Removes the deprecated network.[AP|STA]_IF form from the esp32 port
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Seemingly ESP-IDF incorrectly marks RTC FAST memory region
as MALLOC_CAP_EXEC on ESP32-S2 when it isn't. This memory is
the lowest priority, so it only is returned if D/IRAM is exhausted.
Apply this workaround to treat the allocation as failed if it gives us
non-executable RAM back, rather than crashing.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
The cleanup in 548babf8 relies on some functions not available in older
ESP-IDF. Temporarily restore them, until we drop support for ESP-IDF <5.2.
PWM functionality should end up the same regardless of ESP-IDF version, and
also no different from MicroPython V1.23.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
These were added to the `network` module but not the `network.WLAN` class,
which is the new home for such constants.
Also:
- Mark the WLAN constants in the `network` module as deprecated, to be
removed in MicroPython 2.0.
- Move the static assert to the WLAN source code, to be close to where it
relates to.
Signed-off-by: Damien George <damien@micropython.org>
This commit fixes PWM configuration across C3, C6, S2 and S3 chips, which
was broken by 6d799378ba. Without this fix
the PWM frequency is limited to a maximum of 2446Hz (on S2 at least).
Signed-off-by: Andrew Leech <andrew@alelec.net>
This commit adds an extra bit of parameters validation to the SPI bus
constructor on ESP32. Passing 0 as the number of bits would trigger a
division by zero error when performing read/write operations on an SPI
bus created in such a fashion.
Fixes issue #5910.
Signed-off-by: Alessandro Gatti <a.gatti@frob.it>
For in-tree builds, these are effectively equivalent. However for
out-of-tree builds it's preferable to have as little as possible in the
top-level CMakeLists.txt file (as the out-of-tree build needs its own
copy).
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
This fixes a regression introduced in commit
4247921c4e, where this ring-buffer polling
was accidentally put inside the `#if MICROPY_HW_ESP_USB_SERIAL_JTAG`.
Signed-off-by: Andrew Leech <andrew@alelec.net>
This is a workaround for a bug in ESP-IDF where the configuration setting
for maximum active TCP sockets (PCBs) is not applied.
Fixes cases where a lot of short-lived TCP connections can cause:
- Excessive memory usage (unbounded number of sockets in TIME-WAIT).
- Much higher risk of stalled connections due to repeated port numbers. The
maximum number of active TCP PCBs is reduced from 16 to 12 to further
reduce this risk (trade-off against possibility of TIME-WAIT
Assassination as described in RFC1337).
This is not a watertight fix for the second point: a peer can still reuse a
port number while a previous socket is in TIME-WAIT, and LWIP will reject
that connection (in an RFC compliant way) causing the peer to stall.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Regression introduced in 337742f.
The hang occurs because the esp32 port was calling "from ISR" port-layer
functions to set/clear the interrupt mask. FreeRTOS kernel therefore
doesn't know the CPU is in a critical section. In taskYIELD() the riscv
port layer blocks after yielding until it knows the yield has happened, and
would block indefinitely if IRQs are disabled (until INT WDT triggers).
Moving to the "public" portENTER_CRITICAL/portEXIT_CRITICAL API means that
FreeRTOS knows we're in a critical section and can react accordingly.
Adds a regression test for this case (should be safe to run on all ports).
On single core CPUs, this should result in almost exactly the same
behaviour apart from fixing this case.
On dual core CPUs, we now have cross-CPU mutual exclusion for atomic
sections. This also shouldn't change anything, mostly because all the code
which enters an atomic section runs on the same CPU. If it does change
something, it will be to fix a thread safety bug.
There is some risk that this change triggers a FreeRTOS crash where there
is a call to a blocking FreeRTOS API with interrupts disabled. Previously
this code might have worked, but was probably thread unsafe and would have
hung in some circumstances.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
In idf v5.2.1 if the port flag is set it's validated even on jobs that
don't access hardware like clean. This causes the job to fail if device
isn't connected.
Signed-off-by: Andrew Leech <andrew@alelec.net>
Enables support for the ESP standard DTR/RTS based reboot to bootloader.
Switches from OTG to Serial/Jtag mode to workaround issue discussed
in: https://github.com/espressif/arduino-esp32/issues/6762
Signed-off-by: Andrew Leech <andrew@alelec.net>
Uses newer TinyUSB synopsys/dwc2 driver for esp32s2 and esp32s3 rather than
the IDF tinyusb component. This allows re-use of other tinyusb integration
code and features shared between ports.
