5e26862b2c
.. and switch makerfabs tft7 over to it as a test. We have our existing way of "reserving" PSRAM for esp-idf (we actually control it all but add back the "reserved" part). However, this does not work with off the shelf esp_lcd, which only will allocate a framebuffer in PSRAM if CONFIG_SPIRAM_USE_CAPS_ALLOC (or CONFIG_SPIRAM_USE_ALLOC) is defined, not if CONFIG_SPIRAM_USE_MEMMAP is. This new way is possibly compatible with more esp-idf code, but it complicates CircuitPython's initial startup since nothing until port_heap_init is permitted to use the CP heap or supervisor allocator. In practice this seems to be OK today. Right now this doesn't change the setting across all boards with PSRAM and so it does not revert esp-idf to its prior state. Instead, what I'm thinking is that we can do it during or just after the IDF5 update when sdkconfig files will be getting an overhaul anyway. |
||
---|---|---|
.. | ||
shared | ||
stub | ||
background_callback.h | ||
board.h | ||
cpu.h | ||
fatfs.h | ||
filesystem.h | ||
flash_root_pointers.h | ||
flash.h | ||
linker.h | ||
memory.h | ||
port.h | ||
serial.h | ||
spi_flash_api.h | ||
supervisor.mk | ||
usb.h | ||
workflow.h |