This simplifies allocating outside of the VM because the VM doesn't
take up all remaining memory by default.
On ESP we delegate to the IDF for allocations. For all other ports,
we use TLSF to manage an outer "port" heap. The IDF uses TLSF
internally and we use their fork for the other ports.
This also removes the dynamic C stack sizing. It wasn't often used
and is not possible with a fixed outer heap.
Fixes#8512. Fixes#7334.
the `Makefile:...` version broke the shared bindings matrix generation, as
it would fail if esp-idf wasn't in the environment (and we wouldn't want
it to do that much work anyway)
Here's why this helps fix the build error:
If this file does not exist or is out of date, then it is generated
and then the Makefile is re-read.
I don't know why this worked before but stopped now; it must have
to do with the rework of header generation in the MP build system.
while developing esp-camera I had the problem that firmware.elf was
not regenerated if the only file I edited was in the esp32-camera
submodule.
By telling make that $(IDF_CMAKE_TARGETS), the list of .a fliles
produced by ninja-building esp-idf, depend on esp-idf-stamp and that
firmware.elf in turn depends on these files, the ninja build is re-run
on each make, which is reasonably quick if nothing needs to be rebuilt.
Adding `-u ld_include_highint_hdl` forces the linker to keep the
high priority interrupt handler that calls the ipc_isr handler.
The deep sleep is waiting for this interrupt to be handled on core
0 before sleeping from core 1.
Fixes#6090
This uses the esp32-camera code instead of our own homebrewed camera code.
In theory it supports esp32, esp32-s2 and esp32-s3, as long as they have
PSRAM.
This is very basic and doesn't support changing any camera parameters,
including switching resolution or pixelformat.
This is tested on the Kaluga (ESP32-S2) and ESP32-S3-Eye boards.
First, reserve some PSRAM by putting this line in `CIRCUITPY/_env`:
```
CIRCUITPY_RESERVED_PSRAM=524288
```
and hard-reset the board for it to take effect.
Now, the following script will take a very low-resolution jpeg file and print
it in the REPL in escape coded form:
```python
import board
import esp32_camera
c = esp32_camera.Camera(
data_pins=board.CAMERA_DATA,
external_clock_pin=board.CAMERA_XCLK,
pixel_clock_pin=board.CAMERA_PCLK,
vsync_pin=board.CAMERA_VSYNC,
href_pin=board.CAMERA_HREF,
pixel_format=esp32_camera.PixelFormat.JPEG,
i2c=board.I2C(),
external_clock_frequency=20_000_000)
m = c.take()
if m is not None:
print(bytes(m))
```
Then on desktop open a python repl and run something like
```python
>>> with open("my.jpg", "wb") as f: f.write(<BIG PASTE FROM REPL>)
```
and open my.jpg in a viewer.