Signed-off-by: Andrew Leech <andrew@alelec.net>
The ESP32 port contains a workaround to avoid having a certain function
in `py/parse.c` being generated incorrectly. The compiler in question
is not part of any currently supported version of ESP-IDF anymore, and the
problem inside the compiler (well, assembler in this case) has been
corrected a few years ago.
This commit removes all traces of that workaround from the source tree.
Signed-off-by: Alessandro Gatti <a.gatti@frob.it>
This is for boards not covered by the Olimex ESP32 PoE implementation. The
major setting is about the PHY interface configuration.
Tested with esp-idf v5.0.4 and Olimex ESP32 EVB boards.
Signed-off-by: shiggy <mail@shiggytech.de>
Workaround for what appears to be an upstream issue:
https://github.com/espressif/esp-idf/issues/14456
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Regression introduced by 5e692d04 now at MICROPY_HW_USB_CDC is set.
The ARDUINO_NANO_ESP32 specifically builds shared/tinyusb/mp_usb_cdc.c
for the 1200bps reset behaviour. However MicroPython esp32 doesn't yet
use the rest of the shared/tinyusb functionality.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
This fixes issue of ESP32-S3 switching its config over to USB serial/JTAG
instead of native USB.
The the existing logic was hard to follow, adding this config macro makes
it easier to see which USB is in use and to have board definitions that
enable/disable different USB levels.
This commit also drops (nominal) support for manually setting
CONFIG_ESP_CONSOLE_USB_CDC in sdkconfig. No included board configs use this
and it didn't seem to work (if secondary console was set to the default USB
Serial/JTAG then there is no serial output on any port, and if secondary
console was set to None then linking fails.) Can be re-added if there's a
use case for it.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Regression in 0a11832cd in IDF 5.0.x where macro
CONFIG_ESP_CONSOLE_USB_SERIAL_JTAG_ENABLED is not defined.
With this patch, ESP32-S3 still USB Serial/JTAG incorrectly (now on all
ESP-IDF versions).
Closes#15701
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
The UART.IRQ_IDLE callback is called about two character times after the
last byte, or 1 ms, whichever is larger. For the irq, timer 0 is used.
machine_timer.c had to be reworked to make it's mechanisms available for
machine_uart.c.
The irq.flags() value is change only at a requested event. Otherwise keep
the state.
Signed-off-by: robert-hh <robert@hammelrath.com>
IDF 3 builds are very old now (it seems like the last successful builds are
from 2021), and the current IDF 5 is stable. So remove IDF 3 variants.
Signed-off-by: Matt Trentini <matt.trentini@gmail.com>
The extra limit for C3 dates from 6823514 which added C3 support.
Measuring the minimum stack margins that can pass the stress tests I
measured 768 bytes for ESP32-S3 and 512 bytes for ESP32-C3 on ESP-IDF
V5.2.2 and similar on V5.0.4. i.e. The ESP32-C3 actually needs less stack
margin not more!
I think the extra margin for ESP32-C3 probably arose from:
1. Some toolchain inefficiency in the IDF V4.x RISC-V compiler codegen,
that has since been improved.
OR
2. The race condition that was fixed in e3955f42 where sometimes the limit
wasn't set correctly at all. This seems to trigger more on C3, presumably
some timing artifact, and I'd believe that some binaries might be more
susceptible than others due to random factors.
OR
3. Commit 6007f3e206 which enabled custom
NLR handling for ESP32-C3.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
This value should have been adjusted when the new cstack API was adopted in
e3955f421d, as otherwise the stack limit is too small especially on
ESP32-C3 where the stack limit was 6144 - 2048 - 2048.
Some extra margin is needed for bluetooth irq because invoke_irq_handler()
isn't a top-level task function, NimBLE calls through multiple layers
first. Measuring this overhead on IDF V5.2.2 (by putting an abort() in
invoke_irq_handler() and then measuring the stack size) yielded 672 bytes
on ESP32-S3 and 612 bytes on ESP32-C3, similar to the size reported in
cd66aa05cf.
Sticking with 1024 bytes for added safety margin. This means on Xtensa the
total margin for the BLE task stays the same (2048 bytes) as before
switching to cstack.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
If verbose debugging is enabled there is some stdout output happening
before the GIL is ready (for example, GC initialisation), and the code
assumed that no string printing occurred before the interpreter was fully
initialised. Printing long strings would operate without holding the GIL,
which would crash if string output would happen too early in the startup
process.
This commit addresses that issue, making sure verbose debugging output will
work even before the interpreter is fully initialised (as if it is not yet
ready there's no GIL to take care of).
