circuitpython/supervisor
Jeff Epler dc77f3146f serial_bytes_available: don't double-count bytes on usb cdc
In 9.0.x, serial_bytes_available returned a bool and tud_cdc_available was
harmlessly checked twice for any characters.

When the routine was changed to return an int, the double checking led to
over-reporting the number of characters available. In code that would attempt
to read this many bytes from sys.stdin, this made the read call block since
only 1 byte was actually available.

This behavior came up in the discussion of #9393. I don't mark this bug as
closing that one, because that issue seems to be reporting multiple things that
this change would not address, such as delays in `sys.stdout.write()` or
problems seen while using webserial.
2024-07-03 11:36:30 -05:00
..
shared serial_bytes_available: don't double-count bytes on usb cdc 2024-07-03 11:36:30 -05:00
stub update headers of most CircuitPython-only files 2024-05-17 14:56:28 -04:00
background_callback.h guard2once -s ... 2024-05-19 20:40:44 -04:00
board.h guard2once -s ... 2024-05-19 20:40:44 -04:00
cpu.h guard2once -s ... 2024-05-19 20:40:44 -04:00
fatfs.h guard2once -s ... 2024-05-19 20:40:44 -04:00
filesystem.h update headers of most CircuitPython-only files 2024-05-17 14:56:28 -04:00
flash.h guard2once -s ... 2024-05-19 20:40:44 -04:00
linker.h guard2once -s ... 2024-05-19 20:40:44 -04:00
port.h update headers of most CircuitPython-only files 2024-05-17 14:56:28 -04:00
port_heap.h update headers of most CircuitPython-only files 2024-05-17 14:56:28 -04:00
spi_flash_api.h guard2once -s ... 2024-05-19 20:40:44 -04:00
supervisor.mk Fix cyw43 and build with usb_cdc 2024-04-26 15:59:51 -07:00
usb.h update headers of most CircuitPython-only files 2024-05-17 14:56:28 -04:00
workflow.h update headers of most CircuitPython-only files 2024-05-17 14:56:28 -04:00