3bca93b2d0
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> |
||
---|---|---|
.. | ||
Makefile | ||
README.md | ||
head.S | ||
main.c | ||
mpconfigport.h | ||
mphalport.h | ||
powerpc.lds | ||
qstrdefsport.h | ||
uart_lpc_serial.c | ||
uart_lpc_serial.h | ||
uart_potato.c | ||
uart_potato.h | ||
unistd.h |
README.md
The PowerPC port that runs on microwatt and qemu
This port is intended to be a minimal MicroPython port that runs in QEMU, microwatt simulator with ghdl or microwatt on Xilinx FPGA with potato UART.
Building
By default the port will be built with the potato uart for microwatt:
$ make
To instead build for a machine with LPC serial, such as QEMU powernv:
$ make UART=lpc_serial
Cross compilation for POWERPC
If you need to cross compilers you'll want to grab a powerpc64le compiler (not powerpc or powerpc64).
On Ubuntu (18.04) you'll want:
$ apt install gcc-powerpc64le-linux-gnu
(Use CROSS_COMPILE=powerpc64le-linux-gnu-)
If your distro doesn't have cross compilers, you can get cross compilers here:
- https://toolchains.bootlin.com/ (use CROSS_COMPILE=powerpc64le-buildroot-linux-gnu-)
(Avoid musl libc as it defines __assert_fail() differently to glibc which breaks the micropython powerpc code)
Then do:
$ make CROSS_COMPILE=<compiler prefix>
Building will produce the build/firmware.bin file which can be used QEMU or microwatt.
To run in QEMU use:
$ ./qemu-system-ppc64 -M powernv -cpu POWER9 -nographic -bios build/firmware.bin