Also, the threshold that would indicate whether a string is "long" (and
thus requiring a GIL release/lock operation) or not was hardcoded to 20
bytes. This commit makes that configurable, maintaining 20 bytes as a
default.
Fixes issue #15408.
Signed-off-by: Alessandro Gatti <a.gatti@frob.it>
Commit a66bd7a489 added the
ESP32_GENERIC_C3_USB board (now merged with ESP32_GENERIC_C3) and changed
the brownout detector from the default level 7 (~2.51V) to level 4
(~2.92V).
Raising the level again seems to fix random BOD resets on some of the
cheaper ESP32-C3 dev boards (that likely skimp on power supply
capacitance).
Specifically, this change prevents random resets running multi_bluetooth
tests on ESP32-C3 "SuperMini" board.
Also removed from the LOLIN_C3_MINI board as it seems this config is a copy
of the generic one.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
The ESP-IDF default on C3 is primary UART0, secondary USB serial/jtag.
Previously MicroPython configured the primary as USB Serial/JTAG and
manually worked with the UART0 console. However UART0 console stopped
working this way in v5.2.2.
The big change is that CONFIG_ESP_CONSOLE_USB_SERIAL_JTAG is no longer set,
as primary console is UART0. However
CONFIG_ESP_CONSOLE_SECONDARY_USB_SERIAL_JTAG is set and IDF provides a
macro CONFIG_ESP_CONSOLE_USB_SERIAL_JTAG_ENABLED which is set if either
primary or secondary esp_console is USB serial/jtag. So need to use that
macro instead.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Saves code size, MicroPython doesn't appear to rely on any of the missing
formatters (64-bit integers, c99-style named arguments).
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Replaces the deprecated ESP32 calibration API with the "line" method
instead.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
This change moves that complexity out into the stack checker and fixes the
bug where stack margin wasn't set correctly by ESP32-C3 threads.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
`get_lan()`: If the ethernet MAC address is uninitialised, set it to the
address reserved by the ESP32 for the ETH interface.
SPI LAN devices may be initialised with a MAC address of 00:00:00:00:00:00.
So check that a valid unicast MAC address has been set (using
`LAN.config(mac=...)`) when initialising the LAN interface.
Fixes#15425.
Signed-off-by: Glenn Moloney <glenn.moloney@gmail.com>
This PR ensures that `network.LAN.active(True/False)` will succeed if the
LAN is already in the desired state.
Currently, `lan.active(True)` will raise an `OSError` exception if the LAN
is already in the desired state. This is inconsistent with
`network.WLAN.active(True/False)` and causes `lan.active(True)` to raise an
exception after a soft reset (causing common network startup scripts to
fail for LAN interfaces).
Signed-off-by: Glenn Moloney <glenn.moloney@gmail.com>
Finalisers that run during `gc_sweep_all()` may run native code, for
example if an open file is closed and the underlying block device is
implemented in native code, then the filesystem driver (eg FAT) may call
into the native code.
Therefore, native code must be freed after the call to `gc_sweep_all()`.
That can only be achieved if the GC heap is not used to store the list of
allocated native code blocks. Instead, this commit makes the native code
blocks a linked list.
Signed-off-by: Damien George <damien@micropython.org>
Without this commit, math.gamma(-float("inf")) returns inf instead of
raising a math domain ValueError. Needed for float/math_domain_special.py
test to pass on esp32.
Root cause is an upstream libm bug, has been reported to ESP-IDF.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
ESP-IDF driver always requires at least two DMA buffers, so ensure that's
the case.
Failures during initialisation were being lost because ESP_ERROR_CHECK is
configured as a no-op, so the failure was deferred until read() or write()
was called on the port. Raise an error from init, instead.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
It seems like at some point Espressif NimBLE team changed
nimble_port_init and nimble_port_deinit to manage HCI init
internally:
https://github.com/espressif/esp-nimble/commit/f8a79b04c9743543b8959727d7
This change is included in all the IDF versions that MicroPython supports.
As a result, existing code that called esp_nimble_hci_deinit() explicitly
would trigger a use-after-free bug and heap corruption (specifically this
calls through to ble_transport_deinit() which calls os_mempool_free(). The
second time this writes out to a bunch of memory pools where the backing
buffers have already been freed.)
Symptoms were intermittent random crashes after de-activating Bluetooth
(running multi_bluetooth/ble_gatt_data_transfer.py could sometimes
reproduce). Setting Heap Poisoning to Comprehensive in menuconfig caused
the bug to be detected every time.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
The RV32 code emitter assumed that the arch-specific NLR was used
instead of the setjmp/longjmp based NLR code. If the latter NLR
provider was chosen, the emitter would allocate space on the stack
for the NLR buffer but would not fill it in.
