This prevents a very subtle bug caused by writing e.g. `bytearray('\xfd')`
which gives you `(0xc3, 0xbd)`.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
There are two calls to mp_builtin___import__():
1. ports/unix/main.c:main_() which provides a str in args[0]
2. py/runtime.c:mp_import_name() which provides a qstr in args[0]
The default implementation of mp_builtin___import__() is
mp_builtin___import___default() which has a different implementation based
on MICROPY_ENABLE_EXTERNAL_IMPORT.
If MICROPY_ENABLE_EXTERNAL_IMPORT is disabled then the handling of weak
links assumes that args[0] is a `const char *`, when it is either a str or
qstr object.
Use the existing qstr of the module name instead, and also use a vstr
instead of strcpy() to ensure no overflow occurs.
Emscripten strongly advises the use of optimisation when compiling with
ASYNCIFY enabled. Testing the difference betwen O3 and Os for various
configurations gives:
flags firmware.wasm micropython.js perf
-O3 -s ASYNCIFY 1342003 212845 0 (baseline)
-O3 -s ASYNCIFY -s WASM=0 - 7064750 -30%
-O3 367131 196569 +140%
-O3 -s WASM=0 - 2818260 +30%
-Os -s ASYNCIFY 1135450 213064 +40%
-Os -s ASYNCIFY -s WASM=0 - 6239768 -30%
-Os 295028 196569 +180%
-Os -s WASM=0 - 2271358 +30%
The first row is prior to this commit. The second and third columns show
firmware size (add them to get the total size). The fourth column shows
the approximate change in performance compared to the baseline. The
performance was measured using run-perfbench.py and the error was large, up
to 20%, although general trends in the change in performance could still be
seen.
In summary, using using Os instead of O3 makes it a little bit faster in
all cases, and smaller output (wasm/js) in all cases.
Signed-off-by: Damien George <damien@micropython.org>
This simplifies the config file. This is not a no-op, it does enable a few
new features to bring the port in line with this config level.
Signed-off-by: Damien George <damien@micropython.org>
So that filesystems mounted with "mpremote mount" can have their files
iterated over, making them consistent with other files.
Signed-off-by: Damien George <damien@micropython.org>
The except handler for OSError didn't include the line that actually calls
os.listdir, so an invalid path wasn't handled correctly.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Checks are added for pwm.freq(), pwm_duty(), pwm_duty_u10() and
pwm.duty_u16(). This avoids a core dump on ESP32C3, and misleading error
messages on Xtensa ESP32 devices.
Set the size of machine_pin_irq_handler array to GPIO_NUM_MAX:
- Min GPIO_NUM_MAX is 22 for IDF_TARGET_ESP32C3.
- Max GPIO_NUM_MAX is 49 for IDF_TARGET_ESP32S3.
The MP_REGISTER_ROOT_POINTER entry must be hard-coded, because the location
that it's evaluated by the compiler does not include the relevant IDF
header to get a definition of GPIO_NUM_MAX.
Each SoC family has its own clocks and timings/timeouts. For I2C, the
default source clock is either APB (ESP32, ESP32-S2) or XTAL (ESP32-S3,
ESP32-C3) as shown in the datasheets. Since
machine_i2c.c/machine_hw_i2c_init() uses the default clk_flags (0), the
alternate low-power clock source is never selected in ESP-IDF
i2c.c/i2c_param_config(). There is not an API in i2c.c to get the source
clock frequency, so a compile-time value is used based on SoC family.
Also, the maximum timeout is different across the SoC families, so use the
I2C_LL_MAX_TIMEOUT constant to eliminate the warning from
i2c_set_timeout().
With these changes, the following results were obtained. The I2C SCL
frequencies were measured with a Saleae logic analyzer.
ESP32 (TTGO T Dislay)
I2C(0, scl=22, sda=21, freq=101781) Measured: 100KHz
I2C(0, scl=22, sda=21, freq=430107) Measured: 400KHz
I2C(0, scl=22, sda=21, freq=1212121) Measured: 941KHz
ESP32-S3 (TTGO T-QT)
I2C(0, scl=34, sda=33, freq=111111) Measured: 107KHz
I2C(0, scl=34, sda=33, freq=444444) Measured: 400KHz
I2C(0, scl=34, sda=33, freq=1111111) Measured: 842KHz
ESP32-C3 (XIAO ESP32C3)
I2C(0, scl=7, sda=6, freq=107816) Measured: 103KHz
I2C(0, scl=7, sda=6, freq=444444) Measured: 380KHz
I2C(0, scl=7, sda=6, freq=1176470) Measured: 800KHz
(ESP32-S2 board was not available for testing.)
So that it doesn't clash with the extmod version.
Also make the default for this enabled, so that most boards do not need to
configure it.
Signed-off-by: Damien George <damien@micropython.org>
This issue affected i.MX RT 1052, 1062 and 1064. It seems to be addressed
by Errata ERR006223, which also mentions i.MX RT101x and 102x, but these
devices worked well even without the change. As a side effect, the current
consumption at an idle REPL drops significantly with this fix.
Fixes issue #7235.
Commit 64af916c11 removed the version string
from docs/conf.py. py/mpconfig.h is a better place to get the version
from, so use that (when there is no git repository).
Signed-off-by: Damien George <damien@micropython.org>
When looking at latest (the default for docs.micropython.org), make it
clear that this isn't the release version.
- Changes the version in the top-left to "latest".
- Adds a message to the top of each page to explain.
For future release versions, add a short message to link to the latest
version.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
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.
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.
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.
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.
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).
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.
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.
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.
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.
Matt Trentini
Jim Mussared
Simon Arlott
Damien George
Nicholas H.Tollervey
robert-hh
Ihor Nehrutsa
Mark Grosen