialization.

After other resets (triggered by watchdogs, machine.reset(), ...), the user
is responsible to check and validate the contents of the user area.

This new behaviour can be changed by enabling
MICROPY_HW_RTC_MEM_INIT_ALWAYS: in that case the RTC memory is always
cleared on boot.
Signed-off-by: Thomas Wenrich <twenrich@gmail.com>

Signed-off-by: Damien George <damien@micropython.org>

The amount of free IRAM in ESP32 SPIRAM builds is very small and went over
the limit due to commit 30b0ee34.  This
commit enables further optimisations to reduce IRAM usage.
Signed-off-by: Damien George <damien@micropython.org>

CCaches are scoped per-job.

Uses https://github.com/hendrikmuhs/ccache-action to get desired behaviour
(updating the cache on each run).
Signed-off-by: Angus Gratton <angus@redyak.com.au>

This is for consistency with the previous commit that uses this approach
for esp32.
Signed-off-by: Angus Gratton <angus@redyak.com.au>

Allows splitting the esp32 job into multiple parts without too much
boilerplate.  The matrix is parameterised using the name of the function to
call in tools/ci.sh, to minimise the dependency on GitHub Actions.

This can get esp32 build times down around 3m if IDF is cached already.

If the cache is cold, the cache preparation step on each job can double up
against each other.  However, restructuring the workflow to not do this
seems either complex or requires copy-pasting the entire cache step.
Signed-off-by: Angus Gratton <angus@redyak.com.au>

Cache is keyed on the ESP-IDF version used in CI, so there shouldn't be any
cache invalidation issues when ESP-IDF version changes.

Restoring from cache takes approx 15s, compared to 2-3m to perform these
steps (ESP-IDF tools install, ESP-IDF clone, ESP-IDF submodule clone) the
first time.

Cache size is approx 1.6GB, the git clone is tweaked as much as possible to
keep the size down.
Signed-off-by: Angus Gratton <angus@redyak.com.au>

Configures the I2S PLL to produce a frequency that the I2S clock generator
can use to create an optimal SCK frequency.  The I2S PLL configuration
table is automatically generated at build time.

Fixes issue #10280.
Signed-off-by: Mike Teachman <mike.teachman@gmail.com>

This was broken by commit 48b5a7b0.
Signed-off-by: Damien George <damien@micropython.org>

This board has MICROPY_VFS enabled, which should take precedence over
MICROPY_MBFS (and did prior to 22d9116c).
Signed-off-by: Damien George <damien@micropython.org>

This should have been enabled in 48b5a7b0
but was missed.
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Carlos Gil <carlosgilglez@gmail.com>

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>

To match other ports.
Signed-off-by: Carlos Gil <carlosgilglez@gmail.com>

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>

MICROPY_BEGIN_ATOMIC_SECTION/MICROPY_END_ATOMIC_SECTION belong more to the
MicroPython HAL rather than build configuration settings, so move their
default configuration to py/mphal.h, and require all users of these macros
to include py/mphal.h (here, py/objexcept.c and py/scheduler.c).

This helps ports separate configuration from their HAL implementations, and
can improve build times (because mpconfig.h is included everywhere, whereas
mphal.h is not).
Signed-off-by: Damien George <damien@micropython.org>

Or this port may end up accidentally including unwanted headers from stm32.
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Changes:
- os.uname() is removed to save space; sys.version and sys.implementation
  can be used instead.
- os.sync() now uses the common extmod version and syncs by calling the FAT
  FS sync function, which eventually calls sflash_disk_flush().
Signed-off-by: Damien George <damien@micropython.org>

Tested on a WIPY.
Signed-off-by: Damien George <damien@micropython.org>

The os.dupterm() function has changed on this port, it now matches the
semantics used by all other ports (except it's restricted to accept only
machine.UART objects).
Signed-off-by: Damien George <damien@micropython.org>

To make this a little more consistent with other ports.
Signed-off-by: Damien George <damien@micropython.org>

Now that the MICROPY_BEGIN_ATOMIC_SECTION/MICROPY_END_ATOMIC_SECTION macros
act the same as disable_irq/enable_irq, it's possible to use the common
extmod implementation of these machine functions.
Signed-off-by: Damien George <damien@micropython.org>

By disabling ets_loop_iter when the atomic section is active.
Signed-off-by: Damien George <damien@micropython.org>

This commit changes the cc3200 port to use the common machine
implementation of machine.disable_irq() and machine.enable_irq().  This
eliminates its dependency on the stm32 port's code.  The behaviour of
cc3200 for these functions is changed:
- disable_irq() now returns an (opaque) integer rather than a bool
- enable_irq(state) must be passed and argument, which is the return value
  of disable_irq() rather than a bool
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>

Signed-off-by: Damien George <damien@micropython.org>

And use it in qemu-arm, unix and windows ports to enable PinBase.
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>

Signed-off-by: Damien George <damien@micropython.org>

MICROPY_HW_ENABLE_HW_I2C and MICROPY_PY_MACHINE_I2C are equivalent, so
just use the latter.
Signed-off-by: Damien George <damien@micropython.org>

Prior to this change, if a board did not define any hardware I2C pins, via
MICROPY_HW_I2Cx_SCL, then machine.I2C would alias to machine.SoftI2C.

That doesn't really make sense, and SoftI2C should always be used if there
is no hardware implementation.  So this commit makes it so that machine.I2C
is only available if at least one set of I2C hardware pins are defined via
the MICROPY_HW_I2Cx_SCL/SDA macros.

For all boards that define at least one set of I2C hardware pins (which is
most of them) this commit is a no-op.  The only boards that change are:
LEGO_HUB_NO6, LEGO_HUB_NO7, STM32H7B3I_DK.
Signed-off-by: Damien George <damien@micropython.org>

MICROPY_PY_MACHINE_SPI is defined in mpconfigport.h to be equal to
MICROPY_PY_MACHINE_HW_SPI, so they are equivalent options.  The former one
is preferred because it's used by all other ports.

The default in mpconfigport.h is to enable this option, and all boards that
enable SPI have this removed from their mpconfigboard.h file so they pick
up the default.
Signed-off-by: Damien George <damien@micropython.org>