This change turns off setjmp()-based NLR and GCREGS for the ESP32C3
target, in favour of more platform-tailored alternatives. As setjmp()
NLR is now disabled by default, the RV32 emitter can be safely enabled
by default as well for the target in question.
Signed-off-by: Alessandro Gatti <a.gatti@frob.it>
The ESP32C3 has only two timers in one group. In the code this is
reflected as two groups with one timer.
Signed-off-by: robert-hh <robert@hammelrath.com>
Explicitly yield each time a thread mutex is unlocked.
Key to understanding this bug is that Python threads run at equal RTOS
priority, and although ESP-IDF FreeRTOS (and I think vanilla FreeRTOS)
scheduler will round-robin equal priority tasks in the ready state it does
not make a similar guarantee for tasks moving between ready and waiting.
The pathological case of this bug is when one Python thread task is busy
(i.e. never blocks) it will hog the CPU more than expected, sometimes for
an unbounded amount of time. This happens even though it periodically
unlocks the GIL to allow another task to run.
Assume T1 is busy and T2 is blocked waiting for the GIL. T1 is executing
and hits a condition to yield execution:
1. T1 calls MP_THREAD_GIL_EXIT
2. FreeRTOS sees T2 is waiting for the GIL and moves it to the Ready list
(but does not preempt, as T2 is same priority, so T1 keeps running).
3. T1 immediately calls MP_THREAD_GIL_ENTER and re-takes the GIL.
4. Pre-emptive context switch happens, T2 wakes up, sees GIL is not
available, and goes on the waiting list for the GIL again.
To break this cycle step 4 must happen before step 3, but this may be a
very narrow window of time so it may not happen regularly - and
quantisation of the timing of the tick interrupt to trigger a context
switch may mean it never happens.
Yielding at the end of step 2 maximises the chance for another task to run.
Adds a test that fails on esp32 before this fix and passes afterwards.
Fixes issue #15423.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Being able to send data out in LSB format can be useful, and having support
in the low-level driver is much better than requiring Python code to
reorder the bits before sending them / after receiving them. In particular
if the hardware does not support the LSB format (eg RP2040) then one needs
to use the SoftSPI in LSB mode.
For this change a default definition of `MICROPY_PY_MACHINE_SPI_MSB/_LSB`
was added to `py/mpconfig.h`, making them available to all ports. The
identical defines in `esp32/mpconfigport.h` were deleted.
Resolves issues #5340, #11404.
Signed-off-by: robert-hh <robert@hammelrath.com>
Use new function mp_obj_new_str_from_cstr() where appropriate. It
simplifies the code, and makes it smaller too.
Signed-off-by: Jon Foster <jon@jon-foster.co.uk>
This commit reworks board variants on the esp32 port. It's a simple change
that moves the board variant configuration from an "if" statement within
`mpconfigboard.cmake` into separate files for each variant, with the name
of the variant encoded in the filename: `mpconfigvariant_VARIANT.cmake`.
Optionally, the base variant can have its own options in
`mpconfigvariant.cmake` (this is an optional file, but all other variants
of the base must have a corresponding mpconfigvariant file).
There are two benefits to this:
- The build system now gives an error if the variant that you specified
doesn't exist (because the mpconfigvariant file must exist with the
variant name you specify).
- No more error-prone if-logic needed in the .cmake files.
The way to build a variant is unchanged, still via:
$ make BOARD_VARIANT=VARIANT
Signed-off-by: Damien George <damien@micropython.org>
This fixes the build for some esp32 and nrf boards (for example
`ARDUINO_NANO_33_BLE_SENSE` and `ARDUINO_NANO_ESP32`) due to commit
c98789a6d8. Changes are:
- Allow the CDC TX/RX functions in `mp_usbd_cdc.c` to be enabled
separately to those needed for `MICROPY_HW_USB_CDC_1200BPS_TOUCH`.
- Add `MICROPY_EXCLUDE_SHARED_TINYUSB_USBD_CDC` option as a temporary
workaround for the nrf port to use.
- Declare `mp_usbd_line_state_cb()` in a header as a public function.
- Fix warning with type cast of `.callback_line_state_changed`.
Signed-off-by: Damien George <damien@micropython.org>
There are a few TinyUSB CDC functions used for stdio that are currently
replicated across a number of ports. Not surprisingly in a couple of cases
these have started to diverge slightly, with additional features added to
one of them.
