The previous computation incorrectly assumed that the uint32_t ticks
counter MICROPY_SOFT_TIMER_TICKS_MS was in the range [0,0x80000000) where
its actually [0,0xffffffff]. This means the diff calculation can be
simplified compared to the original implementation copied from
utime_mphal.c, which has to deal with a ticks range constrained by the
small int range.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
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.
The default now includes all sub-components (security, l2cap, etc)
and using the kwarg options is no longer supported.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The default now includes all sub-components (security, l2cap, etc)
and using the kwarg options is no longer supported.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
So it can run on targets with low memory, eg esp8266.
Also enable the viper_4args() sub-test, which is now supported.
Signed-off-by: Damien George <damien@micropython.org>
This ensures that all builds unconditionally run makeversionhdr.py and
makemanifest.py to generate mpversion.h and frozen_content.c respectively.
This now matches the Makefile behavior, and in particular this fixes the
issue on ESP32 builds that changes in code-to-be-frozen will cause the
build to update. Both these already tools know not to touch their output
if there is no change.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Prior to this commit, on Pico W (where the CYW43 driver is enabled) the PIO
instruction memory was not released on soft reset, so using PIO after a
soft reset would eventually (after a few soft resets) lead to ENOMEM when
allocating a PIO program.
This commit fixes that by tracking the use of PIO memory by this module and
freeing it on soft reset.
Similarly, use of the state machines themselves are tracked and released on
soft reset.
Fixes issue #9003.
Signed-off-by: Damien George <damien@micropython.org>
Make this more generally useful and in line with what the mingw
and unix ports do: 16bit dig size to work on 32bit ports, a
self-contained qstrdefs.preprocessed.h because makemanifest.py
uses that, and a dev variant which effectively puts this to use:
previously the uasyncio module wasn't frozen but instead tests
ran by importing it from the extmod/ directory.
Code in tools/mpy-tool.py and py/frozenmod.c relies on the source file
path encoded in a .mpy file to have forward slashes (e.g. by searching
for '/__init__.py'). Enforce that when creating these files, thereby
fixing import of .mpy files and frozen modules not working before
because they could have backslashes when built with the windows port.
The mpversion.h file must exist before py/ source can be preprocessed,
but this went unnoticed because micropython.vcxproj always calls
MakeVersionHdr before MakeQstrDefs.
The variant.props may have incompatible build options which break
the mpy-cross build and in any case mpy-cross has nothing to do
with variant support.
This is in line with the change made for other ports in d53c3b6a: since
the default output directory already includes the variant name in it
there's no need to add it to the executable as well.
This will ensure that any board with networking support gets:
- webrepl
- mip
- urequests
- ntptime
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
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>
Prior to this commit, Pin(Pin.OPEN_DRAIN, value=0) would not set the
initial value of the open-drain pin to low, instead it would be high.
Signed-off-by: Damien George <damien@micropython.org>
The mp_plat_print output is already being used by the subsequent call to
mp_obj_print_exception(). And this eliminates all references to printf for
this port (at least in non-debug builds).
Signed-off-by: Damien George <damien@micropython.org>
Unless MICROPY_OBJ_REPR == MICROPY_OBJ_REPR_D, these macros only work with
values and "->"/"." expressions as their sole argument. In other words,
the macros are broken with expressions which contain operations of lower
precedence than the cast operator.
Depending on situation, the old code either results in compiler error:
MP_OBJ_TO_PTR(flag ? o1 : o2) expands into "(void *)flag ? o1 : o2",
which some compiler configurations will reject (e.g. GCC -Wint-conversion
-Wint-to-pointer-cast -Werror)
Or in an incorrect address calculation:
For ptr declared as "uint8_t *" the MP_OBJ_FROM_PTR(ptr + off)
expands into ((mp_obj_t)ptr) + off, resulting in an obviously
wrong address.
Signed-off-by: Alex Riesen <alexander.riesen@cetitec.com>
This is important for literal tuples, e.g.
f"{a,b,}, {c}" --> "{}".format((a,b), (c),)
which would otherwise result in either a syntax error or the wrong result.
Fixes issue #9635.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
32-bit platforms only support a slice offset start of 24 bit max due to the
limited size of the mp_obj_array_t.free member. Similarly on 64-bit
platforms the limit is 56 bits.
This commit adds an OverflowError if the user attempts to slice a
memoryview beyond this limit.
Signed-off-by: Damien George <damien@micropython.org>
The delay is 1 ms. It avoids the crashes reported by the
issues #8289, #8792 and #9236 with esp-idf versions >= 4.2, but does
not solve an underlying problem in the esp-idf.
The major setting is about the PHY interface configuration. The
configuration matches the Olimex ESP32 Gateway as well.
Tested with esp-idf v4.2.4 and Olimex ESP32 POE boards.