This commit consolidates a couple of key shared functions used directly by
TinyUSB based ports, and makes those functions available to all.
Signed-off-by: Andrew Leech <andrew@alelec.net>
This adds support for the TCP_NODELAY socket option for lwIP sockets.
Generally, TCP sockets use the Nagle algorithm and will send data when
an ACK is received or after all previously-sent data has already been
ACKed.
If the TCP_NODELAY option is set for a socket, every write to the socket
will trigger a packet to be sent.
Signed-off-by: Jared Hancock <jared@greezybacon.me>
When a fatal error occurs it's important to know which precise version it
occurred on in order to be able to decode the crash dump information such
as the backtrace.
By wrapping around the built-in IDF panic handler we can print some extra
information whenever a fatal error occurs. The message links to a new wiki
page which contains additional information on how to debug ESP32 issues,
and links to the bug reporting issue template.
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
For ESP32C3/S2/S3 IDFv5 exposes new internal temperature API which is
different to the base ESP32, IDFv4.
Thanks to @robert-hh for cleaner code and testing sensor capability in
these devices.
See discussion #10443.
Signed-off-by: Rick Sorensen <rick.sorensen@gmail.com>
If the heap allocation fails we will crash if we continue, so at least we
can show a clear error message so one can figure out memory allocation was
the problem (instead of just seeing some arbitrary null pointer error
later).
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
This workaround makes sure that all ringbuf functions that may be called
from an ISR are placed in IRAM. See
https://github.com/espressif/esp-idf/issues/13378
Note that this means that all esp32-og builds get non-ISR ringbuf functions
placed in flash now, whereas previously it was just the spiram variant.
This might be a good thing (e.g. free up some IRAM for native/viper).
Fixes issue #14005.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Disabled by default, but enabled on all boards that previously had
`MICROPY_PY_MACHINE_BARE_METAL_FUNCS` enabled.
Signed-off-by: Damien George <damien@micropython.org>
Added a 4MiB flash partitioning variant for ESP32S3: adds support for 4MiB
discrete flash boards or ESP32-S3FH4R2 with embedded 4MiB flash based ones.
Tested on the waveshare ESP32-S3 Mini w/ESP32-S3FH4R2.
Signed-off-by: Stanislav Ponomarev <me@stasponomarev.com>
If the `timeout_char` parameter is not given, we should still configure the
UART to ensure the UART is always initialized consistently. So the default
of 0 gets applied correctly, or if, for example, the baudrate was changed
the char timeout isn't still based on the old baudrate causing weird
behaviour, etc.
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
Prior to this commit, the pin defined for power would be used by the
esp_idf driver to reset the PHY. That worked, but sometimes the MDIO
configuration started before the power was fully settled, leading to an
error.
With the change in this commit, the power for the PHY is independently
enabled in network_lan.c with a 100ms delay to allow the power to settle.
A separate define for a reset pin is provided, even if the PHY reset
pin is rarely connected.
Fixes issue #14013.
Signed-off-by: robert-hh <robert@hammelrath.com>
On these targets it's possible to enter the bootloader by setting a bit in
an RTC register before resetting.
Structure it in a way that a board can still provide a custom bootloader
handler. The handler here will be the default if none is provided, for any
board based on the supported targets.
Signed-off-by: Trent Piepho <tpiepho@gmail.com>
Currently only the Arduino Nano ESP32 defines a machine.bootloader handler
for ESP32. All other boards will intentionally hang.
There is no error message, nor is a NotImplementedError raised. There's no
indication if Micropython has crashed, or if the bootloader was entered but
USB is not working, which is a real problem the ESP32 bootloader has. It's
not possible escape from this hang with ^C or any other means besides
physical access to the reset pin or the ability to cycle power.
Change this to only define an implementation of machine.bootloader() when
there is a handler for it.
Signed-off-by: Trent Piepho <tpiepho@gmail.com>
The new IDF v5.2 deprecated the task cleanup callback we use, so support
for the new option has been implemented in the previous commit. This also
requires a change in the sdkconfig, via a new variable
${SDKCONFIG_IDF_VERSION_SPECIFIC} which is used in all mpconfigboard.cmake
files to include an extra sdkconfig file based on the IDF version in use.
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
The legacy I2S "shim" is removed and replaced by the new I2S driver. The
new driver fixes a bug where mono audio plays only in one channel.
Application code size is reduced by 2672 bytes with this change. Tested on
ESP32, ESP32+spiram, ESP32-S3 using example code from
https://github.com/miketeachman/micropython-i2s-examples
Signed-off-by: Mike Teachman <mike.teachman@gmail.com>
The STATIC macro was introduced a very long time ago in commit
d5df6cd44a. The original reason for this was
to have the option to define it to nothing so that all static functions
become global functions and therefore visible to certain debug tools, so
one could do function size comparison and other things.
This STATIC feature is rarely (if ever) used. And with the use of LTO and
heavy inline optimisation, analysing the size of individual functions when
they are not static is not a good representation of the size of code when
fully optimised.
So the macro does not have much use and it's simpler to just remove it.
Then you know exactly what it's doing. For example, newcomers don't have
to learn what the STATIC macro is and why it exists. Reading the code is
also less "loud" with a lowercase static.
One other minor point in favour of removing it, is that it stops bugs with
`STATIC inline`, which should always be `static inline`.
Methodology for this commit was:
1) git ls-files | egrep '\.[ch]$' | \
xargs sed -Ei "s/(^| )STATIC($| )/\1static\2/"
2) Do some manual cleanup in the diff by searching for the word STATIC in
comments and changing those back.
3) "git-grep STATIC docs/", manually fixed those cases.
4) "rg -t python STATIC", manually fixed codegen lines that used STATIC.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Because `mpthreadport.h` is included by `mpthread.h`.
Also remove unnecessary include of `mpthreadport.h` in esp32's `main.c`.
Signed-off-by: Damien George <damien@micropython.org>
This combines the argument parsing and checking for the machine.SPI.init()
and machine.SPI() interfaces.
The only real difference was unspecified arguments in init() mean to keep
the same value, while in new they get default values.
Behavior has changed for passing the "id" argument to init(). On other
ports this isn't allowed. But on esp32 it would change the SPI controller
of the static SPI instance to the new id. This results in multiple static
spi objects for the same controller and they would fight over which one has
inconsistent mpy vs esp-idf state. This has been changed to not allow "id"
with init(), like other ports.
In a few causes, a loop is used over arguments that are handled the same
way instead of cut & pasting the same stanza of code for each argument.
The init_internal function had a lot of arguments, which is not efficient
to pass. Pass the args mp_arg_val_t array instead as a single argument.
This reduced both the number of C lines and the compiled code size.
Summary of code size change: Two argument lists of 72 bytes are replaced
by a single shared 72 byte list. New shared argument parsing code is small
enough to be inlined, but is still efficient enough to shrink the overall
code size by 349 bytes of the three argument handlering functions.
add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-349 (-349)
Function old new delta
machine_hw_spi_make_new 255 203 -52
machine_hw_spi_init 122 67 -55
machine_hw_spi_init_internal 698 456 -242
Total: Before=1227667, After=1227318, chg -0.03%
add/remove: 2/0 grow/shrink: 0/2 up/down: 92/-144 (-52)
Data old new delta
spi_allowed_args - 72 +72
defaults$0 - 20 +20
allowed_args$1 240 168 -72
allowed_args$0 1080 1008 -72
Total: Before=165430, After=165378, chg -0.03%
add/remove: 0/0 grow/shrink: 0/0 up/down: 0/0 (0)
Signed-off-by: Trent Piepho <tpiepho@gmail.com>
The Python BLE IRQ handler will most likely run on the NimBLE task, so its
C stack must be large enough to accommodate reasonably complicated Python
code (eg a few call depths). So increase this stack size.
Also increase the headroom from 1024 to 2048 bytes. This is needed because
(1) the esp32 architecture uses a fair amount of stack in general; and (2)
by the time execution gets to setting the Python stack top via
`mp_stack_set_top()` in this interlock code, about 600 bytes of stack are
already used, which reduces the amount available for Python.
Fixes issue #12349.
Signed-off-by: Damien George <damien@micropython.org>
In case callbacks must run (eg a disconnect event happens during the
deinit) and the GIL must be obtained to run the callback.
Fixes part of issue #12349.
Signed-off-by: Damien George <damien@micropython.org>
PPP is not that commonly used, let it be turned off in the board config to
save space. It is still on by default.
On an basic ESP32-S3 build, turning off PPP with LWIP still on saves ~35 kB
of codend 4 kB of data.
text data bss dec hex filename
1321257 304296 2941433 4566986 45afca before-ppp-off.elf
1285101 299920 2810305 4395326 43113e after-ppp-off.elf
-------------------------------
-36156 -4376 -56
Note that the BSS segment size includes all NOBITS sections in ELF file.
Some of these are aligned to 64kB chunk sized dummy blocks, I think for
alignment to MMU boundaries, and these went down by 1 block each, so 128
kiB of BSS is not really part of the binary size reduction.
Signed-off-by: Trent Piepho <tpiepho@gmail.com>
The standard Arduino pinout uses LEDR/G/B and LED_BUILTIN (if available).
This patch adds aliases to match the standard pinout, while retaining
LED_RED/GREEN/BLUE for compatibility with existing scripts and examples.
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
Make can't handle paths with spaces, see https://savannah.gnu.org/bugs/?712
The following workarounds exist:
- When using make's built-in functions:
- Use relative paths wherever possible to avoid spaces in the first
place.
- All spaces in paths can be escaped with backslashes; quotes don't
work.
- Some users use the shell to temporarily rename directories, or to
create symlinks without spaces.
- When using make to pass commands to the system's shell, enclose paths in
quotes. While make will still interpret quoted strings with spaces as
multiple words, the system's shell will correctly parse the resulting
command.
This commit contains the following fixes:
- In ports/stm32/mboot/Makefile: Use relative paths to avoid spaces when
using built-in functions.
- In all other files: Use quotes to enclose paths when make is used to call
shell functions.
All changes have been tested with a directory containing spaces.
Signed-off-by: Iksas <iksas@mailbox.org>
- Completes a longstanding TODO in the code, to not ignore
the optional family, type, proto and flags arguments to
socket.getaddrinfo().
- Note that passing family=socket.AF_INET6 will now cause queries
to fail (OSError -202). Previously this argument was ignored so
IPV4 results were returned instead.
- Optional 'type' argument is now always copied into the result. If not
set, results have type SOCK_STREAM.
- Fixes inconsistency where previously querying mDNS local suffix (.local)
hostnames returned results with socket type 0 (invalid), but all other
queries returned results with socket type SOCK_STREAM (regardless of
'type' argument).
- Optional proto argument is now returned in the result tuple, if supplied.
- Optional flags argument is now passed through to lwIP. lwIP has handling
for AI_NUMERICHOST, AI_V4MAPPED, AI_PASSIVE (untested, constants for
these are not currently exposed in the esp32 socket module).
- Also fixes a possible memory leak in an obscure code path
(lwip_getaddrinfo apparently sometimes returns a result structure with
address "0.0.0.0" instead of failing, and this structure would have been
leaked.)
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
Instead, configure the default once at compile-time. This means the GAP
name will no longer be set to default after re-initializing Bluetooth.
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
MicroPython code may rely on the return value of sys.stdout.buffer.write()
to reflect the number of bytes actually written. While in most scenarios a
write() operation is successful, there are cases where it fails, leading to
data loss. This problem arises because, currently, write() merely returns
the number of bytes it was supposed to write, without indication of
failure.
One scenario where write() might fail, is where USB is used and the
receiving end doesn't read quickly enough to empty the receive buffer. In
that case, write() on the MicroPython side can timeout, resulting in the
loss of data without any indication, a behavior observed notably in
communication between a Pi Pico as a client and a Linux host using the ACM
driver.
A complex issue arises with mp_hal_stdout_tx_strn() when it involves
multiple outputs, such as USB, dupterm and hardware UART. The challenge is
in handling cases where writing to one output is successful, but another
fails, either fully or partially. This patch implements the following
solution:
mp_hal_stdout_tx_strn() attempts to write len bytes to all of the possible
destinations for that data, and returns the minimum successful write
length.
The implementation of this is complicated by several factors:
- multiple outputs may be enabled or disabled at compiled time
- multiple outputs may be enabled or disabled at runtime
- mp_os_dupterm_tx_strn() is one such output, optionally containing
multiple additional outputs
- each of these outputs may or may not be able to report success
- each of these outputs may or may not be able to report partial writes
As a result, there's no single strategy that fits all ports, necessitating
unique logic for each instance of mp_hal_stdout_tx_strn().
Note that addressing sys.stdout.write() is more complex due to its data
modification process ("cooked" output), and it remains unchanged in this
patch. Developers who are concerned about accurate return values from
write operations should use sys.stdout.buffer.write().
This patch might disrupt some existing code, but it's also expected to
resolve issues, considering that the peculiar return value behavior of
sys.stdout.buffer.write() is not well-documented and likely not widely
known. Therefore, it's improbable that much existing code relies on the
previous behavior.
Signed-off-by: Maarten van der Schrieck <maarten@thingsconnected.nl>
This gets back the old heap-size behaviour on ESP32, before auto-split-heap
was introduced: after the heap is grown one time the size is 111936 bytes,
with about 40k left for the IDF. That's enough to start WiFi and do a
HTTPS request.
Signed-off-by: Damien George <damien@micropython.org>
esp8266 doesn't need ets task because the notify is now scheduled (see
commits 7d57037906 and
c60caf1995 for relevant history).
Signed-off-by: Damien George <damien@micropython.org>
Also, IDF v5.1.2 is now supported, just not used by default.
IDF v5.0.2 still builds but we cannot guarantee continued support for this
version moving forward.
Signed-off-by: IhorNehrutsa <IhorNehrutsa@gmail.com>
Disable unused EC curves and default certificate bundle which is not
implemented in MicroPython. This reduces the firmware size significantly.
This follows commit 68f166dae9.
Signed-off-by: Carlos Gil Gonzalez <carlosgilglez@gmail.com>
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>
The amount of free IRAM in ESP32 SPIRAM builds is very small and went over
the limit due to commit 30b0ee34d3. This
commit enables further optimisations to reduce IRAM usage.
Signed-off-by: Damien George <damien@micropython.org>
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>
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>
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>
Commit 7ea06a3e26 moved the
`rmt_write_items()` call to fix RMT looping for ESP32-S3, but broke it for
the other ESP32s. This commit conditionally compiles the location of that
call.
Signed-off-by: Mark Blakeney <mark.blakeney@bullet-systems.net>
Prior to this change, after calling connect() the status() method for the
STA interface would either return STAT_GOT_IP or STAT_CONNECTION. The
latter would be returned because wifi_sta_connect_requested==true and
conf_wifi_sta_reconnects==0 by default. As such there was no way to know
anything about errors when attempting to connect, such as a bad password.
Now, status() can return STAT_NO_AP_FOUND and STAT_WRONG_PASSWORD when
those conditions are met.
Fixes issue #12930.
Signed-off-by: IhorNehrutsa <Ihor.Nehrutsa@gmail.com>
In ESP-IDF, enabling SPIRAM in menuconfig sets some Kconfig options:
- "Wi-Fi Cache TX Buffers" enabled. By default this tries to allocate 32 of
these when Wi-Fi is initialised, which requires 54,400 bytes of free heap.
- Switches "Type of WiFi TX buffers" from Dynamic to Static. This
pre-allocates all of the Wi-Fi transmit buffers.
Not a problem if PSRAM is initialised, but it's quite a lot of RAM if PSRAM
failed to initialise! As we use the same config for PSRAM & no-PSRAM builds
now, this either causes Wi-Fi to fail to initialise (seen on S2) or will
eat quite a lot of RAM.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
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>
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>
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>
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>
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>
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>
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>
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>
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>
For now, this implements the functionality required for esp32 and rp2,
including support for numeric pins, rp2 alternate functions, and rp2
extended pins.
This also updates the rp2 port to use the same structure for pins.h and
pins.csv as for esp32, and moves the pin definitions directly into the
table (rather than having a table of pointers), which is a small code size
improvement.
Support for "hidden" pins in pins.csv is added (matching the stm32
implementation).
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
All ports now use `--board-csv`, `--prefix`, `--output-souce`,
`--output-header` and no longer write to stdout. This matches the esp32
implementation.
Ports that have an AF input use `--af-csv` (to match `--board-csv`).
Any additional output files are now prefixed with `output-` (e.g.
`--output-af-const`).
Default arguments are removed (all makefiles should always specify all
arguments, using default values is likely an error).
Replaced the `af-defs-cmp-strings` and `hdr-obj-decls` args for stm32 with
just `mboot-mode`. Previously they were set on the regular build, now the
logic is reversed so mboot sets it.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This improves (decreases) the latency on stdin, on SoCs with built-in USB
and using TinyUSB, like S2 and S3.
Signed-off-by: Andrew Leech <andrew.leech@planetinnovation.com.au>
ESP32-C3 is not Xtensa-based, so build settings are now tailored a bit
better following that fact. ESP-IDF 5.x already adds architecture-specific
modules by itself so there is no need to specify either the `xtensa` or the
`riscv` module in the build settings.
Signed-off-by: Alessandro Gatti <a.gatti@frob.it>
Commit c4e63ace66 enabled the SPI Ethernet
driver and that cost about 13k of firwmare size, pushing the firmware over
the limit of the D2WD and OTA board variants available size.
To fix, disable SPI Ethernet on the D2WD variant, and build the OTA variant
with size optimisation rather than performance optimisation.
Signed-off-by: Damien George <damien@micropython.org>
